texrefs.bib

%% This BibTeX bibliography file was created using BibDesk.
%% http://bibdesk.sourceforge.net/


%% Created for Andrew Kern at 2016-02-01 14:09:45 -0500 


%% Saved with string encoding Unicode (UTF-8) 



@article{rasmussen2014genome,
	Author = {Rasmussen, Matthew D and Hubisz, Melissa J and Gronau, Ilan and Siepel, Adam},
	Date-Added = {2016-02-01 19:09:41 +0000},
	Date-Modified = {2016-02-01 19:09:41 +0000},
	Journal = {PLoS Genet},
	Number = {5},
	Pages = {e1004342},
	Publisher = {Public Library of Science},
	Title = {Genome-wide inference of ancestral recombination graphs},
	Volume = {10},
	Year = {2014}}

@article{ferrer2014detecting,
	Author = {Ferrer-Admetlla, Anna and Liang, Mason and Korneliussen, Thorfinn and Nielsen, Rasmus},
	Date-Added = {2016-02-01 19:09:01 +0000},
	Date-Modified = {2016-02-01 19:09:01 +0000},
	Journal = {Molecular biology and evolution},
	Number = {5},
	Pages = {1275--1291},
	Publisher = {SMBE},
	Title = {On detecting incomplete soft or hard selective sweeps using haplotype structure},
	Volume = {31},
	Year = {2014}}

@article{voight2006map,
	Author = {Voight, Benjamin F and Kudaravalli, Sridhar and Wen, Xiaoquan and Pritchard, Jonathan K},
	Date-Added = {2016-02-01 19:07:37 +0000},
	Date-Modified = {2016-02-01 19:07:37 +0000},
	Journal = {PLoS Biol},
	Number = {3},
	Pages = {e72},
	Publisher = {Public Library of Science},
	Title = {A map of recent positive selection in the human genome},
	Volume = {4},
	Year = {2006}}

@article{li2011new,
	Author = {Li, Haipeng},
	Date-Added = {2016-02-01 19:07:00 +0000},
	Date-Modified = {2016-02-01 19:07:00 +0000},
	Journal = {Molecular biology and evolution},
	Number = {1},
	Pages = {365--375},
	Publisher = {SMBE},
	Title = {A new test for detecting recent positive selection that is free from the confounding impacts of demography},
	Volume = {28},
	Year = {2011}}

@article{breiman2001random,
	Author = {Breiman, Leo},
	Date-Added = {2016-02-01 15:43:14 +0000},
	Date-Modified = {2016-02-01 15:43:14 +0000},
	Journal = {Machine learning},
	Number = {1},
	Pages = {5--32},
	Publisher = {Springer},
	Title = {Random forests},
	Volume = {45},
	Year = {2001}}

@article{quinlan1986induction,
	Author = {Quinlan, J. Ross},
	Date-Added = {2016-02-01 15:40:37 +0000},
	Date-Modified = {2016-02-01 15:40:37 +0000},
	Journal = {Machine learning},
	Number = {1},
	Pages = {81--106},
	Publisher = {Springer},
	Title = {Induction of decision trees},
	Volume = {1},
	Year = {1986}}

@article{geurts2006extremely,
	Author = {Geurts, Pierre and Ernst, Damien and Wehenkel, Louis},
	Date-Added = {2016-02-01 15:29:37 +0000},
	Date-Modified = {2016-02-01 15:29:37 +0000},
	Journal = {Machine learning},
	Number = {1},
	Pages = {3--42},
	Publisher = {Springer},
	Title = {Extremely randomized trees},
	Volume = {63},
	Year = {2006}}

@article{garud2015recent,
	Author = {Garud, Nandita R and Messer, Philipp W and Buzbas, Erkan O and Petrov, Dmitri A},
	Date-Added = {2016-02-01 15:28:12 +0000},
	Date-Modified = {2016-02-01 15:28:12 +0000},
	Journal = {PLoS Genet},
	Number = {2},
	Pages = {e1005004},
	Publisher = {Public Library of Science},
	Title = {Recent selective sweeps in North American Drosophila melanogaster show signatures of soft sweeps},
	Volume = {11},
	Year = {2015}}

@article{messer282013,
	Author = {Messer, PW and Petrov, D},
	Date-Added = {2016-02-01 15:28:08 +0000},
	Date-Modified = {2016-02-01 15:28:08 +0000},
	Journal = {Trends Ecol. Evol},
	Pages = {659--669},
	Title = {a. 2013. Population genomics of rapid adaptation by soft selective sweeps},
	Volume = {28}}

@article{gutenkunst2009inferring,
	Author = {Gutenkunst, Ryan N and Hernandez, Ryan D and Williamson, Scott H and Bustamante, Carlos D},
	Date-Added = {2016-01-28 19:51:59 +0000},
	Date-Modified = {2016-01-28 19:51:59 +0000},
	Journal = {PLoS Genet},
	Number = {10},
	Pages = {e1000695},
	Title = {Inferring the joint demographic history of multiple populations from multidimensional SNP frequency data},
	Volume = {5},
	Year = {2009}}

@article{tennessen2012evolution,
	Author = {Tennessen, Jacob A and Bigham, Abigail W and O’Connor, Timothy D and Fu, Wenqing and Kenny, Eimear E and Gravel, Simon and McGee, Sean and Do, Ron and Liu, Xiaoming and Jun, Goo and others},
	Date-Added = {2015-12-03 18:14:38 +0000},
	Date-Modified = {2015-12-03 18:14:38 +0000},
	Journal = {science},
	Number = {6090},
	Pages = {64--69},
	Publisher = {American Association for the Advancement of Science},
	Title = {Evolution and functional impact of rare coding variation from deep sequencing of human exomes},
	Volume = {337},
	Year = {2012}}

@article{berg2015coalescent,
	Author = {Berg, Jeremy J and Coop, Graham},
	Date-Added = {2015-12-03 18:03:41 +0000},
	Date-Modified = {2015-12-03 18:03:41 +0000},
	Journal = {Genetics},
	Number = {2},
	Pages = {707--725},
	Publisher = {Genetics Soc America},
	Title = {A Coalescent Model for a Sweep of a Unique Standing Variant},
	Volume = {201},
	Year = {2015}}

@article{schrider2015soft,
	Author = {Schrider, Daniel R and Mendes, F{\'a}bio K and Hahn, Matthew W and Kern, Andrew D},
	Date-Added = {2015-11-19 15:10:12 +0000},
	Date-Modified = {2015-11-19 15:10:12 +0000},
	Journal = {Genetics},
	Number = {1},
	Pages = {267--284},
	Publisher = {Genetics Soc America},
	Title = {Soft shoulders ahead: spurious signatures of soft and partial selective sweeps result from linked hard sweeps},
	Volume = {200},
	Year = {2015}}

@article{softShoulders,
	Author = {Schrider, Daniel R and Mendes, Fabio K and Hahn, Matthew W and Kern, Andrew D},
	Date-Added = {2015-02-04 22:01:24 +0000},
	Date-Modified = {2015-02-04 22:09:51 +0000},
	Journal = {Genetics},
	Title = {Soft shoulders ahead: spurious signatures of soft and partial selective sweeps result from linked hard sweeps},
	Volume = {accepted, pending revision},
	Year = {2015}}

@article{comeron2012many,
	Author = {Comeron, Josep M and Ratnappan, Ramesh and Bailin, Samuel},
	Date-Added = {2015-02-03 19:41:04 +0000},
	Date-Modified = {2015-02-03 19:41:04 +0000},
	Journal = {PLoS genetics},
	Number = {10},
	Pages = {e1002905},
	Publisher = {Public Library of Science},
	Title = {The many landscapes of recombination in Drosophila melanogaster},
	Volume = {8},
	Year = {2012}}

@article{kelly1997test,
	Author = {Kelly, John K},
	Date-Added = {2015-02-03 19:37:05 +0000},
	Date-Modified = {2015-02-03 19:37:05 +0000},
	Journal = {Genetics},
	Number = {3},
	Pages = {1197--1206},
	Publisher = {Genetics Soc America},
	Title = {A test of neutrality based on interlocus associations},
	Volume = {146},
	Year = {1997}}

@book{scholkopf2001learning,
	Author = {Scholkopf, Bernhard and Smola, Alexander J},
	Date-Added = {2015-02-03 19:36:11 +0000},
	Date-Modified = {2015-02-03 19:36:11 +0000},
	Publisher = {MIT press},
	Title = {Learning with kernels: support vector machines, regularization, optimization, and beyond},
	Year = {2001}}

@book{vapnik2000nature,
	Author = {Vapnik, Vladimir},
	Date-Added = {2015-02-03 19:35:42 +0000},
	Date-Modified = {2015-02-03 19:35:42 +0000},
	Publisher = {Springer Science \& Business Media},
	Title = {The nature of statistical learning theory},
	Year = {2000}}

@article{pritchard2010genetics,
	Author = {Pritchard, Jonathan K and Pickrell, Joseph K and Coop, Graham},
	Date-Added = {2015-02-03 18:40:34 +0000},
	Date-Modified = {2015-02-03 18:40:34 +0000},
	Journal = {Current Biology},
	Number = {4},
	Pages = {R208--R215},
	Publisher = {Elsevier},
	Title = {The genetics of human adaptation: hard sweeps, soft sweeps, and polygenic adaptation},
	Volume = {20},
	Year = {2010}}

@article{joachims2009cutting,
	Author = {Joachims, Thorsten and Finley, Thomas and Yu, Chun-Nam John},
	Date-Added = {2015-01-30 18:51:52 +0000},
	Date-Modified = {2015-01-30 18:51:52 +0000},
	Journal = {Machine Learning},
	Number = {1},
	Pages = {27--59},
	Publisher = {Springer},
	Title = {Cutting-plane training of structural SVMs},
	Volume = {77},
	Year = {2009}}

@inproceedings{tsochantaridis2004support,
	Author = {Tsochantaridis, Ioannis and Hofmann, Thomas and Joachims, Thorsten and Altun, Yasemin},
	Booktitle = {Proceedings of the twenty-first international conference on Machine learning},
	Date-Added = {2015-01-30 18:51:35 +0000},
	Date-Modified = {2015-01-30 18:51:35 +0000},
	Organization = {ACM},
	Pages = {104},
	Title = {Support vector machine learning for interdependent and structured output spaces},
	Year = {2004}}

@book{tsochantaridis2005support,
	Author = {Tsochantaridis, Ioannis},
	Date-Added = {2015-01-30 18:51:25 +0000},
	Date-Modified = {2015-01-30 18:51:25 +0000},
	Publisher = {Brown University},
	Title = {Support vector machine learning for interdependent and structured output spaces},
	Year = {2005}}

@inproceedings{tsochantaridis2005large,
	Author = {Tsochantaridis, Ioannis and Joachims, Thorsten and Hofmann, Thomas and Altun, Yasemin},
	Booktitle = {Journal of Machine Learning Research},
	Date-Added = {2015-01-30 18:51:02 +0000},
	Date-Modified = {2015-01-30 18:51:02 +0000},
	Pages = {1453--1484},
	Title = {Large margin methods for structured and interdependent output variables},
	Year = {2005}}

@article{durrett2004approximating,
	Author = {Durrett, Richard and Schweinsberg, Jason},
	Date-Added = {2015-01-28 18:47:00 +0000},
	Date-Modified = {2015-01-28 18:47:00 +0000},
	Journal = {Theoretical population biology},
	Number = {2},
	Pages = {129--138},
	Publisher = {Elsevier},
	Title = {Approximating selective sweeps},
	Volume = {66},
	Year = {2004}}

@article{guyon2003introduction,
	Author = {Guyon, Isabelle and Elisseeff, Andr{\'e}},
	Date-Added = {2014-10-01 20:58:15 +0000},
	Date-Modified = {2014-10-01 20:58:15 +0000},
	Journal = {The Journal of Machine Learning Research},
	Pages = {1157--1182},
	Publisher = {JMLR. org},
	Title = {An introduction to variable and feature selection},
	Volume = {3},
	Year = {2003}}

@article{Duchen:2013uj,
	Author = {Duchen, Pablo and Zivkovic, Daniel and Hutter, Stephan and Stephan, Wolfgang and Laurent, Stefan},
	Date-Added = {2014-10-01 20:39:03 +0000},
	Date-Modified = {2014-10-01 20:39:03 +0000},
	Journal = {GENETICS},
	Month = jan,
	Number = {1},
	Pages = {291--301},
	Title = {{Demographic Inference Reveals African and European Admixture in the North American Drosophila melanogaster Population}},
	Volume = {193},
	Year = {2013}}

@article{keinan2012recent,
	Author = {Keinan, Alon and Clark, Andrew G},
	Date-Added = {2014-10-01 20:31:31 +0000},
	Date-Modified = {2014-10-01 20:31:31 +0000},
	Journal = {science},
	Number = {6082},
	Pages = {740--743},
	Publisher = {American Association for the Advancement of Science},
	Title = {Recent explosive human population growth has resulted in an excess of rare genetic variants},
	Volume = {336},
	Year = {2012}}

@article{Altshuler:2010en,
	Author = {Altshuler, David M and Gibbs, Richard A and Peltonen, Leena and Altshuler, David M and Gibbs, Richard A and Peltonen, Leena and Dermitzakis, Emmanouil and Schaffner, Stephen F and Yu, Fuli and Peltonen, Leena and Dermitzakis, Emmanouil and Bonnen, Penelope E and Altshuler, David M and Gibbs, Richard A and de Bakker, Paul I W and Deloukas, Panos and Gabriel, Stacey B and Gwilliam, Rhian and Hunt, Sarah and Inouye, Michael and Jia, Xiaoming and Palotie, Aarno and Parkin, Melissa and Whittaker, Pamela and Yu, Fuli and Chang, Kyle and Hawes, Alicia and Lewis, Lora R and Ren, Yanru and Wheeler, David and Gibbs, Richard A and Marie Muzny, Donna and Barnes, Chris and Darvishi, Katayoon and Hurles, Matthew and Korn, Joshua M and Kristiansson, Kati and Lee, Charles and McCarroll, Steven A and Nemesh, James and Dermitzakis, Emmanouil and Keinan, Alon and Montgomery, Stephen B and Pollack, Samuela and Price, Alkes L and Soranzo, Nicole and Bonnen, Penelope E and Gibbs, Richard A and Gonzaga-Jauregui, Claudia and Keinan, Alon and Price, Alkes L and Yu, Fuli and Anttila, Verneri and Brodeur, Wendy and Daly, Mark J and Leslie, Stephen and McVean, Gil and Moutsianas, Loukas and Nguyen, Huy and Schaffner, Stephen F and Zhang, Qingrun and Ghori, Mohammed J R and McGinnis, Ralph and McLaren, William and Pollack, Samuela and Price, Alkes L and Schaffner, Stephen F and Takeuchi, Fumihiko and Grossman, Sharon R and Shlyakhter, Ilya and Hostetter, Elizabeth B and Sabeti, Pardis C and Adebamowo, Clement A and Foster, Morris W and Gordon, Deborah R and Licinio, Julio and Cristina Manca, Maria and Marshall, Patricia A and Matsuda, Ichiro and Ngare, Duncan and Ota Wang, Vivian and Reddy, Deepa and Rotimi, Charles N and Royal, Charmaine D and Sharp, Richard R and Zeng, Changqing and Brooks, Lisa D and McEwen, Jean E},
	Date-Added = {2014-10-01 20:30:59 +0000},
	Date-Modified = {2014-10-01 20:30:59 +0000},
	Journal = {NATURE},
	Month = sep,
	Number = {7311},
	Pages = {52--58},
	Title = {{Integrating common and rare genetic variation in diverse human populations}},
	Volume = {467},
	Year = {2010}}

@article{Durbin:2010gj,
	Author = {Durbin, Richard M and Altshuler, David L and Abecasis, Gon{\c c}alo R and Bentley, David R and Chakravarti, Aravinda and Clark, Andrew G and Collins, Francis S and De La Vega, Francisco M and Donnelly, Peter and Egholm, Michael and Flicek, Paul and Gabriel, Stacey B and Gibbs, Richard A and Knoppers, Bartha M and Lander, Eric S and Lehrach, Hans and Mardis, Elaine R and McVean, Gil A and Nickerson, Debbie A and Peltonen, Leena and Schafer, Alan J and Sherry, Stephen T and Wang, Jun and Wilson, Richard K and Deiros, David and Metzker, Mike and Muzny, Donna and Reid, Jeff and Wheeler, David and Li, Jingxiang and Jian, Min and Li, Guoqing and Li, Ruiqiang and Liang, Huiqing and Tian, Geng and Wang, Bo and Wang, Jian and Wang, Wei and Yang, Huanming and Zhang, Xiuqing and Zheng, Huisong and Ambrogio, Lauren and Bloom, Toby and Cibulskis, Kristian and Fennell, Tim J and Jaffe, David B and Shefler, Erica and Sougnez, Carrie L and Gormley, Niall and Humphray, Sean and Kingsbury, Zoya and Koko-Gonzales, Paula and Stone, Jennifer and McKernan, Kevin J and Costa, Gina L and Ichikawa, Jeffry K and Lee, Clarence C and Sudbrak, Ralf and Borodina, Tatiana A and Dahl, Andreas and Davydov, Alexey N and Marquardt, Peter and Mertes, Florian and Nietfeld, Wilfiried and Rosenstiel, Philip and Schreiber, Stefan and Soldatov, Aleksey V and Timmermann, Bernd and Tolzmann, Marius and Affourtit, Jason and Ashworth, Dana and Attiya, Said and Bachorski, Melissa and Buglione, Eli and Burke, Adam and Caprio, Amanda and Celone, Christopher and Clark, Shauna and Conners, David and Desany, Brian and Gu, Lisa and Guccione, Lorri and Kao, Kalvin and Kebbel, Andrew and Knowlton, Jennifer and Labrecque, Matthew and McDade, Louise and Mealmaker, Craig and Minderman, Melissa and Nawrocki, Anne and Niazi, Faheem and Pareja, Kristen and Ramenani, Ravi and Riches, David and Song, Wanmin and Turcotte, Cynthia and Wang, Shally and Dooling, David and Fulton, Lucinda and Fulton, Robert and Weinstock, George and Burton, John and Carter, David M and Churcher, Carol and Coffey, Alison and Cox, Anthony and Palotie, Aarno and Quail, Michael and Skelly, Tom and Stalker, James and Swerdlow, Harold P and Turner, Daniel and De Witte, Anniek and Giles, Shane and Bainbridge, Matthew and Challis, Danny and Sabo, Aniko and Yu, Fuli and Yu, Jin and Fang, Xiaodong and Guo, Xiaosen and Li, Yingrui and Luo, Ruibang and Tai, Shuaishuai and Wu, Honglong and Zheng, Hancheng and Zheng, Xiaole and Zhou, Yan and Marth, Gabor T and Garrison, Erik P and Huang, Weichun and Indap, Amit and Kural, Deniz and Lee, Wan-Ping and Leong, Wen Fung and Quinlan, Aaron R and Stewart, Chip and Stromberg, Michael P and Ward, Alistair N and Wu, Jiantao and Lee, Charles and Mills, Ryan E and Shi, Xinghua and Daly, Mark J and DePristo, Mark A and Ball, Aaron D and Banks, Eric and Browning, Brian L and Garimella, Kiran V and Grossman, Sharon R and Handsaker, Robert E and Hanna, Matt and Hartl, Chris and Kernytsky, Andrew M and Korn, Joshua M and Li, Heng and Maguire, Jared R and McCarroll, Steven A and McKenna, Aaron and Nemesh, James C and Philippakis, Anthony A and Poplin, Ryan E and Price, Alkes and Rivas, Manuel A and Sabeti, Pardis C and Schaffner, Stephen F and Shlyakhter, Ilya A and Cooper, David N and Ball, Edward V and Mort, Matthew and Phillips, Andrew D and Stenson, Peter D and Sebat, Jonathan and Makarov, Vladimir and Ye, Kenny and Yoon, Seungtai C and Bustamante, Carlos D and Boyko, Adam and Degenhardt, Jeremiah and Gravel, Simon and Gutenkunst, Ryan N and Kaganovich, Mark and Keinan, Alon and Lacroute, Phil and Ma, Xin and Reynolds, Andy and Clarke, Laura and Cunningham, Fiona and Herrero, Javier and Keenen, Stephen and Kulesha, Eugene and Leinonen, Rasko and McLaren, William M and Radhakrishnan, Rajesh and Smith, Richard E and Zalunin, Vadim and Zheng-Bradley, Xiangqun and Korbel, Jan O and St{\"u}tz, Adrian M and Bauer, Markus and Cheetham, R Keira and Cox, Tony and Eberle, Michael and James, Terena and Kahn, Scott and Murray, Lisa and Ye, Kai and Fu, Yutao and Hyland, Fiona C L and Manning, Jonathan M and McLaughlin, Stephen F and Peckham, Heather E and Sakarya, Onur and Sun, Yongming A and Tsung, Eric F and Batzer, Mark A and Konkel, Miriam K and Walker, Jerilyn A and Albrecht, Marcus W and Amstislavskiy, Vyacheslav S and Herwig, Ralf and Parkhomchuk, Dimitri V and Agarwala, Richa and Khouri, Hoda M and Morgulis, Aleksandr O and Paschall, Justin E and Phan, Lon D and Rotmistrovsky, Kirill E and Sanders, Robert D and Shumway, Martin F and Xiao, Chunlin and Auton, Adam and Iqbal, Zamin and Lunter, Gerton and Marchini, Jonathan L and Moutsianas, Loukas and Myers, Simon and Tumian, Afidalina and Knight, James and Winer, Roger and Craig...},
	Date-Added = {2014-10-01 20:30:59 +0000},
	Date-Modified = {2014-10-01 20:30:59 +0000},
	Journal = {NATURE},
	Number = {7319},
	Pages = {1061--1073},
	Title = {{A map of human genome variation from population-scale sequencing}},
	Volume = {467},
	Year = {2010}}

@article{McVean:2012co,
	Author = {McVean, Gil A and Altshuler Co-Chair, David M and Durbin Co-Chair, Richard M and Abecasis, Gon{\c c}alo R and Bentley, David R and Chakravarti, Aravinda and Clark, Andrew G and Donnelly, Peter and Eichler, Evan E and Flicek, Paul and Gabriel, Stacey B and Gibbs, Richard A and Green, Eric D and Hurles, Matthew E and Knoppers, Bartha M and Korbel, Jan O and Lander, Eric S and Lee, Charles and Lehrach, Hans and Mardis, Elaine R and Marth, Gabor T and McVean, Gil A and Nickerson, Deborah A and Schmidt, Jeanette P and Sherry, Stephen T and Wang, Jun and Wilson, Richard K and Gibbs Principal Investigator, Richard A and Dinh, Huyen and Kovar, Christie and Lee, Sandra and Lewis, Lora and Muzny, Donna and Reid, Jeff and Wang, Min and Wang Principal Investigator, Jun and Fang, Xiaodong and Guo, Xiaosen and Jian, Min and Jiang, Hui and Jin, Xin and Li, Guoqing and Li, Jingxiang and Li, Yingrui and Li, Zhuo and Liu, Xiao and Lu, Yao and Ma, Xuedi and Su, Zhe and Tai, Shuaishuai and Tang, Meifang and Wang, Bo and Wang, Guangbiao and Wu, Honglong and Wu, Renhua and Yin, Ye and Zhang, Wenwei and Zhao, Jiao and Zhao, Meiru and Zheng, Xiaole and Zhou, Yan and Lander Principal Investigator, Eric S and Altshuler, David M and Gabriel Co-Chair, Stacey B and Gupta, Namrata and Flicek Principal Investigator, Paul and Clarke, Laura and Leinonen, Rasko and Smith, Richard E and Zheng-Bradley, Xiangqun and Bentley Principal Investigator, David R and Grocock, Russell and Humphray, Sean and James, Terena and Kingsbury, Zoya and Lehrach Principal Investigator, Hans and Sudbrak Project Leader, Ralf and Albrecht, Marcus W and Amstislavskiy, Vyacheslav S and Borodina, Tatiana A and Lienhard, Matthias and Mertes, Florian and Sultan, Marc and Timmermann, Bernd and Yaspo, Marie-Laure and Sherry Principal Investigator, Stephen T and McVean Principal Investigator, Gil A and Mardis Co-Principal Investigator Co-Chair, Elaine R and Wilson Co-Principal Investigator, Richard K and Fulton, Lucinda and Fulton, Robert and Weinstock, George M and Durbin Principal Investigator, Richard M and Balasubramaniam, Senduran and Burton, John and Danecek, Petr and Keane, Thomas M and Kolb-Kokocinski, Anja and McCarthy, Shane and Stalker, James and Quail, Michael and Schmidt Principal Investigator, Jeanette P and Davies, Christopher J and Gollub, Jeremy and Webster, Teresa and Wong, Brant and Zhan, Yiping and Auton Principal Investigator, Adam and Gibbs Principal Investigator, Richard A and Yu Project Leader, Fuli and Bainbridge, Matthew and Challis, Danny and Evani, Uday S and Lu, James and Muzny, Donna and Nagaswamy, Uma and Reid, Jeff and Sabo, Aniko and Wang, Yi and Yu, Jin and Wang Principal Investigator, Jun and Coin, Lachlan J M and Fang, Lin and Guo, Xiaosen and Jin, Xin and Li, Guoqing and Li, Qibin and Li, Yingrui and Li, Zhenyu and Lin, Haoxiang and Liu, Binghang and Luo, Ruibang and Qin, Nan and Shao, Haojing and Wang, Bingqiang and Xie, Yinlong and Ye, Chen and Yu, Chang and Zhang, Fan and Zheng, Hancheng and Zhu, Hongmei and Marth Principal Investigator, Gabor T and Garrison, Erik P and Kural, Deniz and Lee, Wan-Ping and Fung Leong, Wen and Ward, Alistair N and Wu, Jiantao and Zhang, Mengyao and Lee Principal Investigator, Charles and Griffin, Lauren and Hsieh, Chih-Heng and Mills, Ryan E and Shi, Xinghua and von Grotthuss, Marcin and Zhang, Chengsheng and Daly Principal Investigator, Mark J and DePristo Project Leader, Mark A and Altshuler, David M and Banks, Eric and Bhatia, Gaurav and Carneiro, Mauricio O and del Angel, Guillermo and Gabriel, Stacey B and Genovese, Giulio and Gupta, Namrata and Handsaker, Robert E and Hartl, Chris and Lander, Eric S and McCarroll, Steven A and Nemesh, James C and Poplin, Ryan E and Schaffner, Stephen F and Shakir, Khalid and Yoon Principal Investigator, Seungtai C and Lihm, Jayon and Makarov, Vladimir and Jin Principal Investigator, Hanjun and Kim, Wook and Cheol Kim, Ki and Korbel Principal Investigator, Jan O and Rausch, Tobias and Flicek Principal Investigator, Paul and Beal, Kathryn and Clarke, Laura and Cunningham, Fiona and Herrero, Javier and McLaren, William M and Ritchie, Graham R S and Smith, Richard E and Zheng-Bradley, Xiangqun and Clark Principal Investigator, Andrew G and Gottipati, Srikanth and Keinan, Alon and Rodriguez-Flores, Juan L and Sabeti Principal Investigator, Pardis C and Grossman, Sharon R and Tabrizi, Shervin and Tariyal, Ridhi and Cooper Principal Investigator, David N and Ball, Edward V and Stenson, Peter D and Bentley Principal Investigator, David R and Barnes, Bret and Bauer, Markus and Keira Cheetham, R and Cox, Tony and Eberle, Michael and Humphray, Sean and Kahn, Scott and Murray, Lisa and Peden, John and Shaw, Richard and Ye Principa...},
	Date-Added = {2014-10-01 20:30:59 +0000},
	Date-Modified = {2014-10-01 20:30:59 +0000},
	Journal = {NATURE},
	Month = oct,
	Number = {7422},
	Pages = {56--65},
	Title = {{An integrated map of genetic variation from 1,092 human genomes}},
	Volume = {491},
	Year = {2012}}

@article{Benjamin:2012uy,
	Author = {Benjamin, Daniel J. and Cesarini, David and van der Loos, Matthijs J. H. M. and Dawes, Christopher T. and Koellinger, Philipp D. and Magnusson, Patrik K. E. and Chabris, Christopher F. and Conley, Dalton and Laibson, David and Johannesson, Magnus and Visscher, Peter M},
	Date-Added = {2014-09-30 00:39:28 +0000},
	Date-Modified = {2014-09-30 00:39:28 +0000},
	Journal = {P NATL ACAD SCI USA},
	Month = jan,
	Number = {21},
	Pages = {8026--8031},
	Title = {{The genetic architecture of economic and political preferences}},
	Volume = {109},
	Year = {2012}}

@article{Benjamini:1995cd,
	Author = {Benjamini, Yoav and Hochberg, Yosef},
	Date-Added = {2014-09-30 00:39:28 +0000},
	Date-Modified = {2014-09-30 00:39:28 +0000},
	Journal = {Journal of the Royal Statistical Society. Series B (Methodological), Vol. 57, No. 1. (1995), pp. 289-300, doi:10.2307/2346101},
	Number = {1},
	Pages = {289--300},
	Title = {{Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing}},
	Volume = {57},
	Year = {1995}}

@article{Pavlidis2008,
	Author = {Pavlidis, P and Hutter, S and Stephan, W},
	Date-Added = {2014-09-23 20:23:29 +0000},
	Date-Modified = {2014-09-23 20:23:29 +0000},
	Journal = {MOL ECOL},
	Number = {16},
	Pages = {3585--3598},
	Title = {{A population genomic approach to map recent positive selection in model species.}},
	Volume = {17},
	Year = {2008}}

@article{Pavlidis:2010bb,
	Author = {Pavlidis, Pavlos and Jensen, Jeffrey D and Stephan, Wolfgang},
	Date-Added = {2014-09-23 20:23:29 +0000},
	Date-Modified = {2014-09-23 20:23:29 +0000},
	Journal = {GENETICS},
	Month = jul,
	Number = {3},
	Pages = {907--922},
	Title = {{Searching for footprints of positive selection in whole-genome SNP data from nonequilibrium populations.}},
	Volume = {185},
	Year = {2010}}

@article{Pavlidis:2013ug,
	Author = {Pavlidis, Pavlos and Zivkovic, Daniel and Stamatakis, Alexandros and Alachiotis, Nikolaos},
	Date-Added = {2014-09-23 20:23:29 +0000},
	Date-Modified = {2014-09-23 20:23:29 +0000},
	Journal = {MOL BIOL EVOL},
	Month = jan,
	Title = {{SweeD: Likelihood-based detection of selective sweeps in thousands of genomes}},
	Year = {2013}}

@article{Sattath:2011mz,
	Abstract = {In Drosophila, multiple lines of evidence converge in suggesting that beneficial substitutions to the genome may be common. All suffer from confounding factors, however, such that the interpretation of the evidence-in particular, conclusions about the rate and strength of beneficial substitutions-remains tentative. Here, we use genome-wide polymorphism data in D. simulans and sequenced genomes of its close relatives to construct a readily interpretable characterization of the effects of positive selection: the shape of average neutral diversity around amino acid substitutions. As expected under recurrent selective sweeps, we find a trough in diversity levels around amino acid but not around synonymous substitutions, a distinctive pattern that is not expected under alternative models. This characterization is richer than previous approaches, which relied on limited summaries of the data (e.g., the slope of a scatter plot), and relates to underlying selection parameters in a straightforward way, allowing us to make more reliable inferences about the prevalence and strength of adaptation. Specifically, we develop a coalescent-based model for the shape of the entire curve and use it to infer adaptive parameters by maximum likelihood. Our inference suggests that ∼13% of amino acid substitutions cause selective sweeps. Interestingly, it reveals two classes of beneficial fixations: a minority (approximately 3%) that appears to have had large selective effects and accounts for most of the reduction in diversity, and the remaining 10%, which seem to have had very weak selective effects. These estimates therefore help to reconcile the apparent conflict among previously published estimates of the strength of selection. More generally, our findings provide unequivocal evidence for strongly beneficial substitutions in Drosophila and illustrate how the rapidly accumulating genome-wide data can be leveraged to address enduring questions about the genetic basis of adaptation.},
	Author = {Sattath, Shmuel and Elyashiv, Eyal and Kolodny, Oren and Rinott, Yosef and Sella, Guy},
	Date-Added = {2014-09-23 16:33:12 +0000},
	Date-Modified = {2014-09-23 16:33:12 +0000},
	Doi = {10.1371/journal.pgen.1001302},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Adaptation, Biological; Amino Acid Substitution; Animals; Base Sequence; Chromosome Mapping; Drosophila; Drosophila melanogaster; Evolution, Molecular; Genetic Variation; Genome, Insect; Molecular Sequence Data; Polymorphism, Genetic; Selection, Genetic},
	Number = {2},
	Pages = {e1001302},
	Pmc = {PMC3037414},
	Pmid = {21347283},
	Pst = {epublish},
	Title = {Pervasive adaptive protein evolution apparent in diversity patterns around amino acid substitutions in Drosophila simulans},
	Volume = {7},
	Year = {2011},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1001302}}

@article{kirkpatrick2012s,
	Author = {Kirkpatrick, Mark and Kern, Andrew},
	Date-Added = {2014-09-23 16:29:32 +0000},
	Date-Modified = {2014-09-23 16:29:32 +0000},
	Journal = {Genetics},
	Number = {4},
	Pages = {1153--1155},
	Publisher = {Genetics Soc America},
	Title = {Where's the money? Inversions, genes, and the hunt for genomic targets of selection},
	Volume = {190},
	Year = {2012}}

@article{reinhardt2014parallel,
	Author = {Reinhardt, Josie A and Kolaczkowski, Bryan and Jones, Corbin D and Begun, David J and Kern, Andrew D},
	Date-Added = {2014-09-23 16:29:26 +0000},
	Date-Modified = {2014-09-23 16:29:26 +0000},
	Journal = {Genetics},
	Number = {1},
	Pages = {361--373},
	Publisher = {Genetics Soc America},
	Title = {Parallel Geographic Variation in Drosophila melanogaster},
	Volume = {197},
	Year = {2014}}

@article{langley2012genomic,
	Author = {Langley, Charles H and Stevens, Kristian and Cardeno, Charis and Lee, Yuh Chwen G and Schrider, Daniel R and Pool, John E and Langley, Sasha A and Suarez, Charlyn and Corbett-Detig, Russell B and Kolaczkowski, Bryan and others},
	Date-Added = {2014-09-23 15:13:28 +0000},
	Date-Modified = {2014-09-23 15:13:28 +0000},
	Journal = {Genetics},
	Number = {2},
	Pages = {533--598},
	Publisher = {Genetics Soc America},
	Title = {Genomic variation in natural populations of Drosophila melanogaster},
	Volume = {192},
	Year = {2012}}

@article{Mackay:2012fd,
	Author = {Mackay, Trudy F C and Richards, Stephen and Stone, Eric A and Barbadilla, Antonio and Ayroles, Julien F and Zhu, Dianhui and Casillas, Sonia and Han, Yi and Magwire, Michael M and Cridland, Julie M and Richardson, Mark F and Anholt, Robert R H and Barr{\'o}n, Maite and Bess, Crystal and Blankenburg, Kerstin Petra and Carbone, Mary Anna and Castellano, David and Chaboub, Lesley and Duncan, Laura and Harris, Zeke and Javaid, Mehwish and Jayaseelan, Joy Christina and Jhangiani, Shalini N and Jordan, Katherine W and Lara, Fremiet and Lawrence, Faye and Lee, Sandra L and Librado, Pablo and Linheiro, Raquel S and Lyman, Richard F and Mackey, Aaron J and Munidasa, Mala and Muzny, Donna Marie and Nazareth, Lynne and Newsham, Irene and Perales, Lora and Pu, Ling-Ling and Qu, Carson and R{\`a}mia, Miquel and Reid, Jeffrey G and Rollmann, Stephanie M and Rozas, Julio and Saada, Nehad and Turlapati, Lavanya and Worley, Kim C and Wu, Yuan-Qing and Yamamoto, Akihiko and Zhu, Yiming and Bergman, Casey M and Thornton, Kevin R and Mittelman, David and Gibbs, Richard A},
	Date-Added = {2014-09-23 15:12:40 +0000},
	Date-Modified = {2014-09-23 15:12:40 +0000},
	Journal = {NATURE},
	Month = feb,
	Number = {7384},
	Pages = {173--178},
	Title = {{The Drosophila melanogaster Genetic Reference Panel}},
	Volume = {482},
	Year = {2012}}

@article{hernandez2011classic,
	Author = {Hernandez, Ryan D and Kelley, Joanna L and Elyashiv, Eyal and Melton, S Cord and Auton, Adam and McVean, Gilean and Sella, Guy and Przeworski, Molly and others},
	Date-Added = {2014-09-23 15:09:36 +0000},
	Date-Modified = {2014-09-23 15:09:36 +0000},
	Journal = {Science},
	Number = {6019},
	Pages = {920--924},
	Publisher = {American Association for the Advancement of Science},
	Title = {Classic selective sweeps were rare in recent human evolution},
	Volume = {331},
	Year = {2011}}

@article{peter2012distinguishing,
	Author = {Peter, Benjamin M and Huerta-Sanchez, Emilia and Nielsen, Rasmus},
	Date-Added = {2014-09-23 15:07:26 +0000},
	Date-Modified = {2014-09-23 15:07:26 +0000},
	Journal = {PLoS genetics},
	Number = {10},
	Pages = {e1003011},
	Publisher = {Public Library of Science},
	Title = {Distinguishing between selective sweeps from standing variation and from a de novo mutation},
	Volume = {8},
	Year = {2012}}

@inproceedings{altun2003hidden,
	Author = {Altun, Yasemin and Tsochantaridis, Ioannis and Hofmann, Thomas and others},
	Booktitle = {ICML},
	Date-Added = {2014-09-19 15:02:45 +0000},
	Date-Modified = {2014-09-19 15:02:45 +0000},
	Pages = {3--10},
	Title = {Hidden markov support vector machines},
	Volume = {3},
	Year = {2003}}

@article{Montgomery:2006xp,
	Abstract = {MOTIVATION: Our understanding of gene regulation is currently limited by our ability to collectively synthesize and catalogue transcriptional regulatory elements stored in scientific literature. Over the past decade, this task has become increasingly challenging as the accrual of biologically validated regulatory sequences has accelerated. To meet this challenge, novel community-based approaches to regulatory element annotation are required.
SUMMARY: Here, we present the Open Regulatory Annotation (ORegAnno) database as a dynamic collection of literature-curated regulatory regions, transcription factor binding sites and regulatory mutations (polymorphisms and haplotypes). ORegAnno has been designed to manage the submission, indexing and validation of new annotations from users worldwide. Submissions to ORegAnno are immediately cross-referenced to EnsEMBL, dbSNP, Entrez Gene, the NCBI Taxonomy database and PubMed, where appropriate.
AVAILABILITY: ORegAnno is available directly through MySQL, Web services, and online at http://www.oreganno.org. All software is licensed under the Lesser GNU Public License (LGPL).},
	Author = {Montgomery, S B and Griffith, O L and Sleumer, M C and Bergman, C M and Bilenky, M and Pleasance, E D and Prychyna, Y and Zhang, X and Jones, S J M},
	Date-Added = {2014-01-21 02:11:11 +0000},
	Date-Modified = {2014-01-21 02:11:11 +0000},
	Doi = {10.1093/bioinformatics/btk027},
	Journal = {Bioinformatics},
	Journal-Full = {Bioinformatics (Oxford, England)},
	Mesh = {Binding Sites; Database Management Systems; Databases, Genetic; Documentation; Gene Expression Regulation; Genetic Variation; Internet; Natural Language Processing; Periodicals as Topic; Promoter Regions, Genetic; Protein Binding; Transcription Factors},
	Month = {Mar},
	Number = {5},
	Pages = {637-40},
	Pmid = {16397004},
	Pst = {ppublish},
	Title = {ORegAnno: an open access database and curation system for literature-derived promoters, transcription factor binding sites and regulatory variation},
	Volume = {22},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/btk027}}

@article{Hamosh:2005sw,
	Abstract = {Online Mendelian Inheritance in Man (OMIM) is a comprehensive, authoritative and timely knowledgebase of human genes and genetic disorders compiled to support human genetics research and education and the practice of clinical genetics. Started by Dr Victor A. McKusick as the definitive reference Mendelian Inheritance in Man, OMIM (http://www.ncbi.nlm.nih.gov/omim/) is now distributed electronically by the National Center for Biotechnology Information, where it is integrated with the Entrez suite of databases. Derived from the biomedical literature, OMIM is written and edited at Johns Hopkins University with input from scientists and physicians around the world. Each OMIM entry has a full-text summary of a genetically determined phenotype and/or gene and has numerous links to other genetic databases such as DNA and protein sequence, PubMed references, general and locus-specific mutation databases, HUGO nomenclature, MapViewer, GeneTests, patient support groups and many others. OMIM is an easy and straightforward portal to the burgeoning information in human genetics.},
	Author = {Hamosh, Ada and Scott, Alan F and Amberger, Joanna S and Bocchini, Carol A and McKusick, Victor A},
	Date-Added = {2014-01-21 02:10:05 +0000},
	Date-Modified = {2014-01-21 02:10:05 +0000},
	Doi = {10.1093/nar/gki033},
	Journal = {Nucleic Acids Res},
	Journal-Full = {Nucleic acids research},
	Mesh = {Chromosome Mapping; Databases, Genetic; Genes; Genetic Diseases, Inborn; Humans; Phenotype; User-Computer Interface},
	Month = {Jan},
	Number = {Database issue},
	Pages = {D514-7},
	Pmc = {PMC539987},
	Pmid = {15608251},
	Pst = {ppublish},
	Title = {Online Mendelian Inheritance in Man (OMIM), a knowledgebase of human genes and genetic disorders},
	Volume = {33},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gki033}}

@article{shimoyama2011rgd,
	Author = {Shimoyama, Mary and Smith, Jennifer R and Hayman, Tom and Laulederkind, Stan and Lowry, Tim and Nigam, Rajni and Petri, Victoria and Wang, Shur-Jen and Dwinell, Melinda and Jacob, Howard and others},
	Date-Added = {2014-01-21 02:08:38 +0000},
	Date-Modified = {2014-01-21 02:08:38 +0000},
	Journal = {Human genomics},
	Number = {2},
	Pages = {124},
	Publisher = {NIH Public Access},
	Title = {RGD: a comparative genomics platform},
	Volume = {5},
	Year = {2011}}

@article{hindorff2009potential,
	Author = {Hindorff, Lucia A and Sethupathy, Praveen and Junkins, Heather A and Ramos, Erin M and Mehta, Jayashri P and Collins, Francis S and Manolio, Teri A},
	Date-Added = {2014-01-21 02:06:15 +0000},
	Date-Modified = {2014-01-21 02:06:15 +0000},
	Journal = {Proceedings of the National Academy of Sciences},
	Number = {23},
	Pages = {9362--9367},
	Publisher = {National Acad Sciences},
	Title = {Potential etiologic and functional implications of genome-wide association loci for human diseases and traits},
	Volume = {106},
	Year = {2009}}

@article{Harrow:2012hs,
	Abstract = {The GENCODE Consortium aims to identify all gene features in the human genome using a combination of computational analysis, manual annotation, and experimental validation. Since the first public release of this annotation data set, few new protein-coding loci have been added, yet the number of alternative splicing transcripts annotated has steadily increased. The GENCODE 7 release contains 20,687 protein-coding and 9640 long noncoding RNA loci and has 33,977 coding transcripts not represented in UCSC genes and RefSeq. It also has the most comprehensive annotation of long noncoding RNA (lncRNA) loci publicly available with the predominant transcript form consisting of two exons. We have examined the completeness of the transcript annotation and found that 35% of transcriptional start sites are supported by CAGE clusters and 62% of protein-coding genes have annotated polyA sites. Over one-third of GENCODE protein-coding genes are supported by peptide hits derived from mass spectrometry spectra submitted to Peptide Atlas. New models derived from the Illumina Body Map 2.0 RNA-seq data identify 3689 new loci not currently in GENCODE, of which 3127 consist of two exon models indicating that they are possibly unannotated long noncoding loci. GENCODE 7 is publicly available from gencodegenes.org and via the Ensembl and UCSC Genome Browsers.},
	Author = {Harrow, Jennifer and Frankish, Adam and Gonzalez, Jose M and Tapanari, Electra and Diekhans, Mark and Kokocinski, Felix and Aken, Bronwen L and Barrell, Daniel and Zadissa, Amonida and Searle, Stephen and Barnes, If and Bignell, Alexandra and Boychenko, Veronika and Hunt, Toby and Kay, Mike and Mukherjee, Gaurab and Rajan, Jeena and Despacio-Reyes, Gloria and Saunders, Gary and Steward, Charles and Harte, Rachel and Lin, Michael and Howald, C{\'e}dric and Tanzer, Andrea and Derrien, Thomas and Chrast, Jacqueline and Walters, Nathalie and Balasubramanian, Suganthi and Pei, Baikang and Tress, Michael and Rodriguez, Jose Manuel and Ezkurdia, Iakes and van Baren, Jeltje and Brent, Michael and Haussler, David and Kellis, Manolis and Valencia, Alfonso and Reymond, Alexandre and Gerstein, Mark and Guig{\'o}, Roderic and Hubbard, Tim J},
	Date-Added = {2014-01-21 02:02:50 +0000},
	Date-Modified = {2014-01-21 02:02:50 +0000},
	Doi = {10.1101/gr.135350.111},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Animals; Computational Biology; DNA, Complementary; Databases, Genetic; Evolution, Molecular; Exons; Genetic Loci; Genome, Human; Genomics; Humans; Internet; Models, Molecular; Molecular Sequence Annotation; Open Reading Frames; Pseudogenes; Quality Control; RNA Splice Sites; RNA, Long Noncoding; Reproducibility of Results; Untranslated Regions},
	Month = {Sep},
	Number = {9},
	Pages = {1760-74},
	Pmc = {PMC3431492},
	Pmid = {22955987},
	Pst = {ppublish},
	Title = {GENCODE: the reference human genome annotation for The ENCODE Project},
	Volume = {22},
	Year = {2012},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.135350.111}}

@article{becker2004genetic,
	Author = {Becker, Kevin G and Barnes, Kathleen C and Bright, Tiffani J and Wang, S Alex},
	Date-Added = {2014-01-21 02:01:56 +0000},
	Date-Modified = {2014-01-21 02:01:56 +0000},
	Journal = {Nature genetics},
	Number = {5},
	Pages = {431--432},
	Publisher = {Nature Publishing Group},
	Title = {The genetic association database},
	Volume = {36},
	Year = {2004}}

@article{Sundquist:2008uf,
	Abstract = {The genome of an admixed individual with ancestors from isolated populations is a mosaic of chromosomal blocks, each following the statistical properties of variation seen in those populations. By analyzing polymorphisms in the admixed individual against those seen in representatives from the populations, we can infer the ancestral source of the individual's haploblocks. In this paper we describe a novel approach for ancestry inference, HAPAA (HMM-based analysis of polymorphisms in admixed ancestries), that models the allelic and haplotypic variation in the populations and captures the signal of correlation due to linkage disequilibrium, resulting in greatly improved accuracy. We also introduce a methodology for evaluating the effect of genetic divergence between ancestral populations and time-to-admixture on inference accuracy. Using HAPAA, we explore the limits of ancestry inference in closely related populations.},
	Author = {Sundquist, Andreas and Fratkin, Eugene and Do, Chuong B and Batzoglou, Serafim},
	Date-Added = {2014-01-20 20:27:56 +0000},
	Date-Modified = {2014-01-20 20:27:56 +0000},
	Doi = {10.1101/gr.072850.107},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Ethnic Groups; Genetics, Population; Genome, Human; Humans; Linkage Disequilibrium; Markov Chains; Polymorphism, Genetic},
	Month = {Apr},
	Number = {4},
	Pages = {676-82},
	Pmc = {PMC2279255},
	Pmid = {18353807},
	Pst = {ppublish},
	Title = {Effect of genetic divergence in identifying ancestral origin using HAPAA},
	Volume = {18},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.072850.107}}

@article{Lujan:2005ys,
	Abstract = {Our understanding of the role played by neurotransmitter receptors in the developing brain has advanced in recent years. The major excitatory and inhibitory neurotransmitters in the brain, glutamate and GABA, activate both ionotropic (ligand-gated ion channels) and metabotropic (G protein-coupled) receptors, and are generally associated with neuronal communication in the mature brain. However, before the emergence of their role in neurotransmission in adulthood, they also act to influence earlier developmental events, some of which occur prior to synapse formation: such as proliferation, migration, differentiation or survival processes during neural development. To fulfill these actions in the constructing of the nervous system, different types of glutamate and GABA receptors need to be expressed both at the right time and at the right place. The identification by molecular cloning of 16 ionotropic glutamate receptor subunits, eight metabotropic glutamate receptor subtypes, 21 ionotropic and two metabotropic GABA receptor subunits, some of which exist in alternatively splice variants, has enriched our appreciation of how molecular diversity leads to functional diversity in the brain. It now appears that many different types of glutamate and GABA receptor subunits have prominent expression in the embryonic and/or postnatal brain, whereas others are mainly present in the adult brain. Although the significance of this differential expression of subunits is not fully understood, it appears that the change in subunit composition is essential for normal development in particular brain regions. This review focuses on emerging information relating to the expression and role of glutamatergic and GABAergic neurotransmitter receptors during prenatal and postnatal development.},
	Author = {Luj{\'a}n, R and Shigemoto, R and L{\'o}pez-Bendito, G},
	Date-Added = {2014-01-20 19:38:54 +0000},
	Date-Modified = {2014-01-20 19:38:54 +0000},
	Doi = {10.1016/j.neuroscience.2004.09.042},
	Journal = {Neuroscience},
	Journal-Full = {Neuroscience},
	Mesh = {Animals; Brain; Cell Differentiation; Cell Movement; Cell Proliferation; Glutamic Acid; Humans; Neurons; Receptors, GABA; Receptors, Neurotransmitter; Signal Transduction; Synapses},
	Number = {3},
	Pages = {567-80},
	Pmid = {15590141},
	Pst = {ppublish},
	Title = {Glutamate and GABA receptor signalling in the developing brain},
	Volume = {130},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.neuroscience.2004.09.042}}

@article{petroff2002book,
	Author = {Petroff, Ognen AC},
	Date-Added = {2014-01-20 19:38:16 +0000},
	Date-Modified = {2014-01-20 19:38:16 +0000},
	Journal = {The Neuroscientist},
	Number = {6},
	Pages = {562--573},
	Publisher = {SAGE Publications},
	Title = {Book Review: GABA and glutamate in the human brain},
	Volume = {8},
	Year = {2002}}

@article{Liu:2012wf,
	Abstract = {Over the course of ontogenesis, the human brain and human cognitive abilities develop in parallel, resulting in a phenotype strikingly distinct from that of other primates. Here, we used microarrays and RNA-sequencing to examine human-specific gene expression changes taking place during postnatal brain development in the prefrontal cortex and cerebellum of humans, chimpanzees, and rhesus macaques. We show that the most prominent human-specific expression change affects genes associated with synaptic functions and represents an extreme shift in the timing of synaptic development in the prefrontal cortex, but not the cerebellum. Consequently, peak expression of synaptic genes in the prefrontal cortex is shifted from <1 yr in chimpanzees and macaques to 5 yr in humans. This result was supported by protein expression profiles of synaptic density markers and by direct observation of synaptic density by electron microscopy. Mechanistically, the human-specific change in timing of synaptic development involves the MEF2A-mediated activity-dependent regulatory pathway. Evolutionarily, this change may have taken place after the split of the human and the Neanderthal lineages.},
	Author = {Liu, Xiling and Somel, Mehmet and Tang, Lin and Yan, Zheng and Jiang, Xi and Guo, Song and Yuan, Yuan and He, Liu and Oleksiak, Anna and Zhang, Yan and Li, Na and Hu, Yuhui and Chen, Wei and Qiu, Zilong and P{\"a}{\"a}bo, Svante and Khaitovich, Philipp},
	Date-Added = {2014-01-20 19:37:32 +0000},
	Date-Modified = {2014-01-20 19:37:32 +0000},
	Doi = {10.1101/gr.127324.111},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Adolescent; Adult; Aged; Aged, 80 and over; Animals; Cerebellum; Child; Child, Preschool; Evolution, Molecular; Gene Expression Profiling; Gene Expression Regulation, Developmental; Humans; Infant; Infant, Newborn; Macaca mulatta; Middle Aged; Neuromuscular Junction; Oligonucleotide Array Sequence Analysis; Pan troglodytes; Prefrontal Cortex; Sequence Analysis, RNA; Species Specificity; Synapses; Young Adult},
	Month = {Apr},
	Number = {4},
	Pages = {611-22},
	Pmc = {PMC3317144},
	Pmid = {22300767},
	Pst = {ppublish},
	Title = {Extension of cortical synaptic development distinguishes humans from chimpanzees and macaques},
	Volume = {22},
	Year = {2012},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.127324.111}}

@article{Halligan:2006qr,
	Abstract = {Non-coding DNA comprises approximately 80% of the euchromatic portion of the Drosophila melanogaster genome. Non-coding sequences are known to contain functionally important elements controlling gene expression, but the proportion of sites that are selectively constrained is still largely unknown. We have compared the complete D. melanogaster and Drosophila simulans genome sequences to estimate mean selective constraint (the fraction of mutations that are eliminated by selection) in coding and non-coding DNA by standardizing to substitution rates in putatively unconstrained sequences. We show that constraint is positively correlated with intronic and intergenic sequence length and is generally remarkably strong in non-coding DNA, implying that more than half of all point mutations in the Drosophila genome are deleterious. This fraction is also likely to be an underestimate if many substitutions in non-coding DNA are adaptively driven to fixation. We also show that substitutions in long introns and intergenic sequences are clustered, such that there is an excess of substitutions <8 bp apart and a deficit farther apart. These results suggest that there are blocks of constrained nucleotides, presumably involved in gene expression control, that are concentrated in long non-coding sequences. Furthermore, we infer that there is more than three times as much functional non-coding DNA as protein-coding DNA in the Drosophila genome. Most deleterious mutations therefore occur in non-coding DNA, and these may make an important contribution to a wide variety of evolutionary processes.},
	Author = {Halligan, Daniel L and Keightley, Peter D},
	Date-Added = {2014-01-20 18:36:44 +0000},
	Date-Modified = {2014-01-20 18:36:44 +0000},
	Doi = {10.1101/gr.5022906},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Animals; Base Sequence; DNA; DNA, Intergenic; Drosophila melanogaster; Evolution, Molecular; Gene Expression Regulation; Genome, Insect; Introns; Molecular Sequence Data; Point Mutation; Selection, Genetic; Sequence Analysis, DNA; Sequence Homology, Nucleic Acid; Species Specificity},
	Month = {Jul},
	Number = {7},
	Pages = {875-84},
	Pmc = {PMC1484454},
	Pmid = {16751341},
	Pst = {ppublish},
	Title = {Ubiquitous selective constraints in the Drosophila genome revealed by a genome-wide interspecies comparison},
	Volume = {16},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.5022906}}

@article{Hupalo:2013ez,
	Abstract = {Here, we describe the construction of a phylogenetically deep, whole-genome alignment of 20 flowering plants, along with an analysis of plant genome conservation. Each included angiosperm genome was aligned to a reference genome, Arabidopsis thaliana, using the LASTZ/MULTIZ paradigm and tools from the University of California-Santa Cruz Genome Browser source code. In addition to the multiple alignment, we created a local genome browser displaying multiple tracks of newly generated genome annotation, as well as annotation sourced from published data of other research groups. An investigation into A. thaliana gene features present in the aligned A. lyrata genome revealed better conservation of start codons, stop codons, and splice sites within our alignments (51% of features from A. thaliana conserved without interruption in A. lyrata) when compared with previous publicly available plant pairwise alignments (34% of features conserved). The detailed view of conservation across angiosperms revealed not only high coding-sequence conservation but also a large set of previously uncharacterized intergenic conservation. From this, we annotated the collection of conserved features, revealing dozens of putative noncoding RNAs, including some with recorded small RNA expression. Comparing conservation between kingdoms revealed a faster decay of vertebrate genome features when compared with angiosperm genomes. Finally, conserved sequences were searched for folding RNA features, including but not limited to noncoding RNA (ncRNA) genes. Among these, we highlight a double hairpin in the 5'-untranslated region (5'-UTR) of the PRIN2 gene and a putative ncRNA with homology targeting the LAF3 protein.},
	Author = {Hupalo, Daniel and Kern, Andrew D},
	Date-Added = {2014-01-20 15:56:09 +0000},
	Date-Modified = {2014-01-20 15:56:09 +0000},
	Doi = {10.1093/molbev/mst082},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Keywords = {Arabidopsis; RNA folding; alignment; angiosperm; comparative genomics; conservation; ultraconserved elements},
	Month = {Jul},
	Number = {7},
	Pages = {1729-44},
	Pmid = {23640124},
	Pst = {ppublish},
	Title = {Conservation and functional element discovery in 20 angiosperm plant genomes},
	Volume = {30},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/mst082}}

@article{Forbes:2010qf,
	Abstract = {The catalogue of Somatic Mutations in Cancer (COSMIC) (http://www.sanger.ac.uk/cosmic/) is the largest public resource for information on somatically acquired mutations in human cancer and is available freely without restrictions. Currently (v43, August 2009), COSMIC contains details of 1.5-million experiments performed through 13,423 genes in almost 370,000 tumours, describing over 90,000 individual mutations. Data are gathered from two sources, publications in the scientific literature, (v43 contains 7797 curated articles) and the full output of the genome-wide screens from the Cancer Genome Project (CGP) at the Sanger Institute, UK. Most of the world's literature on point mutations in human cancer has now been curated into COSMIC and while this is continually updated, a greater emphasis on curating fusion gene mutations is driving the expansion of this information; over 2700 fusion gene mutations are now described. Whole-genome sequencing screens are now identifying large numbers of genomic rearrangements in cancer and COSMIC is now displaying details of these analyses also. Examination of COSMIC's data is primarily web-driven, focused on providing mutation range and frequency statistics based upon a choice of gene and/or cancer phenotype. Graphical views provide easily interpretable summaries of large quantities of data, and export functions can provide precise details of user-selected data.},
	Author = {Forbes, Simon A and Tang, Gurpreet and Bindal, Nidhi and Bamford, Sally and Dawson, Elisabeth and Cole, Charlotte and Kok, Chai Yin and Jia, Mingming and Ewing, Rebecca and Menzies, Andrew and Teague, Jon W and Stratton, Michael R and Futreal, P Andrew},
	Date-Added = {2014-01-20 15:50:26 +0000},
	Date-Modified = {2014-01-20 15:50:26 +0000},
	Doi = {10.1093/nar/gkp995},
	Journal = {Nucleic Acids Res},
	Journal-Full = {Nucleic acids research},
	Mesh = {Access to Information; Computational Biology; Computer Graphics; Databases, Genetic; Databases, Nucleic Acid; Databases, Protein; Genome, Human; Humans; Information Storage and Retrieval; Internet; Mutation; Neoplasms; Software},
	Month = {Jan},
	Number = {Database issue},
	Pages = {D652-7},
	Pmc = {PMC2808858},
	Pmid = {19906727},
	Pst = {ppublish},
	Title = {COSMIC (the Catalogue of Somatic Mutations in Cancer): a resource to investigate acquired mutations in human cancer},
	Volume = {38},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gkp995}}

@article{Pool:2012vf,
	Abstract = {Drosophila melanogaster has played a pivotal role in the development of modern population genetics. However, many basic questions regarding the demographic and adaptive history of this species remain unresolved. We report the genome sequencing of 139 wild-derived strains of D. melanogaster, representing 22 population samples from the sub-Saharan ancestral range of this species, along with one European population. Most genomes were sequenced above 25X depth from haploid embryos. Results indicated a pervasive influence of non-African admixture in many African populations, motivating the development and application of a novel admixture detection method. Admixture proportions varied among populations, with greater admixture in urban locations. Admixture levels also varied across the genome, with localized peaks and valleys suggestive of a non-neutral introgression process. Genomes from the same location differed starkly in ancestry, suggesting that isolation mechanisms may exist within African populations. After removing putatively admixed genomic segments, the greatest genetic diversity was observed in southern Africa (e.g. Zambia), while diversity in other populations was largely consistent with a geographic expansion from this potentially ancestral region. The European population showed different levels of diversity reduction on each chromosome arm, and some African populations displayed chromosome arm-specific diversity reductions. Inversions in the European sample were associated with strong elevations in diversity across chromosome arms. Genomic scans were conducted to identify loci that may represent targets of positive selection within an African population, between African populations, and between European and African populations. A disproportionate number of candidate selective sweep regions were located near genes with varied roles in gene regulation. Outliers for Europe-Africa F(ST) were found to be enriched in genomic regions of locally elevated cosmopolitan admixture, possibly reflecting a role for some of these loci in driving the introgression of non-African alleles into African populations.},
	Author = {Pool, John E and Corbett-Detig, Russell B and Sugino, Ryuichi P and Stevens, Kristian A and Cardeno, Charis M and Crepeau, Marc W and Duchen, Pablo and Emerson, J J and Saelao, Perot and Begun, David J and Langley, Charles H},
	Date-Added = {2014-01-20 15:12:56 +0000},
	Date-Modified = {2014-01-20 15:12:56 +0000},
	Doi = {10.1371/journal.pgen.1003080},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Adaptation, Physiological; Africa South of the Sahara; Alleles; Animals; Base Sequence; Drosophila melanogaster; Europe; Evolution, Molecular; Genetic Variation; Genome, Insect; High-Throughput Nucleotide Sequencing; Metagenomics; Selection, Genetic},
	Number = {12},
	Pages = {e1003080},
	Pmc = {PMC3527209},
	Pmid = {23284287},
	Pst = {ppublish},
	Title = {Population Genomics of sub-saharan Drosophila melanogaster: African diversity and non-African admixture},
	Volume = {8},
	Year = {2012},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1003080}}

@article{Cotney:2013ff,
	Abstract = {The evolution of human anatomical features likely involved changes in gene regulation during development. However, the nature and extent of human-specific developmental regulatory functions remain unknown. We obtained a genome-wide view of cis-regulatory evolution in human embryonic tissues by comparing the histone modification H3K27ac, which provides a quantitative readout of promoter and enhancer activity, during human, rhesus, and mouse limb development. Based on increased H3K27ac, we find that 13% of promoters and 11% of enhancers have gained activity on the human lineage since the human-rhesus divergence. These gains largely arose by modification of ancestral regulatory activities in the limb or potential co-option from other tissues and are likely to have heterogeneous genetic causes. Most enhancers that exhibit gain of activity in humans originated in mammals. Gains at promoters and enhancers in the human limb are associated with increased gene expression, suggesting they include molecular drivers of human morphological evolution.},
	Author = {Cotney, Justin and Leng, Jing and Yin, Jun and Reilly, Steven K and DeMare, Laura E and Emera, Deena and Ayoub, Albert E and Rakic, Pasko and Noonan, James P},
	Date-Added = {2014-01-19 19:58:24 +0000},
	Date-Modified = {2014-01-19 19:58:24 +0000},
	Doi = {10.1016/j.cell.2013.05.056},
	Journal = {Cell},
	Journal-Full = {Cell},
	Mesh = {Acetylation; Animals; Biological Evolution; Enhancer Elements, Genetic; Extremities; Gene Expression Regulation, Developmental; Genetics, Medical; Genome-Wide Association Study; Histones; Humans; Macaca mulatta; Mice; Organogenesis; Promoter Regions, Genetic; Transcriptome},
	Month = {Jul},
	Number = {1},
	Pages = {185-96},
	Pmc = {PMC3785101},
	Pmid = {23827682},
	Pst = {ppublish},
	Title = {The evolution of lineage-specific regulatory activities in the human embryonic limb},
	Volume = {154},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.cell.2013.05.056}}

@article{Walldorf:1992pi,
	Abstract = {The empty spiracles (ems) gene of Drosophila melanogaster is necessary for proper head formation and the development of the posterior spiracles. We have isolated a homeobox-containing gene, W13, by cross-homology using the Drosophila muscle segment homeobox gene (msh) as a probe. The W13 gene maps at 88A, where the ems locus has been previously localized genetically. The sequence alterations found in the W13 coding region from two mutant ems alleles show that W13 is the ems gene. A 2.4 kb RNA corresponding to the ems transcript is expressed from cellular blastoderm throughout all embryonic and larval stages. In situ hybridization to whole mount embryos reveals two domains of expression. During the cellular blastoderm stage ems is expressed in the developing head in a single anterior band. This is correlated with its possible function as an anterior gap gene that is expressed in the preantennal, antennal and intercalary segments and is required for the development of the antennal sense organ, the optic lobe and parts of the head skeleton. The early expression of the ems gene is controlled by the anterior morphogen bicoid (bcd). Using a gene fusion we identified a cis-acting element which is a target for the bcd gene product. Later during embryogenesis ems is expressed in lateral regions of each segment, where the tracheal pits form and lateral neuroblasts originate, as well as in the posterior spiracles. This late expression partially correlates with defects seen in the tracheal tree of ems embryos. In addition to a homeodomain, the N-terminal portion of the predicted protein sequence is very proline-rich, whereas the C-terminus has an acidic profile consistent with the role of the ems gene product as a transcription factor.},
	Author = {Walldorf, U and Gehring, W J},
	Date-Added = {2014-01-19 19:45:13 +0000},
	Date-Modified = {2014-01-19 19:45:13 +0000},
	Journal = {EMBO J},
	Journal-Full = {The EMBO journal},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Blotting, Northern; Blotting, Southern; Cloning, Molecular; DNA; Drosophila melanogaster; Embryo, Nonmammalian; Genes, Homeobox; Genomic Library; Head; Microscopy, Electron, Scanning; Molecular Sequence Data; Poly A; Polymerase Chain Reaction; RNA; RNA, Messenger; Recombinant Fusion Proteins; Restriction Mapping; Transcription, Genetic; beta-Galactosidase},
	Month = {Jun},
	Number = {6},
	Pages = {2247-59},
	Pmc = {PMC556692},
	Pmid = {1376248},
	Pst = {ppublish},
	Title = {Empty spiracles, a gap gene containing a homeobox involved in Drosophila head development},
	Volume = {11},
	Year = {1992}}

@article{Hamasaki:2004mi,
	Abstract = {Genetic studies of neocortical area patterning are limited, because mice deficient for candidate regulatory genes die before areas emerge and have other complicating issues. To define roles for the homeodomain transcription factor EMX2, we engineered nestin-Emx2 transgenic mice that overexpress Emx2 in cortical progenitors coincident with expression of endogenous Emx2 and survive postnatally. Cortical size, lamination, thalamus, and thalamocortical pathfinding are normal in homozygous nestin-Emx2 mice. However, primary sensory and motor areas are disproportionately altered in size and shift rostrolaterally. Heterozygous transgenics have similar but smaller changes. Opposite changes are found in heterozygous Emx2 knockout mice. Fgf8 expression in the commissural plate of nestin-Emx2 mice is indistinguishable from wild-type, but Pax6 expression is downregulated in rostral cortical progenitors, suggesting that EMX2 repression of PAX6 specification of rostral identities contributes to reduced rostral areas. We conclude that EMX2 levels in cortical progenitors disproportionately specify sizes and positions of primary cortical areas.},
	Author = {Hamasaki, Tadashi and Leing{\"a}rtner, Axel and Ringstedt, Thomas and O'Leary, Dennis D M},
	Date-Added = {2014-01-19 19:44:37 +0000},
	Date-Modified = {2014-01-19 19:44:37 +0000},
	Doi = {10.1016/j.neuron.2004.07.016},
	Journal = {Neuron},
	Journal-Full = {Neuron},
	Mesh = {Animals; Cell Size; Eye Proteins; Gene Expression Regulation, Developmental; Homeodomain Proteins; Humans; Mice; Mice, Inbred C57BL; Mice, Knockout; Mice, Transgenic; Motor Cortex; Neocortex; Paired Box Transcription Factors; Rats; Repressor Proteins; Somatosensory Cortex; Stem Cells; Transcription Factors},
	Month = {Aug},
	Number = {3},
	Pages = {359-72},
	Pmid = {15294144},
	Pst = {ppublish},
	Title = {EMX2 regulates sizes and positioning of the primary sensory and motor areas in neocortex by direct specification of cortical progenitors},
	Volume = {43},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.neuron.2004.07.016}}

@article{Simeone:1992qa,
	Abstract = {We cloned two homeobox genes, Emx1 and Emx2, related to empty spiracles, a gene expressed in very anterior body regions during early Drosophila embryogenesis, and studied their expression in mouse embryos. Emx1 expression is detectable from day 9.5 of gestation whereas Emx2 appears to be already expressed in 8.5 day embryos. Both genes are expressed in the presumptive cerebral cortex and olfactory bulbs. Emx1 is expressed exclusively there, whereas Emx2 is also expressed in some neuroectodermal areas in embryonic head including olfactory placodes in earlier stages and olfactory epithelia later in development.},
	Author = {Simeone, A and Gulisano, M and Acampora, D and Stornaiuolo, A and Rambaldi, M and Boncinelli, E},
	Date-Added = {2014-01-19 19:43:46 +0000},
	Date-Modified = {2014-01-19 19:43:46 +0000},
	Journal = {EMBO J},
	Journal-Full = {The EMBO journal},
	Mesh = {Amino Acid Sequence; Animals; Blotting, Northern; Cerebral Cortex; Cloning, Molecular; DNA; Drosophila; Female; Gene Expression; Genes, Homeobox; Mice; Mice, Inbred C57BL; Molecular Sequence Data; Nucleic Acid Hybridization; Pregnancy; RNA Probes; Sequence Homology, Nucleic Acid},
	Month = {Jul},
	Number = {7},
	Pages = {2541-50},
	Pmc = {PMC556729},
	Pmid = {1352754},
	Pst = {ppublish},
	Title = {Two vertebrate homeobox genes related to the Drosophila empty spiracles gene are expressed in the embryonic cerebral cortex},
	Volume = {11},
	Year = {1992}}

@article{Brunelli:1996kl,
	Author = {Brunelli, S and Faiella, A and Capra, V and Nigro, V and Simeone, A and Cama, A and Boncinelli, E},
	Date-Added = {2014-01-19 19:43:19 +0000},
	Date-Modified = {2014-01-19 19:43:19 +0000},
	Doi = {10.1038/ng0196-94},
	Journal = {Nat Genet},
	Journal-Full = {Nature genetics},
	Mesh = {Base Sequence; Brain; Brain Diseases; DNA Primers; Female; Genes, Homeobox; Homeodomain Proteins; Humans; Magnetic Resonance Imaging; Male; Molecular Sequence Data; Nerve Tissue Proteins; Pedigree; Point Mutation; Polymorphism, Single-Stranded Conformational; Tomography, X-Ray Computed; Transcription Factors},
	Month = {Jan},
	Number = {1},
	Pages = {94-6},
	Pmid = {8528262},
	Pst = {ppublish},
	Title = {Germline mutations in the homeobox gene EMX2 in patients with severe schizencephaly},
	Volume = {12},
	Year = {1996},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/ng0196-94}}

@article{king1975evolution,
	Author = {King, Mary-Claire and Wilson, Allan C},
	Date-Added = {2014-01-19 18:01:51 +0000},
	Date-Modified = {2014-01-19 18:01:51 +0000},
	Journal = {Science},
	Number = {4184},
	Pages = {107--116},
	Title = {Evolution at two levels in humans and chimpanzees},
	Volume = {188},
	Year = {1975}}

@article{McLean:2011pb,
	Abstract = {Humans differ from other animals in many aspects of anatomy, physiology, and behaviour; however, the genotypic basis of most human-specific traits remains unknown. Recent whole-genome comparisons have made it possible to identify genes with elevated rates of amino acid change or divergent expression in humans, and non-coding sequences with accelerated base pair changes. Regulatory alterations may be particularly likely to produce phenotypic effects while preserving viability, and are known to underlie interesting evolutionary differences in other species. Here we identify molecular events particularly likely to produce significant regulatory changes in humans: complete deletion of sequences otherwise highly conserved between chimpanzees and other mammals. We confirm 510 such deletions in humans, which fall almost exclusively in non-coding regions and are enriched near genes involved in steroid hormone signalling and neural function. One deletion removes a sensory vibrissae and penile spine enhancer from the human androgen receptor (AR) gene, a molecular change correlated with anatomical loss of androgen-dependent sensory vibrissae and penile spines in the human lineage. Another deletion removes a forebrain subventricular zone enhancer near the tumour suppressor gene growth arrest and DNA-damage-inducible, gamma (GADD45G), a loss correlated with expansion of specific brain regions in humans. Deletions of tissue-specific enhancers may thus accompany both loss and gain traits in the human lineage, and provide specific examples of the kinds of regulatory alterations and inactivation events long proposed to have an important role in human evolutionary divergence.},
	Author = {McLean, Cory Y and Reno, Philip L and Pollen, Alex A and Bassan, Abraham I and Capellini, Terence D and Guenther, Catherine and Indjeian, Vahan B and Lim, Xinhong and Menke, Douglas B and Schaar, Bruce T and Wenger, Aaron M and Bejerano, Gill and Kingsley, David M},
	Date-Added = {2014-01-19 18:00:18 +0000},
	Date-Modified = {2014-01-19 18:00:18 +0000},
	Doi = {10.1038/nature09774},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Biological Evolution; Brain; Chromosomes, Mammalian; Conserved Sequence; DNA; DNA, Intergenic; Enhancer Elements, Genetic; Evolution, Molecular; Genes, Tumor Suppressor; Genome, Human; Human Characteristics; Humans; Male; Mice; Organ Specificity; Pan troglodytes; Penis; Regulatory Sequences, Nucleic Acid; Sequence Deletion; Species Specificity; Transgenes},
	Month = {Mar},
	Number = {7337},
	Pages = {216-9},
	Pmc = {PMC3071156},
	Pmid = {21390129},
	Pst = {ppublish},
	Title = {Human-specific loss of regulatory DNA and the evolution of human-specific traits},
	Volume = {471},
	Year = {2011},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature09774}}

@article{McLean:2010la,
	Abstract = {We developed the Genomic Regions Enrichment of Annotations Tool (GREAT) to analyze the functional significance of cis-regulatory regions identified by localized measurements of DNA binding events across an entire genome. Whereas previous methods took into account only binding proximal to genes, GREAT is able to properly incorporate distal binding sites and control for false positives using a binomial test over the input genomic regions. GREAT incorporates annotations from 20 ontologies and is available as a web application. Applying GREAT to data sets from chromatin immunoprecipitation coupled with massively parallel sequencing (ChIP-seq) of multiple transcription-associated factors, including SRF, NRSF, GABP, Stat3 and p300 in different developmental contexts, we recover many functions of these factors that are missed by existing gene-based tools, and we generate testable hypotheses. The utility of GREAT is not limited to ChIP-seq, as it could also be applied to open chromatin, localized epigenomic markers and similar functional data sets, as well as comparative genomics sets.},
	Author = {McLean, Cory Y and Bristor, Dave and Hiller, Michael and Clarke, Shoa L and Schaar, Bruce T and Lowe, Craig B and Wenger, Aaron M and Bejerano, Gill},
	Date-Added = {2014-01-19 17:59:30 +0000},
	Date-Modified = {2014-01-19 17:59:30 +0000},
	Doi = {10.1038/nbt.1630},
	Journal = {Nat Biotechnol},
	Journal-Full = {Nature biotechnology},
	Mesh = {Animals; Chromatin Immunoprecipitation; Data Mining; Databases, Genetic; E1A-Associated p300 Protein; Genome; Genomics; Humans; Jurkat Cells; Mice; Protein Binding; Regulatory Elements, Transcriptional; Serum Response Factor; Software},
	Month = {May},
	Number = {5},
	Pages = {495-501},
	Pmid = {20436461},
	Pst = {ppublish},
	Title = {GREAT improves functional interpretation of cis-regulatory regions},
	Volume = {28},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nbt.1630}}

@article{Olson:1999fy,
	Author = {Olson, M V},
	Date-Added = {2014-01-19 16:36:56 +0000},
	Date-Modified = {2014-01-19 16:36:56 +0000},
	Doi = {10.1086/302219},
	Journal = {Am J Hum Genet},
	Journal-Full = {American journal of human genetics},
	Mesh = {Animals; Evolution, Molecular; Gene Deletion; Humans},
	Month = {Jan},
	Number = {1},
	Pages = {18-23},
	Pmc = {PMC1377697},
	Pmid = {9915938},
	Pst = {ppublish},
	Title = {When less is more: gene loss as an engine of evolutionary change},
	Volume = {64},
	Year = {1999},
	Bdsk-Url-1 = {http://dx.doi.org/10.1086/302219}}

@article{Gilad:2003gd,
	Abstract = {Olfactory receptor (OR) genes constitute the basis for the sense of smell and are encoded by the largest mammalian gene superfamily of >1,000 genes. In humans, >60% of these are pseudogenes. In contrast, the mouse OR repertoire, although of roughly equal size, contains only approximately 20% pseudogenes. We asked whether the high fraction of nonfunctional OR genes is specific to humans or is a common feature of all primates. To this end, we have compared the sequences of 50 human OR coding regions, regardless of their functional annotations, to those of their putative orthologs in chimpanzees, gorillas, orangutans, and rhesus macaques. We found that humans have accumulated mutations that disrupt OR coding regions roughly 4-fold faster than any other species sampled. As a consequence, the fraction of OR pseudogenes in humans is almost twice as high as in the non-human primates, suggesting a human-specific process of OR gene disruption, likely due to a reduced chemosensory dependence relative to apes.},
	Author = {Gilad, Yoav and Man, Orna and P{\"a}{\"a}bo, Svante and Lancet, Doron},
	Date-Added = {2014-01-19 16:30:58 +0000},
	Date-Modified = {2014-01-19 16:30:58 +0000},
	Doi = {10.1073/pnas.0535697100},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Animals; DNA; Evolution, Molecular; Gene Silencing; Gorilla gorilla; Humans; Macaca mulatta; Mice; Molecular Sequence Data; Multigene Family; Pan troglodytes; Pongo pygmaeus; Primates; Pseudogenes; Receptors, Odorant; Species Specificity},
	Month = {Mar},
	Number = {6},
	Pages = {3324-7},
	Pmc = {PMC152291},
	Pmid = {12612342},
	Pst = {ppublish},
	Title = {Human specific loss of olfactory receptor genes},
	Volume = {100},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0535697100}}

@article{Young:2002la,
	Abstract = {We report a comprehensive comparative analysis of human and mouse olfactory receptor (OR) genes. The OR family is the largest mammalian gene family known. We identify approximately 93% of an estimated 1500 mouse ORs, exceeding previous estimates and the number of human ORs by 50%. Only 20% are pseudogenes, giving a functional OR repertoire in mice that is three times larger than that of human. The proteins encoded by intact human ORs are less highly conserved than those of mouse, in patterns that suggest that even some apparently intact human OR genes may encode non-functional proteins. Mouse ORs are clustered in 46 genomic locations, compared to a much more dispersed pattern in human. We find orthologous clusters at syntenic human locations for most mouse genes, indicating that most OR gene clusters predate primate-rodent divergence. However, many recent local OR duplications in both genomes obscure one-to-one orthologous relationships, thereby complicating cross-species inferences about OR-ligand interactions. Local duplications are the major force shaping the gene family. Recent interchromosomal duplications of ORs have also occurred, but much more frequently in human than in mouse. In addition to clarifying the evolutionary forces shaping this gene family, our study provides the basis for functional studies of the transcriptional regulation and ligand-binding capabilities of the OR gene family.},
	Author = {Young, Janet M and Friedman, Cynthia and Williams, Eleanor M and Ross, Joseph A and Tonnes-Priddy, Lori and Trask, Barbara J},
	Date-Added = {2014-01-19 16:30:18 +0000},
	Date-Modified = {2014-01-19 16:30:18 +0000},
	Journal = {Hum Mol Genet},
	Journal-Full = {Human molecular genetics},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Chromosome Mapping; Chromosomes, Artificial, Bacterial; Conserved Sequence; Evolution, Molecular; Humans; Mice; Molecular Sequence Data; Multigene Family; Phylogeny; Pseudogenes; Receptors, Odorant; Sequence Alignment; Smell; Synteny; Tandem Repeat Sequences},
	Month = {Mar},
	Number = {5},
	Pages = {535-46},
	Pmid = {11875048},
	Pst = {ppublish},
	Title = {Different evolutionary processes shaped the mouse and human olfactory receptor gene families},
	Volume = {11},
	Year = {2002}}

@article{Rouquier:1998qq,
	Abstract = {We demonstrate that members of the olfactory receptor (OR) gene family are distributed on all but a few human chromosomes. Through FISH analysis, we show that OR sequences reside at more than 25 locations in the human genome. Their distribution is biased for terminal bands. Flow-sorted chromosomes were used to isolate 87 OR sequences derived from 16 chromosomes. Their sequence-relationships are indicative of the inter- and intrachromosomal duplications responsible for OR family expansion. The human genome has accumulated a striking number of dysfunctional copies: 72% of the sequences are pseudogenes. ORF-containing sequences predominate on chromosomes 7, 16 and 17.},
	Author = {Rouquier, S and Taviaux, S and Trask, B J and Brand-Arpon, V and van den Engh, G and Demaille, J and Giorgi, D},
	Date-Added = {2014-01-19 16:29:32 +0000},
	Date-Modified = {2014-01-19 16:29:32 +0000},
	Doi = {10.1038/ng0398-243},
	Journal = {Nat Genet},
	Journal-Full = {Nature genetics},
	Mesh = {Amino Acid Sequence; Base Sequence; Chromosome Mapping; Chromosomes, Human; Chromosomes, Human, Pair 17; Cloning, Molecular; Conserved Sequence; DNA Primers; Genetic Techniques; Humans; In Situ Hybridization, Fluorescence; Introns; Molecular Sequence Data; Multigene Family; Receptors, Odorant; Sequence Analysis; Sequence Homology, Amino Acid},
	Month = {Mar},
	Number = {3},
	Pages = {243-50},
	Pmid = {9500546},
	Pst = {ppublish},
	Title = {Distribution of olfactory receptor genes in the human genome},
	Volume = {18},
	Year = {1998},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/ng0398-243}}

@article{Irie:1998xe,
	Abstract = {N-Glycolylneuraminic acid (NeuGc) is abundantly expressed in most mammals, but it is not detectable in humans. The expression of NeuGc is controlled by cytidine monophospho-N-acetylneuraminic acid (CMP-NeuAc) hydroxylase activity. We previously cloned a cDNA for mouse CMP-NeuAc hydroxylase and found that the human genome contains a homologue. We report here the molecular basis for the absence of NeuGc in humans. We cloned a cDNA for human CMP-NeuAc hydroxylase from a HeLa cell cDNA library. The cDNA encodes a 486-amino acid protein, and its deduced amino acid sequence lacks a domain corresponding to the N-terminal 104 amino acids of the mouse CMP-NeuAc hydroxylase protein, although the human protein is highly identical (93%) to the rest of the mouse hydroxylase protein. The N-terminal truncation of the human hydroxylase is caused by deletion of a 92-base pair-long exon in human genomic DNA. The human hydroxylase expressed in COS-7 cells exhibited no enzymatic activity, and a mouse hydroxylase mutant, which lacks the N-terminal domain, was also inactive. A chimera composed of the human hydroxylase and the N-terminal domain of the mouse hydroxylase displayed the enzyme activity. These results indicate that the human homologue of CMP-NeuAc hydroxylase is inactive because it lacks an N-terminal domain that is essential for enzyme activity. The absence of NeuGc in human glycoconjugates is due to a partial deletion in the gene that encodes CMP-NeuAc hydroxylase.},
	Author = {Irie, A and Koyama, S and Kozutsumi, Y and Kawasaki, T and Suzuki, A},
	Date-Added = {2014-01-19 16:27:21 +0000},
	Date-Modified = {2014-01-19 16:27:21 +0000},
	Journal = {J Biol Chem},
	Journal-Full = {The Journal of biological chemistry},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; DNA, Complementary; Humans; Mice; Mixed Function Oxygenases; Molecular Sequence Data; Neuraminic Acids; Restriction Mapping; Sequence Analysis, DNA; Sequence Deletion},
	Month = {Jun},
	Number = {25},
	Pages = {15866-71},
	Pmid = {9624188},
	Pst = {ppublish},
	Title = {The molecular basis for the absence of N-glycolylneuraminic acid in humans},
	Volume = {273},
	Year = {1998}}

@article{Chou:1998rw,
	Abstract = {Sialic acids are important cell-surface molecules of animals in the deuterostome lineage. Although humans do not express easily detectable amounts of N-glycolylneuraminic acid (Neu5Gc, a hydroxylated form of the common sialic acid N-acetylneuraminic acid, Neu5Ac), it is a major component in great ape tissues, except in the brain. This difference correlates with lack of the hydroxylase activity that converts CMP-Neu5Ac to CMP-Neu5Gc. Here we report cloning of human and chimpanzee hydroxylase cDNAs. Although this chimpanzee cDNA is similar to the murine homologue, the human cDNA contains a 92-bp deletion resulting in a frameshift mutation. The isolated human gene also shows evidence for this deletion. Genomic PCR analysis indicates that this deletion does not occur in any of the African great apes. The gene is localized to 6p22-p23 in both humans and great apes, which does not correspond to known chromosomal rearrangements that occurred during hominoid evolution. Thus, the lineage leading to modern humans suffered a mutation sometime after the common ancestor with the chimpanzee and bonobo, potentially affecting recognition by a variety of endogenous and exogenous sialic acid-binding lectins. Also, the expression of Neu5Gc previously reported in human fetuses and tumors as well as the traces detected in some normal adult humans must be mediated by an alternate pathway.},
	Author = {Chou, H H and Takematsu, H and Diaz, S and Iber, J and Nickerson, E and Wright, K L and Muchmore, E A and Nelson, D L and Warren, S T and Varki, A},
	Date-Added = {2014-01-19 16:26:48 +0000},
	Date-Modified = {2014-01-19 16:26:48 +0000},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Cloning, Molecular; DNA Primers; DNA, Complementary; Evolution, Molecular; Hominidae; Humans; In Situ Hybridization, Fluorescence; Mice; Mixed Function Oxygenases; Molecular Sequence Data; Mutation; Pan troglodytes; Sequence Homology, Amino Acid; Sequence Homology, Nucleic Acid},
	Month = {Sep},
	Number = {20},
	Pages = {11751-6},
	Pmc = {PMC21712},
	Pmid = {9751737},
	Pst = {ppublish},
	Title = {A mutation in human CMP-sialic acid hydroxylase occurred after the Homo-Pan divergence},
	Volume = {95},
	Year = {1998}}

@article{Fischer:2002qr,
	Abstract = {Caspase 12 has been cloned from rodent cells, in which it mediated apoptosis in response to endoplasmic reticulum stress. Based on experiments with murine cells it was suggested that this caspase plays a central role in the pathogenesis of Alzheimer's disease. By alignment of the murine caspase 12 cDNA with the human genome sequence we localized the human caspase 12 gene at a single locus within the caspase 1/ICE gene cluster on chromosome 11q22.3. RT-PCR and molecular cloning revealed that nine alternatively spliced transcripts of this gene are expressed. A frame shift mutation and a premature stop codon which is present in all splice variants preclude the expression of a full length protein. An additional loss-of-function mutation within the SHG box, a critical site in caspases, prohibits any proteins, if they are produced, from acting catalytically. Based on our data we conclude that functional caspase 12 is lost in humans and that it can therefore not play a role in Alzheimer's disease.},
	Author = {Fischer, Heinz and Koenig, Ulrich and Eckhart, Leopold and Tschachler, Erwin},
	Date-Added = {2014-01-19 16:25:59 +0000},
	Date-Modified = {2014-01-19 16:25:59 +0000},
	Doi = {10.1016/S0006-291X(02)00289-9},
	Journal = {Biochem Biophys Res Commun},
	Journal-Full = {Biochemical and biophysical research communications},
	Mesh = {Alternative Splicing; Amino Acid Sequence; Animals; Caspase 12; Caspases; Chromosomes, Human, Pair 11; Humans; Mice; Molecular Sequence Data; Mutation; RNA, Messenger; Sequence Alignment; Sequence Homology, Nucleic Acid; Tissue Distribution},
	Month = {May},
	Number = {2},
	Pages = {722-6},
	Pmid = {12054529},
	Pst = {ppublish},
	Title = {Human caspase 12 has acquired deleterious mutations},
	Volume = {293},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/S0006-291X(02)00289-9}}

@article{Stedman:2004hl,
	Abstract = {Powerful masticatory muscles are found in most primates, including chimpanzees and gorillas, and were part of a prominent adaptation of Australopithecus and Paranthropus, extinct genera of the family Hominidae. In contrast, masticatory muscles are considerably smaller in both modern and fossil members of Homo. The evolving hominid masticatory apparatus--traceable to a Late Miocene, chimpanzee-like morphology--shifted towards a pattern of gracilization nearly simultaneously with accelerated encephalization in early Homo. Here, we show that the gene encoding the predominant myosin heavy chain (MYH) expressed in these muscles was inactivated by a frameshifting mutation after the lineages leading to humans and chimpanzees diverged. Loss of this protein isoform is associated with marked size reductions in individual muscle fibres and entire masticatory muscles. Using the coding sequence for the myosin rod domains as a molecular clock, we estimate that this mutation appeared approximately 2.4 million years ago, predating the appearance of modern human body size and emigration of Homo from Africa. This represents the first proteomic distinction between humans and chimpanzees that can be correlated with a traceable anatomic imprint in the fossil record.},
	Author = {Stedman, Hansell H and Kozyak, Benjamin W and Nelson, Anthony and Thesier, Danielle M and Su, Leonard T and Low, David W and Bridges, Charles R and Shrager, Joseph B and Minugh-Purvis, Nancy and Mitchell, Marilyn A},
	Date-Added = {2014-01-19 16:19:01 +0000},
	Date-Modified = {2014-01-19 16:19:01 +0000},
	Doi = {10.1038/nature02358},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Computational Biology; Dogs; Evolution, Molecular; Exons; Fossils; Frameshift Mutation; History, Ancient; Hominidae; Humans; Macaca; Masticatory Muscles; Molecular Sequence Data; Myosin Heavy Chains; Myosins; Pan troglodytes; Phylogeny; Pongo pygmaeus; Skull; Time Factors},
	Month = {Mar},
	Number = {6981},
	Pages = {415-8},
	Pmid = {15042088},
	Pst = {ppublish},
	Title = {Myosin gene mutation correlates with anatomical changes in the human lineage},
	Volume = {428},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature02358}}

@article{Davydov:2010fp,
	Abstract = {Computational efforts to identify functional elements within genomes leverage comparative sequence information by looking for regions that exhibit evidence of selective constraint. One way of detecting constrained elements is to follow a bottom-up approach by computing constraint scores for individual positions of a multiple alignment and then defining constrained elements as segments of contiguous, highly scoring nucleotide positions. Here we present GERP++, a new tool that uses maximum likelihood evolutionary rate estimation for position-specific scoring and, in contrast to previous bottom-up methods, a novel dynamic programming approach to subsequently define constrained elements. GERP++ evaluates a richer set of candidate element breakpoints and ranks them based on statistical significance, eliminating the need for biased heuristic extension techniques. Using GERP++ we identify over 1.3 million constrained elements spanning over 7% of the human genome. We predict a higher fraction than earlier estimates largely due to the annotation of longer constrained elements, which improves one to one correspondence between predicted elements with known functional sequences. GERP++ is an efficient and effective tool to provide both nucleotide- and element-level constraint scores within deep multiple sequence alignments.},
	Author = {Davydov, Eugene V and Goode, David L and Sirota, Marina and Cooper, Gregory M and Sidow, Arend and Batzoglou, Serafim},
	Date-Added = {2014-01-19 15:45:17 +0000},
	Date-Modified = {2014-01-19 15:45:17 +0000},
	Doi = {10.1371/journal.pcbi.1001025},
	Journal = {PLoS Comput Biol},
	Journal-Full = {PLoS computational biology},
	Mesh = {Algorithms; Animals; Genome, Human; Genomics; Humans; Mammals; Models, Genetic; Phylogeny; Sequence Alignment; Sequence Analysis, DNA; Software; User-Computer Interface},
	Number = {12},
	Pages = {e1001025},
	Pmc = {PMC2996323},
	Pmid = {21152010},
	Pst = {epublish},
	Title = {Identifying a high fraction of the human genome to be under selective constraint using GERP++},
	Volume = {6},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pcbi.1001025}}

@article{Kong:2010eu,
	Abstract = {Meiotic recombinations contribute to genetic diversity by yielding new combinations of alleles. Recently, high-resolution recombination maps were inferred from high-density single-nucleotide polymorphism (SNP) data using linkage disequilibrium (LD) patterns that capture historical recombination events. The use of these maps has been demonstrated by the identification of recombination hotspots and associated motifs, and the discovery that the PRDM9 gene affects the proportion of recombinations occurring at hotspots. However, these maps provide no information about individual or sex differences. Moreover, locus-specific demographic factors like natural selection can bias LD-based estimates of recombination rate. Existing genetic maps based on family data avoid these shortcomings, but their resolution is limited by relatively few meioses and a low density of markers. Here we used genome-wide SNP data from 15,257 parent-offspring pairs to construct the first recombination maps based on directly observed recombinations with a resolution that is effective down to 10 kilobases (kb). Comparing male and female maps reveals that about 15% of hotspots in one sex are specific to that sex. Although male recombinations result in more shuffling of exons within genes, female recombinations generate more new combinations of nearby genes. We discover novel associations between recombination characteristics of individuals and variants in the PRDM9 gene and we identify new recombination hotspots. Comparisons of our maps with two LD-based maps inferred from data of HapMap populations of Utah residents with ancestry from northern and western Europe (CEU) and Yoruba in Ibadan, Nigeria (YRI) reveal population differences previously masked by noise and map differences at regions previously described as targets of natural selection.},
	Author = {Kong, Augustine and Thorleifsson, Gudmar and Gudbjartsson, Daniel F and Masson, Gisli and Sigurdsson, Asgeir and Jonasdottir, Aslaug and Walters, G Bragi and Jonasdottir, Adalbjorg and Gylfason, Arnaldur and Kristinsson, Kari Th and Gudjonsson, Sigurjon A and Frigge, Michael L and Helgason, Agnar and Thorsteinsdottir, Unnur and Stefansson, Kari},
	Date-Added = {2014-01-19 15:16:55 +0000},
	Date-Modified = {2014-01-19 15:16:55 +0000},
	Doi = {10.1038/nature09525},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Alleles; Chromosomes, Human; DNA-Binding Proteins; Europe; Exons; Female; Genetics, Population; Haplotypes; Heterozygote; Histone-Lysine N-Methyltransferase; Humans; Linkage Disequilibrium; Male; Meiosis; Nigeria; Pedigree; Polymorphism, Single Nucleotide; Recombination, Genetic; Sample Size; Selection, Genetic; Sex Characteristics; Utah},
	Month = {Oct},
	Number = {7319},
	Pages = {1099-103},
	Pmid = {20981099},
	Pst = {ppublish},
	Title = {Fine-scale recombination rate differences between sexes, populations and individuals},
	Volume = {467},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature09525}}

@article{chang2011libsvm,
	Author = {Chang, Chih-Chung and Lin, Chih-Jen},
	Date-Added = {2014-01-17 19:03:57 +0000},
	Date-Modified = {2014-01-17 19:03:57 +0000},
	Journal = {ACM Transactions on Intelligent Systems and Technology (TIST)},
	Number = {3},
	Pages = {27},
	Publisher = {ACM},
	Title = {LIBSVM: a library for support vector machines},
	Volume = {2},
	Year = {2011}}

@article{Lindblad-Toh:2011cs,
	Abstract = {The comparison of related genomes has emerged as a powerful lens for genome interpretation. Here we report the sequencing and comparative analysis of 29 eutherian genomes. We confirm that at least 5.5% of the human genome has undergone purifying selection, and locate constrained elements covering ∼4.2% of the genome. We use evolutionary signatures and comparisons with experimental data sets to suggest candidate functions for ∼60% of constrained bases. These elements reveal a small number of new coding exons, candidate stop codon readthrough events and over 10,000 regions of overlapping synonymous constraint within protein-coding exons. We find 220 candidate RNA structural families, and nearly a million elements overlapping potential promoter, enhancer and insulator regions. We report specific amino acid residues that have undergone positive selection, 280,000 non-coding elements exapted from mobile elements and more than 1,000 primate- and human-accelerated elements. Overlap with disease-associated variants indicates that our findings will be relevant for studies of human biology, health and disease.},
	Author = {Lindblad-Toh, Kerstin and Garber, Manuel and Zuk, Or and Lin, Michael F and Parker, Brian J and Washietl, Stefan and Kheradpour, Pouya and Ernst, Jason and Jordan, Gregory and Mauceli, Evan and Ward, Lucas D and Lowe, Craig B and Holloway, Alisha K and Clamp, Michele and Gnerre, Sante and Alf{\"o}ldi, Jessica and Beal, Kathryn and Chang, Jean and Clawson, Hiram and Cuff, James and Di Palma, Federica and Fitzgerald, Stephen and Flicek, Paul and Guttman, Mitchell and Hubisz, Melissa J and Jaffe, David B and Jungreis, Irwin and Kent, W James and Kostka, Dennis and Lara, Marcia and Martins, Andre L and Massingham, Tim and Moltke, Ida and Raney, Brian J and Rasmussen, Matthew D and Robinson, Jim and Stark, Alexander and Vilella, Albert J and Wen, Jiayu and Xie, Xiaohui and Zody, Michael C and {Broad Institute Sequencing Platform and Whole Genome Assembly Team} and Baldwin, Jen and Bloom, Toby and Chin, Chee Whye and Heiman, Dave and Nicol, Robert and Nusbaum, Chad and Young, Sarah and Wilkinson, Jane and Worley, Kim C and Kovar, Christie L and Muzny, Donna M and Gibbs, Richard A and {Baylor College of Medicine Human Genome Sequencing Center Sequencing Team} and Cree, Andrew and Dihn, Huyen H and Fowler, Gerald and Jhangiani, Shalili and Joshi, Vandita and Lee, Sandra and Lewis, Lora R and Nazareth, Lynne V and Okwuonu, Geoffrey and Santibanez, Jireh and Warren, Wesley C and Mardis, Elaine R and Weinstock, George M and Wilson, Richard K and {Genome Institute at Washington University} and Delehaunty, Kim and Dooling, David and Fronik, Catrina and Fulton, Lucinda and Fulton, Bob and Graves, Tina and Minx, Patrick and Sodergren, Erica and Birney, Ewan and Margulies, Elliott H and Herrero, Javier and Green, Eric D and Haussler, David and Siepel, Adam and Goldman, Nick and Pollard, Katherine S and Pedersen, Jakob S and Lander, Eric S and Kellis, Manolis},
	Date-Added = {2014-01-17 19:02:11 +0000},
	Date-Modified = {2014-01-17 19:02:11 +0000},
	Doi = {10.1038/nature10530},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Disease; Evolution, Molecular; Exons; Genome; Genome, Human; Genomics; Health; Humans; Mammals; Molecular Sequence Annotation; Phylogeny; RNA; Selection, Genetic; Sequence Alignment; Sequence Analysis, DNA},
	Month = {Oct},
	Number = {7370},
	Pages = {476-82},
	Pmc = {PMC3207357},
	Pmid = {21993624},
	Pst = {epublish},
	Title = {A high-resolution map of human evolutionary constraint using 29 mammals},
	Volume = {478},
	Year = {2011},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature10530}}

@article{Ronen:2013ai,
	Abstract = {Genetic adaptation to external stimuli occurs through the combined action of mutation and selection. A central problem in genetics is to identify loci responsive to specific selective constraints. Many tests have been proposed to identify the genomic signatures of natural selection by quantifying the skew in the site frequency spectrum (SFS) under selection relative to neutrality. We build upon recent work that connects many of these tests under a common framework, by describing how selective sweeps affect the scaled SFS. We show that the specific skew depends on many attributes of the sweep, including the selection coefficient and the time under selection. Using supervised learning on extensive simulated data, we characterize the features of the scaled SFS that best separate different types of selective sweeps from neutrality. We develop a test, SFselect, that consistently outperforms many existing tests over a wide range of selective sweeps. We apply SFselect to polymorphism data from a laboratory evolution experiment of Drosophila melanogaster adapted to hypoxia and identify loci that strengthen the role of the Notch pathway in hypoxia tolerance, but were missed by previous approaches. We further apply our test to human data and identify regions that are in agreement with earlier studies, as well as many novel regions.},
	Author = {Ronen, Roy and Udpa, Nitin and Halperin, Eran and Bafna, Vineet},
	Date-Added = {2014-01-17 15:13:59 +0000},
	Date-Modified = {2014-01-17 15:13:59 +0000},
	Doi = {10.1534/genetics.113.152587},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Keywords = {natural selection; site frequency spectrum; supervised learning},
	Month = {Sep},
	Number = {1},
	Pages = {181-93},
	Pmc = {PMC3761300},
	Pmid = {23770700},
	Pst = {ppublish},
	Title = {Learning natural selection from the site frequency spectrum},
	Volume = {195},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.113.152587}}

@article{Byvatov:2003qe,
	Abstract = {The support vector machine (SVM) approach represents a data-driven method for solving classification tasks. It has been shown to produce lower prediction error compared to classifiers based on other methods like artificial neural networks, especially when large numbers of features are considered for sample description. In this review, the theory and main principles of the SVM approach are outlined, and successful applications in traditional areas of bioinformatics research are described. Current developments in techniques related to the SVM approach are reviewed which might become relevant for future functional genomics and chemogenomics projects. In a comparative study, we developed neural network and SVM models to identify small organic molecules that potentially modulate the function of G-protein coupled receptors. The SVM system was able to correctly classify approximately 90% of the compounds in a cross-validation study yielding a Matthews correlation coefficient of 0.78. This classifier can be used for fast filtering of compound libraries in virtual screening applications.},
	Author = {Byvatov, Evgeny and Schneider, Gisbert},
	Date-Added = {2014-01-17 15:13:00 +0000},
	Date-Modified = {2014-01-17 15:13:00 +0000},
	Journal = {Appl Bioinformatics},
	Journal-Full = {Applied bioinformatics},
	Mesh = {Algorithms; Artificial Intelligence; Computational Biology; Computing Methodologies; Gene Expression Profiling; Neural Networks (Computer); Neuropeptides; Pattern Recognition, Automated; Protein Interaction Mapping; Sequence Alignment; Sequence Analysis},
	Number = {2},
	Pages = {67-77},
	Pmid = {15130823},
	Pst = {ppublish},
	Title = {Support vector machine applications in bioinformatics},
	Volume = {2},
	Year = {2003}}

@article{Marth:2003eu,
	Abstract = {Single-nucleotide polymorphisms (SNPs) constitute the great majority of variations in the human genome, and as heritable variable landmarks they are useful markers for disease mapping and resolving population structure. Redundant coverage in overlaps of large-insert genomic clones, sequenced as part of the Human Genome Project, comprises a quarter of the genome, and it is representative in terms of base compositional and functional sequence features. We mined these regions to produce 500,000 high-confidence SNP candidates as a uniform resource for describing nucleotide diversity and its regional variation within the genome. Distributions of marker density observed at different overlap length scales under a model of recombination and population size change show that the history of the population represented by the public genome sequence is one of collapse followed by a recent phase of mild size recovery. The inferred times of collapse and recovery are Upper Paleolithic, in agreement with archaeological evidence of the initial modern human colonization of Europe.},
	Author = {Marth, Gabor and Schuler, Greg and Yeh, Raymond and Davenport, Ruth and Agarwala, Richa and Church, Deanna and Wheelan, Sarah and Baker, Jonathan and Ward, Ming and Kholodov, Michael and Phan, Lon and Czabarka, Eva and Murvai, Janos and Cutler, David and Wooding, Stephen and Rogers, Alan and Chakravarti, Aravinda and Harpending, Henry C and Kwok, Pui-Yan and Sherry, Stephen T},
	Date-Added = {2014-01-16 19:19:47 +0000},
	Date-Modified = {2014-01-16 19:19:47 +0000},
	Doi = {10.1073/pnas.222673099},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Databases, Nucleic Acid; Gene Frequency; Genetic Markers; Genetic Variation; Genetics, Population; Genome, Human; Humans; Models, Genetic; Recombination, Genetic; Reproducibility of Results; Sequence Analysis, DNA; Time Factors},
	Month = {Jan},
	Number = {1},
	Pages = {376-81},
	Pmc = {PMC140982},
	Pmid = {12502794},
	Pst = {ppublish},
	Title = {Sequence variations in the public human genome data reflect a bottlenecked population history},
	Volume = {100},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.222673099}}

@article{Eyre-Walker:2007wd,
	Abstract = {The distribution of fitness effects (DFE) of new mutations is a fundamental entity in genetics that has implications ranging from the genetic basis of complex disease to the stability of the molecular clock. It has been studied by two different approaches: mutation accumulation and mutagenesis experiments, and the analysis of DNA sequence data. The proportion of mutations that are advantageous, effectively neutral and deleterious varies between species, and the DFE differs between coding and non-coding DNA. Despite these differences between species and genomic regions, some general principles have emerged: advantageous mutations are rare, and those that are strongly selected are exponentially distributed; and the DFE of deleterious mutations is complex and multi-modal.},
	Author = {Eyre-Walker, Adam and Keightley, Peter D},
	Date-Added = {2014-01-16 19:19:05 +0000},
	Date-Modified = {2014-01-16 19:19:05 +0000},
	Doi = {10.1038/nrg2146},
	Journal = {Nat Rev Genet},
	Journal-Full = {Nature reviews. Genetics},
	Mesh = {Amino Acid Substitution; Animals; DNA; Evolution, Molecular; Humans; Models, Genetic; Mutagenesis; Mutation; Polymorphism, Single Nucleotide},
	Month = {Aug},
	Number = {8},
	Pages = {610-8},
	Pmid = {17637733},
	Pst = {ppublish},
	Title = {The distribution of fitness effects of new mutations},
	Volume = {8},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nrg2146}}

@article{Ward:2012rr,
	Abstract = {Although only 5% of the human genome is conserved across mammals, a substantially larger portion is biochemically active, raising the question of whether the additional elements evolve neutrally or confer a lineage-specific fitness advantage. To address this question, we integrate human variation information from the 1000 Genomes Project and activity data from the ENCODE Project. A broad range of transcribed and regulatory nonconserved elements show decreased human diversity, suggesting lineage-specific purifying selection. Conversely, conserved elements lacking activity show increased human diversity, suggesting that some recently became nonfunctional. Regulatory elements under human constraint in nonconserved regions were found near color vision and nerve-growth genes, consistent with purifying selection for recently evolved functions. Our results suggest continued turnover in regulatory regions, with at least an additional 4% of the human genome subject to lineage-specific constraint.},
	Author = {Ward, Lucas D and Kellis, Manolis},
	Date-Added = {2014-01-16 19:13:55 +0000},
	Date-Modified = {2014-01-16 19:13:55 +0000},
	Doi = {10.1126/science.1225057},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Conserved Sequence; Disease; Gene Expression Regulation; Genetic Variation; Genome, Human; Humans; Polymorphism, Single Nucleotide; Regulatory Sequences, Nucleic Acid; Selection, Genetic; Transcription, Genetic},
	Month = {Sep},
	Number = {6102},
	Pages = {1675-8},
	Pmid = {22956687},
	Pst = {ppublish},
	Title = {Evidence of abundant purifying selection in humans for recently acquired regulatory functions},
	Volume = {337},
	Year = {2012},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1225057}}

@article{Somel:2013lq,
	Abstract = {Environmental or genomic changes during evolution can relax negative selection pressure on specific loci, permitting high frequency polymorphisms at previously conserved sites. Here, we jointly analyze population genomic and comparative genomic data to search for functional processes showing relaxed negative selection specifically in the human lineage, whereas remaining evolutionarily conserved in other mammals. Consistent with previous studies, we find that olfactory receptor genes display such a signature of relaxation in humans. Intriguingly, proteasome genes also show a prominent signal of human-specific relaxation: multiple proteasome subunits, including four members of the catalytic core particle, contain high frequency nonsynonymous polymorphisms at sites conserved across mammals. Chimpanzee proteasome genes do not display a similar trend. Human proteasome genes also bear no evidence of recent positive or balancing selection. These results suggest human-specific relaxation of negative selection in proteasome subunits; the exact biological causes, however, remain unknown.},
	Author = {Somel, Mehmet and Wilson Sayres, Melissa A and Jordan, Gregory and Huerta-Sanchez, Emilia and Fumagalli, Matteo and Ferrer-Admetlla, Anna and Nielsen, Rasmus},
	Date-Added = {2014-01-16 19:13:37 +0000},
	Date-Modified = {2014-01-16 19:13:37 +0000},
	Doi = {10.1093/molbev/mst098},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Keywords = {human evolution; negative selection; olfactory transduction; proteasome; relaxation of constraints},
	Month = {Aug},
	Number = {8},
	Pages = {1808-15},
	Pmc = {PMC3708504},
	Pmid = {23699470},
	Pst = {ppublish},
	Title = {A scan for human-specific relaxation of negative selection reveals unexpected polymorphism in proteasome genes},
	Volume = {30},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/mst098}}

@article{Pierron:2013pd,
	Abstract = {Knowledge and understanding about the selective pressures that have shaped present human genetic diversity have dramatically increased in the last few years in parallel with the availability of large genomic datasets. The release of large datasets composed of millions of SNPs across hundreds of genomes by HAPMAP, the Human Genome Diversity Panel, and other projects has led to considerable effort to detect selection signals across the nuclear genome (Coop et al., 2009; Lopez Herraez et al., 2009; Sabeti et al., 2006, 2007; Voight et al., 2006). Most of the research has focused on positive selection forces although other selective forces, such as negative selection, may have played a substantive role on the shape of our genome. Here we studied the selective strengths acting presently on the genome by making computational predictions of the pathogenicity of nonsynonymous protein mutations and interpreting the distribution of scores in terms of selection. We could show that the genetic diversity for all the major pathways is still constrained by negative selection in all 11 human populations studied. In a single exception, we observed a relaxation of negative selection acting on olfactory receptors. Since a decreased number of functioning olfactory receptors in human compared with other primates had already been shown, this suggests that the role of olfactory receptors for survival and reproductive success has decreased during human evolution. By showing that negative selection is still relaxed, the present results imply that no plateau of minimal function has yet been reached in modern humans and therefore that olfactory capability might still be decreasing. This is a first clue to present human evolution.},
	Author = {Pierron, Denis and Cort{\'e}s, Nicol{\'a}s Guti{\'e}rrez and Letellier, Thierry and Grossman, Lawrence I},
	Date-Added = {2014-01-16 19:13:17 +0000},
	Date-Modified = {2014-01-16 19:13:17 +0000},
	Doi = {10.1016/j.ympev.2012.07.032},
	Journal = {Mol Phylogenet Evol},
	Journal-Full = {Molecular phylogenetics and evolution},
	Mesh = {Computational Biology; Evolution, Molecular; Gene Frequency; Genome, Human; Humans; Mutation; Polymorphism, Single Nucleotide; Receptors, Odorant; Selection, Genetic},
	Month = {Feb},
	Number = {2},
	Pages = {558-64},
	Pmid = {22906809},
	Pst = {ppublish},
	Title = {Current relaxation of selection on the human genome: tolerance of deleterious mutations on olfactory receptors},
	Volume = {66},
	Year = {2013},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.ympev.2012.07.032}}

@article{Rhesus-Macaque-Genome-Sequencing-and-Analysis-Consortium:2007fv,
	Abstract = {The rhesus macaque (Macaca mulatta) is an abundant primate species that diverged from the ancestors of Homo sapiens about 25 million years ago. Because they are genetically and physiologically similar to humans, rhesus monkeys are the most widely used nonhuman primate in basic and applied biomedical research. We determined the genome sequence of an Indian-origin Macaca mulatta female and compared the data with chimpanzees and humans to reveal the structure of ancestral primate genomes and to identify evidence for positive selection and lineage-specific expansions and contractions of gene families. A comparison of sequences from individual animals was used to investigate their underlying genetic diversity. The complete description of the macaque genome blueprint enhances the utility of this animal model for biomedical research and improves our understanding of the basic biology of the species.},
	Author = {{Rhesus Macaque Genome Sequencing and Analysis Consortium} and Gibbs, Richard A and Rogers, Jeffrey and Katze, Michael G and Bumgarner, Roger and Weinstock, George M and Mardis, Elaine R and Remington, Karin A and Strausberg, Robert L and Venter, J Craig and Wilson, Richard K and Batzer, Mark A and Bustamante, Carlos D and Eichler, Evan E and Hahn, Matthew W and Hardison, Ross C and Makova, Kateryna D and Miller, Webb and Milosavljevic, Aleksandar and Palermo, Robert E and Siepel, Adam and Sikela, James M and Attaway, Tony and Bell, Stephanie and Bernard, Kelly E and Buhay, Christian J and Chandrabose, Mimi N and Dao, Marvin and Davis, Clay and Delehaunty, Kimberly D and Ding, Yan and Dinh, Huyen H and Dugan-Rocha, Shannon and Fulton, Lucinda A and Gabisi, Ramatu Ayiesha and Garner, Toni T and Godfrey, Jennifer and Hawes, Alicia C and Hernandez, Judith and Hines, Sandra and Holder, Michael and Hume, Jennifer and Jhangiani, Shalini N and Joshi, Vandita and Khan, Ziad Mohid and Kirkness, Ewen F and Cree, Andrew and Fowler, R Gerald and Lee, Sandra and Lewis, Lora R and Li, Zhangwan and Liu, Yih-Shin and Moore, Stephanie M and Muzny, Donna and Nazareth, Lynne V and Ngo, Dinh Ngoc and Okwuonu, Geoffrey O and Pai, Grace and Parker, David and Paul, Heidie A and Pfannkoch, Cynthia and Pohl, Craig S and Rogers, Yu-Hui and Ruiz, San Juana and Sabo, Aniko and Santibanez, Jireh and Schneider, Brian W and Smith, Scott M and Sodergren, Erica and Svatek, Amanda F and Utterback, Teresa R and Vattathil, Selina and Warren, Wesley and White, Courtney Sherell and Chinwalla, Asif T and Feng, Yucheng and Halpern, Aaron L and Hillier, Ladeana W and Huang, Xiaoqiu and Minx, Pat and Nelson, Joanne O and Pepin, Kymberlie H and Qin, Xiang and Sutton, Granger G and Venter, Eli and Walenz, Brian P and Wallis, John W and Worley, Kim C and Yang, Shiaw-Pyng and Jones, Steven M and Marra, Marco A and Rocchi, Mariano and Schein, Jacqueline E and Baertsch, Robert and Clarke, Laura and Cs{\"u}r{\"o}s, Mikl{\'o}s and Glasscock, Jarret and Harris, R Alan and Havlak, Paul and Jackson, Andrew R and Jiang, Huaiyang and Liu, Yue and Messina, David N and Shen, Yufeng and Song, Henry Xing-Zhi and Wylie, Todd and Zhang, Lan and Birney, Ewan and Han, Kyudong and Konkel, Miriam K and Lee, Jungnam and Smit, Arian F A and Ullmer, Brygg and Wang, Hui and Xing, Jinchuan and Burhans, Richard and Cheng, Ze and Karro, John E and Ma, Jian and Raney, Brian and She, Xinwei and Cox, Michael J and Demuth, Jeffery P and Dumas, Laura J and Han, Sang-Gook and Hopkins, Janet and Karimpour-Fard, Anis and Kim, Young H and Pollack, Jonathan R and Vinar, Tomas and Addo-Quaye, Charles and Degenhardt, Jeremiah and Denby, Alexandra and Hubisz, Melissa J and Indap, Amit and Kosiol, Carolin and Lahn, Bruce T and Lawson, Heather A and Marklein, Alison and Nielsen, Rasmus and Vallender, Eric J and Clark, Andrew G and Ferguson, Betsy and Hernandez, Ryan D and Hirani, Kashif and Kehrer-Sawatzki, Hildegard and Kolb, Jessica and Patil, Shobha and Pu, Ling-Ling and Ren, Yanru and Smith, David Glenn and Wheeler, David A and Schenck, Ian and Ball, Edward V and Chen, Rui and Cooper, David N and Giardine, Belinda and Hsu, Fan and Kent, W James and Lesk, Arthur and Nelson, David L and O'brien, William E and Pr{\"u}fer, Kay and Stenson, Peter D and Wallace, James C and Ke, Hui and Liu, Xiao-Ming and Wang, Peng and Xiang, Andy Peng and Yang, Fan and Barber, Galt P and Haussler, David and Karolchik, Donna and Kern, Andy D and Kuhn, Robert M and Smith, Kayla E and Zwieg, Ann S},
	Date-Added = {2014-01-16 16:14:00 +0000},
	Date-Modified = {2014-01-16 16:14:00 +0000},
	Doi = {10.1126/science.1139247},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Animals; Biomedical Research; Evolution, Molecular; Female; Gene Duplication; Gene Rearrangement; Genetic Diseases, Inborn; Genetic Variation; Genome; Humans; Macaca mulatta; Male; Multigene Family; Mutation; Pan troglodytes; Sequence Analysis, DNA; Species Specificity},
	Month = {Apr},
	Number = {5822},
	Pages = {222-34},
	Pmid = {17431167},
	Pst = {ppublish},
	Title = {Evolutionary and biomedical insights from the rhesus macaque genome},
	Volume = {316},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1139247}}

@article{Chimpanzee-Sequencing-and-Analysis-Consortium:2005mz,
	Abstract = {Here we present a draft genome sequence of the common chimpanzee (Pan troglodytes). Through comparison with the human genome, we have generated a largely complete catalogue of the genetic differences that have accumulated since the human and chimpanzee species diverged from our common ancestor, constituting approximately thirty-five million single-nucleotide changes, five million insertion/deletion events, and various chromosomal rearrangements. We use this catalogue to explore the magnitude and regional variation of mutational forces shaping these two genomes, and the strength of positive and negative selection acting on their genes. In particular, we find that the patterns of evolution in human and chimpanzee protein-coding genes are highly correlated and dominated by the fixation of neutral and slightly deleterious alleles. We also use the chimpanzee genome as an outgroup to investigate human population genetics and identify signatures of selective sweeps in recent human evolution.},
	Author = {{Chimpanzee Sequencing and Analysis Consortium}},
	Date-Added = {2014-01-16 16:12:54 +0000},
	Date-Modified = {2014-01-16 16:12:54 +0000},
	Doi = {10.1038/nature04072},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Alleles; Alu Elements; Animals; Base Composition; Computational Biology; DNA Transposable Elements; Disease; Evolution, Molecular; Genome, Human; Genomics; Humans; Mutagenesis; Pan troglodytes; Phylogeny; Polymorphism, Genetic; Recombination, Genetic; Sequence Analysis, DNA; Telomere; Time Factors},
	Month = {Sep},
	Number = {7055},
	Pages = {69-87},
	Pmid = {16136131},
	Pst = {ppublish},
	Title = {Initial sequence of the chimpanzee genome and comparison with the human genome},
	Volume = {437},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature04072}}

@article{ajay2011accurate,
	Author = {Ajay, Subramanian S and Parker, Stephen CJ and Abaan, Hatice Ozel and Fajardo, Karin V Fuentes and Margulies, Elliott H},
	Date-Added = {2014-01-16 15:50:24 +0000},
	Date-Modified = {2014-01-16 15:50:24 +0000},
	Journal = {Genome research},
	Number = {9},
	Pages = {1498--1505},
	Publisher = {Cold Spring Harbor Lab},
	Title = {Accurate and comprehensive sequencing of personal genomes},
	Volume = {21},
	Year = {2011}}

@article{1000-Genomes-Project-Consortium:2012sf,
	Abstract = {By characterizing the geographic and functional spectrum of human genetic variation, the 1000 Genomes Project aims to build a resource to help to understand the genetic contribution to disease. Here we describe the genomes of 1,092 individuals from 14 populations, constructed using a combination of low-coverage whole-genome and exome sequencing. By developing methods to integrate information across several algorithms and diverse data sources, we provide a validated haplotype map of 38 million single nucleotide polymorphisms, 1.4 million short insertions and deletions, and more than 14,000 larger deletions. We show that individuals from different populations carry different profiles of rare and common variants, and that low-frequency variants show substantial geographic differentiation, which is further increased by the action of purifying selection. We show that evolutionary conservation and coding consequence are key determinants of the strength of purifying selection, that rare-variant load varies substantially across biological pathways, and that each individual contains hundreds of rare non-coding variants at conserved sites, such as motif-disrupting changes in transcription-factor-binding sites. This resource, which captures up to 98% of accessible single nucleotide polymorphisms at a frequency of 1% in related populations, enables analysis of common and low-frequency variants in individuals from diverse, including admixed, populations.},
	Author = {{1000 Genomes Project Consortium} and Abecasis, Goncalo R and Auton, Adam and Brooks, Lisa D and DePristo, Mark A and Durbin, Richard M and Handsaker, Robert E and Kang, Hyun Min and Marth, Gabor T and McVean, Gil A},
	Date-Added = {2014-01-16 15:49:25 +0000},
	Date-Modified = {2014-01-16 15:49:25 +0000},
	Doi = {10.1038/nature11632},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Alleles; Binding Sites; Conserved Sequence; Continental Population Groups; Evolution, Molecular; Genetic Variation; Genetics, Medical; Genetics, Population; Genome, Human; Genome-Wide Association Study; Genomics; Haplotypes; Humans; Nucleotide Motifs; Polymorphism, Single Nucleotide; Sequence Deletion; Transcription Factors},
	Month = {Nov},
	Number = {7422},
	Pages = {56-65},
	Pmc = {PMC3498066},
	Pmid = {23128226},
	Pst = {ppublish},
	Title = {An integrated map of genetic variation from 1,092 human genomes},
	Volume = {491},
	Year = {2012},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature11632}}

@article{autosomes2012integrated,
	Author = {Autosomes Chromosome, X},
	Date-Added = {2014-01-16 15:48:39 +0000},
	Date-Modified = {2014-01-16 15:48:39 +0000},
	Journal = {Nature},
	Pages = {1},
	Title = {An integrated map of genetic variation from 1,092 human genomes},
	Volume = {491},
	Year = {2012}}

@article{schrider2013inferring,
	Author = {Schrider, Daniel R and Kern, Andrew D},
	Date-Added = {2014-01-16 15:42:46 +0000},
	Date-Modified = {2014-01-16 15:42:46 +0000},
	Journal = {arXiv preprint arXiv:1309.2521},
	Title = {Inferring selective constraint and recent gain and loss of function from population genomic data},
	Year = {2013}}

@article{mcvicker2009widespread,
	Author = {McVicker, Graham and Gordon, David and Davis, Colleen and Green, Phil},
	Date-Added = {2014-01-14 19:55:22 +0000},
	Date-Modified = {2014-01-14 19:55:22 +0000},
	Journal = {PLoS genetics},
	Number = {5},
	Pages = {e1000471},
	Publisher = {Public Library of Science},
	Title = {Widespread genomic signatures of natural selection in hominid evolution},
	Volume = {5},
	Year = {2009}}

@article{lohmueller2011natural,
	Author = {Lohmueller, Kirk E and Albrechtsen, Anders and Li, Yingrui and Kim, Su Yeon and Korneliussen, Thorfinn and Vinckenbosch, Nicolas and Tian, Geng and Huerta-Sanchez, Emilia and Feder, Alison F and Grarup, Niels and others},
	Date-Added = {2014-01-14 19:54:34 +0000},
	Date-Modified = {2014-01-14 19:54:34 +0000},
	Journal = {PLoS genetics},
	Number = {10},
	Pages = {e1002326},
	Publisher = {Public Library of Science},
	Title = {Natural selection affects multiple aspects of genetic variation at putatively neutral sites across the human genome},
	Volume = {7},
	Year = {2011}}

@article{pollard2010detection,
	Author = {Pollard, Katherine S and Hubisz, Melissa J and Rosenbloom, Kate R and Siepel, Adam},
	Date-Added = {2014-01-14 15:53:04 +0000},
	Date-Modified = {2014-01-14 15:53:04 +0000},
	Journal = {Genome research},
	Number = {1},
	Pages = {110--121},
	Publisher = {Cold Spring Harbor Lab},
	Title = {Detection of nonneutral substitution rates on mammalian phylogenies},
	Volume = {20},
	Year = {2010}}

@article{lunter2006genome,
	Author = {Lunter, Gerton and Ponting, Chris P and Hein, Jotun},
	Date-Added = {2014-01-14 15:52:35 +0000},
	Date-Modified = {2014-01-14 15:52:35 +0000},
	Journal = {PLoS computational biology},
	Number = {1},
	Pages = {e5},
	Publisher = {Public Library of Science},
	Title = {Genome-wide identification of human functional DNA using a neutral indel model},
	Volume = {2},
	Year = {2006}}

@article{chinwalla2002initial,
	Author = {Chinwalla, Asif T and Cook, Lisa L and Delehaunty, Kimberly D and Fewell, Ginger A and Fulton, Lucinda A and Fulton, Robert S and Graves, Tina A and Hillier, LaDeana W and Mardis, Elaine R and McPherson, John D and others},
	Date-Added = {2014-01-14 15:51:59 +0000},
	Date-Modified = {2014-01-14 15:51:59 +0000},
	Journal = {Nature},
	Number = {6915},
	Pages = {520--562},
	Publisher = {Nature Publishing Group},
	Title = {Initial sequencing and comparative analysis of the mouse genome},
	Volume = {420},
	Year = {2002}}

@article{graur2013immortality,
	Author = {Graur, Dan and Zheng, Yichen and Price, Nicholas and Azevedo, Ricardo BR and Zufall, Rebecca A and Elhaik, Eran},
	Date-Added = {2014-01-14 15:50:19 +0000},
	Date-Modified = {2014-01-14 15:50:19 +0000},
	Journal = {Genome biology and evolution},
	Number = {3},
	Pages = {578--590},
	Publisher = {Oxford University Press},
	Title = {On the immortality of television sets:“function” in the human genome according to the evolution-free gospel of ENCODE},
	Volume = {5},
	Year = {2013}}

@article{dunham2012integrated,
	Author = {Dunham, Ian and Birney, Ewan and Lajoie, Bryan R and Sanyal, Amartya and Dong, Xianjun and Greven, Melissa and Lin, Xinying and Wang, Jie and Whitfield, Troy W and Zhuang, Jiali and others},
	Date-Added = {2014-01-14 15:49:31 +0000},
	Date-Modified = {2014-01-14 15:49:31 +0000},
	Title = {An integrated encyclopedia of DNA elements in the human genome},
	Year = {2012}}

@article{boyle2008high,
	Author = {Boyle, Alan P and Davis, Sean and Shulha, Hennady P and Meltzer, Paul and Margulies, Elliott H and Weng, Zhiping and Furey, Terrence S and Crawford, Gregory E},
	Date-Added = {2014-01-14 15:34:49 +0000},
	Date-Modified = {2014-01-14 15:34:49 +0000},
	Journal = {Cell},
	Number = {2},
	Pages = {311--322},
	Publisher = {Elsevier},
	Title = {High-resolution mapping and characterization of open chromatin across the genome},
	Volume = {132},
	Year = {2008}}

@article{barski2007high,
	Author = {Barski, Artem and Cuddapah, Suresh and Cui, Kairong and Roh, Tae-Young and Schones, Dustin E and Wang, Zhibin and Wei, Gang and Chepelev, Iouri and Zhao, Keji},
	Date-Added = {2014-01-14 15:34:08 +0000},
	Date-Modified = {2014-01-14 15:34:08 +0000},
	Journal = {Cell},
	Number = {4},
	Pages = {823--837},
	Publisher = {Elsevier},
	Title = {High-resolution profiling of histone methylations in the human genome},
	Volume = {129},
	Year = {2007}}

@article{guttman2010ab,
	Author = {Guttman, Mitchell and Garber, Manuel and Levin, Joshua Z and Donaghey, Julie and Robinson, James and Adiconis, Xian and Fan, Lin and Koziol, Magdalena J and Gnirke, Andreas and Nusbaum, Chad and others},
	Date-Added = {2014-01-14 15:33:23 +0000},
	Date-Modified = {2014-01-14 15:33:23 +0000},
	Journal = {Nature biotechnology},
	Number = {5},
	Pages = {503--510},
	Publisher = {Nature Publishing Group},
	Title = {Ab initio reconstruction of cell type-specific transcriptomes in mouse reveals the conserved multi-exonic structure of lincRNAs},
	Volume = {28},
	Year = {2010}}

@article{johnson2007genome,
	Author = {Johnson, David S and Mortazavi, Ali and Myers, Richard M and Wold, Barbara},
	Date-Added = {2014-01-14 15:32:29 +0000},
	Date-Modified = {2014-01-14 15:32:29 +0000},
	Journal = {Science},
	Number = {5830},
	Pages = {1497--1502},
	Publisher = {American Association for the Advancement of Science},
	Title = {Genome-wide mapping of in vivo protein-DNA interactions},
	Volume = {316},
	Year = {2007}}

@article{ward2012evidence,
	Author = {Ward, Lucas D and Kellis, Manolis},
	Date-Added = {2014-01-10 18:21:31 +0000},
	Date-Modified = {2014-01-10 18:21:31 +0000},
	Journal = {Science},
	Number = {6102},
	Pages = {1675--1678},
	Publisher = {American Association for the Advancement of Science},
	Title = {Evidence of abundant purifying selection in humans for recently acquired regulatory functions},
	Volume = {337},
	Year = {2012}}

@article{abecasis2010map,
	Author = {Abecasis, GR and Altshuler, David and Auton, A and Brooks, LD and Durbin, RM and Gibbs, Richard A and Hurles, Matt E and McVean, Gil A and Bentley, DR and Chakravarti, A and others},
	Date-Added = {2014-01-10 17:43:23 +0000},
	Date-Modified = {2014-01-10 17:43:23 +0000},
	Journal = {Nature},
	Number = {7319},
	Pages = {1061--1073},
	Title = {A map of human genome variation from population-scale sequencing.},
	Volume = {467},
	Year = {2010}}

@article{rivas2001noncoding,
	Author = {Rivas, Elena and Eddy, Sean R},
	Date-Added = {2014-01-10 17:25:43 +0000},
	Date-Modified = {2014-01-10 17:25:43 +0000},
	Journal = {BMC bioinformatics},
	Number = {1},
	Pages = {8},
	Publisher = {BioMed Central Ltd},
	Title = {Noncoding RNA gene detection using comparative sequence analysis},
	Volume = {2},
	Year = {2001}}

@article{hertel2006hairpins,
	Author = {Hertel, Jana and Stadler, Peter F},
	Date-Added = {2014-01-10 17:22:59 +0000},
	Date-Modified = {2014-01-10 17:22:59 +0000},
	Journal = {Bioinformatics},
	Number = {14},
	Pages = {e197--e202},
	Publisher = {Oxford Univ Press},
	Title = {Hairpins in a Haystack: recognizing microRNA precursors in comparative genomics data},
	Volume = {22},
	Year = {2006}}

@article{korf2001integrating,
	Author = {Korf, Ian and Flicek, Paul and Duan, Daniel and Brent, Michael R},
	Date-Added = {2014-01-10 17:14:20 +0000},
	Date-Modified = {2014-01-10 17:14:20 +0000},
	Journal = {Bioinformatics},
	Number = {suppl 1},
	Pages = {S140--S148},
	Publisher = {Oxford Univ Press},
	Title = {Integrating genomic homology into gene structure prediction},
	Volume = {17},
	Year = {2001}}

@article{birney2004genewise,
	Author = {Birney, Ewan and Clamp, Michele and Durbin, Richard},
	Date-Added = {2014-01-10 17:13:53 +0000},
	Date-Modified = {2014-01-10 17:13:53 +0000},
	Journal = {Genome research},
	Number = {5},
	Pages = {988--995},
	Publisher = {Cold Spring Harbor Lab},
	Title = {GeneWise and genomewise},
	Volume = {14},
	Year = {2004}}

@article{meyer2002comparative,
	Author = {Meyer, Irmtraud M and Durbin, Richard},
	Date-Added = {2014-01-10 17:13:50 +0000},
	Date-Modified = {2014-01-10 17:13:50 +0000},
	Journal = {Bioinformatics},
	Number = {10},
	Pages = {1309--1318},
	Publisher = {Oxford Univ Press},
	Title = {Comparative ab initio prediction of gene structures using pair HMMs},
	Volume = {18},
	Year = {2002}}

@article{Grossman:2010fk,
	Abstract = {The human genome contains hundreds of regions whose patterns of genetic variation indicate recent positive natural selection, yet for most the underlying gene and the advantageous mutation remain unknown. We developed a method, composite of multiple signals (CMS), that combines tests for multiple signals of selection and increases resolution by up to 100-fold. By applying CMS to candidate regions from the International Haplotype Map, we localized population-specific selective signals to 55 kilobases (median), identifying known and novel causal variants. CMS can not just identify individual loci but implicates precise variants selected by evolution.},
	Author = {Grossman, Sharon R and Shylakhter, Ilya and Karlsson, Elinor K and Byrne, Elizabeth H and Morales, Shannon and Frieden, Gabriel and Hostetter, Elizabeth and Angelino, Elaine and Garber, Manuel and Zuk, Or and Lander, Eric S and Schaffner, Stephen F and Sabeti, Pardis C},
	Date-Added = {2011-03-25 08:47:57 -0400},
	Date-Modified = {2011-03-25 08:47:57 -0400},
	Doi = {10.1126/science.1183863},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Computational Biology; DNA, Intergenic; Evolution, Molecular; Genetic Loci; Genetic Variation; Genome, Human; Haplotypes; Humans; Polymorphism, Genetic; Population Groups; Regulatory Sequences, Nucleic Acid; Selection, Genetic; Software},
	Month = {Feb},
	Number = {5967},
	Pages = {883-6},
	Pmid = {20056855},
	Pst = {ppublish},
	Title = {A composite of multiple signals distinguishes causal variants in regions of positive selection},
	Volume = {327},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1183863}}

@article{Katzman:2010kx,
	Abstract = {Regions of the genome that have been the target of positive selection specifically along the human lineage are of special importance in human biology. We used high throughput sequencing combined with methods to enrich human genomic samples for particular targets to obtain the sequence of 22 chromosomal samples at high depth in 40 kb neighborhoods of 49 previously identified 100-400 bp elements that show evidence for human accelerated evolution. In addition to selection, the pattern of nucleotide substitutions in several of these elements suggested an historical bias favoring the conversion of weak (A or T) alleles into strong (G or C) alleles. Here we found strong evidence in the derived allele frequency spectra of many of these 40 kb regions for ongoing weak-to-strong fixation bias. Comparison of the nucleotide composition at polymorphic loci to the composition at sites of fixed substitutions additionally reveals the signature of historical weak-to-strong fixation bias in a subset of these regions. Most of the regions with evidence for historical bias do not also have signatures of ongoing bias, suggesting that the evolutionary forces generating weak-to-strong bias are not constant over time. To investigate the role of selection in shaping these regions, we analyzed the spatial pattern of polymorphism in our samples. We found no significant evidence for selective sweeps, possibly because the signal of such sweeps has decayed beyond the power of our tests to detect them. Together, these results do not rule out functional roles for the observed changes in these regions-indeed there is good evidence that the first two are functional elements in humans-but they suggest that a fixation process (such as biased gene conversion) that is biased at the nucleotide level, but is otherwise selectively neutral, could be an important evolutionary force at play in them, both historically and at present.},
	Author = {Katzman, Sol and Kern, Andrew D and Pollard, Katherine S and Salama, Sofie R and Haussler, David},
	Date-Added = {2010-10-31 11:34:11 -0400},
	Date-Modified = {2010-10-31 11:34:11 -0400},
	Doi = {10.1371/journal.pgen.1000960},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Chromosome Mapping; Evolution, Molecular; GC Rich Sequence; Gene Frequency; Humans; Mutation},
	Number = {5},
	Pages = {e1000960},
	Pmc = {PMC2873926},
	Pmid = {20502635},
	Pst = {epublish},
	Title = {GC-biased evolution near human accelerated regions},
	Volume = {6},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000960}}

@article{Kolaczkowski:2010uq,
	Abstract = {RNA interference (RNAi) is quickly emerging as a vital component of genome organization, gene regulation and immunity in Drosophila and other species. Previous studies have suggested that, as a whole, genes involved in RNAi are under intense positive selection in D. melanogaster. Here we characterize the extent and patterns of adaptive evolution in 23 known Drosophila RNAi genes, both within D. melanogaster and across the Drosophila phylogeny. We find strong evidence for recurrent protein-coding adaptation at a large number of RNAi genes, particularly those involved in antiviral immunity and defense against transposable elements. We identify specific functional domains involved in direct protein-RNA interactions as particular hotspots of recurrent adaptation in multiple RNAi genes, suggesting that targeted coadaptive arms-races may be a general feature of RNAi evolution. Our observations suggest a predictive model of how selective pressures generated by evolutionary arms-race scenarios may affect multiple genes across protein interaction networks and other biochemical pathways.},
	Author = {Kolaczkowski, Bryan and Hupalo, Daniel N and Kern, Andrew D},
	Date-Added = {2010-10-31 11:34:10 -0400},
	Date-Modified = {2010-10-31 11:34:10 -0400},
	Doi = {10.1093/molbev/msq284},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Month = {Oct},
	Pmid = {20971974},
	Pst = {aheadofprint},
	Title = {Recurrent adaptation in RNA-interference genes across the Drosophila phylogeny},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msq284}}

@article{kolaczkowskikernetal2010,
	Author = {Kolaczkowski, Bryan and Kern, Andrew D. and Holloway, Alisha K, and Begun, David J},
	Date-Added = {2010-10-31 11:33:17 -0400},
	Date-Modified = {2010-10-31 11:36:07 -0400},
	Journal = {Genetics},
	Title = {A whole-genome view of clinal variation in Australian Drosophila melanogaster},
	Year = {In press}}

@article{kauer2003nonneutral,
	Author = {Kauer, M. and Dieringer, D. and Schl{\\"o}tterer, C.},
	Date-Added = {2010-10-31 10:45:33 -0400},
	Date-Modified = {2010-10-31 10:45:33 -0400},
	Issn = {0737-4038},
	Journal = {Molecular Biology and Evolution},
	Number = {8},
	Pages = {1329},
	Publisher = {SMBE},
	Title = {Nonneutral admixture of immigrant genotypes in African Drosophila melanogaster populations from Zimbabwe},
	Volume = {20},
	Year = {2003}}

@book{Taleb:2010fk,
	Abstract = {Examines the role of the unexpected, discussing why improbable events are not anticipated or understood properly, and how humans rationalize the black swan phenomenon to make it appear less random},
	Address = {New York},
	Annote = {LDR    03356cam  2200361 a 4500
001    16224235
005    20101019142812.0
008    100510r20102007nyua     b    001 0 eng  
906    $a7$bcbc$ccopycat$d2$encip$f20$gy-gencatlg
925 0  $aAcquire$b2 shelf copies$xpolicy default
955    $brg01 2010-05-10 z-processor$irg01 2010-05-10 to CALM$aBarcode 00284450395 returned from bindery 2010-06-09$trg15 2010-10-19 copies 2 & 3 (copy 2 added; copy 3 processed as a discard) to CALM
010    $a  2010292618
020    $a081297381X
020    $a9780812973815 (pbk.)
035    $a(OCoLC)ocn213400968
040    $aYDXCP$cYDXCP$dBAKER$dRL9$dDLC
042    $alccopycat
050 00 $aQ375$b.T35 2010
082 00 $a003/.54$222
100 1  $aTaleb, Nassim.
245 14 $aThe black swan :$bthe impact of the highly improbable /$cNassim Nicholas Taleb.
250    $a2nd ed., Random trade pbk. ed.
260    $aNew York :$bRandom House Trade Paperbacks,$cc2010.
300    $axxxiii, 444 p. :$bill. ;$c21 cm.
500    $a"Originally published in hardcover and in slightly different form in the United States ... by Random House in 2007."-T.p. verso.
504    $aIncludes bibliographical references (p. [400]-429) and index.
505 0  $aPrologue -- Umberto Eco's antilibrary, or how we seek validation. The apprenticeship of an empirical skeptic ; Yevgenia's black swan ; The speculator and the prostitute ; One thousand and one days, or how not to be a sucker ; Confirmation shmonfirmation! ; The narrative fallacy ; Living in the antechamber of hope ; Giacomo Casanova's unfailing luck : the problem of silent evidence ; The Ludic fallacy, or the uncertainty of the nerd -- We just can't predict. The scandal of prediction ; How to look for bird poop ; Epistemocracy, a dream ; Appelles the Painter, or what do you do if you cannot predict? -- Those gray swans of Extremistan. From Mediocristan to Extremistan and back ; The bell curve, that great intellectual fraud ; The aesthetics of randomness ; Locke's madmen, or bell curves in the wrong places ; The uncertainty of the phony -- The end. Half and half, or how to get even with the black swan -- Epilogue : Yevgenia's white swans -- Postscript essay: on robustness an fragility, deeper philosophical and empirical reflections. Learning from mother nature, the oldest and the wisest ; Why I do all this walking, or how systems become fragile ; Margaritas ante porcos ; Asperger and the ontological black swan ; (Perhaps) the most useful problem in the history of modern philosophy ; Fourth quadrant, the solution to that most useful of problems ; What to do with the fourth quadrant ; Ten principles for a black-swan-robust society ; Amor fati: how to become indestructible.
520    $aExamines the role of the unexpected, discussing why improbable events are not anticipated or understood properly, and how humans rationalize the black swan phenomenon to make it appear less random.
650  0 $aUncertainty (Information theory)$xSocial aspects.
650  0 $aForecasting.
856 41 $3Sample text$uhttp://www.loc.gov/catdir/enhancements/fy1009/2010292618-s.html
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/enhancements/fy1009/2010292618-d.html
856 42 $3Contributor biographical information$uhttp://www.loc.gov/catdir/enhancements/fy1009/2010292618-b.html
},
	Author = {Taleb, Nassim},
	Call-Number = {Q375},
	Date-Added = {2010-10-31 10:36:15 -0400},
	Date-Modified = {2010-10-31 10:36:15 -0400},
	Dewey-Call-Number = {003/.54},
	Edition = {2nd ed., Random trade pbk. ed},
	Genre = {Uncertainty (Information theory)},
	Isbn = {081297381X},
	Library-Id = {2010292618},
	Publisher = {Random House Trade Paperbacks},
	Title = {The black swan: the impact of the highly improbable},
	Url = {http://www.loc.gov/catdir/enhancements/fy1009/2010292618-s.html},
	Year = {2010},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/enhancements/fy1009/2010292618-s.html}}

@article{thornton2005recombination,
	Author = {Thornton, K.},
	Date-Added = {2010-09-08 10:34:03 -0400},
	Date-Modified = {2010-09-08 10:34:03 -0400},
	Journal = {Genetics},
	Publisher = {Genetics Soc America},
	Title = {Recombination and the properties of Tajima's D in the context of approximate likelihood calculation},
	Year = {2005}}

@book{nei1987molecular,
	Author = {Nei, M.},
	Date-Added = {2010-09-01 08:52:59 -0400},
	Date-Modified = {2010-09-01 08:52:59 -0400},
	Publisher = {Columbia Univ Pr},
	Title = {Molecular evolutionary genetics},
	Year = {1987}}

@article{futschik2010massively,
	Author = {Futschik, A. and Schlotterer, C.},
	Date-Added = {2010-09-01 08:50:43 -0400},
	Date-Modified = {2010-09-01 08:50:43 -0400},
	Journal = {Genetics},
	Publisher = {Genetics Soc America},
	Title = {Massively Parallel Sequencing of Pooled DNA Samples--The Next Generation of Molecular Markers},
	Year = {2010}}

@article{bradshaw1977interaction,
	Author = {Bradshaw, W.E. and Holzapfel, C.M.},
	Date-Added = {2010-06-30 12:02:11 -0400},
	Date-Modified = {2010-06-30 12:02:11 -0400},
	Journal = {Biological Bulletin},
	Number = {2},
	Pages = {147--158},
	Publisher = {JSTOR},
	Title = {Interaction between photoperiod, temperature, and chilling in dormant larvae of the tree-hole mosquito, Toxorhynchites rutilus Coq},
	Volume = {152},
	Year = {1977}}

@article{hard1993genetic,
	Author = {Hard, J.J. and Bradshaw, W.E. and Holzapfel, C.M.},
	Date-Added = {2010-06-30 12:01:49 -0400},
	Date-Modified = {2010-06-30 12:01:49 -0400},
	Journal = {American Naturalist},
	Number = {3},
	Pages = {457--473},
	Publisher = {JSTOR},
	Title = {The genetic basis of photoperiodism and its evolutionary divergence among populations of the pitcher-plant mosquito, Wyeomyia smithii},
	Volume = {142},
	Year = {1993}}

@article{bradshaw2004adaptation,
	Author = {Bradshaw, W.E. and Zani, P.A. and Holzapfel, C.M.},
	Date-Added = {2010-06-30 12:01:43 -0400},
	Date-Modified = {2010-06-30 12:01:43 -0400},
	Journal = {Evolution},
	Number = {8},
	Pages = {1748--1762},
	Publisher = {John Wiley \& Sons},
	Title = {Adaptation to temperate climates},
	Volume = {58},
	Year = {2004}}

@article{bradshaw2001genetic,
	Author = {Bradshaw, W.E. and Holzapfel, C.M.},
	Date-Added = {2010-06-30 12:01:34 -0400},
	Date-Modified = {2010-06-30 12:01:34 -0400},
	Journal = {Proceedings of the National Academy of Sciences of the United States of America},
	Number = {25},
	Pages = {14509},
	Publisher = {National Acad Sciences},
	Title = {Genetic shift in photoperiodic response correlated with global warming},
	Volume = {98},
	Year = {2001}}

@article{Randetal2010,
	Author = {David M Rand, and Daniel M. Weinreich, and Daniel Lerman, and Donna Folk, and George W. Gilchrist},
	Date-Added = {2010-06-30 11:54:24 -0400},
	Date-Modified = {2010-06-30 11:58:30 -0400},
	Journal = {Evolution Int J Org Evolution},
	Title = {Three selections are better than one: clinal variation of thermal QTL from independent selection experiments in Drosophila},
	Year = {2010}}

@article{pasyukova2000deficiency,
	Author = {Pasyukova, E.G. and Vieira, C. and Mackay, T.F.C.},
	Date-Added = {2010-06-09 13:41:02 -0400},
	Date-Modified = {2010-06-09 13:41:02 -0400},
	Journal = {Genetics},
	Number = {3},
	Pages = {1129},
	Publisher = {Genetics Soc America},
	Title = {Deficiency mapping of quantitative trait loci affecting longevity in Drosophila melanogaster},
	Volume = {156},
	Year = {2000}}

@article{anderson2005response,
	Author = {Anderson, A.R. and Hoffmann, A.A. and McKECHNIE, S.W.},
	Date-Added = {2010-06-09 13:37:44 -0400},
	Date-Modified = {2010-06-09 13:37:44 -0400},
	Journal = {Genetics Research},
	Number = {01},
	Pages = {15--22},
	Publisher = {Cambridge Univ Press},
	Title = {Response to selection for rapid chill-coma recovery in Drosophila melanogaster: physiology and life-history traits},
	Volume = {85},
	Year = {2005}}

@article{mustonen2009fitness,
	Author = {Mustonen, V. and Lassig, M.},
	Date-Added = {2010-06-08 16:37:51 -0400},
	Date-Modified = {2010-06-08 16:42:59 -0400},
	Journal = {Trends in Genetics},
	Number = {3},
	Pages = {111--119},
	Publisher = {Elsevier},
	Title = {From fitness landscapes to seascapes: non-equilibrium dynamics of selection and adaptation},
	Volume = {25},
	Year = {2009}}

@article{ruggieri2009change,
	Author = {Ruggieri, E. and Herbert, T. and Lawrence, KT and Lawrence, CE},
	Date-Added = {2010-06-02 14:18:14 -0400},
	Date-Modified = {2010-06-02 14:18:14 -0400},
	Journal = {Paleoceanography},
	Title = {Change point method for detecting regime shifts in paleoclimatic time series: Application to d18O time series of the Plio-Pleistocene},
	Volume = {24},
	Year = {2009}}

@article{lawrence1993detecting,
	Author = {Lawrence, C.E. and Altschul, S.F. and Boguski, M.S. and Liu, J.S. and Neuwald, A.F. and Wootton, J.C.},
	Date-Added = {2010-06-02 14:16:06 -0400},
	Date-Modified = {2010-06-02 14:17:36 -0400},
	Journal = {Science},
	Pages = {741},
	Title = {Detecting subtle sequence signals: a Gibbs sampling strategy for multiple alignment},
	Volume = {93},
	Year = {1993}}

@article{auger1989algorithms,
	Author = {Auger, I.E. and Lawrence, C.E.},
	Date-Added = {2010-06-02 14:15:07 -0400},
	Date-Modified = {2010-06-02 14:15:07 -0400},
	Journal = {Bulletin of mathematical biology},
	Number = {1},
	Pages = {39--54},
	Publisher = {Springer},
	Title = {Algorithms for the optimal identification of segment neighborhoods},
	Volume = {51},
	Year = {1989}}

@article{Daborn:2002kx,
	Abstract = {Insecticide resistance is one of the most widespread genetic changes caused by human activity, but we still understand little about the origins and spread of resistant alleles in global populations of insects. Here, via microarray analysis of all P450s in Drosophila melanogaster, we show that DDT-R, a gene conferring resistance to DDT, is associated with overtranscription of a single cytochrome P450 gene, Cyp6g1. Transgenic analysis of Cyp6g1 shows that overtranscription of this gene alone is both necessary and sufficient for resistance. Resistance and up-regulation in Drosophila populations are associated with a single Cyp6g1 allele that has spread globally. This allele is characterized by the insertion of an Accord transposable element into the 5' end of the Cyp6g1 gene.},
	Author = {Daborn, P J and Yen, J L and Bogwitz, M R and Le Goff, G and Feil, E and Jeffers, S and Tijet, N and Perry, T and Heckel, D and Batterham, P and Feyereisen, R and Wilson, T G and ffrench-Constant, R H},
	Date-Added = {2010-05-14 11:17:15 -0400},
	Date-Modified = {2010-05-14 11:17:15 -0400},
	Doi = {10.1126/science.1074170},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Alleles; Animals; Animals, Genetically Modified; Base Sequence; Chromosome Mapping; Cytochrome P-450 Enzyme System; DDT; Drosophila Proteins; Drosophila melanogaster; Gene Expression Profiling; Gene Expression Regulation, Enzymologic; Genes, Insect; Insecticide Resistance; Insecticides; Introns; Molecular Sequence Data; Oligonucleotide Array Sequence Analysis; Phylogeny; Reverse Transcriptase Polymerase Chain Reaction; Sequence Analysis, DNA; Substrate Specificity; Transcription, Genetic; Transgenes},
	Month = {Sep},
	Number = {5590},
	Pages = {2253-6},
	Pmid = {12351787},
	Pst = {ppublish},
	Title = {A single p450 allele associated with insecticide resistance in Drosophila},
	Volume = {297},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1074170}}

@article{Aguade:1989uq,
	Abstract = {Restriction map variation in 64 X chromosome lines extracted from three different populations of Drosophila melanogaster was investigated with seven six-nucleotide-recognizing restriction enzymes for a 106-kb region encompassing the yellow gene and the achaete-scute complex that is located in the region of reduced crossing over close to the telomere. Nine restriction site polymorphisms (out of 176 sites scored) and 19 length polymorphisms (15 insertions and 4 deletions) were detected. The estimated level of heterozygosity per nucleotide, H = 0.0003, is much lower than that reported for autosomal and sex-linked loci located in regions with normal levels of crossing over. The overall frequency of polymorphic restriction sites is reduced. Six out of nine restriction site polymorphisms are unique and the other three have frequencies less than 0.17. Some large insertions have reached relatively high frequencies, 0.08 to 0.17. Consistent with the theoretically predicted negative relationship between crossing over and the magnitude of linkage disequilibrium, an increase in the relative number of nonrandom associations was observed in the y-ac-sc region.},
	Author = {Aguade, M and Miyashita, N and Langley, C H},
	Date-Added = {2010-05-14 11:15:40 -0400},
	Date-Modified = {2010-05-14 11:15:40 -0400},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Month = {Jul},
	Number = {3},
	Pages = {607-615},
	Pmc = {PMC1203734},
	Pmid = {17246506},
	Pst = {ppublish},
	Title = {Reduced Variation in the Yellow-Achaete-Scute Region in Natural Populations of Drosophila Melanogaster},
	Volume = {122},
	Year = {1989}}

@book{gelman2004bayesian,
	Author = {Gelman, A.},
	Date-Added = {2010-05-05 11:37:09 -0400},
	Date-Modified = {2010-05-05 11:37:09 -0400},
	Publisher = {CRC press},
	Title = {{Bayesian data analysis}},
	Year = {2004}}

@article{bustamante2003maximum,
	Author = {Bustamante, C.D. and Nielsen, R. and Hartl, D.L.},
	Date-Added = {2010-05-05 11:33:54 -0400},
	Date-Modified = {2010-05-05 11:33:54 -0400},
	Journal = {Theoretical population biology},
	Number = {2},
	Pages = {91--103},
	Publisher = {Elsevier},
	Title = {{Maximum likelihood and Bayesian methods for estimating the distribution of selective effects among classes of mutations using DNA polymorphism data}},
	Volume = {63},
	Year = {2003}}

@article{nachman2003genetic,
	Author = {Nachman, M.W. and Hoekstra, H.E. and D'Agostino, S.L.},
	Date-Added = {2010-04-30 10:52:39 -0400},
	Date-Modified = {2010-04-30 10:52:39 -0400},
	Journal = {Proceedings of the National Academy of Sciences of the United States of America},
	Number = {9},
	Pages = {5268},
	Publisher = {National Acad Sciences},
	Title = {{The genetic basis of adaptive melanism in pocket mice}},
	Volume = {100},
	Year = {2003}}

@article{Haygood:2007kx,
	Abstract = {Surveys of protein-coding sequences for evidence of positive selection in humans or chimpanzees have flagged only a few genes known to function in neural or nutritional processes, despite pronounced differences between humans and chimpanzees in behavior, cognition and diet. It may be that most such differences are due to changes in gene regulation rather than protein structure. Here, we present the first survey of promoter (5'-flanking) regions, which are rich in cis-regulatory sequences, for evidence of positive selection in humans. Our results indicate that positive selection has targeted the regulation of many genes known to be involved in neural development and function, both in the brain and elsewhere in the nervous system, and in nutrition, particularly in glucose metabolism.},
	Author = {Haygood, Ralph and Fedrigo, Olivier and Hanson, Brian and Yokoyama, Ken-Daigoro and Wray, Gregory A},
	Date-Added = {2010-02-23 10:39:04 -0500},
	Date-Modified = {2010-02-23 10:39:04 -0500},
	Doi = {10.1038/ng2104},
	Journal = {Nat Genet},
	Journal-Full = {Nature genetics},
	Mesh = {5' Flanking Region; Animals; Computational Biology; Energy Metabolism; Evolution, Molecular; Gene Expression Regulation, Developmental; Genome, Human; Humans; Models, Genetic; Nervous System; Nutrigenomics; Pan troglodytes; Promoter Regions, Genetic; Selection, Genetic},
	Month = {Sep},
	Number = {9},
	Pages = {1140-4},
	Pmid = {17694055},
	Pst = {ppublish},
	Title = {Promoter regions of many neural- and nutrition-related genes have experienced positive selection during human evolution},
	Volume = {39},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/ng2104}}

@article{Nobrega:2003uq,
	Author = {Nobrega, Marcelo A and Ovcharenko, Ivan and Afzal, Veena and Rubin, Edward M},
	Date-Added = {2010-02-23 10:02:43 -0500},
	Date-Modified = {2010-02-23 10:02:43 -0500},
	Doi = {10.1126/science.1088328},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Animals; Anura; Base Sequence; Conserved Sequence; DNA, Intergenic; Drosophila Proteins; Enhancer Elements, Genetic; Evolution, Molecular; Gene Expression Regulation; Genes, Reporter; Humans; Introns; Mice; Mice, Transgenic; Nuclear Proteins; Synteny; Takifugu; Tetraodontiformes; Xenopus; Zebrafish},
	Month = {Oct},
	Number = {5644},
	Pages = {413},
	Pmid = {14563999},
	Pst = {ppublish},
	Title = {Scanning human gene deserts for long-range enhancers},
	Volume = {302},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1088328}}

@article{Guigo:2003fk,
	Abstract = {A primary motivation for sequencing the mouse genome was to accelerate the discovery of mammalian genes by using sequence conservation between mouse and human to identify coding exons. Achieving this goal proved challenging because of the large proportion of the mouse and human genomes that is apparently conserved but apparently does not code for protein. We developed a two-stage procedure that exploits the mouse and human genome sequences to produce a set of genes with a much higher rate of experimental verification than previously reported prediction methods. RT-PCR amplification and direct sequencing applied to an initial sample of mouse predictions that do not overlap previously known genes verified the regions flanking one intron in 139 predictions, with verification rates reaching 76\%. On average, the confirmed predictions show more restricted expression patterns than the mouse orthologs of known human genes, and two-thirds lack homologs in fish genomes, demonstrating the sensitivity of this dual-genome approach to hard-to-find genes. We verified 112 previously unknown homologs of known proteins, including two homeobox proteins relevant to developmental biology, an aquaporin, and a homolog of dystrophin. We estimate that transcription and splicing can be verified for >1,000 gene predictions identified by this method that do not overlap known genes. This is likely to constitute a significant fraction of the previously unknown, multiexon mammalian genes.},
	Author = {Guigo, Roderic and Dermitzakis, Emmanouil T and Agarwal, Pankaj and Ponting, Chris P and Parra, Genis and Reymond, Alexandre and Abril, Josep F and Keibler, Evan and Lyle, Robert and Ucla, Catherine and Antonarakis, Stylianos E and Brent, Michael R},
	Date-Added = {2010-02-23 10:01:04 -0500},
	Date-Modified = {2010-02-23 10:01:04 -0500},
	Doi = {10.1073/pnas.0337561100},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Amino Acid Sequence; Animals; Exons; Genetic Techniques; Genome; Genome, Human; Humans; Introns; Mice; Molecular Sequence Data; Reverse Transcriptase Polymerase Chain Reaction; Sequence Analysis, DNA; Sequence Homology, Amino Acid; Tissue Distribution},
	Month = {Feb},
	Number = {3},
	Pages = {1140-5},
	Pmc = {PMC298740},
	Pmid = {12552088},
	Pst = {ppublish},
	Title = {Comparison of mouse and human genomes followed by experimental verification yields an estimated 1,019 additional genes},
	Volume = {100},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0337561100}}

@article{Lewontin:1973bs,
	Abstract = {The variation in gene frequency among populations or between generations within a population is a result of breeding structure and selection. But breeding structure should affect all loci and alleles in the same way. If there is significant heterogeneity between loci in their apparent inbreeding coefficients F=s(p) (2)/p(1-p), this heterogeneity may be taken as evidence for selection. We have given the statistical properties of F and shown how tests of heterogeneity can be made. Using data from human populations we have shown highly significant heterogeneity in F values for human polymorphic genes over the world, thus demonstrating that a significant fraction of human polymorphisms owe their current gene frequencies to the action of natural selection. We have also applied the method to temporal variation within a population for data on Dacus oleae and have found no significant evidence of selection.},
	Author = {Lewontin, R C and Krakauer, J},
	Date-Added = {2010-02-11 09:25:47 -0500},
	Date-Modified = {2010-02-11 09:25:47 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Gene Frequency; Humans; Models, Biological; Polymorphism, Genetic; Selection, Genetic; Time Factors},
	Month = {May},
	Number = {1},
	Pages = {175-95},
	Pmid = {4711903},
	Title = {Distribution of gene frequency as a test of the theory of the selective neutrality of polymorphisms},
	Volume = {74},
	Year = {1973}}

@article{Teshima:2009ij,
	Abstract = {BACKGROUND: The pattern of single nucleotide polymorphisms, or SNPs, contains a tremendous amount of information with respect to the mechanisms of the micro-evolutionary process of a species. The inference of the roles of these mechanisms, including natural selection, relies heavily on computer simulations. A coalescent simulation is extremely powerful in generating a large number of samples of DNA sequences from a population (species) when all mutations are neutral, and Hudson's ms software is frequently used for this purpose.However, it has been difficult to incorporate natural selection into the coalescent framework. RESULTS: We herein present a software application to generate samples of DNA sequences when there is a biallelic site targeted by selection. This software application, referred to as mbs, is developed by modifying Hudson's ms. The mbs software is so flexible that it can incorporate any arbitrary histories of population size changes and any mode of selection as long as selection is operating on a biallelic site. CONCLUSION: mbs provides opportunities to investigate the effect of any mode of selection on the pattern of SNPs under various demography.},
	Author = {Teshima, Kosuke M and Innan, Hideki},
	Date-Added = {2010-02-11 09:19:51 -0500},
	Date-Modified = {2010-02-11 09:19:51 -0500},
	Doi = {10.1186/1471-2105-10-166},
	Journal = {BMC Bioinformatics},
	Journal-Full = {BMC bioinformatics},
	Mesh = {Alleles; Base Sequence; Computational Biology; DNA; Demography; Genetics, Population; Polymorphism, Single Nucleotide; Selection, Genetic; Software},
	Pages = {166},
	Pmid = {19480708},
	Title = {mbs: modifying Hudson's ms software to generate samples of DNA sequences with a biallelic site under selection},
	Volume = {10},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/1471-2105-10-166}}

@article{Teshima:2006hc,
	Abstract = {Most models of positive directional selection assume codominance of the beneficial allele. We examine the importance of this assumption by implementing a coalescent model of positive directional selection with arbitrary dominance. We find that, for a given mean fixation time, a beneficial allele has a much weaker effect on diversity at linked neutral sites when the allele is recessive.},
	Author = {Teshima, Kosuke M and Przeworski, Molly},
	Date-Added = {2010-02-11 09:18:30 -0500},
	Date-Modified = {2010-02-11 09:18:30 -0500},
	Doi = {10.1534/genetics.105.044065},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Algorithms; Alleles; Evolution; Gene Frequency; Genes, Dominant; Genes, Recessive; Genetic Variation; Genetics, Population; Linkage Disequilibrium; Models, Genetic; Polymorphism, Genetic; Recombination, Genetic; Selection, Genetic},
	Month = {Jan},
	Number = {1},
	Pages = {713-8},
	Pmid = {16219788},
	Title = {Directional positive selection on an allele of arbitrary dominance},
	Volume = {172},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.105.044065}}

@article{Teshima:2006tg,
	Abstract = {The beneficial substitution of an allele shapes patterns of genetic variation at linked sites. Thus, in principle, adaptations can be mapped by looking for the signature of directional selection in polymorphism data. In practice, such efforts are hampered by the need for an accurate characterization of the demographic history of the species and of the effects of positive selection. In an attempt to circumvent these difficulties, researchers are increasingly taking a purely empirical approach, in which a large number of genomic regions are ordered by summaries of the polymorphism data, and loci with extreme values are considered to be likely targets of positive selection. We evaluated the reliability of the "empirical" approach, focusing on applications to human data and to maize. To do so, we considered a coalescent model of directional selection in a sensible demographic setting, allowing for selection on standing variation as well as on a new mutation. Our simulations suggest that while empirical approaches will identify several interesting candidates, they will also miss many--in some cases, most--loci of interest. The extent of the trade-off depends on the mode of positive selection and the demographic history of the population. Specifically, the false-discovery rate is higher when directional selection involves a recessive rather than a co-dominant allele, when it acts on a previously neutral rather than a new allele, and when the population has experienced a population bottleneck rather than maintained a constant size. One implication of these results is that, insofar as attributes of the beneficial mutation (e.g., the dominance coefficient) affect the power to detect targets of selection, genomic scans will yield an unrepresentative subset of loci that contribute to adaptations.},
	Author = {Teshima, Kosuke M and Coop, Graham and Przeworski, Molly},
	Date-Added = {2010-02-11 09:18:26 -0500},
	Date-Modified = {2010-02-11 09:18:26 -0500},
	Doi = {10.1101/gr.5105206},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Africa South of the Sahara; Demography; Gene Frequency; Genetics, Population; Genomics; Humans; Models, Genetic; Mutation; Polymorphism, Genetic; Research Design; Selection, Genetic; Zea mays},
	Month = {Jun},
	Number = {6},
	Pages = {702-12},
	Pmid = {16687733},
	Title = {How reliable are empirical genomic scans for selective sweeps?},
	Volume = {16},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.5105206}}

@article{Boyko:2008kl,
	Abstract = {Quantifying the distribution of fitness effects among newly arising mutations in the human genome is key to resolving important debates in medical and evolutionary genetics. Here, we present a method for inferring this distribution using Single Nucleotide Polymorphism (SNP) data from a population with non-stationary demographic history (such as that of modern humans). Application of our method to 47,576 coding SNPs found by direct resequencing of 11,404 protein coding-genes in 35 individuals (20 European Americans and 15 African Americans) allows us to assess the relative contribution of demographic and selective effects to patterning amino acid variation in the human genome. We find evidence of an ancient population expansion in the sample with African ancestry and a relatively recent bottleneck in the sample with European ancestry. After accounting for these demographic effects, we find strong evidence for great variability in the selective effects of new amino acid replacing mutations. In both populations, the patterns of variation are consistent with a leptokurtic distribution of selection coefficients (e.g., gamma or log-normal) peaked near neutrality. Specifically, we predict 27-29\% of amino acid changing (nonsynonymous) mutations are neutral or nearly neutral (|s|<0.01\%), 30-42\% are moderately deleterious (0.01\%<|s|<1\%), and nearly all the remainder are highly deleterious or lethal (|s|>1\%). Our results are consistent with 10-20\% of amino acid differences between humans and chimpanzees having been fixed by positive selection with the remainder of differences being neutral or nearly neutral. Our analysis also predicts that many of the alleles identified via whole-genome association mapping may be selectively neutral or (formerly) positively selected, implying that deleterious genetic variation affecting disease phenotype may be missed by this widely used approach for mapping genes underlying complex traits.},
	Author = {Boyko, Adam R and Williamson, Scott H and Indap, Amit R and Degenhardt, Jeremiah D and Hernandez, Ryan D and Lohmueller, Kirk E and Adams, Mark D and Schmidt, Steffen and Sninsky, John J and Sunyaev, Shamil R and White, Thomas J and Nielsen, Rasmus and Clark, Andrew G and Bustamante, Carlos D},
	Date-Added = {2010-02-04 12:29:13 -0500},
	Date-Modified = {2010-02-04 12:29:13 -0500},
	Doi = {10.1371/journal.pgen.1000083},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {African Continental Ancestry Group; Alleles; Amino Acid Substitution; Animals; European Continental Ancestry Group; Evolution, Molecular; Female; Genetics, Population; Genome, Human; Humans; Male; Mutation, Missense; Pan troglodytes; Polymorphism, Single Nucleotide; Selection, Genetic},
	Month = {May},
	Number = {5},
	Pages = {e1000083},
	Pmid = {18516229},
	Title = {Assessing the evolutionary impact of amino acid mutations in the human genome},
	Volume = {4},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000083}}

@article{Sankararaman:2008oq,
	Abstract = {Inference of ancestral information in recently admixed populations, in which every individual is composed of a mixed ancestry (e.g., African Americans in the United States), is a challenging problem. Several previous model-based approaches to admixture have been based on hidden Markov models (HMMs) and Markov hidden Markov models (MHMMs). We present an augmented form of these models that can be used to predict historical recombination events and can model background linkage disequilibrium (LD) more accurately. We also study some of the computational issues that arise in using such Markovian models on realistic data sets. In particular, we present an effective initialization procedure that, when combined with expectation-maximization (EM) algorithms for parameter estimation, yields high accuracy at significantly decreased computational cost relative to the Markov chain Monte Carlo (MCMC) algorithms that have generally been used in earlier studies. We present experiments exploring these modeling and algorithmic issues in two scenarios-the inference of locus-specific ancestries in a population that is assumed to originate from two unknown ancestral populations, and the inference of allele frequencies in one ancestral population given those in another.},
	Author = {Sankararaman, Sriram and Kimmel, Gad and Halperin, Eran and Jordan, Michael I},
	Date-Added = {2010-02-04 11:20:48 -0500},
	Date-Modified = {2010-02-04 11:20:48 -0500},
	Doi = {10.1101/gr.072751.107},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Algorithms; Ethnic Groups; Gene Frequency; Genetics, Population; Humans; Linkage Disequilibrium; Markov Chains; Models, Statistical; Recombination, Genetic},
	Month = {Apr},
	Number = {4},
	Pages = {668-75},
	Pmid = {18353809},
	Title = {On the inference of ancestries in admixed populations},
	Volume = {18},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.072751.107}}

@article{Bryc:2010nx,
	Abstract = {Quantifying patterns of population structure in Africans and African Americans illuminates the history of human populations and is critical for undertaking medical genomic studies on a global scale. To obtain a fine-scale genome-wide perspective of ancestry, we analyze Affymetrix GeneChip 500K genotype data from African Americans (n = 365) and individuals with ancestry from West Africa (n = 203 from 12 populations) and Europe (n = 400 from 42 countries). We find that population structure within the West African sample reflects primarily language and secondarily geographical distance, echoing the Bantu expansion. Among African Americans, analysis of genomic admixture by a principal component-based approach indicates that the median proportion of European ancestry is 18.5\% (25th-75th percentiles: 11.6-27.7\%), with very large variation among individuals. In the African-American sample as a whole, few autosomal regions showed exceptionally high or low mean African ancestry, but the X chromosome showed elevated levels of African ancestry, consistent with a sex-biased pattern of gene flow with an excess of European male and African female ancestry. We also find that genomic profiles of individual African Americans afford personalized ancestry reconstructions differentiating ancient vs. recent European and African ancestry. Finally, patterns of genetic similarity among inferred African segments of African-American genomes and genomes of contemporary African populations included in this study suggest African ancestry is most similar to non-Bantu Niger-Kordofanian-speaking populations, consistent with historical documents of the African Diaspora and trans-Atlantic slave trade.},
	Author = {Bryc, Katarzyna and Auton, Adam and Nelson, Matthew R and Oksenberg, Jorge R and Hauser, Stephen L and Williams, Scott and Froment, Alain and Bodo, Jean-Marie and Wambebe, Charles and Tishkoff, Sarah A and Bustamante, Carlos D},
	Date-Added = {2010-02-04 11:18:42 -0500},
	Date-Modified = {2010-02-04 11:18:42 -0500},
	Doi = {10.1073/pnas.0909559107},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Month = {Jan},
	Number = {2},
	Pages = {786-91},
	Pmid = {20080753},
	Title = {Genome-wide patterns of population structure and admixture in West Africans and African Americans},
	Volume = {107},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0909559107}}

@article{Pritchard:2000cr,
	Abstract = {We describe a model-based clustering method for using multilocus genotype data to infer population structure and assign individuals to populations. We assume a model in which there are K populations (where K may be unknown), each of which is characterized by a set of allele frequencies at each locus. Individuals in the sample are assigned (probabilistically) to populations, or jointly to two or more populations if their genotypes indicate that they are admixed. Our model does not assume a particular mutation process, and it can be applied to most of the commonly used genetic markers, provided that they are not closely linked. Applications of our method include demonstrating the presence of population structure, assigning individuals to populations, studying hybrid zones, and identifying migrants and admixed individuals. We show that the method can produce highly accurate assignments using modest numbers of loci-e.g. , seven microsatellite loci in an example using genotype data from an endangered bird species. The software used for this article is available from http://www.stats.ox.ac.uk/ approximately pritch/home. html.},
	Author = {Pritchard, J K and Stephens, M and Donnelly, P},
	Date-Added = {2010-02-04 11:06:09 -0500},
	Date-Modified = {2010-02-04 11:06:09 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Algorithms; Cluster Analysis; Genetics, Population; Genotype; Humans; Models, Genetic},
	Month = {Jun},
	Number = {2},
	Pages = {945-59},
	Pmid = {10835412},
	Title = {Inference of population structure using multilocus genotype data},
	Volume = {155},
	Year = {2000}}

@article{Falush:2003dq,
	Abstract = {We describe extensions to the method of Pritchard et al. for inferring population structure from multilocus genotype data. Most importantly, we develop methods that allow for linkage between loci. The new model accounts for the correlations between linked loci that arise in admixed populations ("admixture linkage disequilibium"). This modification has several advantages, allowing (1) detection of admixture events farther back into the past, (2) inference of the population of origin of chromosomal regions, and (3) more accurate estimates of statistical uncertainty when linked loci are used. It is also of potential use for admixture mapping. In addition, we describe a new prior model for the allele frequencies within each population, which allows identification of subtle population subdivisions that were not detectable using the existing method. We present results applying the new methods to study admixture in African-Americans, recombination in Helicobacter pylori, and drift in populations of Drosophila melanogaster. The methods are implemented in a program, structure, version 2.0, which is available at http://pritch.bsd.uchicago.edu.},
	Author = {Falush, Daniel and Stephens, Matthew and Pritchard, Jonathan K},
	Date-Added = {2010-02-04 10:54:33 -0500},
	Date-Modified = {2010-02-04 10:54:33 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {African Continental Ancestry Group; Algorithms; Alleles; Animals; Bayes Theorem; Chromosomes; Computer Simulation; Drosophila melanogaster; Evolution, Molecular; Female; Gene Frequency; Genetic Drift; Genetic Markers; Genetics, Population; Genotype; Helicobacter pylori; Humans; Linkage (Genetics); Male; Markov Chains; Models, Genetic; Monte Carlo Method; Recombination, Genetic},
	Month = {Aug},
	Number = {4},
	Pages = {1567-87},
	Pmid = {12930761},
	Title = {Inference of population structure using multilocus genotype data: linked loci and correlated allele frequencies},
	Volume = {164},
	Year = {2003}}

@article{Tang:2005bh,
	Abstract = {The genome of an admixed individual represents a mixture of alleles from different ancestries. In the United States, the two largest minority groups, African-Americans and Hispanics, are both admixed. An understanding of the admixture proportion at an individual level (individual admixture, or IA) is valuable for both population geneticists and epidemiologists who conduct case-control association studies in these groups. Here we present an extension of a previously described frequentist (maximum likelihood or ML) approach to estimate individual admixture that allows for uncertainty in ancestral allele frequencies. We compare this approach both to prior partial likelihood based methods as well as more recently described Bayesian MCMC methods. Our full ML method demonstrates increased robustness when compared to an existing partial ML approach. Simulations also suggest that this frequentist estimator achieves similar efficiency, measured by the mean squared error criterion, as Bayesian methods but requires just a fraction of the computational time to produce point estimates, allowing for extensive analysis (e.g., simulations) not possible by Bayesian methods. Our simulation results demonstrate that inclusion of ancestral populations or their surrogates in the analysis is required by any method of IA estimation to obtain reasonable results.},
	Author = {Tang, Hua and Peng, Jie and Wang, Pei and Risch, Neil J},
	Date-Added = {2010-02-04 10:52:42 -0500},
	Date-Modified = {2010-02-04 10:52:42 -0500},
	Doi = {10.1002/gepi.20064},
	Journal = {Genet Epidemiol},
	Journal-Full = {Genetic epidemiology},
	Mesh = {African Americans; Algorithms; Bayes Theorem; Computer Simulation; European Continental Ancestry Group; Genetics, Population; Genotype; Humans; Likelihood Functions; Linkage Disequilibrium; Microsatellite Repeats; Models, Genetic; Polymorphism, Single Nucleotide},
	Month = {May},
	Number = {4},
	Pages = {289-301},
	Pmid = {15712363},
	Title = {Estimation of individual admixture: analytical and study design considerations},
	Volume = {28},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1002/gepi.20064}}

@article{Tang:2006qf,
	Abstract = {A chromosome in an individual of recently admixed ancestry resembles a mosaic of chromosomal segments, or ancestry blocks, each derived from a particular ancestral population. We consider the problem of inferring ancestry along the chromosomes in an admixed individual and thereby delineating the ancestry blocks. Using a simple population model, we infer gene-flow history in each individual. Compared with existing methods, which are based on a hidden Markov model, the Markov-hidden Markov model (MHMM) we propose has the advantage of accounting for the background linkage disequilibrium (LD) that exists in ancestral populations. When there are more than two ancestral groups, we allow each ancestral population to admix at a different time in history. We use simulations to illustrate the accuracy of the inferred ancestry as well as the importance of modeling the background LD; not accounting for background LD between markers may mislead us to false inferences about mixed ancestry in an indigenous population. The MHMM makes it possible to identify genomic blocks of a particular ancestry by use of any high-density single-nucleotide-polymorphism panel. One application of our method is to perform admixture mapping without genotyping special ancestry-informative-marker panels.},
	Author = {Tang, Hua and Coram, Marc and Wang, Pei and Zhu, Xiaofeng and Risch, Neil},
	Date-Added = {2010-02-04 10:52:15 -0500},
	Date-Modified = {2010-02-04 10:52:15 -0500},
	Doi = {10.1086/504302},
	Journal = {Am J Hum Genet},
	Journal-Full = {American journal of human genetics},
	Mesh = {Genetics, Medical; Humans; Linkage Disequilibrium; Markov Chains; Polymorphism, Single Nucleotide},
	Month = {Jul},
	Number = {1},
	Pages = {1-12},
	Pmid = {16773560},
	Title = {Reconstructing genetic ancestry blocks in admixed individuals},
	Volume = {79},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1086/504302}}

@article{Nielsen:2007ve,
	Abstract = {The recent availability of genome-scale genotyping data has led to the identification of regions of the human genome that seem to have been targeted by selection. These findings have increased our understanding of the evolutionary forces that affect the human genome, have augmented our knowledge of gene function and promise to increase our understanding of the genetic basis of disease. However, inferences of selection are challenged by several confounding factors, especially the complex demographic history of human populations, and concordance between studies is variable. Although such studies will always be associated with some uncertainty, steps can be taken to minimize the effects of confounding factors and improve our interpretation of their findings.},
	Author = {Nielsen, Rasmus and Hellmann, Ines and Hubisz, Melissa and Bustamante, Carlos and Clark, Andrew G},
	Date-Added = {2010-02-04 10:18:01 -0500},
	Date-Modified = {2010-02-04 10:18:01 -0500},
	Doi = {10.1038/nrg2187},
	Journal = {Nat Rev Genet},
	Journal-Full = {Nature reviews. Genetics},
	Mesh = {Evolution, Molecular; Genetics, Population; Genome, Human; Humans; Selection, Genetic},
	Month = {Nov},
	Number = {11},
	Pages = {857-68},
	Pmid = {17943193},
	Title = {Recent and ongoing selection in the human genome},
	Volume = {8},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nrg2187}}

@article{David:1988ly,
	Author = {David, J R and Capy, P},
	Date-Added = {2010-02-03 15:21:25 -0500},
	Date-Modified = {2010-02-03 15:21:25 -0500},
	Journal = {Trends Genet},
	Journal-Full = {Trends in genetics : TIG},
	Mesh = {Animals; Drosophila melanogaster; Evolution; Genetic Variation; Genetics, Population},
	Month = {Apr},
	Number = {4},
	Pages = {106-11},
	Pmid = {3149056},
	Title = {Genetic variation of Drosophila melanogaster natural populations},
	Volume = {4},
	Year = {1988}}

@article{Lynch:2009zr,
	Abstract = {A new generation of high-throughput sequencing strategies will soon lead to the acquisition of high-coverage genomic profiles of hundreds to thousands of individuals within species, generating unprecedented levels of information on the frequencies of nucleotides segregating at individual sites. However, because these new technologies are error prone and yield uneven coverage of alleles in diploid individuals, they also introduce the need for novel methods for analyzing the raw read data. A maximum-likelihood method for the estimation of allele frequencies is developed, eliminating both the need to arbitrarily discard individuals with low coverage and the requirement for an extrinsic measure of the sequence error rate. The resultant estimates are nearly unbiased with asymptotically minimal sampling variance, thereby defining the limits to our ability to estimate population-genetic parameters and providing a logical basis for the optimal design of population-genomic surveys.},
	Author = {Lynch, Michael},
	Date-Added = {2010-02-02 13:46:49 -0500},
	Date-Modified = {2010-02-02 13:46:49 -0500},
	Doi = {10.1534/genetics.109.100479},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Algorithms; Chromosome Mapping; Gene Frequency; Genome, Human; Humans; Sequence Analysis, DNA; Statistics as Topic},
	Month = {May},
	Number = {1},
	Pages = {295-301},
	Pmid = {19293142},
	Title = {Estimation of allele frequencies from high-coverage genome-sequencing projects},
	Volume = {182},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.109.100479}}

@article{Kuhn:2009ys,
	Abstract = {The UCSC Genome Browser Database (GBD, http://genome.ucsc.edu) is a publicly available collection of genome assembly sequence data and integrated annotations for a large number of organisms, including extensive comparative-genomic resources. In the past year, 13 new genome assemblies have been added, including two important primate species, orangutan and marmoset, bringing the total to 46 assemblies for 24 different vertebrates and 39 assemblies for 22 different invertebrate animals. The GBD datasets may be viewed graphically with the UCSC Genome Browser, which uses a coordinate-based display system allowing users to juxtapose a wide variety of data. These data include all mRNAs from GenBank mapped to all organisms, RefSeq alignments, gene predictions, regulatory elements, gene expression data, repeats, SNPs and other variation data, as well as pairwise and multiple-genome alignments. A variety of other bioinformatics tools are also provided, including BLAT, the Table Browser, the Gene Sorter, the Proteome Browser, VisiGene and Genome Graphs.},
	Author = {Kuhn, R M and Karolchik, D and Zweig, A S and Wang, T and Smith, K E and Rosenbloom, K R and Rhead, B and Raney, B J and Pohl, A and Pheasant, M and Meyer, L and Hsu, F and Hinrichs, A S and Harte, R A and Giardine, B and Fujita, P and Diekhans, M and Dreszer, T and Clawson, H and Barber, G P and Haussler, D and Kent, W J},
	Date-Added = {2010-02-02 10:24:37 -0500},
	Date-Modified = {2010-02-02 10:24:37 -0500},
	Doi = {10.1093/nar/gkn875},
	Journal = {Nucleic Acids Res},
	Journal-Full = {Nucleic acids research},
	Mesh = {Animals; Chromosome Mapping; Computer Graphics; Databases, Nucleic Acid; Gene Expression; Genetic Variation; Genomics; Humans; RNA, Messenger; Software; User-Computer Interface},
	Month = {Jan},
	Number = {Database issue},
	Pages = {D755-61},
	Pmid = {18996895},
	Title = {The UCSC Genome Browser Database: update 2009},
	Volume = {37},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gkn875}}

@article{Rozen:2000vn,
	Author = {Rozen, S and Skaletsky, H},
	Date-Added = {2010-02-02 10:22:10 -0500},
	Date-Modified = {2010-02-02 10:22:10 -0500},
	Journal = {Methods Mol Biol},
	Journal-Full = {Methods in molecular biology (Clifton, N.J.)},
	Mesh = {Base Sequence; DNA Primers; Database Management Systems; Internet; Molecular Sequence Data; Polymerase Chain Reaction; Sequence Homology, Nucleic Acid; User-Computer Interface},
	Pages = {365-86},
	Pmid = {10547847},
	Title = {Primer3 on the WWW for general users and for biologist programmers},
	Volume = {132},
	Year = {2000}}

@article{Obbard:2009vn,
	Abstract = {It is estimated that a large proportion of amino acid substitutions in Drosophila have been fixed by natural selection, and as organisms are faced with an ever-changing array of pathogens and parasites to which they must adapt, we have investigated the role of parasite-mediated selection as a likely cause. To quantify the effect, and to identify which genes and pathways are most likely to be involved in the host-parasite arms race, we have re-sequenced population samples of 136 immunity and 287 position-matched non-immunity genes in two species of Drosophila. Using these data, and a new extension of the McDonald-Kreitman approach, we estimate that natural selection fixes advantageous amino acid changes in immunity genes at nearly double the rate of other genes. We find the rate of adaptive evolution in immunity genes is also more variable than other genes, with a small subset of immune genes evolving under intense selection. These genes, which are likely to represent hotspots of host-parasite coevolution, tend to share similar functions or belong to the same pathways, such as the antiviral RNAi pathway and the IMD signalling pathway. These patterns appear to be general features of immune system evolution in both species, as rates of adaptive evolution are correlated between the D. melanogaster and D. simulans lineages. In summary, our data provide quantitative estimates of the elevated rate of adaptive evolution in immune system genes relative to the rest of the genome, and they suggest that adaptation to parasites is an important force driving molecular evolution.},
	Author = {Obbard, Darren J and Welch, John J and Kim, Kang-Wook and Jiggins, Francis M},
	Date-Added = {2010-02-01 12:50:55 -0500},
	Date-Modified = {2010-02-01 12:50:55 -0500},
	Doi = {10.1371/journal.pgen.1000698},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Month = {Oct},
	Number = {10},
	Pages = {e1000698},
	Pmid = {19851448},
	Title = {Quantifying adaptive evolution in the Drosophila immune system},
	Volume = {5},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000698}}

@article{Przeworski:2000kx,
	Abstract = {Studies of nuclear sequence variation are accumulating, such that we can expect a good description of the structure of human variation across populations and genomic regions in the near future. This description will help to elucidate the evolutionary forces that shape patterns of variability. Such an understanding will be of general biological interest, but could also facilitate the design and interpretation of disease-mapping studies. Here, we integrate the results from surveys of nuclear sequence variation. When nuclear sequences are considered together with mtDNA and microsatellites, it becomes clear that neither the standard neutral model, nor a simple long-term exponential growth model, can account for all the available human variation data. A possible explanation is that a subset of loci are not evolving neutrally; even so, more-complex models of effective population size and structure might be necessary to explain the data.},
	Author = {Przeworski, M and Hudson, R R and Di Rienzo, A},
	Date-Added = {2010-02-01 09:51:04 -0500},
	Date-Modified = {2010-02-01 09:51:04 -0500},
	Journal = {Trends Genet},
	Journal-Full = {Trends in genetics : TIG},
	Mesh = {Evolution; Genetic Variation; Genetics, Medical; Humans; Selection, Genetic},
	Month = {Jul},
	Number = {7},
	Pages = {296-302},
	Pmid = {10858659},
	Title = {Adjusting the focus on human variation},
	Volume = {16},
	Year = {2000}}

@article{Roush:1987uq,
	Author = {Roush, R T and McKenzie, J A},
	Date-Added = {2010-02-01 09:36:39 -0500},
	Date-Modified = {2010-02-01 09:36:39 -0500},
	Doi = {10.1146/annurev.en.32.010187.002045},
	Journal = {Annu Rev Entomol},
	Journal-Full = {Annual review of entomology},
	Mesh = {Acari; Alleles; Animals; Crosses, Genetic; Ecology; Genes; Insecticide Resistance; Insects; Phenotype},
	Pages = {361-80},
	Pmid = {3545056},
	Title = {Ecological genetics of insecticide and acaricide resistance},
	Volume = {32},
	Year = {1987},
	Bdsk-Url-1 = {http://dx.doi.org/10.1146/annurev.en.32.010187.002045}}

@article{Andreev:1999fk,
	Abstract = {The number of origins of pesticide resistance-associated mutations is important not only to our understanding of the evolution of resistance but also in modeling its spread. Previous studies of amplified esterase genes in a highly dispersive Culex mosquito have suggested that insecticide resistance-associated mutations (specifically a single-gene duplication event) can occur a single time and then spread throughout global populations. In order to provide data for resistance-associated point mutations, which are more typical of pesticide mechanisms as a whole, we studied the number of independent origins of cyclodiene insecticide resistance in the red flour beetle Tribolium castaneum. Target-site insensitivity to cyclodienes is conferred by single point mutations in the gene Resistance to dieldrin (Rdl), which codes for a subunit of a gamma-aminobutyric acid (GABA) receptor. These point mutations are associated with replacements of alanine 302 which render the receptor insensitive to block by the insecticide. We collected 141 strains of Tribolium worldwide and screened them for resistance. Twenty-four strains contained resistant individuals. After homozygosing 23 of these resistance alleles we derived a nucleotide sequence phylogeny of the resistant strains from a 694-bp section of Rdl, encompassing exon 7 (which contains the resistance-associated mutation) and part of a flanking intron. The phylogeny also included six susceptible alleles chosen at random from a range of geographical locations. Resistance alleles fell into six clades and three clades contained both resistant and susceptible alleles. Although statistical analysis provided support at only the 5-6\% level, the pattern of variation in resistance alleles is more readily explained by multiple independent origins of resistance than by spread of a single resistance-associated mutation. For example, two resistance alleles differed from two susceptible alleles only by the resistance-associated mutation itself, suggesting that they form the susceptible ancestors and that resistance arose independently in several susceptible backgrounds. This suggests that in Tribolium Rdl, de novo mutations for resistance have arisen independently in several populations. Identical alleles were found in geographically distant regions as well, also implying that some Rdl alleles have been exported in stored grain. These differences from the Culex study may stem both from differences in the population genetics of Tribolium versus that of mosquitoes and differences in mutation rates associated with point mutations versus gene duplication events. The Tribolium data therefore suggest that multiple origins of insecticide resistance (associated with specific point mutations) may be more common than the spread of single events. These findings have implications for the way in which we model the evolution and spread of insecticide resistance genes and also suggest that parallel adaptive substitutions may not be uncommon in phyletic evolution.},
	Author = {Andreev, D and Kreitman, M and Phillips, T W and Beeman, R W and ffrench-Constant, R H},
	Date-Added = {2010-02-01 09:34:58 -0500},
	Date-Modified = {2010-02-01 09:34:58 -0500},
	Journal = {J Mol Evol},
	Journal-Full = {Journal of molecular evolution},
	Mesh = {Animals; Base Sequence; DNA; Evolution, Molecular; Genes, Insect; Genetic Variation; Genetics, Population; Insecticide Resistance; Molecular Sequence Data; Phylogeny; Point Mutation; Sequence Homology, Nucleic Acid; Tribolium},
	Month = {May},
	Number = {5},
	Pages = {615-24},
	Pmid = {10198127},
	Title = {Multiple origins of cyclodiene insecticide resistance in Tribolium castaneum (Coleoptera: Tenebrionidae)},
	Volume = {48},
	Year = {1999}}

@article{Pennings:2006kx,
	Abstract = {Polymorphism data can be used to identify loci at which a beneficial allele has recently gone to fixation, given that an accurate description of the signature of selection is available. In the classical model that is used, a favored allele derives from a single mutational origin. This ignores the fact that beneficial alleles can enter a population recurrently by mutation during the selective phase. In this study, we present a combination of analytical and simulation results to demonstrate the effect of adaptation from recurrent mutation on summary statistics for polymorphism data from a linked neutral locus. We also analyze the power of standard neutrality tests based on the frequency spectrum or on linkage disequilibrium (LD) under this scenario. For recurrent beneficial mutation at biologically realistic rates, we find substantial deviations from the classical pattern of a selective sweep from a single new mutation. Deviations from neutrality in the level of polymorphism and in the frequency spectrum are much less pronounced than in the classical sweep pattern. In contrast, for levels of LD, the signature is even stronger if recurrent beneficial mutation plays a role. We suggest a variant of existing LD tests that increases their power to detect this signature.},
	Address = {185 BERRY ST, STE 1300, SAN FRANCISCO, CA 94107 USA},
	Author = {Pennings, Pleuni S. and Hermisson, Joachim},
	Date-Added = {2010-01-28 15:59:06 -0500},
	Date-Modified = {2010-01-28 15:59:06 -0500},
	Doi = {DOI 10.1371/journal.pgen.0020186},
	Isi = {000243482100006},
	Isi-Recid = {154207305},
	Isi-Ref-Recids = {137086016 91714050 134450834 135486829 108201989 132006362 120277645 154207306 150131042 151312210 135031992 115761853 132590034 144698742 115625987 123075733 144345018 123647380 135700279 70956609 154207307 135840447 123662864 153206119 27948158 127075891 146948763 127075881 146298979 150131040 147616498 124221406 126765638 142930491 144344948 143787296 137447129 79198574 150022282 136137856 70616358 119370459 150535797 149221041 120277644 154207308 149685628},
	Journal = {Plos Genetics},
	Month = dec,
	Number = {12},
	Pages = {1998-2012},
	Publisher = {PUBLIC LIBRARY SCIENCE},
	Times-Cited = {23},
	Title = {Soft sweeps III: The signature of positive selection from recurrent mutation},
	Volume = {2},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000243482100006}}

@article{Hermisson:2008uq,
	Abstract = {Genetic hitchhiking describes evolution at a neutral locus that is linked to a selected locus. If a beneficial allele rises to fixation at the selected locus, a characteristic polymorphism pattern (so-called selective sweep) emerges at the neutral locus. The classical model assumes that fixation of the beneficial allele occurs from a single copy of this allele that arises by mutation. However, recent theory [Pennings and Hermisson, 2006a, b] has shown that recurrent beneficial mutation at biologically realistic rates can lead to markedly different polymorphism patterns, so-called soft selective sweeps. We extend an approach that has recently been developed for the classical hitchhiking model [Schweinsberg and Durrett, 2005; Etheridge et al., 2006] to study the recurrent mutation scenario. We show that the genealogy at the neutral locus can be approximated (to leading orders in the selection strength) by a marked Yule process with immigration. Using this formalism, we derive an improved analytical approximation for the expected heterozygosity at the neutral locus at the time of fixation of the beneficial allele.},
	Address = {BOX 354350, SEATTLE, WASHINGTON 98195-4350 USA},
	Author = {Hermisson, Joachim and Pfaffelhuber, Peter},
	Date-Added = {2010-01-28 15:58:43 -0500},
	Date-Modified = {2010-01-28 15:58:43 -0500},
	Isi = {000262319200001},
	Isi-Recid = {175664996},
	Isi-Ref-Recids = {60605099 134450834 108270503 58648499 160341010 151312210 63664627 87389566 175664997 33174 126777190 144345018 49352162 158189807 161165403 64058221 70956609 123662864 52079755 155629641 154516879 146948763 84968299 146298979 150131040 175664998 157436815 154049758 162822412 147616498 133377573 145549756 24983450 79198574 156173333 153974712 125535677 144641668},
	Journal = {Electronic Journal of Probability},
	Keywords = {Selective sweep; genetic hitchhiking; soft selective sweep; diffusion approximation; Yule process; random background},
	Month = nov,
	Pages = {2069-2106},
	Publisher = {UNIV WASHINGTON, DEPT MATHEMATICS},
	Times-Cited = {0},
	Title = {The pattern of genetic hitchhiking under recurrent mutation},
	Volume = {13},
	Year = {2008},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000262319200001}}

@article{houle1991,
	Abstract = {The genetic variance-covariance matrix, G, is determined in part by functional architecture, the pathways by which variation in genotype influences phenotype. I develop a simple architectural model for G for two traits under directional selection constrained by their dependence on a common limiting resource. I assume that genetic variance is maintained by mutation-selection balance. The relative numbers of loci that play a role in acquiring versus allocating a limiting resource play a crucial role in determining genetic covariance. If many loci are involved in acquiring a resource, genetic covariance may be either negative or positive at equilibrium, depending on the fitness function and the input of mutational variance. The form of G does not necessarily reveal the constraint on resource acquisition inherent in the system, and therefore studies estimating G do not test for the existence of life-history tradeoffs. Characters may evolve in patterns that are unpredictable from G. Experiments are suggested that would indicate if this model could explain observations of positive genetic covariance.},
	Author = {Houle, David},
	Copyright = {Copyright {\^A}{\copyright} 1991 Society for the Study of Evolution},
	Date-Added = {2010-01-28 14:37:01 -0500},
	Date-Modified = {2010-01-28 14:37:09 -0500},
	Issn = {00143820},
	Journal = {Evolution},
	Jstor_Articletype = {primary_article},
	Jstor_Formatteddate = {May, 1991},
	Number = {3},
	Pages = {630--648},
	Publisher = {Society for the Study of Evolution},
	Title = {Genetic Covariance of Fitness Correlates: What Genetic Correlations are Made of and Why it Matters},
	Url = {http://www.jstor.org/stable/2409916},
	Volume = {45},
	Year = {1991},
	Bdsk-Url-1 = {http://www.jstor.org/stable/2409916}}

@article{landeArnold,
	Abstract = {Multivariate statistical methods are derived for measuring selection solely from observed changes in the distribution of phenotypic characters in a population within a generation. Selective effects are readily detectable in characters that do not change with age, such as meristic traits or adult characters in species with determinate growth. Ontogenetic characters, including allometric growth rates, can be analyzed in longitudinal studies where individuals are followed through time. Following an approach pioneered by Pearson (1903), this analysis helps to reveal the target(s) of selection, and to quantify its intensity, without identifying the selective agent(s). By accounting for indirect selection through correlated characters, separate forces of directional and stabilizing (or disruptive) selection acting directly on each character can be measured. These directional and stabilizing selection coefficients are respectively the parameters that describe the best linear and quadratic approximations to the selective surface of individual fitness as a function of the phenotypic characters. The theory is illustrated by estimating selective forces on morphological characters influencing survival in pentatomid bugs and in house sparrows during severe weather conditions.},
	Author = {Lande, Russell and Arnold, Stevan J.},
	Copyright = {Copyright {\copyright} 1983 Society for the Study of Evolution},
	Date-Added = {2010-01-28 14:35:33 -0500},
	Date-Modified = {2010-01-28 16:02:36 -0500},
	Issn = {00143820},
	Journal = {Evolution},
	Jstor_Articletype = {primary_article},
	Jstor_Formatteddate = {Nov., 1983},
	Number = {6},
	Pages = {1210--1226},
	Publisher = {Society for the Study of Evolution},
	Title = {The Measurement of Selection on Correlated Characters},
	Url = {http://www.jstor.org/stable/2408842},
	Volume = {37},
	Year = {1983},
	Bdsk-Url-1 = {http://www.jstor.org/stable/2408842}}

@book{Lynch:1998fk,
	Address = {Sunderland, Mass.},
	Annote = {LDR    01036cam  2200265 a 4500
001    3542749
005    19990125071243.4
008    970528s1998    maua     b    001 0 eng  
035    $9(DLC)   97017666
906    $a7$bcbc$corignew$d1$eocip$f19$gy-gencatlg
955    $apc03 to ja00 05-28-97; jb14 05-28-97; jb04 to jc00 05-30-97; jc02 to technician 05-30-97; jc03 06-03-97; CIP ver. pv08 12-10-98
010    $a   97017666 
020    $a0878934812 (clothbound)
040    $aDLC$cDLC$dDLC
050 00 $aQH452.7$b.L96 1998
082 00 $a576.5/3$221
100 1  $aLynch, Michael,$d1951-
245 10 $aGenetics and analysis of quantitative traits /$cMichael Lynch, Bruce Walsh.
260    $aSunderland, Mass. :$bSinauer,$cc1998.
300    $axvi, 980 p. :$bill. ;$c24 cm.
504    $aIncludes bibliographical references (p. 891-[948]) and indexes.
650  0 $aQuantitative genetics.
700 1  $aWalsh, Bruce,$d1957-
920    $a**LC HAS REQ'D # OF SHELF COPIES**
991    $bc-GenColl$hQH452.7$i.L96 1998$p00058747890$tCopy 1$wBOOKS
},
	Author = {Lynch, Michael and Walsh, Bruce},
	Call-Number = {QH452.7},
	Date-Added = {2010-01-28 14:09:56 -0500},
	Date-Modified = {2010-01-28 14:09:56 -0500},
	Dewey-Call-Number = {576.5/3},
	Genre = {Quantitative genetics},
	Isbn = {0878934812 (clothbound)},
	Library-Id = {97017666},
	Publisher = {Sinauer},
	Title = {Genetics and analysis of quantitative traits},
	Year = {1998}}

@article{Orr:2001fk,
	Abstract = {We consider populations that adapt to a sudden environmental change by fixing alleles found at mutation-selection balance. In particular, we calculate probabilities of fixation for previously deleterious alleles, ignoring the input of new mutations. We find that "Haldane's sieve"--the bias against the establishment of recessive beneficial mutations--does not hold under these conditions. Instead probabilities of fixation are generally independent of dominance. We show that this result is robust to patterns of sex expression for both X-linked and autosomal loci. We further show that adaptive evolution is invariably slower at X-linked than autosomal loci when evolution begins from mutation-selection balance. This result differs from that obtained when adaptation uses new mutations, a finding that may have some bearing on recent attempts to distinguish between hitchhiking and background selection by contrasting the molecular population genetics of X-linked vs. autosomal loci. Last, we suggest a test to determine whether adaptation used new mutations or previously deleterious alleles from the standing genetic variation.},
	Author = {Orr, H A and Betancourt, A J},
	Date-Added = {2010-01-20 19:45:54 -0500},
	Date-Modified = {2010-01-20 19:45:54 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Adaptation, Biological; Alleles; Animals; Female; Genes, Recessive; Genetic Variation; Genetics, Population; Humans; Linkage (Genetics); Male; Models, Genetic; Models, Statistical; Mutation; Sex Factors; Time Factors; X Chromosome},
	Month = {Feb},
	Number = {2},
	Pages = {875-84},
	Pmid = {11157004},
	Title = {Haldane's sieve and adaptation from the standing genetic variation},
	Volume = {157},
	Year = {2001}}

@article{Leuenberger:2010fk,
	Abstract = {Until recently, the use of Bayesian inference was limited to a few cases because for many realistic probability models the likelihood function cannot be calculated analytically. The situation changed with the advent of likelihood-free inference algorithms, often subsumed under the term approximate Bayesian computation (ABC). A key innovation was the use of a postsampling regression adjustment, allowing larger tolerance values and as such shifting computation time to realistic orders of magnitude. Here we propose a reformulation of the regression adjustment in terms of a general linear model (GLM). This allows the integration into the sound theoretical framework of Bayesian statistics and the use of its methods, including model selection via Bayes factors. We then apply the proposed methodology to the question of population subdivision among western chimpanzees, Pan troglodytes verus.},
	Author = {Leuenberger, Christoph and Wegmann, Daniel},
	Date-Added = {2010-01-12 11:06:15 -0500},
	Date-Modified = {2010-01-12 11:06:15 -0500},
	Doi = {10.1534/genetics.109.109058},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Month = {Jan},
	Number = {1},
	Pages = {243-52},
	Pmid = {19786619},
	Title = {Bayesian computation and model selection without likelihoods},
	Volume = {184},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.109.109058}}

@article{Altshuler:2008ve,
	Abstract = {Genetic mapping provides a powerful approach to identify genes and biological processes underlying any trait influenced by inheritance, including human diseases. We discuss the intellectual foundations of genetic mapping of Mendelian and complex traits in humans, examine lessons emerging from linkage analysis of Mendelian diseases and genome-wide association studies of common diseases, and discuss questions and challenges that lie ahead.},
	Author = {Altshuler, David and Daly, Mark J and Lander, Eric S},
	Date-Added = {2010-01-12 10:28:49 -0500},
	Date-Modified = {2010-01-12 10:28:49 -0500},
	Doi = {10.1126/science.1156409},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Chromosome Mapping; Cloning, Molecular; Disease; Genome, Human; Genome-Wide Association Study; Genotype; Humans; Linkage (Genetics); Linkage Disequilibrium; Mutation; Physical Chromosome Mapping; Polymorphism, Single Nucleotide; Quantitative Trait, Heritable; Risk Factors; Selection, Genetic},
	Month = {Nov},
	Number = {5903},
	Pages = {881-8},
	Pmid = {18988837},
	Title = {Genetic mapping in human disease},
	Volume = {322},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1156409}}

@article{Katzmanetal2010,
	Author = {Katzman, Sol and Kern, Andrew D. and Pollard, Katherine S. and Salama, Sofie R and Haussler, David},
	Date-Added = {2010-01-12 10:22:42 -0500},
	Date-Modified = {2010-01-12 10:24:06 -0500},
	Journal = {PLoS Genet},
	Title = {GC-Biased Evolution Near Human Accelerated Regions},
	Volume = {In Review},
	Year = {2010}}

@article{Jensen:2008ly,
	Abstract = {The recurrent fixation of newly arising, beneficial mutations in a species reduces levels of linked neutral variability. Models positing frequent weakly beneficial substitutions or, alternatively, rare, strongly selected substitutions predict similar average effects on linked neutral variability, if the product of the rate and strength of selection is held constant. We propose an approximate Bayesian (ABC) polymorphism-based estimator that can be used to distinguish between these models, and apply it to multi-locus data from Drosophila melanogaster. We investigate the extent to which inference about the strength of selection is sensitive to assumptions about the underlying distributions of the rates of substitution and recombination, the strength of selection, heterogeneity in mutation rate, as well as the population's demographic history. We show that assuming fixed values of selection parameters in estimation leads to overestimates of the strength of selection and underestimates of the rate. We estimate parameters for an African population of D. melanogaster ({\^s} approximately 2E-03, ) and compare these to previous estimates. Finally, we show that surveying larger genomic regions is expected to lend much more discriminatory power to the approach. It will thus be of great interest to apply this method to emerging whole-genome polymorphism data sets in many taxa.},
	Author = {Jensen, Jeffrey D and Thornton, Kevin R and Andolfatto, Peter},
	Date-Added = {2010-01-12 10:04:35 -0500},
	Date-Modified = {2010-01-12 10:04:35 -0500},
	Doi = {10.1371/journal.pgen.1000198},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Africa; Animals; Bayes Theorem; Computer Simulation; Demography; Drosophila melanogaster; Evolution, Molecular; Genetic Variation; Genetics, Population; Genome, Insect; Models, Genetic; Models, Statistical; Polymorphism, Genetic; Selection, Genetic},
	Number = {9},
	Pages = {e1000198},
	Pmid = {18802463},
	Title = {An approximate bayesian estimator suggests strong, recurrent selective sweeps in Drosophila},
	Volume = {4},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000198}}

@article{Hudson:1983zr,
	Abstract = {An infinite-site neutral allele model with crossing-over possible at any of an infinite number of sites is studied. A formula for the variance of the number of segregating sites in a sample of gametes is obtained. An approximate expression for the expected homozygosity is also derived. Simulation results are presented to indicate the accuracy of the approximations. The results concerning the number of segregating sites and the expected homozygosity indicate that a two-locus model and the infinite-site model behave similarly for 4Nu less than or equal to 2 and r less than or equal to 5u, where N is the population size, u is the neutral mutation rate, and r is the recombination rate. Simulations of a two-locus model and a four-locus model were also carried out to determine the effect of intragenic recombination on the homozygosity test of Watterson (Genetics 85, 789-814; 88, 405-417) and on the number of unique alleles in a sample. The results indicate that for 4Nu less than or equal to 2 and r less than or equal to 10u, the effect of recombination is quite small.},
	Author = {Hudson, R R},
	Date-Added = {2010-01-12 09:57:11 -0500},
	Date-Modified = {2010-01-12 09:57:11 -0500},
	Journal = {Theor Popul Biol},
	Journal-Full = {Theoretical population biology},
	Mesh = {Alleles; Computers; Homozygote; Models, Biological; Recombination, Genetic},
	Month = {Apr},
	Number = {2},
	Pages = {183-201},
	Pmid = {6612631},
	Title = {Properties of a neutral allele model with intragenic recombination},
	Volume = {23},
	Year = {1983}}

@article{Sabeti:2007ys,
	Abstract = {With the advent of dense maps of human genetic variation, it is now possible to detect positive natural selection across the human genome. Here we report an analysis of over 3 million polymorphisms from the International HapMap Project Phase 2 (HapMap2). We used 'long-range haplotype' methods, which were developed to identify alleles segregating in a population that have undergone recent selection, and we also developed new methods that are based on cross-population comparisons to discover alleles that have swept to near-fixation within a population. The analysis reveals more than 300 strong candidate regions. Focusing on the strongest 22 regions, we develop a heuristic for scrutinizing these regions to identify candidate targets of selection. In a complementary analysis, we identify 26 non-synonymous, coding, single nucleotide polymorphisms showing regional evidence of positive selection. Examination of these candidates highlights three cases in which two genes in a common biological process have apparently undergone positive selection in the same population:LARGE and DMD, both related to infection by the Lassa virus, in West Africa;SLC24A5 and SLC45A2, both involved in skin pigmentation, in Europe; and EDAR and EDA2R, both involved in development of hair follicles, in Asia.},
	Author = {Sabeti, Pardis C and Varilly, Patrick and Fry, Ben and Lohmueller, Jason and Hostetter, Elizabeth and Cotsapas, Chris and Xie, Xiaohui and Byrne, Elizabeth H and McCarroll, Steven A and Gaudet, Rachelle and Schaffner, Stephen F and Lander, Eric S and {International HapMap Consortium} and Frazer, Kelly A and Ballinger, Dennis G and Cox, David R and Hinds, David A and Stuve, Laura L and Gibbs, Richard A and Belmont, John W and Boudreau, Andrew and Hardenbol, Paul and Leal, Suzanne M and Pasternak, Shiran and Wheeler, David A and Willis, Thomas D and Yu, Fuli and Yang, Huanming and Zeng, Changqing and Gao, Yang and Hu, Haoran and Hu, Weitao and Li, Chaohua and Lin, Wei and Liu, Siqi and Pan, Hao and Tang, Xiaoli and Wang, Jian and Wang, Wei and Yu, Jun and Zhang, Bo and Zhang, Qingrun and Zhao, Hongbin and Zhao, Hui and Zhou, Jun and Gabriel, Stacey B and Barry, Rachel and Blumenstiel, Brendan and Camargo, Amy and Defelice, Matthew and Faggart, Maura and Goyette, Mary and Gupta, Supriya and Moore, Jamie and Nguyen, Huy and Onofrio, Robert C and Parkin, Melissa and Roy, Jessica and Stahl, Erich and Winchester, Ellen and Ziaugra, Liuda and Altshuler, David and Shen, Yan and Yao, Zhijian and Huang, Wei and Chu, Xun and He, Yungang and Jin, Li and Liu, Yangfan and Shen, Yayun and Sun, Weiwei and Wang, Haifeng and Wang, Yi and Wang, Ying and Xiong, Xiaoyan and Xu, Liang and Waye, Mary M Y and Tsui, Stephen K W and Xue, Hong and Wong, J Tze-Fei and Galver, Luana M and Fan, Jian-Bing and Gunderson, Kevin and Murray, Sarah S and Oliphant, Arnold R and Chee, Mark S and Montpetit, Alexandre and Chagnon, Fanny and Ferretti, Vincent and Leboeuf, Martin and Olivier, Jean-Fran{\c c}ois and Phillips, Michael S and Roumy, St{\'e}phanie and Sall{\'e}e, Cl{\'e}mentine and Verner, Andrei and Hudson, Thomas J and Kwok, Pui-Yan and Cai, Dongmei and Koboldt, Daniel C and Miller, Raymond D and Pawlikowska, Ludmila and Taillon-Miller, Patricia and Xiao, Ming and Tsui, Lap-Chee and Mak, William and Song, You Qiang and Tam, Paul K H and Nakamura, Yusuke and Kawaguchi, Takahisa and Kitamoto, Takuya and Morizono, Takashi and Nagashima, Atsushi and Ohnishi, Yozo and Sekine, Akihiro and Tanaka, Toshihiro and Tsunoda, Tatsuhiko and Deloukas, Panos and Bird, Christine P and Delgado, Marcos and Dermitzakis, Emmanouil T and Gwilliam, Rhian and Hunt, Sarah and Morrison, Jonathan and Powell, Don and Stranger, Barbara E and Whittaker, Pamela and Bentley, David R and Daly, Mark J and de Bakker, Paul I W and Barrett, Jeff and Chretien, Yves R and Maller, Julian and McCarroll, Steve and Patterson, Nick and Pe'er, Itsik and Price, Alkes and Purcell, Shaun and Richter, Daniel J and Sabeti, Pardis and Saxena, Richa and Schaffner, Stephen F and Sham, Pak C and Varilly, Patrick and Altshuler, David and Stein, Lincoln D and Krishnan, Lalitha and Smith, Albert Vernon and Tello-Ruiz, Marcela K and Thorisson, Gudmundur A and Chakravarti, Aravinda and Chen, Peter E and Cutler, David J and Kashuk, Carl S and Lin, Shin and Abecasis, Gon{\c c}alo R and Guan, Weihua and Li, Yun and Munro, Heather M and Qin, Zhaohui Steve and Thomas, Daryl J and McVean, Gilean and Auton, Adam and Bottolo, Leonardo and Cardin, Niall and Eyheramendy, Susana and Freeman, Colin and Marchini, Jonathan and Myers, Simon and Spencer, Chris and Stephens, Matthew and Donnelly, Peter and Cardon, Lon R and Clarke, Geraldine and Evans, David M and Morris, Andrew P and Weir, Bruce S and Tsunoda, Tatsuhiko and Johnson, Todd A and Mullikin, James C and Sherry, Stephen T and Feolo, Michael and Skol, Andrew and Zhang, Houcan and Zeng, Changqing and Zhao, Hui and Matsuda, Ichiro and Fukushima, Yoshimitsu and Macer, Darryl R and Suda, Eiko and Rotimi, Charles N and Adebamowo, Clement A and Ajayi, Ike and Aniagwu, Toyin and Marshall, Patricia A and Nkwodimmah, Chibuzor and Royal, Charmaine D M and Leppert, Mark F and Dixon, Missy and Peiffer, Andy and Qiu, Renzong and Kent, Alastair and Kato, Kazuto and Niikawa, Norio and Adewole, Isaac F and Knoppers, Bartha M and Foster, Morris W and Clayton, Ellen Wright and Watkin, Jessica and Gibbs, Richard A and Belmont, John W and Muzny, Donna and Nazareth, Lynne and Sodergren, Erica and Weinstock, George M and Wheeler, David A and Yakub, Imtaz and Gabriel, Stacey B and Onofrio, Robert C and Richter, Daniel J and Ziaugra, Liuda and Birren, Bruce W and Daly, Mark J and Altshuler, David and Wilson, Richard K and Fulton, Lucinda L and Rogers, Jane and Burton, John and Carter, Nigel P and Clee, Christopher M and Griffiths, Mark and Jones, Matthew C and McLay, Kirsten and Plumb, Robert W and Ross, Mark T and Sims, Sarah K and Willey, David L and Chen, Zhu and Han, Hua and Kang, Le and Godbout, Martin and Wallenburg, John C and L'Archev{\^e}que, Paul and Bellemare, Guy and Saeki, Koji and Wang, Hongguang and An, Daochang and Fu, Hongbo and Li, Qing and Wang, Zhen and Wang, Renwu and Holden, Arthur L and Brooks, Lisa D and McEwen, Jean E and Guyer, Mark S and Wang, Vivian Ota and Peterson, Jane L and Shi, Michael and Spiegel, Jack and Sung, Lawrence M and Zacharia, Lynn F and Collins, Francis S and Kennedy, Karen and Jamieson, Ruth and Stewart, John},
	Date-Added = {2010-01-12 09:54:23 -0500},
	Date-Modified = {2010-01-12 09:54:23 -0500},
	Doi = {10.1038/nature06250},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Antiporters; Edar Receptor; Gene Frequency; Genetics, Population; Genome, Human; Geography; Haplotypes; Humans; Models, Molecular; Polymorphism, Single Nucleotide; Protein Structure, Tertiary; Selection, Genetic},
	Month = {Oct},
	Number = {7164},
	Pages = {913-8},
	Pmid = {17943131},
	Title = {Genome-wide detection and characterization of positive selection in human populations},
	Volume = {449},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature06250}}

@article{Kern:2008vn,
	Abstract = {Although Drosophila melanogaster has been the subject of intensive analysis of polymorphism and divergence, little is known about the distribution of variation at the most distal regions of chromosomes arms. Here we report a survey of genetic variation on the tip of 3L in D. melanogaster and D. simulans. Levels of single nucleotide polymorphism in the most distal euchromatic sequence are approximately one order of magnitude less than that typically observed in genomic regions of normal crossing over, consistent with what might be expected under models of linked selection in regions of low crossing over. However, despite this reduced level of nucleotide variation, we found abundant deletion polymorphism. These deletions create at least three gene presence/absence polymorphisms within D. melanogaster: the putative G-protein coupled receptor mthl-8 (which is the most distal known or predicted gene on 3L) and the unannotated mRNAs AY060886 and BT006009. Strikingly, D. simulans is also segregating deletions that cause mthl8 presence/absence polymorphism. Breakpoint sequencing and tests of correlations with segregating SNPs in D. melanogaster suggest that each deletion is unique. Cloned breakpoint sequences revealed the presence of Het-A elements just distal to unique, canonical euchromatic sequences. This pattern suggests a model in which repeated telomeric deficiencies cause deletions of euchromatic sequence followed by subsequent "healing" by retrotranposition of Het-A elements. These data reveal the dominance of telomeric dynamics on the evolution of closely linked sequences in Drosophila.},
	Author = {Kern, Andrew D and Begun, David J},
	Date-Added = {2010-01-12 09:47:27 -0500},
	Date-Modified = {2010-01-12 09:47:27 -0500},
	Doi = {10.1534/genetics.107.078345},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Chromosomes; DNA Transposable Elements; Drosophila; Drosophila Proteins; Drosophila melanogaster; Evolution; Gene Deletion; Gene Products, gag; Genes, Insect; Genetic Variation; Genetics, Population; Linkage Disequilibrium; Polymorphism, Genetic; Polymorphism, Single Nucleotide; Species Specificity; Telomere},
	Month = {Jun},
	Number = {2},
	Pages = {1021-7},
	Pmid = {18505885},
	Title = {Recurrent deletion and gene presence/absence polymorphism: telomere dynamics dominate evolution at the tip of 3L in Drosophila melanogaster and D. simulans},
	Volume = {179},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.107.078345}}

@article{kernHaussler2010,
	Author = {Kern, AD and Haussler, D.},
	Date-Added = {2010-01-07 12:37:26 -0500},
	Date-Modified = {2010-01-07 12:38:59 -0500},
	Journal = {Mol Biol Evol},
	Title = {A population genetic Hidden Markov Model for detecting genomic regions under selection},
	Volume = {In press},
	Year = {2010}}

@article{Ptak:2004kx,
	Abstract = {Recent experiments using sperm typing have demonstrated that, in several regions of the human genome, recombination does not occur uniformly but instead is concentrated in "hotspots" of 1-2 kb. Moreover, the crossover asymmetry observed in a subset of these has led to the suggestion that hotspots may be short-lived on an evolutionary time scale. To test this possibility, we focused on a region known to contain a recombination hotspot in humans, TAP2, and asked whether chimpanzees, the closest living evolutionary relatives of humans, harbor a hotspot in a similar location. Specifically, we used a new statistical approach to estimate recombination rate variation from patterns of linkage disequilibrium in a sample of 24 western chimpanzees (Pan troglodytes verus). This method has been shown to produce reliable results on simulated data and on human data from the TAP2 region. Strikingly, however, it finds very little support for recombination rate variation at TAP2 in the western chimpanzee data. Moreover, simulations suggest that there should be stronger support if there were a hotspot similar to the one characterized in humans. Thus, it appears that the human TAP2 recombination hotspot is not shared by western chimpanzees. These findings demonstrate that fine-scale recombination rates can change between very closely related species and raise the possibility that rates differ among human populations, with important implications for linkage-disequilibrium based association studies.},
	Author = {Ptak, Susan E and Roeder, Amy D and Stephens, Matthew and Gilad, Yoav and P{\"a}{\"a}bo, Svante and Przeworski, Molly},
	Date-Added = {2010-01-07 08:29:40 -0500},
	Date-Modified = {2010-01-07 08:29:40 -0500},
	Doi = {10.1371/journal.pbio.0020155},
	Journal = {PLoS Biol},
	Journal-Full = {PLoS biology},
	Mesh = {ATP-Binding Cassette Transporters; Animals; Base Sequence; Computer Simulation; Evolution, Molecular; Genetic Variation; Haplotypes; Humans; Linkage Disequilibrium; Models, Genetic; Molecular Sequence Data; Mutation; Pan troglodytes; Polymorphism, Single Nucleotide; Recombination, Genetic; Sequence Analysis, DNA},
	Month = {Jun},
	Number = {6},
	Pages = {e155},
	Pmid = {15208713},
	Title = {Absence of the TAP2 human recombination hotspot in chimpanzees},
	Volume = {2},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pbio.0020155}}

@article{Keightley:2005uq,
	Abstract = {Although sequences containing regulatory elements located close to protein-coding genes are often only weakly conserved during evolution, comparisons of rodent genomes have implied that these sequences are subject to some selective constraints. Evolutionary conservation is particularly apparent upstream of coding sequences and in first introns, regions that are enriched for regulatory elements. By comparing the human and chimpanzee genomes, we show here that there is almost no evidence for conservation in these regions in hominids. Furthermore, we show that gene expression is diverging more rapidly in hominids than in murids per unit of neutral sequence divergence. By combining data on polymorphism levels in human noncoding DNA and the corresponding human-chimpanzee divergence, we show that the proportion of adaptive substitutions in these regions in hominids is very low. It therefore seems likely that the lack of conservation and increased rate of gene expression divergence are caused by a reduction in the effectiveness of natural selection against deleterious mutations because of the low effective population sizes of hominids. This has resulted in the accumulation of a large number of deleterious mutations in sequences containing gene control elements and hence a widespread degradation of the genome during the evolution of humans and chimpanzees.},
	Author = {Keightley, Peter D and Lercher, Martin J and Eyre-Walker, Adam},
	Date-Added = {2010-01-07 08:24:27 -0500},
	Date-Modified = {2010-01-07 08:24:27 -0500},
	Doi = {10.1371/journal.pbio.0030042},
	Journal = {PLoS Biol},
	Journal-Full = {PLoS biology},
	Mesh = {Animals; Chromosome Mapping; Evolution, Molecular; Gene Expression Regulation; Genome; Genome, Human; Hominidae; Humans; Models, Genetic; Muridae},
	Month = {Feb},
	Number = {2},
	Pages = {e42},
	Pmid = {15678168},
	Title = {Evidence for widespread degradation of gene control regions in hominid genomes},
	Volume = {3},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pbio.0030042}}

@article{Kolaczkowski:2008xz,
	Abstract = {Evolutionary relationships are typically inferred from molecular sequence data using a statistical model of the evolutionary process. When the model accurately reflects the underlying process, probabilistic phylogenetic methods recover the correct relationships with high accuracy. There is ample evidence, however, that models commonly used today do not adequately reflect real-world evolutionary dynamics. Virtually all contemporary models assume that relatively fast-evolving sites are fast across the entire tree, whereas slower sites always evolve at relatively slower rates. Many molecular sequences, however, exhibit site-specific changes in evolutionary rates, called "heterotachy." Here we examine the accuracy of 2 phylogenetic methods for incorporating heterotachy, the mixed branch length model--which incorporates site-specific rate changes by summing likelihoods over multiple sets of branch lengths on the same tree--and the covarion model, which uses a hidden Markov process to allow sites to switch between variable and invariable as they evolve. Under a variety of simple heterogeneous simulation conditions, the mixed model was dramatically more accurate than homotachous models, which were subject to topological biases as well as biases in branch length estimates. When data were simulated with strong versions of the types of heterotachy observed in real molecular sequences, the mixed branch length model was more accurate than homotachous techniques. Analyses of empirical data sets confirmed that the mixed branch length model can improve phylogenetic accuracy under conditions that cause homotachous models to fail. In contrast, the covarion model did not improve phylogenetic accuracy compared with homotachous models and was sometimes substantially less accurate. We conclude that a mixed branch length approach, although not the solution to all phylogenetic errors, is a valuable strategy for improving the accuracy of inferred trees.},
	Author = {Kolaczkowski, Bryan and Thornton, Joseph W},
	Date-Added = {2010-01-11 15:54:25 -0500},
	Date-Modified = {2010-01-11 15:54:25 -0500},
	Doi = {10.1093/molbev/msn042},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Animals; Computer Simulation; Evolution, Molecular; Humans; Models, Genetic; Phylogeny; Reproducibility of Results; Sequence Analysis, DNA},
	Month = {Jun},
	Number = {6},
	Pages = {1054-66},
	Pmid = {18319244},
	Title = {A mixed branch length model of heterotachy improves phylogenetic accuracy},
	Volume = {25},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msn042}}

@article{Pollard:2010oa,
	Abstract = {Methods for detecting nucleotide substitution rates that are faster or slower than expected under neutral drift are widely used to identify candidate functional elements in genomic sequences. However, most existing methods consider either reductions (conservation) or increases (acceleration) in rate but not both, or assume that selection acts uniformly across the branches of a phylogeny. Here we examine the more general problem of detecting departures from the neutral rate of substitution in either direction, possibly in a clade-specific manner. We consider four statistical, phylogenetic tests for addressing this problem: a likelihood ratio test, a score test, a test based on exact distributions of numbers of substitutions, and the genomic evolutionary rate profiling (GERP) test. All four tests have been implemented in a freely available program called phyloP. Based on extensive simulation experiments, these tests are remarkably similar in statistical power. With 36 mammalian species, they all appear to be capable of fairly good sensitivity with low false-positive rates in detecting strong selection at individual nucleotides, moderate selection in 3-bp elements, and weaker or clade-specific selection in longer elements. By applying phyloP to mammalian multiple alignments from the ENCODE project, we shed light on patterns of conservation/acceleration in known and predicted functional elements, approximate fractions of sites subject to constraint, and differences in clade-specific selection in the primate and glires clades. We also describe new "Conservation" tracks in the UCSC Genome Browser that display both phyloP and phastCons scores for genome-wide alignments of 44 vertebrate species.},
	Author = {Pollard, Katherine S and Hubisz, Melissa J and Rosenbloom, Kate R and Siepel, Adam},
	Date-Added = {2010-01-11 15:53:40 -0500},
	Date-Modified = {2010-01-11 15:53:40 -0500},
	Doi = {10.1101/gr.097857.109},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Month = {Jan},
	Number = {1},
	Pages = {110-21},
	Pmid = {19858363},
	Title = {Detection of nonneutral substitution rates on mammalian phylogenies},
	Volume = {20},
	Year = {2010},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.097857.109}}

@article{Siepel:2004wb,
	Abstract = {A few models have appeared in recent years that consider not only the way substitutions occur through evolutionary history at each site of a genome, but also the way the process changes from one site to the next. These models combine phylogenetic models of molecular evolution, which apply to individual sites, and hidden Markov models, which allow for changes from site to site. Besides improving the realism of ordinary phylogenetic models, they are potentially very powerful tools for inference and prediction-for example, for gene finding or prediction of secondary structure. In this paper, we review progress on combined phylogenetic and hidden Markov models and present some extensions to previous work. Our main result is a simple and efficient method for accommodating higher-order states in the HMM, which allows for context-dependent models of substitution-that is, models that consider the effects of neighboring bases on the pattern of substitution. We present experimental results indicating that higher-order states, autocorrelated rates, and multiple functional categories all lead to significant improvements in the fit of a combined phylogenetic and hidden Markov model, with the effect of higher-order states being particularly pronounced.},
	Address = {2 MADISON AVENUE, LARCHMONT, NY 10538 USA},
	Author = {Siepel, A and Haussler, D},
	Date-Added = {2010-01-11 15:51:17 -0500},
	Date-Modified = {2010-01-11 15:51:17 -0500},
	Isi = {000222588300012},
	Isi-Recid = {135471947},
	Isi-Ref-Recids = {127311022 133765914 113827666 78791004 100205130 68106636 106944062 100367801 108068263 11845470 43930323 23697362 94203001 84933676 88533246 97925417 57684838 121852969 99996694 121595196 116216435 94939370 108633209 89412940 110374097 85997771 99778534 116716738 108367622 107555809 111182162 135471948 110624401 102111360 122737572 135471949 90470500 88533244 107932774 128335136 106490829 119742704 81974090 93007753 90920129 130287179 133765913 135471950 130670437 95661813 89818446 135471951 119935439 117041203 85384143 102567719 90119541 96240950 86599948 88167305 135471952},
	Journal = {Journal of Computational Biology},
	Keywords = {phylogenetic models; hidden Markov models; gene prediction; maximum likelihood; context-dependent substitution},
	Number = {2-3},
	Pages = {413-428},
	Publisher = {MARY ANN LIEBERT INC PUBL},
	Times-Cited = {75},
	Title = {Combining phylogenetic and hidden Markov models in biosequence analysis},
	Type = {Proceedings Paper},
	Volume = {11},
	Year = {2004},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000222588300012}}

@article{Siepel:2005le,
	Abstract = {We have conducted a comprehensive search for conserved elements in vertebrate genomes, using genome-wide multiple alignments of five vertebrate species (human, mouse, rat, chicken, and Fugu rubripes). Parallel searches have been performed with multiple alignments of four insect species (three species of Drosophila and Anopheles gambiae), two species of Caenorhabditis, and seven species of Saccharomyces. Conserved elements were identified with a computer program called phastCons, which is based on a two-state phylogenetic hidden Markov model (phylo-HMM). PhastCons works by fitting a phylo-HMM to the data by maximum likelihood, subject to constraints designed to calibrate the model across species groups, and then predicting conserved elements based on this model. The predicted elements cover roughly 3\%-8\% of the human genome (depending on the details of the calibration procedure) and substantially higher fractions of the more compact Drosophila melanogaster (37\%-53\%), Caenorhabditis elegans (18\%-37\%), and Saccharaomyces cerevisiae (47\%-68\%) genomes. From yeasts to vertebrates, in order of increasing genome size and general biological complexity, increasing fractions of conserved bases are found to lie outside of the exons of known protein-coding genes. In all groups, the most highly conserved elements (HCEs), by log-odds score, are hundreds or thousands of bases long. These elements share certain properties with ultraconserved elements, but they tend to be longer and less perfectly conserved, and they overlap genes of somewhat different functional categories. In vertebrates, HCEs are associated with the 3' UTRs of regulatory genes, stable gene deserts, and megabase-sized regions rich in moderately conserved noncoding sequences. Noncoding HCEs also show strong statistical evidence of an enrichment for RNA secondary structure.},
	Author = {Siepel, Adam and Bejerano, Gill and Pedersen, Jakob S and Hinrichs, Angie S and Hou, Minmei and Rosenbloom, Kate and Clawson, Hiram and Spieth, John and Hillier, Ladeana W and Richards, Stephen and Weinstock, George M and Wilson, Richard K and Gibbs, Richard A and Kent, W James and Miller, Webb and Haussler, David},
	Date-Added = {2010-01-11 15:48:04 -0500},
	Date-Modified = {2010-01-11 15:48:04 -0500},
	Doi = {10.1101/gr.3715005},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {3' Untranslated Regions; Animals; Base Pairing; Base Sequence; Caenorhabditis elegans; Conserved Sequence; DNA, Intergenic; Evolution, Molecular; Genome; Humans; Insects; Molecular Sequence Data; Saccharomyces; Vertebrates; Yeasts},
	Month = {Aug},
	Number = {8},
	Pages = {1034-50},
	Pmid = {16024819},
	Title = {Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.3715005}}

@article{Kosiol:2008xd,
	Abstract = {Genome-wide scans for positively selected genes (PSGs) in mammals have provided insight into the dynamics of genome evolution, the genetic basis of differences between species, and the functions of individual genes. However, previous scans have been limited in power and accuracy owing to small numbers of available genomes. Here we present the most comprehensive examination of mammalian PSGs to date, using the six high-coverage genome assemblies now available for eutherian mammals. The increased phylogenetic depth of this dataset results in substantially improved statistical power, and permits several new lineage- and clade-specific tests to be applied. Of approximately 16,500 human genes with high-confidence orthologs in at least two other species, 400 genes showed significant evidence of positive selection (FDR<0.05), according to a standard likelihood ratio test. An additional 144 genes showed evidence of positive selection on particular lineages or clades. As in previous studies, the identified PSGs were enriched for roles in defense/immunity, chemosensory perception, and reproduction, but enrichments were also evident for more specific functions, such as complement-mediated immunity and taste perception. Several pathways were strongly enriched for PSGs, suggesting possible co-evolution of interacting genes. A novel Bayesian analysis of the possible "selection histories" of each gene indicated that most PSGs have switched multiple times between positive selection and nonselection, suggesting that positive selection is often episodic. A detailed analysis of Affymetrix exon array data indicated that PSGs are expressed at significantly lower levels, and in a more tissue-specific manner, than non-PSGs. Genes that are specifically expressed in the spleen, testes, liver, and breast are significantly enriched for PSGs, but no evidence was found for an enrichment for PSGs among brain-specific genes. This study provides additional evidence for widespread positive selection in mammalian evolution and new genome-wide insights into the functional implications of positive selection.},
	Author = {Kosiol, Carolin and Vinar, Tom{\'a}s and da Fonseca, Rute R and Hubisz, Melissa J and Bustamante, Carlos D and Nielsen, Rasmus and Siepel, Adam},
	Date-Added = {2010-01-11 15:46:23 -0500},
	Date-Modified = {2010-01-11 15:46:23 -0500},
	Doi = {10.1371/journal.pgen.1000144},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Bayes Theorem; Databases, Genetic; Dogs; Evolution, Molecular; Gene Expression; Genome; Humans; Likelihood Functions; Macaca mulatta; Mammals; Mice; Pan troglodytes; Phylogeny; Primates; Rats; Rodentia; Selection, Genetic; Sequence Alignment},
	Number = {8},
	Pages = {e1000144},
	Pmid = {18670650},
	Title = {Patterns of positive selection in six Mammalian genomes},
	Volume = {4},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000144}}

@article{Akashi:1997sh,
	Abstract = {In Escherichia coli, Saccharomyces cerevisiae, and Drosophila melanogaster, codon bias may be maintained by a balance among mutation pressure, genetic drift, and natural selection favoring translationally superior codons. Under such an evolutionary model, silent mutations fall into two fitness categories: preferred mutations that increase codon bias and unpreferred changes in the opposite direction. This prediction can be tested by comparing the frequency spectra of synonymous changes segregating within populations; natural selection will elevate the frequencies of advantageous mutations relative to that of deleterious changes. The frequency distributions of preferred and unpreferred mutations differ in the predicted direction among 99 alleles of two D. pseudoobscura genes and five alleles of eight D. simulans genes. This result confirms the existence of fitness classes of silent mutations. Maximum likelihood estimates suggest that selection intensity at silent sites is, on average, very weak in both D. pseudoobscura and D. simulans (magnitude of NS approximately 1). Inference of evolutionary processes from within-species sequence variation is often hindered by the assumption of a stationary frequency distribution. This assumption can be avoided when identifying the action of selection and tested when estimating selection intensity.},
	Author = {Akashi, H and Schaeffer, S W},
	Date-Added = {2010-01-11 15:41:57 -0500},
	Date-Modified = {2010-01-11 15:41:57 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Codon; DNA; Drosophila melanogaster; Models, Genetic; Molecular Sequence Data; Polymorphism, Genetic; Selection, Genetic},
	Month = {May},
	Number = {1},
	Pages = {295-307},
	Pmid = {9136019},
	Title = {Natural selection and the frequency distributions of "silent" DNA polymorphism in Drosophila},
	Volume = {146},
	Year = {1997}}

@article{Wong:2004pr,
	Abstract = {We present a maximum-likelihood method for examining the selection pressure and detecting positive selection in noncoding regions using multiple aligned DNA sequences. The rate of substitution in noncoding regions relative to the rate of synonymous substitution in coding regions is modeled by a parameter zeta. When a site in a noncoding region is evolving neutrally zeta = 1, while zeta > 1 indicates the action of positive selection, and zeta < 1 suggests negative selection. Using a combined model for the evolution of noncoding and coding regions, we develop two likelihood-ratio tests for the detection of selection in noncoding regions. Data analysis of both simulated and real viral data is presented. Using the new method we show that positive selection in viruses is acting primarily in protein-coding regions and is rare or absent in noncoding regions.},
	Author = {Wong, Wendy S W and Nielsen, Rasmus},
	Date-Added = {2010-01-11 15:38:54 -0500},
	Date-Modified = {2010-01-11 15:38:54 -0500},
	Doi = {10.1534/genetics.102.010959},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Base Sequence; Codon; Genetic Code; Models, Genetic; Models, Theoretical; Selection, Genetic},
	Month = {Jun},
	Number = {2},
	Pages = {949-58},
	Pmid = {15238543},
	Title = {Detecting selection in noncoding regions of nucleotide sequences},
	Volume = {167},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.102.010959}}

@article{Cutter:2006fh,
	Abstract = {Adaptive codon usage provides evidence of natural selection in one of its most subtle forms: a fitness benefit of one synonymous codon relative to another. Codon usage bias is evident in the coding sequences of a broad array of taxa, reflecting selection for translational efficiency and/or accuracy as well as mutational biases. Here, we quantify the magnitude of selection acting on alternative codons in genes of the nematode Caenorhabditis remanei, an outcrossing relative of the model organism C. elegans, by fitting the expected mutation-selection-drift equilibrium frequency distribution of preferred and unpreferred codon variants to the empirical distribution. This method estimates the intensity of selection on synonymous codons in genes with high codon bias as N(e)s = 0.17, a value significantly greater than zero. In addition, we demonstrate for the first time that estimates of ongoing selection on codon usage among genes, inferred from nucleotide polymorphism data, correlate strongly with long-term patterns of codon usage bias, as measured by the frequency of optimal codons in a gene. From the pattern of polymorphisms in introns, we also infer that these findings do not result from the operation of biased gene conversion toward G or C nucleotides. We therefore conclude that coincident patterns of current and ancient selection are responsible for shaping biased codon usage in the C. remanei genome.},
	Author = {Cutter, Asher D and Charlesworth, Brian},
	Date-Added = {2010-01-11 15:37:58 -0500},
	Date-Modified = {2010-01-11 15:37:58 -0500},
	Doi = {10.1016/j.cub.2006.08.067},
	Journal = {Curr Biol},
	Journal-Full = {Current biology : CB},
	Mesh = {Animals; Base Composition; Caenorhabditis; Codon; Genetics, Population; Likelihood Functions; Models, Genetic; Polymorphism, Genetic; Selection, Genetic},
	Month = {Oct},
	Number = {20},
	Pages = {2053-7},
	Pmid = {17055986},
	Title = {Selection intensity on preferred codons correlates with overall codon usage bias in Caenorhabditis remanei},
	Volume = {16},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.cub.2006.08.067}}

@article{Yang:1998sw,
	Abstract = {An excess of nonsynonymous substitutions over synonymous ones is an important indicator of positive selection at the molecular level. A lineage that underwent Darwinian selection may have a nonsynonymous/synonymous rate ratio (dN/dS) that is different from those of other lineages or greater than one. In this paper, several codon-based likelihood models that allow for variable dN/dS ratios among lineages were developed. They were then used to construct likelihood ratio tests to examine whether the dN/dS ratio is variable among evolutionary lineages, whether the ratio for a few lineages of interest is different from the background ratio for other lineages in the phylogeny, and whether the dN/dS ratio for the lineages of interest is greater than one. The tests were applied to the lysozyme genes of 24 primate species. The dN/dS ratios were found to differ significantly among lineages, indicating that the evolution of primate lysozymes is episodic, which is incompatible with the neutral theory. Maximum-likelihood estimates of parameters suggested that about nine nonsynonymous and zero synonymous nucleotide substitutions occurred in the lineage leading to hominoids, and the dN/dS ratio for that lineage is significantly greater than one. The corresponding estimates for the lineage ancestral to colobine monkeys were nine and one, and the dN/dS ratio for the lineage is not significantly greater than one, although it is significantly higher than the background ratio. The likelihood analysis thus confirmed most, but not all, conclusions Messier and Stewart reached using reconstructed ancestral sequences to estimate synonymous and nonsynonymous rates for different lineages.},
	Author = {Yang, Z},
	Date-Added = {2010-01-11 15:36:38 -0500},
	Date-Modified = {2010-01-11 15:36:38 -0500},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Animals; Evolution, Molecular; Genetic Variation; Likelihood Functions; Models, Biological; Muramidase; Primates; Selection, Genetic},
	Month = {May},
	Number = {5},
	Pages = {568-73},
	Pmid = {9580986},
	Title = {Likelihood ratio tests for detecting positive selection and application to primate lysozyme evolution},
	Volume = {15},
	Year = {1998}}

@article{Zhang:2005lo,
	Abstract = {Detecting positive Darwinian selection at the DNA sequence level has been a subject of considerable interest. However, positive selection is difficult to detect because it often operates episodically on a few amino acid sites, and the signal may be masked by negative selection. Several methods have been developed to test positive selection that acts on given branches (branch methods) or on a subset of sites (site methods). Recently, Yang, Z., and R. Nielsen (2002. Codon-substitution models for detecting molecular adaptation at individual sites along specific lineages. Mol. Biol. Evol. 19:908-917) developed likelihood ratio tests (LRTs) based on branch-site models to detect positive selection that affects a small number of sites along prespecified lineages. However, computer simulations suggested that the tests were sensitive to the model assumptions and were unable to distinguish between relaxation of selective constraint and positive selection (Zhang, J. 2004. Frequent false detection of positive selection by the likelihood method with branch-site models. Mol. Biol. Evol. 21:1332-1339). Here, we describe a modified branch-site model and use it to construct two LRTs, called branch-site tests 1 and 2. We applied the new tests to reanalyze several real data sets and used computer simulation to examine the performance of the two tests by examining their false-positive rate, power, and robustness. We found that test 1 was unable to distinguish relaxed constraint from positive selection affecting the lineages of interest, while test 2 had acceptable false-positive rates and appeared robust against violations of model assumptions. As test 2 is a direct test of positive selection on the lineages of interest, it is referred to as the branch-site test of positive selection and is recommended for use in real data analysis. The test appeared conservative overall, but exhibited better power in detecting positive selection than the branch-based test. Bayes empirical Bayes identification of amino acid sites under positive selection along the foreground branches was found to be reliable, but lacked power.},
	Address = {GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND},
	Author = {Zhang, JZ and Nielsen, R and Yang, ZH},
	Date-Added = {2010-01-11 15:34:38 -0500},
	Date-Modified = {2010-01-11 15:34:38 -0500},
	Doi = {DOI 10.1093/molbev/msi237},
	Isi = {000233361500014},
	Isi-Recid = {147389129},
	Isi-Ref-Recids = {114006332 742890 116183196 98816449 115113308 104469990 62972546 64167118 112258708 125192081 117857478 127161889 102567719 114895769 104992663 143718525 95498764 135306297 103143872 104620650},
	Journal = {Molecular Biology and Evolution},
	Keywords = {computer simulation; branch-site model; likelihood ratio test; positive selection},
	Month = dec,
	Number = {12},
	Pages = {2472-2479},
	Publisher = {OXFORD UNIV PRESS},
	Times-Cited = {178},
	Title = {Evaluation of an improved branch-site likelihood method for detecting positive selection at the molecular level},
	Volume = {22},
	Year = {2005},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000233361500014}}

@article{Anisimova:2007hs,
	Abstract = {Detection of positive Darwinian selection has become ever more important with the rapid growth of genomic data sets. Recent branch-site models of codon substitution account for variation of selective pressure over branches on the tree and across sites in the sequence and provide a means to detect short episodes of molecular adaptation affecting just a few sites. In likelihood ratio tests based on such models, the branches to be tested for positive selection have to be specified a priori. In the absence of a biological hypothesis to designate so-called foreground branches, one may test many branches, but a correction for multiple testing becomes necessary. In this paper, we employ computer simulation to evaluate the performance of 6 multiple test correction procedures when the branch-site models are used to test every branch on the phylogeny for positive selection. Four of the methods control the familywise error rates (FWERs), whereas the other 2 control the false discovery rate (FDR). We found that all correction procedures achieved acceptable FWER except for extremely divergent sequences and serious model violations, when the test may become unreliable. The power of the test to detect positive selection is influenced by the strength of selection and the sequence divergence, with the highest power observed at intermediate divergences. The 4 correction procedures that control the FWER had similar power. We recommend Rom's procedure for its slightly higher power, but the simple Bonferroni correction is useable as well. The 2 correction procedures that control the FDR had slightly more power and also higher FWER, We demonstrate the multiple test procedures by analyzing gene sequences from the extracellular domain of the cluster of differentiation 2 (CD2) gene from 10 mammalian species. Both our simulation and real data analysis suggest that the Multiple test procedures are useful when multiple branches have to be tested on the same data set.},
	Address = {GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND},
	Author = {Anisimova, Maria and Yang, Ziheng},
	Date-Added = {2010-01-11 15:33:55 -0500},
	Date-Modified = {2010-01-11 15:33:55 -0500},
	Doi = {DOI 10.1093/molbev/msm042},
	Isi = {000246802400014},
	Isi-Recid = {156429449},
	Isi-Ref-Recids = {25921756 125192095 158137995 122752833 90155838 115373815 135396388 134485559 132352083 78777279 122913941 130851515 88533246 131588237 150131004 136323035 67659349 66110258 70283632 145791040 134945377 109269731 134168640 144977427 104469990 104482958 143092909 73708306 62972546 130864652 126051257 33994657 137234078 104992663 143718525 114895769 125192081 102567719 135306297 147389129},
	Journal = {Molecular Biology and Evolution},
	Keywords = {multiple hypothesis testing; family-wise error rate (FWER); false discovery rate (FDR); positive selection; branch-site model; molecular adaptation},
	Month = may,
	Number = {5},
	Pages = {1219-1228},
	Publisher = {OXFORD UNIV PRESS},
	Times-Cited = {19},
	Title = {Multiple hypothesis testing to detect lineages under positive selection that affects only a few sites},
	Volume = {24},
	Year = {2007},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000246802400014}}

@article{BRITTEN:1986kc,
	Address = {1200 NEW YORK AVE, NW, WASHINGTON, DC 20005},
	Author = {Britten, RJ},
	Date-Added = {2010-01-11 15:29:57 -0500},
	Date-Modified = {2010-01-12 15:22:35 -0500},
	Isi = {A1986A391100025},
	Isi-Recid = {58449901},
	Isi-Ref-Recids = {39401851 48761294 49626989 29055691 55190134 51086739 40481880 42258748 58449902 25448669 58449903 50242525 45478312 58449904 54554920 40666973 42732008 20062755 43639203 40892122 53912839 54554922 34012566 20420748 46829000 40798844 41807842 54554923 48990088 44125464 41337940 44469807 22335249 43930321 22583548 14888862 22335241 40892128 38405601 50135064 40892314 43886884 55370457 56377034 42971627 58449905 52003587 58449906 43119399 55030334 41171712},
	Journal = {Science},
	Month = mar,
	Number = {4744},
	Pages = {1393-1398},
	Publisher = {AMER ASSOC ADVANCEMENT SCIENCE},
	Times-Cited = {550},
	Title = {RATES OF DNA-SEQUENCE EVOLUTION DIFFER BETWEEN TAXONOMIC GROUPS},
	Volume = {231},
	Year = {1986},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A1986A391100025}}

@article{Musio:2002if,
	Abstract = {Human chromosomes are heterogeneous in structure and function and this is the base for the specific banding patterns produced by various chromosome staining techniques. The Human Genome Data Base as of January 2001 was searched for genes mapped to individual chromosomal bands to study the different aspects of human genome organization as they appear at the cytogenetic level of resolution. Genes are unequally distributed both on human chromosomes and chromosome bands. Among more than 5000 genes mapped at individual bands. 81 \% were located in G-negative bands, which correspond to half of the human genome. The main practical value of having a dense genetic physical map of genes is to accelerate the discovery by positional candidate cloning of human disease genes. Gene content agrees with H3 family isochores and with GC-rich flavors. Interestingly. two G-positive bands, namely 2p chromosome bandings is 12 and 7q35, contain a high number of genes. The finding of heterogeneity in gene content suggests that chromosome banding is not only due to differences in gene content. (C) 2002 Elsevier Science Inc. All rights reserved.},
	Address = {360 PARK AVE SOUTH, NEW YORK, NY 10010-1710 USA},
	Author = {Musio, A and Mariani, T and Vezzoni, P and Frattini, A},
	Date-Added = {2010-01-11 15:27:24 -0500},
	Date-Modified = {2010-01-11 15:27:24 -0500},
	Isi = {000175695600016},
	Isi-Recid = {124781885},
	Isi-Ref-Recids = {110734353 124781886 93700412 84085695 118689570 91342750 83638704 77252299 91661130 80084131 86966542 89391497 97669349 85660346 42262707},
	Journal = {Cancer Genetics and Cytogenetics},
	Month = apr,
	Number = {2},
	Pages = {168-171},
	Publisher = {ELSEVIER SCIENCE INC},
	Times-Cited = {9},
	Title = {Heterogeneous gene distribution reflects human genome complexity as detected at the cytogenetic level},
	Volume = {134},
	Year = {2002},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000175695600016}}

@article{Ko:2006ud,
	Abstract = {Fluctuations in base composition appear to be prevalent in Drosophila and mammal genome evolution, but their timescale, genomic breadth, and causes remain obscure. Here, we study base composition evolution within the X chromosomes of Drosophila melanogaster and five of its close relatives. Substitutions were inferred on six extant and two ancestral lineages for 14 near-telomeric and 9 nontelomeric genes. GC content evolution is highly variable both within the genome and within the phylogenetic tree. In the lineages leading to D. yakuba and D. orena, GC content at silent sites has increased rapidly near telomeres, but has decreased in more proximal (nontelomeric) regions. D. orena shows a 17-fold excess of GC-increasing vs. AT-increasing synonymous changes within a small (similar to 130-kb) region close to the telomeric end. Base composition changes within introns are consistent with changes in mutation patterns, but stronger GC elevation at synonymous sites suggests contributions of natural selection or biased gene conversion. The Drosophila yakuba lineage shows a less extreme elevation of GC content distributed over a wider genetic region (similar to 1.2 Mb). A lack of change in GC content for most introns within this region suggests a role of natural selection in localized base composition fluctuations.},
	Address = {428 EAST PRESTON ST, BALTIMORE, MD 21202 USA},
	Author = {Ko, Wen-Ya and Piao, Shengfu and Akashi, Hiroshi},
	Date-Added = {2010-01-11 15:25:37 -0500},
	Date-Modified = {2010-01-11 15:25:37 -0500},
	Doi = {DOI 10.1534/genetics.105.054346},
	Isi = {000241134400031},
	Isi-Recid = {152679696},
	Isi-Ref-Recids = {136137822 97984361 108468556 122231039 131302751 90119556 149608010 73849571 72629152 132590038 146742973 132145393 132590026 115396666 128065972 135188953 121039177 93700412 118249051 146007458 101582607 129746022 145791032 123010137 143300828 128893886 125951400 132245988 88127548 133780422 108468560 104620682 142855368 127161876 128065982 26938825 7996157 105872160 124613424 145845815 42807444 109505242 146255341 133216687 57684838 123662802 67987777 11501144 136704835 54432857 133539574 142193752 85384117 133160933 131835728 117811977 36058349 62269606 103546948 105928711 144698736 119924863 126471556 129909190 115281266 145883687 110111320 95279257 80784801 120277609 61349167 132657980 132145388 132006365 125044480 117385996 111660345 116069012 129289901 127214655 93258697 18768599 117385974 125500733 81350173 7784061 112475307 105554801 119354474 100966567 123305641 128388860 142855233 67936534 96451118 102567719},
	Journal = {Genetics},
	Month = sep,
	Number = {1},
	Pages = {349-362},
	Publisher = {GENETICS},
	Times-Cited = {4},
	Title = {Strong regional heterogeneity in base composition evolution on the Drosophila X chromosome},
	Volume = {174},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000241134400031}}

@article{Gardner:2002bd,
	Abstract = {The parasite Plasmodium falciparum is responsible for hundreds of millions of cases of malaria, and kills more than one million African children annually. Here we report an analysis of the genome sequence of P. falciparum clone 3D7. The 23-megabase nuclear genome consists of 14 chromosomes, encodes about 5,300 genes, and is the most (A + T)-rich genome sequenced to date. Genes involved in antigenic variation are concentrated in the subtelomeric regions of the chromosomes. Compared to the genomes of free-living eukaryotic microbes, the genome of this intracellular parasite encodes fewer enzymes and transporters, but a large proportion of genes are devoted to immune evasion and host-parasite interactions. Many nuclear-encoded proteins are targeted to the apicoplast, an organelle involved in fatty-acid and isoprenoid metabolism. The genome sequence provides the foundation for future studies of this organism, and is being exploited in the search for new drugs and vaccines to fight malaria.},
	Address = {MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND},
	Author = {Gardner, MJ and Hall, N and Fung, E and White, O and Berriman, M and Hyman, RW and Carlton, JM and Pain, A and Nelson, KE and Bowman, S and Paulsen, IT and James, K and Eisen, JA and Rutherford, K and Salzberg, SL and Craig, A and Kyes, S and Chan, MS and Nene, V and Shallom, SJ and Suh, B and Peterson, J and Angiuoli, S and Pertea, M and Allen, J and Selengut, J and Haft, D and Mather, MW and Vaidya, AB and Martin, DMA and Fairlamb, AH and Fraunholz, MJ and Roos, DS and Ralph, SA and McFadden, GI and Cummings, LM and Subramanian, GM and Mungall, C and Venter, JC and Carucci, DJ and Hoffman, SL and Newbold, C and Davis, RW and Fraser, CM and Barrell, B},
	Date-Added = {2010-01-11 14:55:10 -0500},
	Date-Modified = {2010-01-11 14:55:10 -0500},
	Doi = {DOI 10.1038/nature01097},
	Isi = {000178348400045},
	Isi-Recid = {126472355},
	Isi-Ref-Recids = {117839760 124653330 121892092 111283663 118289333 114924138 77632219 117308917 116950126 92106424 102621512 122960810 108601750 52251875 122642910 117595484 101909962 111133730 120311238 72207025 64713931 105174938 126472424 85660435 108300176 98150280 119417966 107541713 84593417 85929881 121261209 125316960 123834380 117881704 116378541 59105411 63620665 115625984 87830968 113061385 104563095 119851376 116069009 118955069 102897323 117294224 123568193 119559094 126472425 90058464 117132040 96053671 75519110 120311239 97492619 126472426 107615364 125313708 123335732 126472427 113483727 123584986 119799809 120856428 96556392 88453927 100749610 126472428 111619227 122960684 123329588 122370789 108506244 124951262 70817987 99541026 119155752 119234565 122038923 111238433 112739904 78144248 126472430 52490790 87921952 86502617 121853759 124463088 108701036 96053414 120277427 121590700 102451178 108973093 105790141 106536541 99350095 58221682 118684622 96748652 117756414 107945825 116169478 114799535 119638401 92114680 59821581 122172704 122432647 123335761 123335744 123321321 105775022 120331200 111182544 124135337 85111058 97358070 105227784 114713600 124416420 113441998 121119305 79819482 114224889 112603098 92106427 113921304 122206940 111535043 112534596 95781153 107615368 118581330 124737109 98046822 87787695 68900315 110738022 126472436 106961646 82473738 69425940 98512562 116950125 125394997 122913566 65268639 118838426 114390160 114697192 107352100 118289357 90525094 66105158 125177088 97025867 95386879 101800069 122052027 123524750 116479903 118689569 122723185 123009853},
	Journal = {Nature},
	Month = oct,
	Number = {6906},
	Pages = {498-511},
	Publisher = {NATURE PUBLISHING GROUP},
	Times-Cited = {1424},
	Title = {Genome sequence of the human malaria parasite Plasmodium falciparum},
	Volume = {419},
	Year = {2002},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000178348400045}}

@article{Yu:2004mw,
	Abstract = {Proteins function mainly through interactions, especially with DNA and other proteins. While some large-scale interaction networks are now available for a number of model organisms, their experimental generation remains difficult. Consequently, interolog mapping--the transfer of interaction annotation from one organism to another using comparative genomics--is of significant value. Here we quantitatively assess the degree to which interologs can be reliably transferred between species as a function of the sequence similarity of the corresponding interacting proteins. Using interaction information from Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster, and Helicobacter pylori, we find that protein-protein interactions can be transferred when a pair of proteins has a joint sequence identity >80\% or a joint E-value <10(-70). (These "joint" quantities are the geometric means of the identities or E-values for the two pairs of interacting proteins.) We generalize our interolog analysis to protein-DNA binding, finding such interactions are conserved at specific thresholds between 30\% and 60\% sequence identity depending on the protein family. Furthermore, we introduce the concept of a "regulog"--a conserved regulatory relationship between proteins across different species. We map interologs and regulogs from yeast to a number of genomes with limited experimental annotation (e.g., Arabidopsis thaliana) and make these available through an online database at http://interolog.gersteinlab.org. Specifically, we are able to transfer approximately 90,000 potential protein-protein interactions to the worm. We test a number of these in two-hybrid experiments and are able to verify 45 overlaps, which we show to be statistically significant.},
	Author = {Yu, Haiyuan and Luscombe, Nicholas M and Lu, Hao Xin and Zhu, Xiaowei and Xia, Yu and Han, Jing-Dong J and Bertin, Nicolas and Chung, Sambath and Vidal, Marc and Gerstein, Mark},
	Date-Added = {2010-01-11 14:52:23 -0500},
	Date-Modified = {2010-01-11 14:52:23 -0500},
	Doi = {10.1101/gr.1774904},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Amino Acid Sequence; Animals; Bacterial Proteins; Binding Sites; Caenorhabditis elegans; Caenorhabditis elegans Proteins; Computational Biology; Conserved Sequence; DNA; DNA, Bacterial; DNA, Fungal; DNA, Helminth; DNA-Binding Proteins; Databases, Protein; Drosophila Proteins; Drosophila melanogaster; Genome; Genome, Bacterial; Genome, Fungal; Helicobacter pylori; Protein Binding; Protein Interaction Mapping; Proteins; Saccharomyces cerevisiae; Saccharomyces cerevisiae Proteins; Sequence Homology, Amino Acid},
	Month = {Jun},
	Number = {6},
	Pages = {1107-18},
	Pmid = {15173116},
	Title = {Annotation transfer between genomes: protein-protein interologs and protein-DNA regulogs},
	Volume = {14},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.1774904}}

@article{Ptacek:2005qc,
	Abstract = {Protein phosphorylation is estimated to affect 30\% of the proteome and is a major regulatory mechanism that controls many basic cellular processes. Until recently, our biochemical understanding of protein phosphorylation on a global scale has been extremely limited; only one half of the yeast kinases have known in vivo substrates and the phosphorylating kinase is known for less than 160 phosphoproteins. Here we describe, with the use of proteome chip technology, the in vitro substrates recognized by most yeast protein kinases: we identified over 4,000 phosphorylation events involving 1,325 different proteins. These substrates represent a broad spectrum of different biochemical functions and cellular roles. Distinct sets of substrates were recognized by each protein kinase, including closely related kinases of the protein kinase A family and four cyclin-dependent kinases that vary only in their cyclin subunits. Although many substrates reside in the same cellular compartment or belong to the same functional category as their phosphorylating kinase, many others do not, indicating possible new roles for several kinases. Furthermore, integration of the phosphorylation results with protein-protein interaction and transcription factor binding data revealed novel regulatory modules. Our phosphorylation results have been assembled into a first-generation phosphorylation map for yeast. Because many yeast proteins and pathways are conserved, these results will provide insights into the mechanisms and roles of protein phosphorylation in many eukaryotes.},
	Author = {Ptacek, Jason and Devgan, Geeta and Michaud, Gregory and Zhu, Heng and Zhu, Xiaowei and Fasolo, Joseph and Guo, Hong and Jona, Ghil and Breitkreutz, Ashton and Sopko, Richelle and McCartney, Rhonda R and Schmidt, Martin C and Rachidi, Najma and Lee, Soo-Jung and Mah, Angie S and Meng, Lihao and Stark, Michael J R and Stern, David F and De Virgilio, Claudio and Tyers, Mike and Andrews, Brenda and Gerstein, Mark and Schweitzer, Barry and Predki, Paul F and Snyder, Michael},
	Date-Added = {2010-01-11 14:43:14 -0500},
	Date-Modified = {2010-01-11 14:43:14 -0500},
	Doi = {10.1038/nature04187},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Eukaryotic Cells; Fungal Proteins; Phosphorylation; Protein Array Analysis; Protein Kinases; Protein Transport; Proteome; Proteomics; Reproducibility of Results; Substrate Specificity; Yeasts},
	Month = {Dec},
	Number = {7068},
	Pages = {679-84},
	Pmid = {16319894},
	Title = {Global analysis of protein phosphorylation in yeast},
	Volume = {438},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature04187}}

@book{Morris:2008ss,
	Address = {Norfolk, U.K.},
	Annote = {LDR    01446cam  22004097a 4500
001    15384666
005    20091120100332.0
008    071011s2008    enkaf    b    001 0 eng  
906    $a7$bcbc$ccopycat$d2$encip$f20$gy-gencatlg
925 0  $aacquire$b2 shelf copies$xpolicy default
955    $anb05 2008-07-28 to ASCD for processing$ijx85 2008-09-17$ejx85 2008-09-17 to BCCD
035    $a(OCoLC)ocn170922279
040    $aNLM$cNLM$dUKM$dYDXCP$dBAKER$dBTCTA$dAGL$dDLC
010    $a  2008274834
015    $aGBA795586$2bnb
016 7  $a101474307$2DNLM
016 7  $a014408109$2Uk
020    $a9781904455257 (hard)
020    $a1904455255 (hard)
035    $a(OCoLC)170922279
042    $aukblcatcopy$anlmcopyc
050 00 $aQP623$b.R5725 2008
060 00 $a2008 F-828
060 10 $aQU 58.7$bR6258 2008
070 0  $aQP623$b.R582 2008
082 04 $a572.865$222
245 00 $aRNA and the regulation of gene expression :$ba hidden layer of complexity /$cedited by Kevin V. Morris.
260    $aNorfolk, U.K. :$bCaister Academic Press,$cc2008.
300    $avii, 228 p., [3] p. of plates :$bill. ;$c26 cm.
504    $aIncludes bibliographical references and index.
650 12 $aRNA.
650 22 $aGene Expression Regulation.
650  0 $aRNA.
650  0 $aGenetic regulation.
700 1  $aMorris, Kevin V.
856 41 $3Table of contents only$uhttp://www.loc.gov/catdir/toc/fy1002/2008274834.html
923    $acopyright
},
	Author = {Morris, Kevin V},
	Call-Number = {QP623},
	Date-Added = {2010-01-11 14:41:08 -0500},
	Date-Modified = {2010-01-11 14:41:08 -0500},
	Dewey-Call-Number = {572.865},
	Genre = {RNA},
	Isbn = {9781904455257 (hard)},
	Library-Id = {2008274834},
	Publisher = {Caister Academic Press},
	Title = {RNA and the regulation of gene expression: a hidden layer of complexity},
	Url = {http://www.loc.gov/catdir/toc/fy1002/2008274834.html},
	Year = {2008},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/toc/fy1002/2008274834.html}}

@article{King:2007fc,
	Abstract = {Identification of functional genomic regions using interspecies comparison will be most effective when the full span of relationships between genomic function and evolutionary constraint are utilized. We find that sets of putative transcriptional regulatory sequences, defined by ENCODE experimental data, have a wide span of evolutionary histories, ranging from stringent constraint shown by deep phylogenetic comparisons to recent selection on lineage-specific elements. This diversity of evolutionary histories can be captured, at least in part, by the suite of available comparative genomics tools, especially after correction for regional differences in the neutral substitution rate. Putative transcriptional regulatory regions show alignability in different clades, and the genes associated with them are enriched for distinct functions. Some of the putative regulatory regions show evidence for recent selection, including a primate-specific, distal promoter that may play a novel role in regulation.},
	Author = {King, David C and Taylor, James and Zhang, Ying and Cheng, Yong and Lawson, Heather A and Martin, Joel and {ENCODE groups for Transcriptional Regulation and Multispecies Sequence Analysis} and Chiaromonte, Francesca and Miller, Webb and Hardison, Ross C},
	Date-Added = {2010-01-11 14:38:55 -0500},
	Date-Modified = {2010-01-11 14:38:55 -0500},
	Doi = {10.1101/gr.5592107},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Animals; Databases, Genetic; Evolution, Molecular; Gene Expression Regulation; Genomics; Humans; Primates; Regulatory Sequences, Nucleic Acid; Transcription, Genetic},
	Month = {Jun},
	Number = {6},
	Pages = {775-86},
	Pmid = {17567996},
	Title = {Finding cis-regulatory elements using comparative genomics: some lessons from ENCODE data},
	Volume = {17},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.5592107}}

@article{Keeling:2004rq,
	Abstract = {The complete genome of the apicomplexan parasite Cryptosporidium parvum reveals many new insights into apicomplexan biology and evolution, as well as the general process of genome reduction in parasites. The genome is globally compacted, but gene loss seems to be focused, in particular in relation to organelles. Massive losses of mitochondrial genes have taken place and there is no evidence of any plastid-related genes, providing a useful tool for examining putative plastid proteins in Plasmodium and other apicomplexans.},
	Author = {Keeling, Patrick J},
	Date-Added = {2010-01-11 14:25:03 -0500},
	Date-Modified = {2010-01-11 14:25:03 -0500},
	Journal = {Dev Cell},
	Journal-Full = {Developmental cell},
	Mesh = {Animals; Cryptosporidium parvum; DNA, Mitochondrial; Evolution, Molecular; Genome, Protozoan; Models, Animal; Plastids; Protozoan Proteins},
	Month = {May},
	Number = {5},
	Pages = {614-6},
	Pmid = {15130487},
	Title = {Reduction and compaction in the genome of the apicomplexan parasite Cryptosporidium parvum},
	Volume = {6},
	Year = {2004}}

@article{Keeling:2004kh,
	Author = {Keeling, Patrick J and Slamovits, Claudio H},
	Date-Added = {2010-01-11 14:23:16 -0500},
	Date-Modified = {2010-01-11 14:23:16 -0500},
	Doi = {10.1128/EC.3.6.1363-1369.2004},
	Journal = {Eukaryot Cell},
	Journal-Full = {Eukaryotic cell},
	Mesh = {Animals; DNA; Evolution, Molecular; Genome, Fungal; Genome, Protozoan; Microsporidia; Models, Genetic; Phylogeny; Species Specificity},
	Month = {Dec},
	Number = {6},
	Pages = {1363-9},
	Pmid = {15590811},
	Title = {Simplicity and complexity of microsporidian genomes},
	Volume = {3},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1128/EC.3.6.1363-1369.2004}}

@article{Petrov:2000cq,
	Abstract = {Eukaryotic genome sizes range over five orders of magnitude. This variation cannot be explained by differences in organismic complexity (the C value paradox). To test the hypothesis that some variation in genome size can be attributed to differences in the patterns of insertion and deletion (indel) mutations among organisms, this study examines the indel spectrum in Laupala crickets, which have a genome size 11 times larger than that of Drosophila. Consistent with the hypothesis, DNA loss is more than 40 times slower in Laupala than in Drosophila.},
	Author = {Petrov, D A and Sangster, T A and Johnston, J S and Hartl, D L and Shaw, K L},
	Date-Added = {2010-01-11 14:21:07 -0500},
	Date-Modified = {2010-01-11 14:21:07 -0500},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Animals; DNA; Drosophila; Evolution, Molecular; Genome; Gryllidae; Likelihood Functions; Multigene Family; Mutation; Phylogeny; Polymerase Chain Reaction; Pseudogenes; Retroelements; Sequence Deletion; Species Specificity},
	Month = {Feb},
	Number = {5455},
	Pages = {1060-2},
	Pmid = {10669421},
	Title = {Evidence for DNA loss as a determinant of genome size},
	Volume = {287},
	Year = {2000}}

@article{Petrov:1996mb,
	Abstract = {Pseudogenes are common in mammals but virtually absent in Drosophila. All putative Drosophila pseudogenes show patterns of molecular evolution that are inconsistent with the lack of functional constraints. The absence of bona fide pseudogenes is not only puzzling, it also hampers attempts to estimate rates and patterns of neutral DNA change. The estimation problem is especially acute in the case of deletions and insertions, which are likely to have large effects when they occur in functional genes and are therefore subject to strong purifying selection. We propose a solution to this problem by taking advantage of the propensity of retrotransposable elements without long terminal repeats (non-LTR) to create non-functional, 'dead-on-arrival' copies of themselves as a common by-product of their transpositional cycle. Phylogenetic analysis of a non-LTR element, Helena, demonstrates that copies lose DNA at an unusually high rate, suggesting that lack of pseudogenes in Drosophila is the product of rampant deletion of DNA in unconstrained regions. This finding has important implications for the study of genome evolution in general and the 'C-value paradox' in particular.},
	Author = {Petrov, D A and Lozovskaya, E R and Hartl, D L},
	Date-Added = {2010-01-11 14:20:33 -0500},
	Date-Modified = {2010-01-11 14:20:33 -0500},
	Doi = {10.1038/384346a0},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Cloning, Molecular; DNA; Drosophila; Evolution, Molecular; Molecular Sequence Data; Phylogeny; Pseudogenes; RNA-Directed DNA Polymerase; Retroelements; Sequence Deletion},
	Month = {Nov},
	Number = {6607},
	Pages = {346-9},
	Pmid = {8934517},
	Title = {High intrinsic rate of DNA loss in Drosophila},
	Volume = {384},
	Year = {1996},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/384346a0}}

@article{Angrist:1998gb,
	Author = {Angrist, M},
	Date-Added = {2010-01-11 14:13:11 -0500},
	Date-Modified = {2010-01-11 14:13:11 -0500},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Animals; Caenorhabditis elegans; Chickens; Fishes, Poisonous; Genome; Humans; Zebrafish},
	Month = {Jul},
	Number = {7},
	Pages = {683-5},
	Pmid = {9685314},
	Title = {Less is more: compact genomes pay dividends},
	Volume = {8},
	Year = {1998}}

@article{Venkatesh:2000jl,
	Abstract = {At 400 Mb, the Japanese pufferfish, Fugu rubripes, has the smallest vertebrate genome but has a similar gene repertoire to other vertebrates. Its genes are densely packed with short intergenic and intronic sequences devoid of repetitive elements. It likely has a mutational bias towards DNA elimination and is probably close to a 'minimal' vertebrate genome. As such it is a useful reference genome for gene discovery and gene validation in other vertebrates. Its usefulness in the discovery of conserved regulatory elements has already been demonstrated. The Fugu genome sequence is a good complement to genetic studies in other vertebrates.},
	Author = {Venkatesh, B and Gilligan, P and Brenner, S},
	Date-Added = {2010-01-11 14:11:15 -0500},
	Date-Modified = {2010-01-11 14:11:15 -0500},
	Journal = {FEBS Lett},
	Journal-Full = {FEBS letters},
	Mesh = {Animals; Fishes; Genome; Humans; Japan; Mammals; Phylogeny; Vertebrates},
	Month = {Jun},
	Number = {1-2},
	Pages = {3-7},
	Pmid = {10878239},
	Title = {Fugu: a compact vertebrate reference genome},
	Volume = {476},
	Year = {2000}}

@article{Delmotte:2006zt,
	Abstract = {Background: Understanding evolutionary processes that drive genome reduction requires determining the tempo ( rate) and the mode ( size and types of deletions) of gene losses. In this study, we analysed five endosymbiotic genome sequences of the gamma-proteobacteria ( three different Buchnera aphidicola strains, Wigglesworthia glossinidia, Blochmannia floridanus) to test if gene loss could be driven by the selective importance of genes. We used a parsimony method to reconstruct a minimal ancestral genome of insect endosymbionts and quantified gene loss along the branches of the phylogenetic tree. To evaluate the selective or functional importance of genes, we used a parameter that measures the level of adaptive codon bias in E. coli (i. e. codon adaptive index, or CAI), and also estimates of evolutionary rates (Ka) between pairs of orthologs either in freeliving bacteria or in pairs of symbionts.

Results: Our results demonstrate that genes lost in the early stages of symbiosis were on average less selectively constrained than genes conserved in any of the extant symbiotic strains studied. These results also extend to more recent events of gene losses (i.e. among Buchnera strains) that still tend to concentrate on genes with low adaptive bias in E. coli and high evolutionary rates both in free-living and in symbiotic lineages. In addition, we analyzed the physical organization of gene losses for early steps of symbiosis acquisition under the hypothesis of a common origin of different symbioses. In contrast with previous findings we show that gene losses mostly occurred through loss of rather small blocks and mostly in syntenic regions between at least one of the symbionts and present-day E. coli.

Conclusion: At both ancient and recent stages of symbiosis evolution, gene loss was at least partially influenced by selection, highly conserved genes being retained more readily than lowly conserved genes: although losses might result from drift due to the bottlenecking of endosymbiontic populations, we demonstrated that purifying selection also acted by retaining genes of greater selective importance.},
	Address = {MIDDLESEX HOUSE, 34-42 CLEVELAND ST, LONDON W1T 4LB, ENGLAND},
	Author = {Delmotte, F. and Rispe, C. and Schaber, J. and Silva, F. J. and Moya, A.},
	Date-Added = {2010-01-11 14:08:10 -0500},
	Date-Modified = {2010-01-11 14:08:10 -0500},
	Doi = {DOI 10.1186/1471-2148-6-56},
	Isi = {000239765000001},
	Isi-Recid = {151697707},
	Isi-Ref-Recids = {127468996 127214652 112939928 107692698 106310055 144402225 135418066 134800290 114560091 112408428 118676668 148409026 130851500 130588945 145689870 149126527 118545152 105872160 124271809 130864630 136483826 143092925 127026557 116450980 133592190 131528488 145513202 133266993 81886723 121940436 95279257 127214910 146085342 119758466 146085341 120235481 122005215 142383759 132787991 125044480 145141350 61547225 116468980 129405090 122130046 125332483 128102519 127214908},
	Journal = {Bmc Evolutionary Biology},
	Month = jul,
	Publisher = {BIOMED CENTRAL LTD},
	Times-Cited = {7},
	Title = {Tempo and mode of early gene loss in endosymbiotic bacteria from insects},
	Volume = {6},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000239765000001}}

@article{Wang:2006il,
	Abstract = {Pseudogenization is a widespread phenomenon in genome evolution, and it has been proposed to serve as an engine of evolutionary change, especially during human origins (the "less-is-more'' hypothesis). However, there has been no comprehensive analysis of human-specific pseudogenes. Furthermore, it is unclear whether pseudogenization itself can be selectively favored and thus play an active role in human evolution. Here we conduct a comparative genomic analysis and a literature survey to identify 80 nonprocessed pseudogenes that were inactivated in the human lineage after its separation from the chimpanzee lineage. Many functions are involved among these genes, with chemoreception and immune response being outstandingly overrepresented, suggesting potential species-specific features in these aspects of human physiology. To explore the possibility of adaptive pseudogenization, we focus on CASPASE12, a cysteinyl aspartate proteinase participating in inflammatory and innate immune response to endotoxins. We provide population genetic evidence that the nearly complete fixation of a null allele at CASPASE12 has been driven by positive selection, probably because the null allele confers protection from severe sepsis. We estimate that the selective advantage of the null allele is about 0.9\% and the pseudogenization started shortly before the out-of-Africa migration of modern humans. Interestingly, two other genes related to sepsis were also pseudogenized in humans, possibly by selection. These adaptive gene losses might have occurred because of changes in our environment or genetic background that altered the threat from or response to sepsis. The identification and analysis of human-specific pseudogenes open the door for understanding the roles of gene losses in human origins, and the demonstration that gene loss itself can be adaptive supports and extends the "less-is-more'' hypothesis.},
	Address = {185 BERRY ST, STE 1300, SAN FRANCISCO, CA 94107 USA},
	Author = {Wang, XX and Grus, WE and Zhang, JZ},
	Date-Added = {2010-01-11 14:06:34 -0500},
	Date-Modified = {2010-01-11 14:06:34 -0500},
	Doi = {DOI 10.1371/journal.pbio.0040052},
	Isi = {000235991300008},
	Isi-Recid = {149221042},
	Isi-Ref-Recids = {145958636 136600289 149221056 97828667 126877180 125419539 136502534 128677791 118320133 126406995 107154458 124670297 125977009 146203815 115761853 143092901 124678710 135798298 143840603 128893873 131067761 128963393 142790831 144698709 132249088 143946818 149221057 129642999 123075733 104160126 117794548 107552092 121729256 123647380 112104333 132154935 124326438 50517071 23961558 125513451 135799612 121718385 124003694 120156025 145958614 131927745 27948158 129851544 129130104 147389094 127910864 108777871 143092880 131302812 129051233 115129242 126765638 147678180 63203468 134323664 157539966 137447129 133767862 105616439 112396790 70616358 119370459 93222169 125974320 132296793 125736419 136929810 134586666 130078885 118451813 130094778 128065984 132296791 106379741},
	Journal = {Plos Biology},
	Month = mar,
	Number = {3},
	Pages = {366-377},
	Publisher = {PUBLIC LIBRARY SCIENCE},
	Times-Cited = {58},
	Title = {Gene losses during human origins},
	Volume = {4},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000235991300008}}

@article{Hershberg:2007tw,
	Abstract = {Background: Obligate pathogenic bacteria lose more genes relative to facultative pathogens, which, in turn, lose more genes than free-living bacteria. It was suggested that the increased gene loss in obligate pathogens may be due to a reduction in the effectiveness of purifying selection. Less attention has been given to the causes of increased gene loss in facultative pathogens.

Results: We examined in detail the rate of gene loss in two groups of facultative pathogenic bacteria: pathogenic Escherichia coli, and Shigella. We show that Shigella strains are losing genes at an accelerated rate relative to pathogenic E. coli. We demonstrate that a genome-wide reduction in the effectiveness of selection contributes to the observed increase in the rate of gene loss in Shigella.

Conclusion: When compared with their closely related pathogenic E. coli relatives, the more niche-limited Shigella strains appear to be losing genes at a significantly accelerated rate. A genome-wide reduction in the effectiveness of purifying selection plays a role in creating this observed difference. Our results demonstrate that differences in the effectiveness of selection contribute to differences in rate of gene loss in facultative pathogenic bacteria. We discuss how the lifestyle and pathogenicity of Shigella may alter the effectiveness of selection, thus influencing the rate of gene loss.},
	Address = {CURRENT SCIENCE GROUP, MIDDLESEX HOUSE, 34-42 CLEVELAND ST, LONDON W1T 4LB, ENGLAND},
	Author = {Hershberg, Ruth and Tang, Hua and Petrov, Dmitri A.},
	Date-Added = {2010-01-11 14:04:27 -0500},
	Date-Modified = {2010-01-11 14:04:27 -0500},
	Doi = {DOI 10.1186/gb-2007-8-8-r164},
	Isi = {000253938500016},
	Isi-Recid = {161199642},
	Isi-Ref-Recids = {161199643 106310055 112939928 161199644 150947196 122448867 117856137 152679928 127026557 127021741 147605890 145955837 104620764 137373592 111966320 76254773 123823676 84343561 135407361 60323569 153930288 119758466 149466889 131042886 65498351 115953949 113441944 124090439 111325819 144927695 134221135 147532708 102567719},
	Journal = {Genome Biology},
	Number = {8},
	Publisher = {BIOMED CENTRAL LTD},
	Times-Cited = {11},
	Title = {Reduced selection leads to accelerated gene loss in Shigella},
	Volume = {8},
	Year = {2007},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000253938500016}}

@article{Krylov:2003qo,
	Abstract = {Lineage-specific gene loss, to a large extent, accounts for the differences in gene repertoires between genomes, particularly among eukaryotes. We derived a parsimonious scenario of gene losses for eukaryotic orthologous groups (KOGs) from seven complete eukaryotic genomes. The scenario involves substantial gene loss in fungi, nematodes, and insects. Based on this evolutionary scenario and estimates of the divergence times between major eukaryotic phyla, we introduce a numerical measure, the propensity for gene loss (PGL). We explore the connection among the propensity of a gene to be lost in evolution (PGL value), protein sequence divergence, the effect of gene knockout on fitness, the number of protein-protein interactions, and expression level for the genes in KOGs. Significant correlations between PGL and each of these variables were detected. Genes that have a lower propensity to be lost in eukaryotic evolution accumulate fewer substitutions in their protein sequences and tend to be essential for the organism viability, tend to be highly expressed, and have many interaction partners. The dependence between PGL and gene dispensability and interactivity is much stronger than that for sequence evolution rate. Thus, propensity of a gene to be lost during evolution seems to be a direct reflection of its biological importance.},
	Address = {500 SUNNYSIDE BLVD, WOODBURY, NY 11797-2924 USA},
	Author = {Krylov, DM and Wolf, YI and Rogozin, IB and Koonin, EV},
	Date-Added = {2010-01-11 14:01:10 -0500},
	Date-Modified = {2010-01-11 14:01:10 -0500},
	Doi = {DOI 10.1101/gr.1589103},
	Isi = {000185876400003},
	Isi-Recid = {131528488},
	Isi-Ref-Recids = {95993164 115898887 101966837 117053345 124933511 93353734 129447534 128678027 48726759 102480495 31442518 96451110 124482695 128055892 115860344 129405104 127214905 125073071 117145438 120368652 110997709 119659776 79944488 130670743 125268880 127806349 122370789 50517071 98641052 87029158 130242461 130582643 129447528 123823676 131528489 120235481 123010200 102480512 118289325 131082692 108679457 32193114 128677787},
	Journal = {Genome Research},
	Month = oct,
	Number = {10},
	Pages = {2229-2235},
	Publisher = {COLD SPRING HARBOR LAB PRESS, PUBLICATIONS DEPT},
	Times-Cited = {115},
	Title = {Gene loss, protein sequence divergence, gene dispensability, expression level, and interactivity are correlated in eukaryotic evolution},
	Volume = {13},
	Year = {2003},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000185876400003}}

@article{Knowles:2009ye,
	Abstract = {The origin of new genes is extremely important to evolutionary innovation. Most new genes arise from existing genes through duplication or recombination. The origin of new genes from noncoding DNA is extremely rare, and very few eukaryotic examples are known. We present evidence for the de novo origin of at least three human protein-coding genes since the divergence with chimp. Each of these genes has no protein-coding homologs in any other genome, but is supported by evidence from expression and, importantly, proteomics data. The absence of these genes in chimp and macaque cannot be explained by sequencing gaps or annotation error. High-quality sequence data indicate that these loci are noncoding DNA in other primates. Furthermore, chimp, gorilla, gibbon, and macaque share the same disabling sequence difference, supporting the inference that the ancestral sequence was noncoding over the alternative possibility of parallel gene inactivation in multiple primate lineages. The genes are not well characterized, but interestingly, one of them was first identified as an up-regulated gene in chronic lymphocytic leukemia. This is the first evidence for entirely novel human-specific protein-coding genes originating from ancestrally noncoding sequences. We estimate that 0.075\% of human genes may have originated through this mechanism leading to a total expectation of 18 such cases in a genome of 24,000 protein-coding genes.},
	Address = {500 SUNNYSIDE BLVD, WOODBURY, NY 11797-2924 USA},
	Author = {Knowles, David G. and McLysaght, Aoife},
	Date-Added = {2010-01-11 11:48:30 -0500},
	Date-Modified = {2010-01-11 11:48:30 -0500},
	Doi = {DOI 10.1101/gr.095026.109},
	Isi = {000270389700007},
	Isi-Recid = {183796830},
	Isi-Ref-Recids = {156024166 157186243 149696288 136502534 162822402 133298791 159607718 146086518 132854882 96748801 153189843 154200859 175390652 124326438 151188657 157247471 131927745 159737137 146086530 65498351 171817214 152250362 171614986 114799559 172235357 176786225 149221041 173883795 161817883 157681422 172726008},
	Journal = {Genome Research},
	Month = oct,
	Number = {10},
	Pages = {1752-1759},
	Publisher = {COLD SPRING HARBOR LAB PRESS, PUBLICATIONS DEPT},
	Times-Cited = {0},
	Title = {Recent de novo origin of human protein-coding genes},
	Volume = {19},
	Year = {2009},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000270389700007}}

@article{Siepel:2009fu,
	Address = {500 SUNNYSIDE BLVD, WOODBURY, NY 11797-2924 USA},
	Author = {Siepel, Adam},
	Date-Added = {2010-01-11 11:45:46 -0500},
	Date-Modified = {2010-01-11 11:45:46 -0500},
	Doi = {DOI 10.1101/gr.098376.109},
	Isi = {000270389700001},
	Isi-Recid = {183796810},
	Isi-Ref-Recids = {157186243 54957 181446334 149696288 162822402 157681380 159607718 38299061 45679224 115660413 31816615 151188657 131927745 87296566 1992718 105698840 122130048 19722228 159467947 183796811 149111432 172726008},
	Journal = {Genome Research},
	Month = oct,
	Number = {10},
	Pages = {1693-1695},
	Publisher = {COLD SPRING HARBOR LAB PRESS, PUBLICATIONS DEPT},
	Times-Cited = {0},
	Title = {Darwinian alchemy: Human genes from noncoding DNA},
	Volume = {19},
	Year = {2009},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000270389700001}}

@article{Fukuchi:2004lh,
	Abstract = {Genome annotation produces a considerable number of putative proteins lacking sequence similarity to known proteins. These are referred to as "orphans." The proportion of orphan genes varies among genomes, and is independent of genome size. In the present study, we show that the proportion of orphan genes roughly correlates with the isolation index of organisms (IIO), an indicator introduced in the present study, which represents the degree of isolation of a given genome as measured by sequence similarity. However, there are outlier genomes with respect to the linear correlation, consisting of those genomes that may contain excess amounts of orphan genes. Comparisons of genome sequences among closely related strains revealed that some of the annotated genes are not conserved, suggesting that they are ORFs occurring by chance. Exclusion of these non-conserved ORFs within closely related genomes improved the correlation between the proportion of orphan genes and the IIO values. Assuming that the correlation holds in general, this relationship was used to estimate the number of "authentic" orphan genes in a genome. Using this definition of authentic orphan genes, the anomalies arising from over-assignments, e.g., the percentages of structural annotations, were corrected for 16 genomes, including those of five archaea.},
	Address = {ORDER DEPT., C P O BOX 235, TOKYO, 100-8691, JAPAN},
	Author = {Fukuchi, S and Nishikawa, K},
	Date-Added = {2010-01-11 11:40:22 -0500},
	Date-Modified = {2010-01-11 11:40:22 -0500},
	Isi = {000224288100001},
	Isi-Recid = {136747471},
	Isi-Ref-Recids = {127214652 115860335 108506416 101966837 113441916 101960587 117195676 126472424 120008866 105482766 116470903 98658925 96563333 125628280 126378623 93201351 116944845 115988594 98421625 115499485 129182979 129730238 122960813 107395336 112542828 122960804 127285533 129147375 127584668 116468980 115798756 120996810 125332483 128102519 127816691 122960795 113933854},
	Journal = {Dna Research},
	Keywords = {comparative genomics; orphan genes; re-annotation},
	Month = aug,
	Number = {4},
	Pages = {219-231},
	Publisher = {UNIVERSAL ACADEMY PRESS INC},
	Times-Cited = {7},
	Title = {Estimation of the number of authentic orphan genes in bacterial genomes},
	Volume = {11},
	Year = {2004},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000224288100001}}

@article{Merkeev:2008ff,
	Abstract = {The origin and function of orphan genes (OGs) is a mysterious problem in modern molecular biology. The recently developed PHOG database helped to shed light on some aspects in the evolution of these genes. Presumably, a rapid evolution is the main factor that influences the origin of OGs. The evolutionary rate of particular genes reflects the degree of their conservation, although exceptions from this rule contribute to the dynamic process of genome evolution during speciation. It is demonstrated that a great number of OGs detected is an artifact of insufficient sequencing. If DNAs of all organisms living on Earth were sequenced, then the OG number would be greatly reduced, giving the way to genes specific of particular taxonomic groups.},
	Address = {233 SPRING ST, NEW YORK, NY 10013-1578 USA},
	Author = {Merkeev, I. V. and Mironov, A. A.},
	Date-Added = {2010-01-11 11:34:25 -0500},
	Date-Modified = {2010-01-11 11:34:25 -0500},
	Doi = {DOI 10.1134/S0026893308010196},
	Isi = {000255955000019},
	Isi-Recid = {162642762},
	Isi-Ref-Recids = {115860335 131528483 113334220 112199077 151406616 151406614 119983654 122065442 134738832 136302056 131174851 132347666},
	Journal = {Molecular Biology},
	Keywords = {orphan genes; phylogenetic orthologous groups (PHOGs); molecular evolution; taxonomic specificity},
	Month = {Jan-Feb},
	Number = {1},
	Pages = {127-132},
	Publisher = {MAIK NAUKA/INTERPERIODICA/SPRINGER},
	Times-Cited = {0},
	Title = {Orphan genes: Function, evolution, and composition},
	Volume = {42},
	Year = {2008},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000255955000019}}

@article{Bridgham:2008pi,
	Abstract = {Gene duplication is the predominant mechanism for the evolution of new genes. Major existing models of this process assume that duplicate genes are redundant; degenerative mutations in one copy can therefore accumulate close to neutrally, usually leading to loss from the genome. When gene products dimerize or interact with other molecules for their functions, however, degenerative mutations in one copy may produce repressor alleles that inhibit the function of the other and are therefore exposed to selection. Here, we describe the evolution of a duplicate repressor by simple degenerative mutations in the steroid hormone receptors (SRs), a biologically crucial vertebrate gene family. We isolated and characterized the SRs of the cephalochordate Branchiostoma floridae, which diverged from other chordates just after duplication of the ancestral SR. The B. floridae genome contains two SRs: BfER, an ortholog of the vertebrate estrogen receptors, and BfSR, an ortholog of the vertebrate receptors for androgens, progestins, and corticosteroids. BfSR is specifically activated by estrogens and recognizes estrogen response elements (EREs) in DNA; BfER does not activate transcription in response to steroid hormones but binds EREs, where it competitively represses BfSR. The two genes are partially coexpressed, particularly in ovary and testis, suggesting an ancient role in germ cell development. These results corroborate previous findings that the ancestral steroid receptor was estrogen-sensitive and indicate that, after duplication, BfSR retained the ancestral function, while BfER evolved the capacity to negatively regulate BfSR. Either of two historical mutations that occurred during BfER evolution is sufficient to generate a competitive repressor. Our findings suggest that after duplication of genes whose functions depend on specific molecular interactions, high-probability degenerative mutations can yield novel functions, which are then exposed to positive or negative selection; in either case, the probability of neofunctionalization relative to gene loss is increased compared to existing models.},
	Author = {Bridgham, Jamie T and Brown, Justine E and Rodr{\'\i}guez-Mar{\'\i}, Adriana and Catchen, Julian M and Thornton, Joseph W},
	Date-Added = {2010-01-11 10:57:46 -0500},
	Date-Modified = {2010-01-11 10:57:46 -0500},
	Doi = {10.1371/journal.pgen.1000191},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Chordata, Nonvertebrate; Evolution, Molecular; Gene Duplication; Models, Genetic; Mutation; Phylogeny; Receptors, Estrogen; Receptors, Steroid},
	Number = {9},
	Pages = {e1000191},
	Pmid = {18787702},
	Title = {Evolution of a new function by degenerative mutation in cephalochordate steroid receptors},
	Volume = {4},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000191}}

@article{Clark:1994mi,
	Abstract = {The ubiquity of multigene families is evidence for the frequent occurrence of gene duplication, but the origin of multigene families from a single gene remains a little-studied aspect of genome evolution. Although it is clear that a duplication can arise and become fixed in a population purely by random genetic drift and that the rate of fixation is accelerated if the duplication is directly advantageous, the nature of gene duplication suggests that other factors may influence the fate of a novel duplication. In the face of disadvantageous loss-of-function mutations, duplication of a functional gene may provide a buffer against such mutations. Here the conditions for invasion of a rare duplication starting from a mutation-selection balance are derived with formal population genetic models in both haploids and diploids. Recurrent duplication protects the duplicated chromosome from loss and can be very effective in increasing its frequency in a population. In the absence of recurrent duplication, one might suppose that a duplication would be favored by natural selection because it can mask the effects of deleterious mutations. However, the models show that a duplication can invade only if it provides a direct advantage to the organism. This result is closely related to recent theoretical work on the evolution of ploidy.},
	Author = {Clark, A G},
	Date-Added = {2010-01-11 10:57:05 -0500},
	Date-Modified = {2010-01-11 10:57:05 -0500},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Diploidy; Models, Theoretical; Multigene Family; Mutation; Polymorphism, Genetic; Stochastic Processes},
	Month = {Apr},
	Number = {8},
	Pages = {2950-4},
	Pmid = {8159686},
	Title = {Invasion and maintenance of a gene duplication},
	Volume = {91},
	Year = {1994}}

@article{Force:1999qa,
	Abstract = {The origin of organismal complexity is generally thought to be tightly coupled to the evolution of new gene functions arising subsequent to gene duplication. Under the classical model for the evolution of duplicate genes, one member of the duplicated pair usually degenerates within a few million years by accumulating deleterious mutations, while the other duplicate retains the original function. This model further predicts that on rare occasions, one duplicate may acquire a new adaptive function, resulting in the preservation of both members of the pair, one with the new function and the other retaining the old. However, empirical data suggest that a much greater proportion of gene duplicates is preserved than predicted by the classical model. Here we present a new conceptual framework for understanding the evolution of duplicate genes that may help explain this conundrum. Focusing on the regulatory complexity of eukaryotic genes, we show how complementary degenerative mutations in different regulatory elements of duplicated genes can facilitate the preservation of both duplicates, thereby increasing long-term opportunities for the evolution of new gene functions. The duplication-degeneration-complementation (DDC) model predicts that (1) degenerative mutations in regulatory elements can increase rather than reduce the probability of duplicate gene preservation and (2) the usual mechanism of duplicate gene preservation is the partitioning of ancestral functions rather than the evolution of new functions. We present several examples (including analysis of a new engrailed gene in zebrafish) that appear to be consistent with the DDC model, and we suggest several analytical and experimental approaches for determining whether the complementary loss of gene subfunctions or the acquisition of novel functions are likely to be the primary mechanisms for the preservation of gene duplicates. For a newly duplicated paralog, survival depends on the outcome of the race between entropic decay and chance acquisition of an advantageous regulatory mutation. Sidow 1996(p. 717) On one hand, it may fix an advantageous allele giving it a slightly different, and selectable, function from its original copy. This initial fixation provides substantial protection against future fixation of null mutations, allowing additional mutations to accumulate that refine functional differentiation. Alternatively, a duplicate locus can instead first fix a null allele, becoming a pseudogene. Walsh 1995 (p. 426) Duplicated genes persist only if mutations create new and essential protein functions, an event that is predicted to occur rarely. Nadeau and Sankoff 1997 (p. 1259) Thus overall, with complex metazoans, the major mechanism for retention of ancient gene duplicates would appear to have been the acquisition of novel expression sites for developmental genes, with its accompanying opportunity for new gene roles underlying the progressive extension of development itself. Cooke et al. 1997 (p. 362)},
	Author = {Force, A and Lynch, M and Pickett, F B and Amores, A and Yan, Y L and Postlethwait, J},
	Date-Added = {2010-01-11 10:55:46 -0500},
	Date-Modified = {2010-01-11 10:55:46 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Base Sequence; DNA Primers; Evolution; Gene Duplication; Genes, Regulator; Genetic Complementation Test; Humans; Models, Genetic; Mutation; Phylogeny},
	Month = {Apr},
	Number = {4},
	Pages = {1531-45},
	Pmid = {10101175},
	Title = {Preservation of duplicate genes by complementary, degenerative mutations},
	Volume = {151},
	Year = {1999}}

@article{Kimura:1974kl,
	Abstract = {THE FOLLOWING FIVE PRINCIPLES WERE DEDUCED FROM THE ACCUMULATED EVIDENCE ON MOLECULAR EVOLUTION AND THEORETICAL CONSIDERATIONS OF THE POPULATION DYNAMICS OF MUTANT SUBSTITUTIONS: (i) for each protein, the rate of evolution in terms of amino acid substitutions is approximately constant/site per year for various lines, as long as the function and tertiary structure of the molecule remain essentially unaltered. (ii) Functionally less important molecules or parts of a molecule evolve (in terms of mutant substitutions) faster than more important ones. (iii) Those mutant substitutions that disrupt less the existing structure and function of a molecule (conservative substitutions) occur more frequently in evolution than more disruptive ones. (iv) Gene duplication must always precede the emergence of a gene having a new function. (v) Selective elimination of definitely deleterious mutants and random fixation of selectively neutral or very slightly deleterious mutants occur far more frequently in evolution than positive Darwinian selection of definitely advantageous mutants.},
	Author = {Kimura, M and Ota, T},
	Date-Added = {2010-01-11 10:54:58 -0500},
	Date-Modified = {2010-01-11 10:54:58 -0500},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Evolution; Genetic Code; Genetics, Population; Molecular Biology; Mutation; Selection, Genetic},
	Month = {Jul},
	Number = {7},
	Pages = {2848-52},
	Pmid = {4527913},
	Title = {On some principles governing molecular evolution},
	Volume = {71},
	Year = {1974}}

@book{Ohno:1970fu,
	Address = {Berlin},
	Annote = {LDR    00773cam  2200265   4500
001    4632198
005    20021018132349.0
008    701109s1970    nyua     b    001 0 eng  
035    $9(DLC)   78112882
906    $a7$bcbc$corignew$d2$encip$f19$gy-gencatlg
010    $a   78112882 
015    $aGDB***
040    $aDLC$cDLC$dDLC
050 00 $aQH366.2$b.O37
082 00 $a575.01/65
100 1  $aOhno, Susumu.
245 10 $aEvolution by gene duplication.
260    $aBerlin,$aNew York,$bSpringer-Verlag,$c1970.
300    $axv, 160 p.$billus.$c26 cm.
350    $aDM36.00
504    $aIncludes bibliographies.
650  0 $aMutation (Biology)
650  0 $aEvolution (Biology)
740 0  $aGene duplication.
991    $bc-GenColl$hQH431$i.O43$p00053128737$tCopy 1$wBOOKS
},
	Author = {Ohno, Susumu},
	Call-Number = {QH366.2},
	Date-Added = {2010-01-11 10:54:13 -0500},
	Date-Modified = {2010-01-11 10:54:13 -0500},
	Dewey-Call-Number = {575.01/65},
	Genre = {Mutation (Biology)},
	Library-Id = {78112882},
	Publisher = {Springer-Verlag},
	Title = {Evolution by gene duplication},
	Year = {1970}}

@article{Taylor:2003dz,
	Abstract = {Through phylogeny reconstruction we identified 49 genes with a single copy in man, mouse, and chicken, one or two copies in the tetraploid frog Xenopus laevis, and two copies in zebrafish (Danlo rerio). For 22 of these genes, both zebrafish duplicates had orthologs in the pufferfish (Takifugu rubripes). For another 20 of these genes, we found only one pufferfish ortholog but in each case it was more closely related to one of the zebrafish duplicates than to the other. Forty-three pairs of duplicated genes map to 24 of the 25 zebrafish linkage groups but they are not randomly distributed; we identified 10 duplicated regions of the zebrafish genome that each contain between two and five sets of paralogous genes. These phylogeny and synteny data suggest that the common ancestor of zebrafish and pufferfish, a fish that gave rise to similar to22,000 species, experienced a large-scale gene or complete genome duplication event and that the pufferfish has lost many duplicates that the zebrafish has retained.},
	Address = {1 BUNGTOWN RD, PLAINVIEW, NY 11724 USA},
	Author = {Taylor, JS and Braasch, I and Frickey, T and Meyer, A and Van de Peer, Y},
	Date-Added = {2010-01-11 10:51:10 -0500},
	Date-Modified = {2010-01-11 10:51:10 -0500},
	Doi = {DOI 10.1101/gr.640303},
	Isi = {000181418600006},
	Isi-Recid = {128636722},
	Isi-Ref-Recids = {33728646 73849571 107897655 125986876 117184460 35852208 116716724 111967719 41249501 111007215 112117479 36391001 30975881 109567890 122328186 109763923 124151664 123010195 116278315 119313547 69760203 106399299 40871570 124654638 120737258 120896951 117406160 117792848 112796647 89451379 19722228 117812053 103580266 118404419 120544028 63203468 123149047 38613103 98839228 66375 103143862 97209324 121286681 122765222 122195171 103685296 20781935 126917314 89133145 117853269 115884364 76260355 85484849 106331686 123149034 100749701 119744269 117812055 121426615 124151812},
	Journal = {Genome Research},
	Month = mar,
	Number = {3},
	Pages = {382-390},
	Publisher = {COLD SPRING HARBOR LAB PRESS},
	Times-Cited = {256},
	Title = {Genome duplication, a trait shared by 22,000 species of ray-finned fish},
	Volume = {13},
	Year = {2003},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000181418600006}}

@article{Cui:2006fv,
	Abstract = {Genomic comparisons provide evidence for ancient genome-wide duplications in a diverse array of animals and plants. We developed a birth-death model to identify evidence for genome duplication in EST data, and applied a mixture model to estimate the age distribution of paralogous pairs identified in EST sets for species representing the basal-most extant flowering plant lineages. We found evidence for episodes of ancient genome-wide duplications in the basal angiosperm lineages including Nuphar advena (yellow water lily: Nymphaeaceae) and the magnoliids Persea americana (avocado: Lauraceae), Liriodendron tulipifera (tulip poplar: Magnoliaceae), and Saruma henryi (Aristolochiaceae). In addition, we detected independent genome duplications in the basal eudicot Eschscholzia californica (California poppy: Papaveraceae) and the basal monocot Acorus americanus (Acoraceae), both of which were distinct from duplications documented for ancestral grass (Poaceae) and core eudicot lineages. Among gymnosperms, we found equivocal evidence for ancient polyploidy in Welwitschia mirabilis (Gnetales) and no evidence for polyploidy in pine, although gymnosperms generally have much larger genomes than the angiosperms investigated. Cross-species sequence divergence estimates suggest that synonymous substitution rates in the basal angiosperms are less than half those previously reported for core eudicots and members of Poaceae. These lower substitution rates permit inference of older duplication events. We hypothesize that evidence of an ancient duplication observed in the Nuphar data may represent a genome duplication in the common ancestor of all or most extant angiosperms, except Amborella.},
	Address = {500 SUNNYSIDE BLVD, WOODBURY, NY 11797-2924 USA},
	Author = {Cui, Liying and Wall, P. Kerr and Leebens-Mack, James H. and Lindsay, Bruce G. and Soltis, Douglas E. and Doyle, Jeff J. and Soltis, Pamela S. and Carlson, John E. and Arumuganathan, Kathiravetpilla and Barakat, Abdelali and Albert, Victor A. and Ma, Hong and dePamphilis, Claude W.},
	Date-Added = {2010-01-11 10:48:36 -0500},
	Date-Modified = {2010-01-11 10:48:36 -0500},
	Doi = {DOI 10.1101/gr.4825606},
	Isi = {000237973200006},
	Isi-Recid = {150535807},
	Isi-Ref-Recids = {124646657 129240509 146435064 144902316 128916287 132590108 128257145 135587758 116192623 150535808 130157989 128771456 115035377 150535809 142594277 31980 150535810 147277378 147384548 148904813 144213521 83457146 136349525 104563109 104563105 109567890 118923933 97486512 88533246 45707525 114660762 17938168 125025986 131588237 132754605 120290016 109692377 132484932 117728683 136827394 133945969 142241932 110072431 105554762 116194807 146298931 75823167 132237147 117406160 143854261 119794115 86685184 131163929 125025987 234252 60323569 19722228 118217649 135418132 134377980 123231387 137027836 33870047 97209647 126877174 129722968 118915164 72195141 111251863 205296 142211933 117853269 133469658 137321778 145668829 100749701 64632755 102567719 113434924 143213060 143381386 144344983 124951357 104620650},
	Journal = {Genome Research},
	Month = jun,
	Number = {6},
	Pages = {738-749},
	Publisher = {COLD SPRING HARBOR LAB PRESS, PUBLICATIONS DEPT},
	Times-Cited = {93},
	Title = {Widespread genome duplications throughout the history of flowering plants},
	Volume = {16},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000237973200006}}

@article{Dehal:2005bs,
	Abstract = {The hypothesis that the relatively large and complex vertebrate genome was created by two ancient, whole genome duplications has been hotly debated, but remains unresolved. We reconstructed the evolutionary relationships of all gene families from the complete gene sets of a tunicate, fish, mouse, and human, and then determined when each gene duplicated relative to the evolutionary tree of the organisms. We confirmed the results of earlier studies that there remains little signal of these events in numbers of duplicated genes, gene tree topology, or the number of genes per multigene family. However, when we plotted the genomic map positions of only the subset of paralogous genes that were duplicated prior to the fish - tetrapod split, their global physical organization provides unmistakable evidence of two distinct genome duplication events early in vertebrate evolution indicated by clear patterns of four-way paralogous regions covering a large part of the human genome. Our results highlight the potential for these large-scale genomic events to have driven the evolutionary success of the vertebrate lineage.},
	Address = {185 BERRY ST, STE 1300, SAN FRANCISCO, CA 94107 USA},
	Author = {Dehal, P and Boore, JL},
	Date-Added = {2010-01-11 10:47:25 -0500},
	Date-Modified = {2010-01-11 10:47:25 -0500},
	Doi = {DOI 10.1371/journal.pbio.0030314},
	Isi = {000232404600005},
	Isi-Recid = {147384548},
	Isi-Ref-Recids = {124646657 114203276 73849571 125986876 135587758 133440104 131299058 127400982 133959273 126471569 127909551 122328186 124745600 113670364 125025986 97831084 131243509 90591986 131546972 109692377 136600274 40894207 96523863 133945969 120156025 127437839 133130384 129394844 82996971 123010140 117406160 125025987 112796647 19722228 129909304 106761976 119009347 124090439 129231015 98839228 122195171 89412910 34066441 132919395 118581009 130851523 117853269 115884364 127311022 119744269 125628191},
	Journal = {Plos Biology},
	Month = oct,
	Number = {10},
	Pages = {1700-1708},
	Publisher = {PUBLIC LIBRARY SCIENCE},
	Times-Cited = {202},
	Title = {Two rounds of whole genome duplication in the ancestral vertebrate},
	Volume = {3},
	Year = {2005},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000232404600005}}

@article{Crow:2006ij,
	Abstract = {Gene and genome duplications provide a source of genetic material for mutation, drift, and selection to act upon, making new evolutionary opportunities possible. As a result, many have argued that genome duplication is a dominant factor in the evolution of complexity and diversity. However, a clear correlation between a genome duplication event and increased complexity and diversity is not apparent, and there are inconsistencies in the patterns of diversity invoked to support this claim. Interestingly, several estimates of genome duplication events in vertebrates are preceded by multiple extinct lineages, resulting in preduplication gaps in extant taxa. Here we argue that gen(om)e duplication could contribute to reduced risk of extinction via functional redundancy, mutational robustness, increased rates of evolution, and adaptation. The timeline for these processes to unfold would not predict immediate increases in species diversity after the duplication event. Rather, reduced probabilities of extinction would predict a latent period between a genome duplication and its effect on species diversity or complexity. In this paper, we will develop the idea that genome duplication could contribute to species diversity through reduced probability of extinction.},
	Address = {GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND},
	Author = {Crow, KD and Wagner, GP},
	Date-Added = {2010-01-11 10:42:59 -0500},
	Date-Modified = {2010-01-11 10:42:59 -0500},
	Doi = {DOI 10.1093/molbev/msj083},
	Isi = {000237320800007},
	Isi-Recid = {150130990},
	Isi-Ref-Recids = {135587758 135587759 128771456 92338093 131012478 132848221 150130991 145005049 110544500 132833919 109567890 134111267 107358539 127580972 136042190 90591986 114401221 112104333 130218407 145777702 30227304 133945969 125472999 116194807 132237154 136348667 49471441 81800625 117406160 137189545 117792848 122960727 122065456 691273 112796647 89451379 19722228 118217649 93677099 117812053 127214891 135602184 133765938 129231015 143206533 111251863 92460458 69982649 142374375 80661135 117853269 144822641 132451653 89734937 113243806 114844983 104620650 124151812 130094778 127483954},
	Journal = {Molecular Biology and Evolution},
	Keywords = {genome duplication; extinction},
	Month = may,
	Number = {5},
	Pages = {887-892},
	Publisher = {OXFORD UNIV PRESS},
	Times-Cited = {24},
	Title = {What is the role of genome duplication in the evolution of complexity and diversity?},
	Type = {Proceedings Paper},
	Volume = {23},
	Year = {2006},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000237320800007}}

@book{Schlosser:2004hc,
	Address = {Chicago},
	Annote = {LDR    01494cam  22003134a 4500
001    13241084
005    20041210201652.0
008    030617s2004    ilua     b    001 0 eng  
906    $a7$bcbc$corignew$d1$eocip$f20$gy-gencatlg
925 0  $aacquire$b2 shelf copies$xpolicy default
955    $apc10 2003-06-17 to ASCD$ajb11 2003-06-17 holding for email from editor$cjb11 2003-06-18$djb08 2003-06-18 to sl$ejb20 2003-06-18 to dewey$aaa07 2003-06-19$aps09 2004-07-27 1 copy rec'd., to CIP ver.$fjb14 2004-10-04 CIP ver.$gjb02 2004-10-05 to BCCD$cjb01 2004-11-08 copy 2 to BCCD
010    $a  2003056415
020    $a0226738531 (cloth : alk. paper)
020    $a0226738558 (pbk. : alk. paper)
040    $aDLC$cDLC$dDLC
042    $apcc
050 00 $aQH491$b.M59 2004
082 00 $a571.8$221
245 00 $aModularity in development and evolution /$cedited by Gerhard Schlosser and G{\"u}nter P. Wagner.
260    $aChicago :$bUniversity of Chicago Press,$c2004.
300    $ax, 600 p. :$bill. ;$c24 cm.
504    $aIncludes bibliographical references.
650  0 $aDevelopmental biology.
650  0 $aEvolution (Biology)
700 1  $aSchlosser, Gerhard,$d1963-
700 1  $aWagner, G{\"u}nter P.
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/description/uchi052/2003056415.html
856 42 $3Contributor biographical information$uhttp://www.loc.gov/catdir/bios/uchi051/2003056415.html
856 41 $3Table of contents$uhttp://www.loc.gov/catdir/toc/uchi051/2003056415.html
},
	Author = {Schlosser, Gerhard and Wagner, G{\"u}nter P},
	Call-Number = {QH491},
	Date-Added = {2010-01-11 10:40:33 -0500},
	Date-Modified = {2010-01-11 10:40:33 -0500},
	Dewey-Call-Number = {571.8},
	Genre = {Developmental biology},
	Isbn = {0226738531 (cloth : alk. paper)},
	Library-Id = {2003056415},
	Publisher = {University of Chicago Press},
	Title = {Modularity in development and evolution},
	Url = {http://www.loc.gov/catdir/description/uchi052/2003056415.html},
	Year = {2004},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/description/uchi052/2003056415.html}}

@article{Snel:2004tg,
	Abstract = {Functional modules are considered the primary building blocks of biomolecular systems. Here we study to what extent functional modules behave cohesively across genomes:That is, are functional modules also evolutionary modules? We probe this question by analyzing for a large collection of functional modules the phyletic patterns of their genes across 110 genomes. The majority of functional modules display limited evolutionary modularity. This result confirms certain comparative genome analyses, but is in contrast to implicit assumptions in the systems analysis of functional genomics data. We show that this apparent interspecies flexibility in the organization of functional modules depends more on functional differentiation within orthologous groups of genes, than on noise in the functional module definitions. When filtering out these sources of nonmodularity, even though very few functional modules behave perfectly modular in evolution, about half behave at least significantly more modular than a random set of genes. There are substantial differences in the evolutionary modularity between individual functional modules as well as between collections of functional modules, partly corresponding to conceptual differences in the functional module definition, which make comparisons between functional module collections biologically difficult to interpret. Analysis within one collection does not suffer from such differences, and we show that within the EcoCyc metabolic pathway database, biosynthetic pathways are evolutionarily more modular than catabolic pathways.},
	Author = {Snel, Berend and Huynen, Martijn A},
	Date-Added = {2010-01-11 10:34:25 -0500},
	Date-Modified = {2010-01-11 10:34:25 -0500},
	Doi = {10.1101/gr.1969504},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Computational Biology; Databases, Genetic; Eukaryotic Cells; Evolution, Molecular; Gene Expression Profiling; Gene Expression Regulation; Genes; Genes, Archaeal; Genes, Bacterial; Metabolism; Phylogeny},
	Month = {Mar},
	Number = {3},
	Pages = {391-7},
	Pmid = {14993205},
	Title = {Quantifying modularity in the evolution of biomolecular systems},
	Volume = {14},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.1969504}}

@book{Duboule:1994kl,
	Address = {Oxford},
	Annote = {LDR    01515cam  2200337 a 4500
001    4417317
005    20070515185523.0
008    931216s1994    enka     b    001 0 eng  
906    $a7$bcbc$corignew$d1$eocip$f19$gy-gencatlg
955    $apc14 to ja00 12-16-93; jc05 12-17-93; jc02 to cpso 12-17-93; jc12 01-04-94; 01-18-94; jk00 02-13-95; CIP ver jk14 03-02-95
035    $9(DLC)   93047573
010    $a   93047573 
020    $a0198599390 (pbk) :$c£35.00 ($47.50 U.S.)
020    $a0198599404 (pbk) :$c£30.00 ($19.50 U.S.)
040    $aDLC$cDLC$dDLC
050 00 $aQH447.8.H65$bG85 1994
082 00 $a574.87/322$220
245 00 $aGuidebook to the homeobox genes /$cedited by Denis Duboule.
260    $aOxford ;$aNew York :$bOxford University Press,$cc1994.
300    $av, 284 p. :$bill. ;$c25 cm.
490 1  $aGuidebook series
500    $a"A Sambrook & Tooze publication."
504    $aIncludes bibliographical references (p. 249-269) and indexes.
650  0 $aHomeobox genes.
700 1  $aDuboule, Denis.
830  0 $aGuidebook series (Oxford, England)
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/enhancements/fy0636/93047573-d.html
856 41 $3Table of contents only$uhttp://www.loc.gov/catdir/enhancements/fy0639/93047573-t.html
856 42 $3Contributor biographical information$uhttp://www.loc.gov/catdir/enhancements/fy0725/93047573-b.html
920    $a** LC HAS REQ'D # OF SHELF COPIES **
991    $bc-GenColl$hQH447.8.H65$iG85 1994$p0005317792A$tCopy 1$wBOOKS
},
	Author = {Duboule, Denis},
	Call-Number = {QH447.8.H65},
	Date-Added = {2010-01-11 10:32:38 -0500},
	Date-Modified = {2010-01-11 10:32:38 -0500},
	Dewey-Call-Number = {574.87/322},
	Genre = {Homeobox genes},
	Isbn = {0198599390 (pbk)},
	Library-Id = {93047573},
	Publisher = {Oxford University Press},
	Series = {Guidebook series},
	Title = {Guidebook to the homeobox genes},
	Url = {http://www.loc.gov/catdir/enhancements/fy0636/93047573-d.html},
	Year = {1994},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/enhancements/fy0636/93047573-d.html}}

@article{Scott:1984oq,
	Abstract = {Genes that regulate the development of the fruit fly Drosophila melanogaster exist as tightly linked clusters in at least two cases. These clusters, the bithorax complex (BX-C) and the Antennapedia complex (ANT-C), both contain multiple homoeotic loci: mutations in each locus cause a transformation of one part of the fly into another. Several repetitive DNA sequences, including at least one transposon, were mapped in the ANT-C. DNA from the 3' exon of Antennapedia (Antp), a homoeotic locus in the ANT-C, hybridized weakly to DNA from the 3' exon of Ultrabithorax (Ubx), a homoeotic locus in the BX-C. DNA from each of these 3' exons also hybridized weakly to DNA from the fushi tarazu locus of the ANT-C. The fushi tarazu (ftz) locus controls the number and differentiation of segments in the developing embryo. Sequence analysis of the cross-hybridizing DNA from the three loci revealed the conservation of predicted amino acid sequences derived from coding parts of the genes. This suggests that two homoeotic loci and a "segment-deficient" locus encode protein products with partially shared structures and that the three loci may be evolutionarily and functionally related.},
	Author = {Scott, M P and Weiner, A J},
	Date-Added = {2010-01-11 10:30:33 -0500},
	Date-Modified = {2010-01-11 10:30:33 -0500},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Cloning, Molecular; DNA Restriction Enzymes; DNA Transposable Elements; Drosophila melanogaster; Genes; Nucleic Acid Hybridization; Repetitive Sequences, Nucleic Acid; Transcription, Genetic},
	Month = {Jul},
	Number = {13},
	Pages = {4115-9},
	Pmid = {6330741},
	Title = {Structural relationships among genes that control development: sequence homology between the Antennapedia, Ultrabithorax, and fushi tarazu loci of Drosophila},
	Volume = {81},
	Year = {1984}}

@article{McGinnis:1984nx,
	Abstract = {A repetitive DNA sequence has been identified in the Drosophila melanogaster genome that appears to be localized specifically within genes of the bithorax and Antennapedia complexes that are required for correct segmental development. Initially identified in cloned copies of the genes Antennapedia, Ultrabithorax and fushi tarazu, the sequence is also contained within two other DNA clones that have characteristics strongly suggesting that they derive from other homoeotic genes.},
	Author = {McGinnis, W and Levine, M S and Hafen, E and Kuroiwa, A and Gehring, W J},
	Date = {1984 Mar 29-Apr 4},
	Date-Added = {2010-01-11 10:29:41 -0500},
	Date-Modified = {2010-01-11 10:29:41 -0500},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Base Sequence; Cloning, Molecular; DNA; DNA Restriction Enzymes; Drosophila melanogaster; Nucleic Acid Hybridization; Repetitive Sequences, Nucleic Acid; Transcription, Genetic},
	Number = {5958},
	Pages = {428-33},
	Pmid = {6323992},
	Title = {A conserved DNA sequence in homoeotic genes of the Drosophila Antennapedia and bithorax complexes},
	Volume = {308},
	Year = {1984}}

@article{Thali:1988cr,
	Abstract = {Homoeotic genes in Drosophila melanogaster are active in spatially restricted metameric domains and control the morphogenesis of segment-specific features such as legs or wings within these domains. They exert their function, according to the 'selector gene' hypothesis, by regulating the expression of subordinate genes. Homoeotic genes also control their own expression and the expression of each other. The proteins encoded by these genes contain a domain, called a homoeodomain, that is strongly conserved, and that shows homologies to proteins that bind DNA and regulate transcription. Homoeoproteins have been shown to bind specific DNA sequences. We show here that the Drosophila homoeotic genes Ultrabithorax (Ubx) and Abdominal-B (Abd-B) code for proteins that are capable of activating transcription of reporter genes linked to specific cis-regulatory target sequences in transfected mammalian cells. Their activity, as well as their target specificity, is similar to that of a mammalian lymphoid-specific octamer transcription factor, OTF-2, which was recently found to contain a homoeodomain.},
	Author = {Thali, M and M{\"u}ller, M M and DeLorenzi, M and Matthias, P and Bienz, M},
	Date-Added = {2010-01-11 10:29:38 -0500},
	Date-Modified = {2010-01-11 10:29:38 -0500},
	Doi = {10.1038/336598a0},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; DNA-Binding Proteins; Drosophila melanogaster; Genes, Homeobox; Hela Cells; Molecular Sequence Data; Plasmids; Regulatory Sequences, Nucleic Acid; Sequence Homology, Nucleic Acid; Transcription Factors; Transfection},
	Month = {Dec},
	Number = {6199},
	Pages = {598-601},
	Pmid = {2904655},
	Title = {Drosophila homoeotic genes encode transcriptional activators similar to mammalian OTF-2},
	Volume = {336},
	Year = {1988},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/336598a0}}

@article{Kuraku:2009dq,
	Abstract = {Hox genes are known to specify spatial identities along the anterior-posterior axis during embryogenesis. In vertebrates and most other deuterostomes, they are arranged in sets of uninterrupted clusters on chromosomes, and are in most cases expressed in a "colinear" fashion, in which genes closer to the 3-end of the Hox clusters are expressed earlier and more anteriorly and genes close to the 5-end of the clusters later and more posteriorly. In this review, we summarize the current understanding of how Hox gene clusters have been modified from basal lineages of deuterostomes to diverse taxa of vertebrates. Our parsimony reconstruction of Hox cluster architecture at various stages of vertebrate evolution highlights that the variation in Hox cluster structures among jawed vertebrates is mostly due to secondary lineage-specific gene losses and an additional genome duplication that occurred in the actinopterygian stem lineage, the teleost-specific genome duplication (TSGD).},
	Author = {Kuraku, Shigehiro and Meyer, Axel},
	Date-Added = {2010-01-11 10:18:27 -0500},
	Date-Modified = {2010-01-11 10:18:27 -0500},
	Doi = {10.1387/ijdb.072533km},
	Journal = {Int J Dev Biol},
	Journal-Full = {The International journal of developmental biology},
	Mesh = {Animals; Body Patterning; Cell Lineage; Developmental Biology; Evolution, Molecular; Fishes; Gene Expression Regulation, Developmental; Genes, Homeobox; Genome; Models, Genetic; Multigene Family},
	Number = {5-6},
	Pages = {765-73},
	Pmid = {19557682},
	Title = {The evolution and maintenance of Hox gene clusters in vertebrates and the teleost-specific genome duplication},
	Volume = {53},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1387/ijdb.072533km}}

@article{Ogishima:2007bh,
	Abstract = {Hox cluster has key roles in regulating the patterning of the antero-posterior axis in a metazoan embryo. It consists of the anterior, central and posterior genes; the central genes have been identified only in bilaterians, but not in cnidarians, and are responsible for archiving morphological complexity in bilaterian development. However, their evolutionary history has not been revealed, that is, there has been a "missing link". Here we show the evolutionary history of Hox clusters of 18 bilaterians and 2 cnidarians by using a new method, "motif-based reconstruction", examining the gain/loss processes of evolutionarily conserved sequences, "motifs", outside the homeodomain. We successfully identified the missing link in the evolution of Hox clusters between the cnidarian-bilaterian ancestor and the bilaterians as the ancestor of the central genes, which we call the proto-central gene. Exploring the correspondent gene with the proto-central gene, we found that one of the acoela Hox genes has the same motif repertory as that of the proto-central gene. This interesting finding suggests that the acoela Hox cluster corresponds with the missing link in the evolution of the Hox cluster between the cnidarian-bilaterian ancestor and the bilaterians. Our findings suggested that motif gains/diversifications led to the explosive diversity of the bilaterian body plan.},
	Author = {Ogishima, Soichi and Tanaka, Hiroshi},
	Date-Added = {2010-01-11 10:14:36 -0500},
	Date-Modified = {2010-01-11 10:14:36 -0500},
	Doi = {10.1016/j.gene.2006.08.011},
	Journal = {Gene},
	Journal-Full = {Gene},
	Mesh = {Amino Acid Motifs; Animals; Cluster Analysis; Cnidaria; Computational Biology; Evolution, Molecular; Genes, Homeobox; Homeodomain Proteins; Multigene Family; Phylogeny},
	Month = {Jan},
	Number = {1-2},
	Pages = {21-30},
	Pmid = {17098381},
	Title = {Missing link in the evolution of Hox clusters},
	Volume = {387},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.gene.2006.08.011}}

@article{Lanfear:2008qf,
	Abstract = {The Hox genes encode transcription factors that play vital roles in the anterior-posterior patterning of all bilaterian phyla studied to date. Additionally, the gain of Hox genes by duplication has been widely implicated as a driving force in the evolution of animal body plans. Because of this, reconstructing the evolution of the Hox cluster has been the focus of intense research interest. It has been commonly assumed that an ancestral four-gene ProtoHox cluster was duplicated early in animal evolution to give rise to the Hox and ParaHox clusters. However, this hypothesis has recently been called into question, and a number of alternative hypotheses of Hox and ParaHox gene evolution have been proposed. Here, we present the first statistical comparisons of current hypotheses of Hox and ParaHox gene evolution. We use two statistical methods that represent two different approaches to the treatment of phylogenetic uncertainty. In the first method, we estimate the maximum-likelihood tree for each hypothesis and compare these trees to one another using a parametric bootstrapping approach. In the second method, we use Bayesian phylogenetics to estimate the posterior distribution of trees, then we calculate the support for each hypothesis from this distribution. The results of both methods are largely congruent. We find that we are able to reject five out of the eight current hypotheses of Hox and ParaHox gene evolution that we consider. We conclude that the ProtoHox cluster is likely to have contained either three or four genes but that there is insufficient phylogenetic signal in the homeodomains to distinguish between these alternatives.},
	Author = {Lanfear, Robert and Bromham, Lindell},
	Date-Added = {2010-01-11 10:11:56 -0500},
	Date-Modified = {2010-01-11 10:11:56 -0500},
	Doi = {10.1080/10635150802430079},
	Journal = {Syst Biol},
	Journal-Full = {Systematic biology},
	Mesh = {Animals; Cluster Analysis; Evolution, Molecular; Homeodomain Proteins; Invertebrates; Mice; Models, Genetic; Multigene Family; Phylogeny; Plants; Transcription Factors},
	Month = {Oct},
	Number = {5},
	Pages = {708-18},
	Pmid = {18853358},
	Title = {Statistical tests between competing hypotheses of Hox cluster evolution},
	Volume = {57},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1080/10635150802430079}}

@article{Kuratani:2009ve,
	Abstract = {Modules can be defined as quasi-autonomous units that are connected loosely with each other within a system. A need for the concept of modularity has emerged as we deal with evolving organisms in evolutionary developmental research, especially because it is unknown how genes are associated with anatomical patterns. One of the strategies to link genotypes with phenotypes could be to relate developmental modules with morphological ones. To do this, it is fundamental to grasp the context in which certain anatomical units and developmental processes are associated with each other specifically. By identifying morphological modularities as units recognized by some categories of general homology as established by comparative anatomy, it becomes possible to identify developmental modules whose genetic components exhibit coextensive expressions. This permits us to distinguish the evolutionary modification in which the identical morphological module simply alters its shape for adaptation, without being decoupled from the functioning gene network ('coupled modularities'), from the evolution of novelty that involves a heterotopic shift between the anatomical and developmental modules. Using this formulation, it becomes possible, within the realm of Geoffroy's homologous networks, to reduce morphological homologies to developmental mechanistic terms by dissociating certain classes of modules that are often associated with actual shapes and functions.},
	Author = {Kuratani, Shigeru},
	Date-Added = {2010-01-11 10:10:09 -0500},
	Date-Modified = {2010-01-11 10:10:09 -0500},
	Doi = {10.1016/j.ydbio.2009.05.564},
	Journal = {Dev Biol},
	Journal-Full = {Developmental biology},
	Mesh = {Animals; Embryology; Evolution; Growth and Development; Jaw; Lampreys},
	Month = {Aug},
	Number = {1},
	Pages = {61-9},
	Pmid = {19467227},
	Title = {Modularity, comparative embryology and evo-devo: developmental dissection of evolving body plans},
	Volume = {332},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.ydbio.2009.05.564}}

@article{Singh:2008ly,
	Abstract = {Responses to extracellular stress directly confer survival fitness by means of complex regulatory networks. Despite their complexity, the networks must be evolvable because of changing ecological and environmental pressures. Although the regulatory networks underlying stress responses are characterized extensively, their mechanism of evolution remains poorly understood. Here, we examine the evolution of three candidate stress response networks (chemotaxis, competence for DNA uptake, and endospore formation) by analyzing their phylogenetic distribution across several hundred diverse bacterial and archaeal lineages. We report that genes in the chemotaxis and sporulation networks group into well defined evolutionary modules with distinct functions, phenotypes, and substitution rates as compared with control sets of randomly chosen genes. The evolutionary modules vary in both number and cohesiveness among the three pathways. Chemotaxis has five coherent modules whose distribution among species shows a clear pattern of interdependence and rewiring. Sporulation, by contrast, is nearly monolithic and seems to be inherited vertically, with three weak modules constituting early and late stages of the pathway. Competence does not seem to exhibit well defined modules either at or below the pathway level. Many of the detected modules are better understood in engineering terms than in protein functional terms, as we demonstrate using a control-based ontology that classifies gene function according to roles such as "sensor," "regulator," and "actuator." Moreover, we show that combinations of the modules predict phenotype, yet surprisingly do not necessarily correlate with phylogenetic inheritance. The architectures of these three pathways are therefore emblematic of different modes and constraints on evolution.},
	Author = {Singh, Amoolya H and Wolf, Denise M and Wang, Peggy and Arkin, Adam P},
	Date-Added = {2010-01-11 10:08:12 -0500},
	Date-Modified = {2010-01-11 10:08:12 -0500},
	Doi = {10.1073/pnas.0709764105},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Archaea; Bacteria; Chemotaxis; DNA; Environment; Evolution; Gene Regulatory Networks; Phenotype; Spores},
	Month = {May},
	Number = {21},
	Pages = {7500-5},
	Pmid = {18495925},
	Title = {Modularity of stress response evolution},
	Volume = {105},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0709764105}}

@article{Peregrin-Alvarez:2009zr,
	Abstract = {BACKGROUND: Cellular metabolism is a fundamental biological system consisting of myriads of enzymatic reactions that together fulfill the basic requirements of life. The recent availability of vast amounts of sequence data from diverse sets of organisms provides an opportunity to systematically examine metabolism from a comparative perspective. Here we supplement existing genome and protein resources with partial genome datasets derived from 193 eukaryotes to present a comprehensive survey of the conservation of metabolism across 26 taxa representing the three domains of life. RESULTS: In general, metabolic enzymes are highly conserved. However, organizing these enzymes within the context of functional pathways revealed a spectrum of conservation from those that are highly conserved (for example, carbohydrate, energy, amino acid and nucleotide metabolism enzymes) to those specific to individual taxa (for example, those involved in glycan metabolism and secondary metabolite pathways). Applying a novel co-conservation analysis, KEGG defined pathways did not generally display evolutionary coherence. Instead, such modularity appears restricted to smaller subsets of enzymes. Expanding analyses to a global metabolic network revealed a highly conserved, but nonetheless flexible, 'core' of enzymes largely involved in multiple reactions across different pathways. Enzymes and pathways associated with the periphery of this network were less well conserved and associated with taxon-specific innovations. CONCLUSIONS: These findings point to an emerging picture in which a core of enzyme activities involving amino acid, energy, carbohydrate and lipid metabolism have evolved to provide the basic functions required for life. However, the precise complement of enzymes associated within this core for each species is flexible.},
	Author = {Peregr{\'\i}n-Alvarez, Jos{\'e} M and Sanford, Chris and Parkinson, John},
	Date-Added = {2010-01-11 10:05:34 -0500},
	Date-Modified = {2010-01-11 10:05:34 -0500},
	Doi = {10.1186/gb-2009-10-6-r63},
	Journal = {Genome Biol},
	Journal-Full = {Genome biology},
	Mesh = {Databases, Protein; Enzymes; Evolution, Molecular; Genome; Metabolic Networks and Pathways},
	Number = {6},
	Pages = {R63},
	Pmid = {19523219},
	Title = {The conservation and evolutionary modularity of metabolism},
	Volume = {10},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/gb-2009-10-6-r63}}

@article{Gavin:2006ys,
	Abstract = {Protein complexes are key molecular entities that integrate multiple gene products to perform cellular functions. Here we report the first genome-wide screen for complexes in an organism, budding yeast, using affinity purification and mass spectrometry. Through systematic tagging of open reading frames (ORFs), the majority of complexes were purified several times, suggesting screen saturation. The richness of the data set enabled a de novo characterization of the composition and organization of the cellular machinery. The ensemble of cellular proteins partitions into 491 complexes, of which 257 are novel, that differentially combine with additional attachment proteins or protein modules to enable a diversification of potential functions. Support for this modular organization of the proteome comes from integration with available data on expression, localization, function, evolutionary conservation, protein structure and binary interactions. This study provides the largest collection of physically determined eukaryotic cellular machines so far and a platform for biological data integration and modelling.},
	Author = {Gavin, Anne-Claude and Aloy, Patrick and Grandi, Paola and Krause, Roland and Boesche, Markus and Marzioch, Martina and Rau, Christina and Jensen, Lars Juhl and Bastuck, Sonja and D{\"u}mpelfeld, Birgit and Edelmann, Angela and Heurtier, Marie-Anne and Hoffman, Verena and Hoefert, Christian and Klein, Karin and Hudak, Manuela and Michon, Anne-Marie and Schelder, Malgorzata and Schirle, Markus and Remor, Marita and Rudi, Tatjana and Hooper, Sean and Bauer, Andreas and Bouwmeester, Tewis and Casari, Georg and Drewes, Gerard and Neubauer, Gitte and Rick, Jens M and Kuster, Bernhard and Bork, Peer and Russell, Robert B and Superti-Furga, Giulio},
	Date-Added = {2010-01-11 10:05:33 -0500},
	Date-Modified = {2010-01-11 10:05:33 -0500},
	Doi = {10.1038/nature04532},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Genome, Fungal; Multiprotein Complexes; Open Reading Frames; Phenotype; Proteome; Proteomics; Saccharomyces cerevisiae; Saccharomyces cerevisiae Proteins},
	Month = {Mar},
	Number = {7084},
	Pages = {631-6},
	Pmid = {16429126},
	Title = {Proteome survey reveals modularity of the yeast cell machinery},
	Volume = {440},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature04532}}

@article{Rokas:2008vn,
	Abstract = {Multicellularity appeared early and repeatedly in life's history; its instantiations presumably required the confluence of environmental, ecological, and genetic factors. Comparisons of several independently evolved pairs of multicellular and unicellular relatives indicate that transitions to multicellularity are typically associated with increases in the numbers of genes involved in cell differentiation, cell-cell communication, and adhesion. Further examination of the DNA record suggests that these increases in gene complexity are the product of evolutionary innovation, tinkering, and expansion of genetic material. Arguably, the most decisive multicellular transition was the emergence of animals. Decades of developmental work have demarcated the genetic toolkit for animal multicellularity, a select set of a few hundred genes from a few dozen gene families involved in adhesion, communication, and differentiation. Examination of the DNA records of the earliest-branching animal phyla and their closest protist relatives has begun to shed light on the origins and assembly of this toolkit. Emerging data favor a model of gradual assembly, with components originating and diversifying at different time points prior to or shortly after the origin of animals.},
	Author = {Rokas, Antonis},
	Date-Added = {2010-01-11 09:57:43 -0500},
	Date-Modified = {2010-01-11 09:57:43 -0500},
	Doi = {10.1146/annurev.genet.42.110807.091513},
	Journal = {Annu Rev Genet},
	Journal-Full = {Annual review of genetics},
	Mesh = {Animals; Bacteria; Bacterial Physiological Phenomena; Cell Adhesion; Cell Communication; Cell Differentiation; Eukaryota; Eukaryotic Cells; Evolution; Phylogeny; Transcription, Genetic},
	Pages = {235-51},
	Pmid = {18983257},
	Title = {The origins of multicellularity and the early history of the genetic toolkit for animal development},
	Volume = {42},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1146/annurev.genet.42.110807.091513}}

@article{Hanada:2009kx,
	Abstract = {The differentiation of both gene expression and protein function is thought to be important as a mechanism of the functionalization of duplicate genes. However, it has not been addressed whether expression or protein divergence of duplicate genes is greater in those genes that have undergone functionalization compared with those that have not. We examined a total of 492 paralogous gene pairs associated with morphological diversification in a plant model organism (Arabidopsis thaliana). Classifying these paralogous gene pairs into high, low, and no morphological diversification groups, based on knock-out data, we found that the divergence rate of both gene expression and protein sequences were significantly higher in either high or low morphological diversification groups compared with those in the no morphological diversification group. These results strongly suggest that the divergence of both expression and protein sequence are important sources for morphological diversification of duplicate genes. Although both mechanisms are not mutually exclusive, our analysis suggested that changes of expression pattern play the minor role (33\%-41\%) and that changes of protein sequence play the major role (59\%-67\%) in morphological diversification. Finally, we examined to what extent duplicate genes are associated with expression or protein divergence exerting morphological diversification at the whole-genome level. Interestingly, duplicate genes randomly chosen from A. thaliana had not experienced expression or protein divergence that resulted in morphological diversification. These results indicate that most duplicate genes have experienced minor functionalization.},
	Author = {Hanada, Kousuke and Kuromori, Takashi and Myouga, Fumiyoshi and Toyoda, Tetsuro and Shinozaki, Kazuo},
	Date-Added = {2010-01-11 09:53:36 -0500},
	Date-Modified = {2010-01-11 09:53:36 -0500},
	Doi = {10.1371/journal.pgen.1000781},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Month = {Dec},
	Number = {12},
	Pages = {e1000781},
	Pmid = {20041196},
	Title = {Increased expression and protein divergence in duplicate genes is associated with morphological diversification},
	Volume = {5},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000781}}

@article{Carroll:2000uq,
	Author = {Carroll, S B},
	Date-Added = {2010-01-11 09:49:51 -0500},
	Date-Modified = {2010-01-11 09:49:51 -0500},
	Journal = {Cell},
	Journal-Full = {Cell},
	Mesh = {Animals; Body Patterning; Evolution; Gene Expression Regulation, Developmental; Genetic Variation; Humans},
	Month = {Jun},
	Number = {6},
	Pages = {577-80},
	Pmid = {10892643},
	Title = {Endless forms: the evolution of gene regulation and morphological diversity},
	Volume = {101},
	Year = {2000}}

@article{Erwin:2009fk,
	Abstract = {Whole-genome sequences from the choanoflagellate Monosiga brevicollis, the placozoan Trichoplax adhaerens and the cnidarian Nematostella vectensis have confirmed results from comparative evolutionary developmental studies that much of the developmental toolkit once thought to be characteristic of bilaterians appeared much earlier in the evolution of animals. The diversity of transcription factors and signalling pathway genes in animals with a limited number of cell types and a restricted developmental repertoire is puzzling, particularly in light of claims that such highly conserved elements among bilaterians provide evidence of a morphologically complex protostome-deuterostome ancestor. Here, I explore the early origination of elements of what became the bilaterian toolkit, and suggest that placozoans and cnidarians represent a depauperate residue of a once more diverse assemblage of early animals, some of which may be represented in the Ediacaran fauna (c. 585-542 Myr ago).},
	Author = {Erwin, Douglas H},
	Date-Added = {2010-01-11 09:47:22 -0500},
	Date-Modified = {2010-01-11 09:47:22 -0500},
	Doi = {10.1098/rstb.2009.0038},
	Journal = {Philos Trans R Soc Lond B Biol Sci},
	Journal-Full = {Philosophical transactions of the Royal Society of London. Series B, Biological sciences},
	Mesh = {Animals; Anthozoa; Eukaryota; Evolution; Evolution, Molecular; Fossils; Gene Expression Regulation, Developmental; Growth and Development; Phylogeny; Placozoa; Signal Transduction; Species Specificity; Transcription Factors},
	Month = {Aug},
	Number = {1527},
	Pages = {2253-61},
	Pmid = {19571245},
	Title = {Early origin of the bilaterian developmental toolkit},
	Volume = {364},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1098/rstb.2009.0038}}

@article{Yeh:2004uq,
	Abstract = {Identification of novel targets for the development of more effective antimalarial drugs and vaccines is a primary goal of the Plasmodium genome project. However, deciding which gene products are ideal drug/vaccine targets remains a difficult task. Currently, a systematic disruption of every single gene in Plasmodium is technically challenging. Hence, we have developed a computational approach to prioritize potential targets. A pathway/genome database (PGDB) integrates pathway information with information about the complete genome of an organism. We have constructed PlasmoCyc, a PGDB for Plasmodium falciparum 3D7, using its annotated genomic sequence. In addition to the annotations provided in the genome database, we add 956 additional annotations to proteins annotated as "hypothetical" using the GeneQuiz annotation system. We apply a novel computational algorithm to PlasmoCyc to identify 216 "chokepoint enzymes." All three clinically validated drug targets are chokepoint enzymes. A total of 87.5\% of proposed drug targets with biological evidence in the literature are chokepoint reactions. Therefore, identifying chokepoint enzymes represents one systematic way to identify potential metabolic drug targets.},
	Author = {Yeh, Iwei and Hanekamp, Theodor and Tsoka, Sophia and Karp, Peter D and Altman, Russ B},
	Date-Added = {2010-01-06 16:53:08 -0500},
	Date-Modified = {2010-01-06 16:53:08 -0500},
	Doi = {10.1101/gr.2050304},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Algorithms; Animals; Catalysis; Computational Biology; Databases, Genetic; Enzyme Inhibitors; Escherichia coli; Escherichia coli Proteins; Genes, Bacterial; Genes, Essential; Genes, Protozoan; Genome, Protozoan; Genomics; Humans; Models, Chemical; Plasmodium falciparum; Predictive Value of Tests; Protozoan Proteins; Software; Substrate Specificity},
	Month = {May},
	Number = {5},
	Pages = {917-24},
	Pmid = {15078855},
	Title = {Computational analysis of Plasmodium falciparum metabolism: organizing genomic information to facilitate drug discovery},
	Volume = {14},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.2050304}}

@article{Qin:2003fk,
	Abstract = {To study the evolution of the yeast protein interaction network, we first classified yeast proteins by their evolutionary histories into isotemporal categories, then analyzed the interaction tendencies within and between the categories, and finally reconstructed the main growth path. We found that two proteins tend to interact with each other if they are in the same or similar categories, but tended to avoid each other otherwise, and that network evolution mirrors the universal tree of life. These observations suggest synergistic selection during network evolution and provide insights into the hierarchical modularity of cellular networks.},
	Author = {Qin, Hong and Lu, Henry H S and Wu, Wei B and Li, Wen-Hsiung},
	Date-Added = {2010-01-06 16:45:09 -0500},
	Date-Modified = {2010-01-06 16:45:09 -0500},
	Doi = {10.1073/pnas.2235584100},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Databases, Genetic; Evolution; Fungi; Genome, Fungal; Models, Biological; Neural Networks (Computer); Phylogeny; Saccharomyces cerevisiae; Saccharomyces cerevisiae Proteins},
	Month = {Oct},
	Number = {22},
	Pages = {12820-4},
	Pmid = {14557537},
	Title = {Evolution of the yeast protein interaction network},
	Volume = {100},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.2235584100}}

@article{Keeling2005601,
	Author = {Patrick J Keeling and Claudio H Slamovits},
	Date-Added = {2010-01-06 15:16:08 -0500},
	Date-Modified = {2010-01-06 15:17:37 -0500},
	Doi = {DOI: 10.1016/j.gde.2005.09.003},
	Issn = {0959-437X},
	Journal = {Current Opinion in Genetics and Development},
	Note = {Genomes and evolution},
	Number = {6},
	Pages = {601 - 608},
	Title = {Causes and effects of nuclear genome reduction},
	Url = {http://www.sciencedirect.com/science/article/B6VS0-4H68T0H-2/2/881e07a45c9b039652e16527096a7825},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://www.sciencedirect.com/science/article/B6VS0-4H68T0H-2/2/881e07a45c9b039652e16527096a7825},
	Bdsk-Url-2 = {http://dx.doi.org/10.1016/j.gde.2005.09.003}}

@article{YANG:1994ly,
	Abstract = {Two approximate methods are proposed for maximum likelihood phylogenetic estimation, which allow variable rates of substitution across nucleotide sites. Three data sets with quite different characteristics were analyzed to examine empirically the performance of these methods. The first, called the ''discrete gamma model,'' uses several categories of rates to approximate the gamma distribution, with equal probability for each category. The mean of each category is used to represent all the rates falling in the category. The performance of this method is found to be quite good, and four such categories appear to be sufficient to produce both an optimum, or near-optimum fit by the model to the data, and also an acceptable approximation to the continuous distribution. The second method, called ''fixed-rates model,'' classifies sites into several classes according to their rates predicted assuming the star tree. Sites in different classes are then assumed to be evolving at these fixed rates when other tree topologies are evaluated. Analyses of the data sets suggest that this method can produce reasonable results, but it seems to share some properties of a least-squares pairwise comparison; for example, interior branch lengths in nonbest trees are often found to be zero. The computational requirements of the two methods are comparable to that of Felsenstein's (1981, J Mol Evol 17:368-376) model, which assumes a single rate for all the sites.},
	Address = {175 FIFTH AVE, NEW YORK, NY 10010},
	Author = {YANG, ZH},
	Date-Added = {2010-01-06 15:00:14 -0500},
	Date-Modified = {2010-01-06 15:00:14 -0500},
	Isi = {A1994PB53900008},
	Isi-Recid = {88167305},
	Isi-Ref-Recids = {32346846 22920316 46096712 14019453 43930323 15413015 18712737 58132842 82166166 69062859 75779273 57684838 74511222 84765867 85384144 71151850 75162822 73521013 74589589 60323569 69760211 83481386 78148561 19965926 85302229 88167306 88167307 86599948 85384143},
	Journal = {Journal of Molecular Evolution},
	Keywords = {PHYLOGENY; MAXIMUM LIKELIHOOD; RATE VARIATION OVER SITES; THE GAMMA DISTRIBUTION; APPROXIMATE METHODS},
	Month = sep,
	Number = {3},
	Pages = {306-314},
	Publisher = {SPRINGER VERLAG},
	Times-Cited = {934},
	Title = {MAXIMUM-LIKELIHOOD PHYLOGENETIC ESTIMATION FROM DNA-SEQUENCES WITH VARIABLE RATES OVER SITES - APPROXIMATE METHODS},
	Volume = {39},
	Year = {1994},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A1994PB53900008}}

@article{10.1371/journal.pone.0001277,
	Abstract = {<sec><title>Background</title><p>Microsporidia are intracellular parasites that are highly-derived relatives of fungi. They have compacted genomes and, despite a high rate of sequence evolution, distantly related species can share high levels of gene order conservation. To date, only two species have been analysed in detail, and data from one of these largely consists of short genomic fragments. It is therefore difficult to determine how conservation has been maintained through microsporidian evolution, and impossible to identify whether certain regions are more prone to genomic stasis.</p></sec><sec><title>Principal Findings</title><p>Here, we analyse three large fragments of the <italic>Enterocytozoon bieneusi</italic> genome (in total 429 kbp), a species of medical significance. A total of 296 ORFs were identified, annotated and their context compared with <italic>Encephalitozoon cuniculi</italic> and <italic>Antonospora locustae</italic>. Overall, a high degree of conservation was found between all three species, and interestingly the level of conservation was similar in all three pairwise comparisons, despite the fact that <italic>A. locustae</italic> is more distantly related to <italic>E. cuniculi</italic> and <italic>E. bieneusi</italic> than either are to each other.</p></sec><sec><title>Conclusions/Significance</title><p>Any two genes that are found together in any pair of genomes are more likely to be conserved in the third genome as well, suggesting that a core of genes tends to be conserved across the entire group. The mechanisms of rearrangments identified among microsporidian genomes were consistent with a very slow evolution of their architecture, as opposed to the very rapid sequence evolution reported for these parasites.</p></sec>},
	Author = {Corradi, Nicolas AND Akiyoshi, Donna E. AND Morrison, Hilary G. AND Feng, Xiaochuan AND Weiss, Louis M. AND Tzipori, Saul AND Keeling, Patrick J.},
	Date-Added = {2010-01-06 14:53:16 -0500},
	Date-Modified = {2010-01-06 14:53:16 -0500},
	Doi = {10.1371/journal.pone.0001277},
	Journal = {PLoS ONE},
	Month = {12},
	Number = {12},
	Pages = {e1277},
	Publisher = {Public Library of Science},
	Title = {Patterns of Genome Evolution among the Microsporidian Parasites <italic>Encephalitozoon cuniculi</italic>, <italic>Antonospora locustae</italic> and <italic>Enterocytozoon bieneusi</italic>},
	Url = {http://dx.plos.org/10.1371%2Fjournal.pone.0001277},
	Volume = {2},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.plos.org/10.1371/journal.pone.0001277},
	Bdsk-Url-2 = {http://dx.doi.org/10.1371/journal.pone.0001277}}

@article{Nabholz:2008zr,
	Abstract = {Mitochondrial DNA (mtDNA) is the most popular marker of molecular diversity in animals, primarily because of its elevated mutation rate. After >20 years of intensive usage, the extent of mitochondrial evolutionary rate variations across species, their practical consequences on sequence analysis methods, and the ultimate reasons for mtDNA hypermutability are still largely unresolved issues. Using an extensive cytochrome b data set, fossil data, and taking advantage of the decoupled dynamics of synonymous and nonsynonymous substitutions, we measure the lineage-specific mitochondrial mutation rate across 1,696 mammalian species and compare it with the nuclear rate. We report an unexpected 2 orders of magnitude mitochondrial mutation rate variation between lineages: cytochrome b third codon positions are renewed every 1-2 Myr, in average, in the fastest evolving mammals, whereas it takes >100 Myr in slow-evolving lineages. This result has obvious implications in the fields of molecular phylogeny, molecular dating, and population genetics. Variations of mitochondrial substitution rate across species are partly explained by body mass, longevity, and age of female sexual maturity. The classical metabolic rate and generation time hypothesis, however, do not fully explain the observed patterns, especially a stronger effect of longevity in long-lived than in short-lived species. We propose that natural selection tends to decrease the mitochondrial mutation rate in long-lived species, in agreement with the mitochondrial theory of aging.},
	Address = {GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND},
	Author = {Nabholz, Benoit and Glemin, Sylvain and Galtier, Nicolas},
	Date-Added = {2010-01-06 14:49:17 -0500},
	Date-Modified = {2010-01-06 14:49:17 -0500},
	Doi = {DOI 10.1093/molbev/msm248},
	Isi = {000253375900013},
	Isi-Recid = {160942369},
	Isi-Ref-Recids = {135840568 133766079 113601763 149975403 153973679 160942370 98792669 36994231 136003778 89107817 144515274 134846680 130751461 142855421 150369836 151226614 109228298 54497548 130706986 128924249 152767903 148589584 137351079 142593682 121617491 142477071 115600846 137189560 131588237 117294781 132208064 128981752 149584049 121073565 146085470 152718431 14888862 155073695 158492412 63490746 127161877 149466888 93361774 79598889 83278082 128499601 125417885 94553864 98458264 94636976 160942371 149649250 107242888 85394438 115612907 160942372 86628633 156651902 118083293 66843278 134723375 103143847 143527277 74589577 118940325 118579716 128307960 136159182 142618564 89412910 108201948 149197598 155065520 145723322 106665281 154881665 115600864},
	Journal = {Molecular Biology and Evolution},
	Keywords = {mutation rate; mitochondrial DNA; theory of aging; mammals},
	Month = jan,
	Number = {1},
	Pages = {120-130},
	Publisher = {OXFORD UNIV PRESS},
	Times-Cited = {27},
	Title = {Strong variations of mitochondrial mutation rate across mammals - the longevity hypothesis},
	Volume = {25},
	Year = {2008},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000253375900013}}

@article{Andreasen:2001ys,
	Abstract = {Heterogeneous DNA substitution rates were found in the 18S-26S nuclear ribosomal DNA internal transcribed spacer (ITS) and external transcribed spacer (ETS) regions of Sidalcea (Malvaceae), a putatively young genus of annuals and perennials. The majority of comparisons revealed that the annual species had significantly higher molecular evolutionary rates than the perennials, whereas rates were consistently homogenous between obligate annual species. These findings led us to conclude that generation time or possibly another biological factor distinguishing annuals and perennials has influenced rates of molecular evolution in Sidalcea. The congruence of relative-rate test results across both spacer regions reinforced the association between life history and rate of rDNA evolution across lineages of checker mallows. Evolutionary rate variation within perennials mainly involved three basally divergent lineages. The faster rate in one lineage, Sidalcea stipularis, compared with other perennials may be the result of genetic drift in the only known, small, population. The other two basally divergent lineages had slower evolutionary rates compared with the remaining perennials; possible explanations for these differences include rate-reducing effects of a suffrutescent (rather than herbaceous) habit and seed dormancy.},
	Address = {PO BOX 1897, LAWRENCE, KS 66044-8897 USA},
	Author = {Andreasen, K and Baldwin, BG},
	Date-Added = {2010-01-06 14:48:43 -0500},
	Date-Modified = {2010-01-06 14:48:43 -0500},
	Isi = {000169180200005},
	Isi-Recid = {120277581},
	Isi-Ref-Recids = {109737038 110453610 109123114 91366739 106499516 103928759 80581833 92283261 58449901 94682489 65066120 112396774 99953169 99267367 101100749 80911171 97486512 95322524 102950688 120277582 116849195 41807846 109706292 100677961 116182177 114006853 119177469 83278082 79598889 80740347 113243722 87386271 108441872 106761962 54418326 112682805 92745162 110071648 108201948 92976075 71645932 55030334},
	Journal = {Molecular Biology and Evolution},
	Keywords = {sidalcea; internal/external transcribed spacers; 18S-26S nuclear ribosomal DNA; nucleotide substitution rates; generation time},
	Month = jun,
	Number = {6},
	Pages = {936-944},
	Publisher = {SOC MOLECULAR BIOLOGY EVOLUTION},
	Times-Cited = {45},
	Title = {Unequal evolutionary rates between annual and perennial lineages of checker mallows (Sidalcea, Malvaceae): Evidence from 18S-26S rDNA internal and external transcribed spacers},
	Volume = {18},
	Year = {2001},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000169180200005}}

@article{Takano:1998vn,
	Abstract = {Rate constancy of DNA sequence evolution was examined for three species of Drosophila, using two samples: the published sequences of eight genes from regions of the normal recombination rates and new data of the four AS-C (ac, sc, l'sc and ase) and ct genes. The AS-C and ci genes were chosen because these genes are located in the regions of very reduced recombination in Drosophila melanogaster and their locations remain unchanged throughout the entire lineages involved, yielding less effect of ancestral polymorphism in the study of rate constancy. The synonymous substitution pattern of the three lineages was found to be erratic in both samples. The dispersion index for replacement substitution was relatively high for the per, G6pd and ac genes. A significant heterogeneity was found in the number of synonymous substitutions in the three lineages between the two samples of genes with different recombination rates. This is partly due to a lack of the lineage effect in the D. melanogaster and Drosophila simulans lineages in the AS-C and ci genes in contrast to AKASHI'S observation of genes in regions of normal recombination. The higher codon bias in Drosophila yakuba as compared with D. melanogaster and D. simulans was observed in the four AS-C genes, which suggests change(s) in action of natural selection involved in codon usage on these genes. Fluctuating selection intensity may also be responsible for the observed locus-lineage interaction effects in synonymous substitution.},
	Address = {428 EAST PRESTON ST, BALTIMORE, MD 21202 USA},
	Author = {Takano, TS},
	Date-Added = {2010-01-06 14:48:12 -0500},
	Date-Modified = {2010-01-06 14:48:12 -0500},
	Isi = {000074028400042},
	Isi-Recid = {105554801},
	Isi-Ref-Recids = {90119556 97984361 66414321 84714562 86328356 67447937 79241356 77886567 70616364 98069438 84275566 84437010 97984296 70666448 80216430 37663022 92471120 97892233 91494676 1980534 48322904 90060050 92608922 94813560 73317821 89818483 41807846 82169447 85384117 25250638 29181054 102308295 61363043 79130454 76254773 41274631 79130463 94203060 43255445 100571271 37580382 89413649 89775467 94110694 20902775 72683716 82844183 98684296 80179839 68929990 92608921 90496259 61885937 62508372 73895449 94403226 63174517 57244292 31828558 84765887 55030334},
	Journal = {Genetics},
	Month = jun,
	Number = {2},
	Pages = {959-970},
	Publisher = {GENETICS},
	Times-Cited = {34},
	Title = {Rate variation of DNA sequence evolution in the Drosophila lineages},
	Volume = {149},
	Year = {1998},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000074028400042}}

@article{Huelsenbeck:1997kx,
	Abstract = {The use of molecular phylogenies to examine evolutionary questions has become commonplace with the automation of DNA sequencing and the availability of efficient computer programs to perform phylogenetic analyses. The application of computer simulation and likelihood ratio tests to evolutionary hypotheses represents a recent methodological development in this field. Likelihood ratio tests have enabled biologists to address many questions in evolutionary biology that have been difficult td resolve in the past, such as whether host-parasite systems are cospeciating and whether models of DNA substitution adequately explain observed sequences.},
	Address = {1200 NEW YORK AVE, NW, WASHINGTON, DC 20005},
	Author = {Huelsenbeck, JP and Rannala, B},
	Date-Added = {2010-01-06 14:44:04 -0500},
	Date-Modified = {2010-01-06 14:44:04 -0500},
	Isi = {A1997WT92500036},
	Isi-Recid = {99996694},
	Isi-Ref-Recids = {70629958 66046038 44188335 14019453 95931344 7648489 7648490 77793679 22364103 11845470 54497548 67748941 43930323 99996704 36391001 89818489 82166166 65140402 92471144 88132715 75043716 57684838 94187349 97209296 99457395 83672315 86005347 99996705 92572045 90983278 95139480 99457389 16311110 87135898 72714421 85228376 79668546 96191800 69760211 95243179 89818487 90920129 63833440 96451494 99457388 86599936 136893 86599948 87386291 88167305 96240950 85384143 91050076},
	Journal = {Science},
	Month = apr,
	Number = {5310},
	Pages = {227-232},
	Publisher = {AMER ASSOC ADVANCEMENT SCIENCE},
	Times-Cited = {479},
	Title = {Phylogenetic methods come of age: Testing hypotheses in an evolutionary context},
	Volume = {276},
	Year = {1997},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A1997WT92500036}}

@inbook{citeulike:2393468,
	Address = {New York},
	Author = {Zuckerkandl, E. and Pauling, L. B.},
	Booktitle = {Horizons in Biochemistry},
	Citeulike-Article-Id = {2393468},
	Date-Added = {2010-01-06 14:41:19 -0500},
	Date-Modified = {2010-01-06 14:41:19 -0500},
	Editor = {Kasha, M. and Pullman, B.},
	Keywords = {evolution, molecular\_clock},
	Pages = {189--225},
	Posted-At = {2008-02-18 11:19:54},
	Priority = {2},
	Publisher = {Academic Press},
	Title = {Molecular disease, evolution, and genetic heterogeneity},
	Year = {1962}}

@article{MARGOLIASH:1963uq,
	Address = {2101 CONSTITUTION AVE NW, WASHINGTON, DC 20418},
	Author = {Margoliash, E},
	Date-Added = {2010-01-06 14:38:36 -0500},
	Date-Modified = {2010-01-12 15:22:51 -0500},
	Isi = {A19639823B00024},
	Isi-Recid = {8857212},
	Isi-Ref-Recids = {7073712 8457272 8857213 7233844 8544236 7922412 8544240 4929640 8506446 8050536 8538009 8547315 6935548 8857214 8857215 7360418 7922655 7922646 6935562 6935563 7922653 8597842 5349643 5494808 6055864 7366349 7784059 8457274 8857216},
	Journal = {Proceedings of the National Academy of Sciences of the United States of America},
	Number = {4},
	Pages = {672-\&},
	Publisher = {NATL ACAD SCIENCES},
	Times-Cited = {158},
	Title = {PRIMARY STRUCTURE AND EVOLUTION OF CYTOCHROME C},
	Volume = {50},
	Year = {1963},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A19639823B00024}}

@article{Kumar:2005fk,
	Abstract = {During the past four decades, the molecular-clock hypothesis has provided an invaluable tool for building evolutionary timescales, and has served as a null model for testing evolutionary and mutation rates in different species. Molecular clocks have also influenced the development of theories of molecular evolution. As DNA-sequencing technologies have progressed, the use of molecular clocks has increased, with a profound effect on our understanding of the temporal diversification of species and genomes.},
	Address = {MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND},
	Author = {Kumar, S},
	Date-Added = {2010-01-06 14:32:24 -0500},
	Date-Modified = {2010-01-06 14:32:24 -0500},
	Doi = {DOI 10.1038/nrg1659},
	Isi = {000230880700018},
	Isi-Recid = {145620589},
	Isi-Ref-Recids = {122104872 95928669 145620590 132833885 133732352 142994430 103692980 101441920 125818308 129789664 143765771 143092882 58449901 14718748 98792669 128678027 114374885 123783612 21525451 134800266 142327681 99287968 135511857 49963193 20985149 94305638 9815815 95817179 132484919 113009052 135799611 103079589 32193120 109396824 54418324 80216430 37663022 143001733 8697681 17409617 49201034 26592509 86891675 108381586 117839953 38143698 64158897 132208064 70479893 125073071 118190460 95817177 129405104 134723384 133303413 97209350 128964502 36306663 115225284 136704835 14888862 50517071 31727565 16311110 72423913 23117610 120737296 104900702 123255371 17171215 25250638 87838091 61711128 55598857 8857212 11046759 79598889 83278082 8143328 42107147 41274631 106384971 113283375 80740347 118965587 115113308 61431238 20902775 134429498 86628633 103143847 128335190 5348089 13777131 14145573 68929990 9895275 124975197 128307960 101092325 84867578 62508372 92572039 133469639 124261030 126490069 108201948 90119532 108679457 127311022 32193114 97846734 55030334 145005057 127578112 11852521 8050612},
	Journal = {Nature Reviews Genetics},
	Month = aug,
	Number = {8},
	Pages = {654-662},
	Publisher = {NATURE PUBLISHING GROUP},
	Times-Cited = {39},
	Title = {Molecular clocks: four decades of evolution},
	Volume = {6},
	Year = {2005},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000230880700018}}

@article{Wittkopp:2009uq,
	Abstract = {Genetic changes contributing to phenotypic differences within or between species have been identified for a handful of traits, but the relationship between alleles underlying intraspecific polymorphism and interspecific divergence is largely unknown. We found that noncoding changes in the tan gene, as well as changes linked to the ebony gene, contribute to pigmentation divergence between closely related Drosophila species. Moreover, we found that alleles linked to tan and ebony fixed in one Drosophila species also contribute to variation within another species, and that multiple genotypes underlie similar phenotypes even within the same population. These alleles appear to predate speciation, which suggests that standing genetic variation present in the common ancestor gave rise to both intraspecific polymorphism and interspecific divergence.},
	Author = {Wittkopp, Patricia J and Stewart, Emma E and Arnold, Lisa L and Neidert, Adam H and Haerum, Belinda K and Thompson, Elizabeth M and Akhras, Saleh and Smith-Winberry, Gabriel and Shefner, Laura},
	Date-Added = {2009-12-16 13:46:58 -0500},
	Date-Modified = {2009-12-16 13:46:58 -0500},
	Doi = {10.1126/science.1176980},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Alleles; Animals; Animals, Genetically Modified; Base Sequence; Chromosomal Proteins, Non-Histone; Crosses, Genetic; DNA-Binding Proteins; Drosophila; Drosophila Proteins; Female; Gene Expression; Gene Expression Regulation; Genes, Insect; Genetic Speciation; Genotype; Introns; Male; Molecular Sequence Data; Phenotype; Pigmentation; Polymorphism, Genetic; Quantitative Trait Loci; Species Specificity},
	Month = {Oct},
	Number = {5952},
	Pages = {540-4},
	Pmid = {19900891},
	Title = {Intraspecific polymorphism to interspecific divergence: genetics of pigmentation in Drosophila},
	Volume = {326},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1176980}}

@article{Genome-10K-Community-of-Scientists:2009fk,
	Abstract = {The human genome project has been recently complemented by whole-genome assessment sequence of 32 mammals and 24 nonmammalian vertebrate species suitable for comparative genomic analyses. Here we anticipate a precipitous drop in costs and increase in sequencing efficiency, with concomitant development of improved annotation technology and, therefore, propose to create a collection of tissue and DNA specimens for 10,000 vertebrate species specifically designated for whole-genome sequencing in the very near future. For this purpose, we, the Genome 10K Community of Scientists (G10KCOS), will assemble and allocate a biospecimen collection of some 16,203 representative vertebrate species spanning evolutionary diversity across living mammals, birds, nonavian reptiles, amphibians, and fishes (ca. 60,000 living species). In this proposal, we present precise counts for these 16,203 individual species with specimens presently tagged and stipulated for DNA sequencing by the G10KCOS. DNA sequencing has ushered in a new era of investigation in the biological sciences, allowing us to embark for the first time on a truly comprehensive study of vertebrate evolution, the results of which will touch nearly every aspect of vertebrate biological enquiry.},
	Author = {{Genome 10K Community of Scientists}},
	Date = {2009 Nov-Dec},
	Date-Added = {2009-12-16 12:52:24 -0500},
	Date-Modified = {2009-12-16 12:52:24 -0500},
	Doi = {10.1093/jhered/esp086},
	Journal = {J Hered},
	Journal-Full = {The Journal of heredity},
	Number = {6},
	Pages = {659-74},
	Pmid = {19892720},
	Title = {Genome 10K: a proposal to obtain whole-genome sequence for 10,000 vertebrate species},
	Volume = {100},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/jhered/esp086}}

@article{Beaumont:2002la,
	Abstract = {We propose a new method for approximate Bayesian statistical inference on the basis of summary statistics. The method is suited to complex problems that arise in population genetics, extending ideas developed in this setting by earlier authors. Properties of the posterior distribution of a parameter, such as its mean or density curve, are approximated without explicit likelihood calculations. This is achieved by fitting a local-linear regression of simulated parameter values on simulated summary statistics, and then substituting the observed summary statistics into the regression equation. The method combines many of the advantages of Bayesian statistical inference with the computational efficiency of methods based on summary statistics. A key advantage of the method is that the nuisance parameters are automatically integrated out in the simulation step, so that the large numbers of nuisance parameters that arise in population genetics problems can be handled without difficulty. Simulation results indicate computational and statistical efficiency that compares favorably with those of alternative methods previously proposed in the literature. We also compare the relative efficiency of inferences obtained using methods based on summary statistics with those obtained directly from the data using MCMC.},
	Author = {Beaumont, Mark A and Zhang, Wenyang and Balding, David J},
	Date-Added = {2009-12-10 13:27:12 -0500},
	Date-Modified = {2009-12-10 13:27:12 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Bayes Theorem; Biometry; Chromosomes, Human, Y; Genetics, Population; Humans; Linear Models; Male; Models, Genetic; Regression Analysis},
	Month = {Dec},
	Number = {4},
	Pages = {2025-35},
	Pmid = {12524368},
	Title = {Approximate Bayesian computation in population genetics},
	Volume = {162},
	Year = {2002}}

@article{Marjoram:2003hf,
	Abstract = {Many stochastic simulation approaches for generating observations from a posterior distribution depend on knowing a likelihood function. However, for many complex probability models, such likelihoods are either impossible or computationally prohibitive to obtain. Here we present a Markov chain Monte Carlo method for generating observations from a posterior distribution without the use of likelihoods. It can also be used in frequentist applications, in particular for maximum-likelihood estimation. The approach is illustrated by an example of ancestral inference in population genetics. A number of open problems are highlighted in the discussion.},
	Author = {Marjoram, Paul and Molitor, John and Plagnol, Vincent and Tavare, Simon},
	Date-Added = {2009-11-24 10:11:09 -0500},
	Date-Modified = {2009-11-24 10:11:09 -0500},
	Doi = {10.1073/pnas.0306899100},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Algorithms; Computer Simulation; DNA; DNA, Mitochondrial; Evolution; Genetics, Population; Humans; Likelihood Functions; Markov Chains; Models, Biological; Monte Carlo Method; Stochastic Processes},
	Month = {Dec},
	Number = {26},
	Pages = {15324-8},
	Pmid = {14663152},
	Title = {Markov chain Monte Carlo without likelihoods},
	Volume = {100},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0306899100}}

@article{Gibert:2001tn,
	Abstract = {Most drosophilid species can be classified either as temperate or tropical. Adults of species were submitted to a cold treatment (0 degrees C) and then brought back to ambient temperature. They generally exhibited a chill coma and the time needed to recover was measured. We found in a set of 26 temperate species that recovery was rapid (average 1.8 min, range 0.15-4.9). In contrast, a long recovery time (average 56 min, range 24-120) was observed for 48 tropical species. A few species, like Drosophila melanogaster, are cosmopolitan and can proliferate under temperate and tropical climates. In 9 of 10 such species, slight genetic differences were found: a shorter recovery in temperate than in tropical populations. Comparing physiological data to phylogeny suggests that chill-coma tolerance has been a recurrent adaptation that is selected for in cold climates but tends to disappear under a permanently warm environment. This major climatic adaptation, evidenced in drosophilids, seems to occur in other insect groups also.},
	Author = {Gibert, P and Moreteau, B and P{\'e}tavy, G and Karan, D and David, J R},
	Date-Added = {2009-11-24 09:54:30 -0500},
	Date-Modified = {2009-11-24 09:54:30 -0500},
	Journal = {Evolution},
	Journal-Full = {Evolution; international journal of organic evolution},
	Mesh = {Acclimatization; Animals; Cold Climate; Coma; Drosophila; Drosophila melanogaster; Evolution; Phylogeny; Species Specificity; Time Factors; Tropical Climate},
	Month = {May},
	Number = {5},
	Pages = {1063-8},
	Pmid = {11430643},
	Title = {Chill-coma tolerance, a major climatic adaptation among Drosophila species},
	Volume = {55},
	Year = {2001}}

@article{Dworkin:2009vz,
	Abstract = {Genetic background effects contribute to the phenotypic consequences of mutations and are pervasive across all domains of life that have been examined, yet little is known about how they modify genetic systems. In part this is due to the lack of tractable model systems that have been explicitly developed to study the genetic and evolutionary consequences of background effects. In this study we demonstrate that phenotypic expressivity of the scalloped(E3) (sd(E3)) mutation of Drosophila melanogaster is background dependent and is the result of at least one major modifier segregating between two standard lab wild-type strains. We provide evidence that at least one of the modifiers is linked to the vestigial region and demonstrate that the background effects modify the spatial distribution of known sd target genes in a genotype-dependent manner. In addition, microarrays were used to examine the consequences of genetic background effects on the global transcriptome. Expression differences between wild-type strains were found to be as large as or larger than the effects of mutations with substantial phenotypic effects, and expression differences between wild type and mutant varied significantly between genetic backgrounds. Significantly, we demonstrate that the epistatic interaction between sd(E3) and an optomotor blind mutation is background dependent. The results are discussed within the context of developing a complex but more realistic view of the consequences of genetic background effects with respect to mutational analysis and studies of epistasis and cryptic genetic variation segregating in natural populations.},
	Author = {Dworkin, Ian and Kennerly, Erin and Tack, David and Hutchinson, Jennifer and Brown, Julie and Mahaffey, James and Gibson, Greg},
	Date-Added = {2009-11-24 09:44:57 -0500},
	Date-Modified = {2009-11-24 09:44:57 -0500},
	Doi = {10.1534/genetics.108.096453},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Drosophila Proteins; Drosophila melanogaster; Epistasis, Genetic; Gene Expression Regulation; Genetic Variation; Genome, Insect; Genomics; Linkage (Genetics); Molecular Sequence Data; Mutation; Nuclear Proteins; Oligonucleotide Array Sequence Analysis; Transcription Factors; Transcription, Genetic; Wing},
	Month = {Mar},
	Number = {3},
	Pages = {1065-76},
	Pmid = {19064709},
	Title = {Genomic consequences of background effects on scalloped mutant expressivity in the wing of Drosophila melanogaster},
	Volume = {181},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.108.096453}}

@article{Schreiber:2002dz,
	Abstract = {Hairless was identified as antagonist in the Notch signaling pathway based on genetic interactions. Molecularly, Hairless inhibits Notch target gene activation by directly binding to the Notch signal transducer Su(H). Additional functional domains apart from the Su(H) binding domain, however, suggest additional roles for the Hairless protein. To further our understanding of Hairless functions, we have performed a genetic screen for modifiers of a rough eye phenotype caused by overexpression of Hairless during eye development. A number of enhancers were identified that comprise mutations in components of Notch- and EGFR-signaling pathways, some unknown genes and the gene rugose. Mutant alleles of rugose display manifold genetic interactions with mutants in Notch and EGFR signaling pathway components. Accordingly, the rugose eye phenotype is rescued by Hairless and enhanced by Delta. Molecularly, interactions might occur at the protein level because rugose appears not to be a direct transcriptional target of Notch.},
	Author = {Schreiber, Simone L and Preiss, Anette and Nagel, Anja C and Wech, Irmgard and Maier, Dieter},
	Date-Added = {2009-11-24 09:44:19 -0500},
	Date-Modified = {2009-11-24 09:44:19 -0500},
	Doi = {10.1002/gene.10102},
	Journal = {Genesis},
	Journal-Full = {Genesis (New York, N.Y. : 2000)},
	Mesh = {A Kinase Anchor Proteins; Adaptor Proteins, Signal Transducing; Alleles; Animals; Carrier Proteins; DNA Mutational Analysis; Drosophila Proteins; Drosophila melanogaster; Eye; Gene Expression Regulation, Developmental; Genes, Dominant; In Situ Hybridization; Membrane Proteins; Mutation; Phenotype; RNA, Messenger; Receptors, Notch; Signal Transduction; Transcription Factors; Transcriptional Activation; Wing},
	Month = {Jul},
	Number = {3},
	Pages = {141-52},
	Pmid = {12124948},
	Title = {Genetic screen for modifiers of the rough eye phenotype resulting from overexpression of the Notch antagonist hairless in Drosophila},
	Volume = {33},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1002/gene.10102}}

@article{Shamloula:2002ta,
	Abstract = {In the developing Drosophila eye, cell fate determination and pattern formation are directed by cell-cell interactions mediated by signal transduction cascades. Mutations at the rugose locus (rg) result in a rough eye phenotype due to a disorganized retina and aberrant cone cell differentiation, which leads to reduction or complete loss of cone cells. The cone cell phenotype is sensitive to the level of rugose gene function. Molecular analyses show that rugose encodes a Drosophila A kinase anchor protein (DAKAP 550). Genetic interaction studies show that rugose interacts with the components of the EGFR- and Notch-mediated signaling pathways. Our results suggest that rg is required for correct retinal pattern formation and may function in cell fate determination through its interactions with the EGFR and Notch signaling pathways.},
	Author = {Shamloula, Hoda K and Mbogho, Mkajuma P and Pimentel, Angel C and Chrzanowska-Lightowlers, Zosia M A and Hyatt, Vanneta and Okano, Hideyuki and Venkatesh, Tadmiri R},
	Date-Added = {2009-11-24 09:43:44 -0500},
	Date-Modified = {2009-11-24 09:43:44 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {A Kinase Anchor Proteins; Adaptor Proteins, Signal Transducing; Animals; Calcium-Calmodulin-Dependent Protein Kinases; Carrier Proteins; DNA-Binding Proteins; Drosophila; Drosophila Proteins; Extracellular Signal-Regulated MAP Kinases; Eye Proteins; GTP-Binding Proteins; Genes, erbB-1; Membrane Proteins; Mutation; Phenotype; Photoreceptor Cells, Invertebrate; Retina; Signal Transduction; ras Proteins},
	Month = {Jun},
	Number = {2},
	Pages = {693-710},
	Pmid = {12072466},
	Title = {rugose (rg), a Drosophila A kinase anchor protein, is required for retinal pattern formation and interacts genetically with multiple signaling pathways},
	Volume = {161},
	Year = {2002}}

@article{Duman:1983oa,
	Author = {Duman, J and Horwath, K},
	Date-Added = {2009-11-24 08:35:46 -0500},
	Date-Modified = {2009-11-24 08:35:46 -0500},
	Doi = {10.1146/annurev.ph.45.030183.001401},
	Journal = {Annu Rev Physiol},
	Journal-Full = {Annual review of physiology},
	Mesh = {Adaptation, Physiological; Animals; Cold Temperature; Freezing; Hemolymph; Insects; Proteins},
	Pages = {261-70},
	Pmid = {6342517},
	Title = {The role of hemolymph proteins in the cold tolerance of insects},
	Volume = {45},
	Year = {1983},
	Bdsk-Url-1 = {http://dx.doi.org/10.1146/annurev.ph.45.030183.001401}}

@article{Bierne:2004db,
	Abstract = {The proportion of amino acid substitutions driven by adaptive evolution can potentially be estimated from polymorphism and divergence data by an extension of the McDonald-Kreitman test. We have developed a maximum-likelihood method to do this and have applied our method to several data sets from three Drosophila species: D. melanogaster, D. simulans, and D. yakuba. The estimated number of adaptive substitutions per codon is not uniformly distributed among genes, but follows a leptokurtic distribution. However, the proportion of amino acid substitutions fixed by adaptive evolution seems to be remarkably constant across the genome (i.e., the proportion of amino acid substitutions that are adaptive appears to be the same in fast-evolving and slow-evolving genes; fast-evolving genes have higher numbers of both adaptive and neutral substitutions). Our estimates do not seem to be significantly biased by selection on synonymous codon use or by the assumption of independence among sites. Nevertheless, an accurate estimate is hampered by the existence of slightly deleterious mutations and variations in effective population size. The analysis of several Drosophila data sets suggests that approximately 25\% +/- 20\% of amino acid substitutions were driven by positive selection in the divergence between D. simulans and D. yakuba.},
	Author = {Bierne, Nicolas and Eyre-Walker, Adam},
	Date-Added = {2009-11-24 08:29:43 -0500},
	Date-Modified = {2009-11-24 08:29:43 -0500},
	Doi = {10.1093/molbev/msh134},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Adaptation, Biological; Amino Acid Substitution; Animals; Codon; Drosophila; Genes, Insect; Genomics; Linkage Disequilibrium},
	Month = {Jul},
	Number = {7},
	Pages = {1350-60},
	Pmid = {15044594},
	Title = {The genomic rate of adaptive amino acid substitution in Drosophila},
	Volume = {21},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msh134}}

@article{Smith:2002dk,
	Abstract = {For over 30 years a central question in molecular evolution has been whether natural selection plays a substantial role in evolution at the DNA sequence level. Evidence has accumulated over the last decade that adaptive evolution does occur at the protein level, but it has remained unclear how prevalent adaptive evolution is. Here we present a simple method by which the number of adaptive substitutions can be estimated and apply it to data from Drosophila simulans and D. yakuba. We estimate that 45\% of all amino-acid substitutions have been fixed by natural selection, and that on average one adaptive substitution occurs every 45 years in these species.},
	Author = {Smith, Nick G C and Eyre-Walker, Adam},
	Date-Added = {2009-11-24 08:29:32 -0500},
	Date-Modified = {2009-11-24 08:29:32 -0500},
	Doi = {10.1038/4151022a},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Adaptation, Biological; Amino Acid Substitution; Animals; Computer Simulation; Drosophila; Drosophila Proteins; Evolution, Molecular; Genes, Insect; Models, Genetic; Polymorphism, Genetic; Selection (Genetics)},
	Month = {Feb},
	Number = {6875},
	Pages = {1022-4},
	Pmid = {11875568},
	Title = {Adaptive protein evolution in Drosophila},
	Volume = {415},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/4151022a}}

@article{Innan:2006ti,
	Abstract = {There are a number of polymorphism-based statistical tests of neutrality, but most of them focus on either the amount or the pattern of polymorphism. In this article, a new test called the two-dimensional (2D) test is developed. This test evaluates a pair of summary statistics in a two-dimensional field. One statistic should summarize the pattern of polymorphism, while the other could be a measure of the level of polymorphism. For the latter summary statistic, the polymorphism-divergence ratio is used following the idea of the Hudson-Kreitman-Aguad{\'e} (HKA) test. To incorporate the HKA test in the 2D test, a summary statistic-based version of the HKA test is developed such that the polymorphism-divergence ratio at a particular region of interest is examined if it is consistent with the average of those in other independent regions.},
	Author = {Innan, Hideki},
	Date-Added = {2009-11-19 13:13:15 -0500},
	Date-Modified = {2009-11-19 13:13:15 -0500},
	Doi = {10.1534/genetics.106.056242},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Computer Simulation; Data Interpretation, Statistical; Evaluation Studies as Topic; Genetics, Population; Likelihood Functions; Models, Genetic; Polymorphism, Genetic},
	Month = {Jul},
	Number = {3},
	Pages = {1725-33},
	Pmid = {16624905},
	Title = {Modified Hudson-Kreitman-Aguade test and two-dimensional evaluation of neutrality tests},
	Volume = {173},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.106.056242}}

@article{Pritchard:1999uz,
	Abstract = {We use variation at a set of eight human Y chromosome microsatellite loci to investigate the demographic history of the Y chromosome. Instead of assuming a population of constant size, as in most of the previous work on the Y chromosome, we consider a model which permits a period of recent population growth. We show that for most of the populations in our sample this model fits the data far better than a model with no growth. We estimate the demographic parameters of this model for each population and also the time to the most recent common ancestor. Since there is some uncertainty about the details of the microsatellite mutation process, we consider several plausible mutation schemes and estimate the variance in mutation size simultaneously with the demographic parameters of interest. Our finding of a recent common ancestor (probably in the last 120,000 years), coupled with a strong signal of demographic expansion in all populations, suggests either a recent human expansion from a small ancestral population, or natural selection acting on the Y chromosome.},
	Author = {Pritchard, J K and Seielstad, M T and Perez-Lezaun, A and Feldman, M W},
	Date-Added = {2009-11-19 13:04:43 -0500},
	Date-Modified = {2009-11-19 13:04:43 -0500},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Data Interpretation, Statistical; Evolution, Molecular; Genetic Variation; Geography; Humans; Microsatellite Repeats; Mutation; Sequence Analysis, DNA; Y Chromosome},
	Month = {Dec},
	Number = {12},
	Pages = {1791-8},
	Pmid = {10605120},
	Title = {Population growth of human Y chromosomes: a study of Y chromosome microsatellites},
	Volume = {16},
	Year = {1999}}

@article{Charlesworth:2006ty,
	Abstract = {Our understanding of balancing selection is currently becoming greatly clarified by new sequence data being gathered from genes in which polymorphisms are known to be maintained by selection. The data can be interpreted in conjunction with results from population genetics models that include recombination between selected sites and nearby neutral marker variants. This understanding is making possible tests for balancing selection using molecular evolutionary approaches. Such tests do not necessarily require knowledge of the functional types of the different alleles at a locus, but such information, as well as information about the geographic distribution of alleles and markers near the genes, can potentially help towards understanding what form of balancing selection is acting, and how long alleles have been maintained.},
	Author = {Charlesworth, Deborah},
	Date-Added = {2009-11-19 12:25:58 -0500},
	Date-Modified = {2009-11-19 12:25:58 -0500},
	Doi = {10.1371/journal.pgen.0020064},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Base Sequence; Chromosome Mapping; Evolution, Molecular; Female; Gene Frequency; Genetic Variation; Genome; Polymorphism, Genetic; Selection (Genetics); Time},
	Month = {Apr},
	Number = {4},
	Pages = {e64},
	Pmid = {16683038},
	Title = {Balancing selection and its effects on sequences in nearby genome regions},
	Volume = {2},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.0020064}}

@article{Hudson:1997co,
	Abstract = {Patterns of variation at the Sod locus of Drosophila melanogaster suggest that the protein polymorphism at this locus has very recently arisen. In addition, it appears that a previously rare DNA variant has been recently and rapidly driven to intermediate frequency. From the size of the region (>20 kb) that has been swept along with this rare variant, and patterns of linkage disequilibrium in the region, it is inferred that strength of selection was large (s > 0.01) and that the sweep occurred more than 25,000 generations ago. In addition, there are striking similarities to patterns of variation observed at the Est6 and Est-P loci, which are located approximately 1,000 kb from Sod.},
	Author = {Hudson, R R and S{\'a}ez, A G and Ayala, F J},
	Date-Added = {2009-11-19 12:17:38 -0500},
	Date-Modified = {2009-11-19 12:17:38 -0500},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Animals; DNA; Drosophila melanogaster; Linkage (Genetics); Polymorphism, Genetic; Selection (Genetics); Sequence Homology, Nucleic Acid; Superoxide Dismutase},
	Month = {Jul},
	Number = {15},
	Pages = {7725-9},
	Pmid = {9223255},
	Title = {DNA variation at the Sod locus of Drosophila melanogaster: an unfolding story of natural selection},
	Volume = {94},
	Year = {1997}}

@article{Zouros:1976hd,
	Abstract = {In species of repleta group of Drosophila about 70\% of the electrophoretic variability is absorbed by the same chromosome which absorbs about 70\% of the cytological variability of the group. However, this does not imply that inversions are actively involved in the maintenance of protein variation. A comparison of cytological and electrophoretic variation of homologous chromosomes points out that the amount of cytological polymorphism varies greatly over species of Drosophila while electrophoretic variation does not. This suggests that allelozymes do not constitute part of the coadapted complexes of genes characterizing the inversions. Rather, the amount of electropheptide molecule and is largely independent of factors such as background genotype and differences in the environment.},
	Author = {Zouros, E},
	Date-Added = {2009-11-19 12:11:39 -0500},
	Date-Modified = {2009-11-19 12:11:39 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Chromosome Aberrations; Chromosome Mapping; Drosophila; Electrophoresis; Genes; Genetic Variation; Heterozygote; Inversion, Chromosome; Isoenzymes; Linkage (Genetics); Polymorphism, Genetic; Species Specificity},
	Month = {May},
	Number = {1},
	Pages = {169-79},
	Pmid = {1269918},
	Title = {The distribution of enzyme and inversion polymorphism over the genome of Drosophila: evidence against balancing selection},
	Volume = {83},
	Year = {1976}}

@article{Begun:1999qf,
	Author = {Begun, D J and Betancourt, A J and Langley, C H and Stephan, W},
	Date-Added = {2009-11-19 12:05:28 -0500},
	Date-Modified = {2009-11-19 12:05:28 -0500},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Alcohol Dehydrogenase; Alleles; Animals; Drosophila melanogaster; Isoenzymes; Polymorphism, Genetic; Sequence Alignment; Sequence Analysis, DNA},
	Month = {Dec},
	Number = {12},
	Pages = {1816-9},
	Pmid = {10605124},
	Title = {Is the fast/slow allozyme variation at the Adh locus of Drosophila melanogaster an ancient balanced polymorphism?},
	Volume = {16},
	Year = {1999}}

@article{Kreitman:1991ea,
	Abstract = {The DNA sequences of 11 Drosophila melanogaster lines are compared across three contiguous regions, the Adh and Adh-dup loci and a noncoding 5' flanking region of Adh. Ninety-eight of approximately 4750 sites are segregating in the sample, 36 in the 5' flanking region, 38 in Adh and 24 in Adh-dup. Several methods are presented to test whether the patterns and levels of polymorphism are consistent with neutral molecular evolution. The analysis of within- and between-species polymorphism indicates that the region is evolving in a nonneutral and complex fashion. A graphical analysis of the data provides support for a hypothesized balanced polymorphism at or near position 1490, site of the amino acid replacement difference between Adhf and Adhs. The Adh-dup locus is less polymorphic than Adh and all 24 of its polymorphisms occur at low frequency--suggestive of a recent selective substitution in the Adh-dup region. Adhs alleles form two distinct evolutionary lineages that differ one from another at a total of nineteen sites in the Adh and Adh-dup loci. The polymorphisms are in complete linkage disequilibrium. A recombination experiment failed to find evidence for recombination suppression between the two allelic classes. Two hypotheses are presented to account for the widespread distribution of the two divergent lineages in natural populations. Natural selection appears to have played an important role in governing the overall patterns of nucleotide variation across the two-gene region.},
	Author = {Kreitman, M and Hudson, R R},
	Date-Added = {2009-11-19 12:01:06 -0500},
	Date-Modified = {2009-11-19 12:01:06 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Alcohol Dehydrogenase; Animals; Base Sequence; Drosophila melanogaster; Evolution; Gene Frequency; Genetic Variation; Molecular Sequence Data; Multigene Family; Polymerase Chain Reaction; Polymorphism, Genetic; Polymorphism, Restriction Fragment Length; Repetitive Sequences, Nucleic Acid},
	Month = {Mar},
	Number = {3},
	Pages = {565-82},
	Pmid = {1673107},
	Title = {Inferring the evolutionary histories of the Adh and Adh-dup loci in Drosophila melanogaster from patterns of polymorphism and divergence},
	Volume = {127},
	Year = {1991}}

@article{Pasvol:1978ls,
	Author = {Pasvol, G and Weatherall, D J and Wilson, R J},
	Date-Added = {2009-11-19 11:59:07 -0500},
	Date-Modified = {2009-11-19 11:59:07 -0500},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Anemia, Sickle Cell; Cells, Cultured; Erythrocytes, Abnormal; Hemoglobin, Sickle; Humans; Malaria; Oxygen; Plasmodium falciparum; Sickle Cell Trait},
	Month = {Aug},
	Number = {5672},
	Pages = {701-3},
	Pmid = {353566},
	Title = {Cellular mechanism for the protective effect of haemoglobin S against P. falciparum malaria},
	Volume = {274},
	Year = {1978}}

@article{Hughes:1990fh,
	Abstract = {Certain major-histocompatibility-complex (MHC) loci are highly polymorphic, and the mechanism of maintenance of this polymorphism remains controversial. Recent studies of the pattern of nucleotide substitution at MHC loci have produced strong evidence that this polymorphism is maintained mainly by positive Darwinian selection that operates on the antigen recognition site (ARS) of the MHC molecule. The ARS of the class I MHC consists of three subregions: (1) the binding cleft, (2) T-cell-receptor-directed residues, and (3) outward-directed residues. Here we report that the rate of nonsynonymous nucleotide substitution is much higher in the binding cleft than in the other ARS subregions. Furthermore, nonsynonymous nucleotide substitutions that result in a change of residue side-chain charge occur significantly more frequently than expected by chance. We conclude that the main target of positive selection on the class I MHC molecules is the binding cleft of the ARS and that this selection acts primarily to promote diversity among alleles with respect to the pattern of residue side-chain charges (charge profile) in the binding cleft. These results provide additional support for the hypothesis that MHC polymorphism is maintained by overdominant selection relating to antigen-binding capacity and thus to disease resistance.},
	Author = {Hughes, A L and Ota, T and Nei, M},
	Date-Added = {2009-11-19 11:57:54 -0500},
	Date-Modified = {2009-11-19 11:57:54 -0500},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Alleles; Amino Acids; Animals; Base Composition; Genes, MHC Class I; Genetic Variation; Histocompatibility Antigens Class I; Humans; Mice; Polymorphism, Genetic; Selection (Genetics)},
	Month = {Nov},
	Number = {6},
	Pages = {515-24},
	Pmid = {2283951},
	Title = {Positive Darwinian selection promotes charge profile diversity in the antigen-binding cleft of class I major-histocompatibility-complex molecules},
	Volume = {7},
	Year = {1990}}

@article{Nordborg:2005lt,
	Abstract = {We resequenced 876 short fragments in a sample of 96 individuals of Arabidopsis thaliana that included stock center accessions as well as a hierarchical sample from natural populations. Although A. thaliana is a selfing weed, the pattern of polymorphism in general agrees with what is expected for a widely distributed, sexually reproducing species. Linkage disequilibrium decays rapidly, within 50 kb. Variation is shared worldwide, although population structure and isolation by distance are evident. The data fail to fit standard neutral models in several ways. There is a genome-wide excess of rare alleles, at least partially due to selection. There is too much variation between genomic regions in the level of polymorphism. The local level of polymorphism is negatively correlated with gene density and positively correlated with segmental duplications. Because the data do not fit theoretical null distributions, attempts to infer natural selection from polymorphism data will require genome-wide surveys of polymorphism in order to identify anomalous regions. Despite this, our data support the utility of A. thaliana as a model for evolutionary functional genomics.},
	Author = {Nordborg, Magnus and Hu, Tina T and Ishino, Yoko and Jhaveri, Jinal and Toomajian, Christopher and Zheng, Honggang and Bakker, Erica and Calabrese, Peter and Gladstone, Jean and Goyal, Rana and Jakobsson, Mattias and Kim, Sung and Morozov, Yuri and Padhukasahasram, Badri and Plagnol, Vincent and Rosenberg, Noah A and Shah, Chitiksha and Wall, Jeffrey D and Wang, Jue and Zhao, Keyan and Kalbfleisch, Theodore and Schulz, Vincent and Kreitman, Martin and Bergelson, Joy},
	Date-Added = {2009-11-19 11:53:08 -0500},
	Date-Modified = {2009-11-19 11:53:08 -0500},
	Doi = {10.1371/journal.pbio.0030196},
	Journal = {PLoS Biol},
	Journal-Full = {PLoS biology},
	Mesh = {Arabidopsis; Gene Frequency; Genetics, Population; Polymorphism, Genetic; Polymorphism, Single Nucleotide},
	Month = {Jul},
	Number = {7},
	Pages = {e196},
	Pmid = {15907155},
	Title = {The pattern of polymorphism in Arabidopsis thaliana},
	Volume = {3},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pbio.0030196}}

@article{Rose:2004mw,
	Abstract = {We have used the naturally occurring plant-parasite system of Arabidopsis thaliana and its common parasite Peronospora parasitica (downy mildew) to study the evolution of resistance specificity in the host population. DNA sequence of the resistance gene, RPP13, from 24 accessions, including 20 from the United Kingdom, revealed amino acid sequence diversity higher than that of any protein coding gene reported so far in A. thaliana. A significant excess of amino acid polymorphism segregating within this species is localized within the leucine-rich repeat (LRR) domain of RPP13. These results indicate that single alleles of the gene have not swept through the population, but instead, a diverse collection of alleles have been maintained. Transgenic complementation experiments demonstrate functional differences among alleles in their resistance to various pathogen isolates, suggesting that the extreme amino acid polymorphism in RPP13 is maintained through continual reciprocal selection between host and pathogen.},
	Author = {Rose, Laura E and Bittner-Eddy, Peter D and Langley, Charles H and Holub, Eric B and Michelmore, Richard W and Beynon, Jim L},
	Date-Added = {2009-11-19 11:52:29 -0500},
	Date-Modified = {2009-11-19 11:52:29 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Alleles; Amino Acids; Arabidopsis; Base Sequence; Genes, Plant; Genetic Complementation Test; Genetic Variation; Geography; Great Britain; Host-Parasite Interactions; Immunity, Innate; Leucine; Molecular Sequence Data; Peronospora; Polymorphism, Genetic; Protein Structure, Tertiary; Recombination, Genetic; Selection (Genetics); Species Specificity; Transgenes},
	Month = {Mar},
	Number = {3},
	Pages = {1517-27},
	Pmid = {15082565},
	Title = {The maintenance of extreme amino acid diversity at the disease resistance gene, RPP13, in Arabidopsis thaliana},
	Volume = {166},
	Year = {2004}}

@article{Hiwatashi:2009hf,
	Abstract = {Color vision is an important characteristic of primates and, intriguingly, Neotropical monkeys are highly polymorphic for this trait. Recent field studies have challenged the conventional view that trichromatic color vision is more adaptive than dichromatic color vision. No study has investigated the pattern of genetic variation in the long to middle-wavelength sensitive (L-M or red-green) opsin gene as compared to that of other genomic regions (neutral references) in wild populations of New World monkeys to look for the signature of natural selection. Here we report such a study conducted on spider monkeys and capuchin monkeys inhabiting Santa Rosa National Park, Costa Rica. The nucleotide sequence of the L-M opsin gene was more polymorphic than the sequences of the neutral references, although the opsin gene sequences were not more divergent between the two species than were the sequences of the neutral references. In a coalescence simulation that took into account the observed nucleotide diversity of the neutral references, the Tajima's D value of the L-M opsin gene deviated significantly in a positive direction from the expected range. These results are the first to statistically demonstrate balancing selection acting on the polymorphic L-M opsin gene of New World monkeys. Taking the results of behavioral and genetic studies together, the balancing selection we detected may indicate that coexistence of different color vision types in the same population, also characteristic of humans, is adaptive.},
	Author = {Hiwatashi, Tomohide and Okabe, Yugo and Tsutsui, Toko and Hiramatsu, Chihiro and Melin, Amanda D and Oota, Hiroki and Schaffner, Colleen M and Aureli, Filippo and Fedigan, Linda M and Innan, Hideki and Kawamura, Shoji},
	Date-Added = {2009-11-19 11:51:22 -0500},
	Date-Modified = {2009-11-19 11:51:22 -0500},
	Doi = {10.1093/molbev/msp262},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Month = {Oct},
	Pmid = {19861643},
	Title = {An explicit signature of balancing selection for color vision variation in New World monkeys},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msp262}}

@article{Chowdhuri:2001kv,
	Abstract = {Expression of hsromega stress gene in the third-instar larvae of 951-lacZ2 (hsromega-lacZ having-844pb sequence) and 498-lacZ1 (hrsomega-lacZ having -498bp sequence) strains of Drosophila melanogaster at LC(50) and lower dietary concentrations of hexachlorocyclohexane (HCH) pentachlorophenol (PCP), and endosulfan was examined in relation to larval mortality by beta galactosidase activity, vital dye staining, and salivary gland polytene chromosome puffing. Our results showed that both HCH and PCP at lower concentrations evoked strong hsromega stress gene expression in the larval tissues while endosulfan did not. On the other hand, puffing data revealed that endosulfan at lower doses, induced well-developed puff at the resident site (93D) of the hsromega gene but the transgenic sites (30B in 951-lacZ2 and 44B in 498-lacZ1 strain) did not show any well-developed puff. Regression in hsromega stress gene expression in 951-lacZ2 strain at LC(50) concentrations of HCH and PCP after 48 h was concurrent with extensive tissue damage as evident by trypan blue staining. Similarly, strong hsromega expression was accompanied by insignificant trypan blue staining in the larval tissues of this strain after shorter duration of exposure (2-12 h) to these toxicants. Although endosulfan under similar experimental condition did not induce hsromega, strong trypan blue staining indicated extensive tissue damage after 48 h of exposure. The present study suggests that all the three toxicants pose cytotoxic potential to Drosophila. While protective role of this stress gene was evident at the initial stages of exposure, extensive tissue damage in the later stages of intoxication accompanied by autorepression of hsromega led to larval mortality. The study further suggests that -844bp upstream sequence of the gene is adequate for hsromega inducibility against HCH and PCP but not for endosulfan for which responsive elements may be searched further upstream.},
	Author = {Chowdhuri, D K and Nazir, A and Saxena, D K},
	Date-Added = {2009-11-19 11:13:57 -0500},
	Date-Modified = {2009-11-19 11:13:57 -0500},
	Journal = {J Biochem Mol Toxicol},
	Journal-Full = {Journal of biochemical and molecular toxicology},
	Mesh = {Animals; Animals, Genetically Modified; Drosophila; Genes, Reporter; Humans; Hydrocarbons, Chlorinated; Insecticides; Lac Operon; Stress, Physiological},
	Number = {4},
	Pages = {173-86},
	Pmid = {11673846},
	Title = {Effect of three chlorinated pesticides on hsromega stress gene in transgenic Drosophila melanogaster},
	Volume = {15},
	Year = {2001}}

@article{Akanksha:2008kl,
	Author = {Akanksha and Mallik, Moushami and Fatima, Roshan and Lakhotia, S C},
	Date-Added = {2009-11-19 11:07:45 -0500},
	Date-Modified = {2009-11-19 11:07:45 -0500},
	Journal = {J Genet},
	Journal-Full = {Journal of genetics},
	Mesh = {Alleles; Animals; DNA Transposable Elements; Drosophila melanogaster; Genes, Insect; Infertility, Male; Male; Promoter Regions, Genetic},
	Month = {Apr},
	Number = {1},
	Pages = {87-90},
	Pmid = {18560179},
	Title = {The hsromega(05241) allele of the noncoding hsromega gene of Drosophila melanogaster is not responsible for male sterility as reported earlier},
	Volume = {87},
	Year = {2008}}

@article{Rako:2007fb,
	Abstract = {Clinal variation in traits often reflects climatic adaptation; in Drosophila melanogaster clinal variation provides an opportunity to link variation in chromosomal inversions, microsatellite loci and various candidate genes to adaptive variation in traits. We undertook association studies with crosses from a single population of D. melanogaster from eastern Australia to investigate the association between genetic markers and traits showing clinal variation. By genotyping parents and phenotyping offspring, we minimized genotyping costs but had the power to detect association between markers and quantitative traits. Consistent with prior studies, we found strong associations between the clinal chromosomal inversion In(3R)Payne and markers within it, as well as among these markers. We also found an association between In(3L)Payne and one marker located within this inversion. Of the five predicted associations between markers and traits, four were detected (increased heat, decreased cold resistance and body size with the heat shock gene hsr-omega S, increased cold resistance with the inversion In(3L)Payne), while one was not detected (heat resistance and the heat shock gene hsp68). In a set of eight exploratory tests, we detected one positive association (between hsp23a and heat resistance) but no associations of heat resistance with alleles at the hsp26, hsp83, Desat 2, alpha-Gpdh, hsp70 loci, while cold resistance was not associated with Frost and Dca loci. These results confirm interactions between hsr-omega and thermal resistance, as well as between In(3L)Payne and cold resistance, but do not provide evidence for associations between thermal responses and alleles at other clinically varying marker genes.},
	Author = {Rako, Lea and Blacket, Mark J and McKechnie, Stephen W and Hoffmann, Ary A},
	Date-Added = {2009-11-19 10:14:41 -0500},
	Date-Modified = {2009-11-19 10:14:41 -0500},
	Doi = {10.1111/j.1365-294X.2007.03332.x},
	Journal = {Mol Ecol},
	Journal-Full = {Molecular ecology},
	Mesh = {Acclimatization; Animals; Australia; Chromosomes; Crosses, Genetic; Drosophila melanogaster; Ecosystem; Female; Genes, Insect; Genetic Variation; Male; Phenotype; Quantitative Trait, Heritable; Regression Analysis; Temperature},
	Month = {Jul},
	Number = {14},
	Pages = {2948-57},
	Pmid = {17614909},
	Title = {Candidate genes and thermal phenotypes: identifying ecologically important genetic variation for thermotolerance in the Australian Drosophila melanogaster cline},
	Volume = {16},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1111/j.1365-294X.2007.03332.x}}

@article{Anderson:2005xz,
	Abstract = {Clinal variation has been described in a number of inversions in Drosophila but these clines are often characterized by cytological techniques using small sample sizes, and associations with specific genes are rarely considered. Here we have developed a molecular assay for In(3R)Payne in Drosophila melanogaster from eastern Australia populations. It shows in repeated samples that the inversion cline is very tightly associated with latitude and is almost fixed in tropical populations while relatively rare in temperate populations. This steep cline has shifted in position in the last 20 years. The heat shock gene, hsr-omega, located centrally inside the inversion sequence, shows a different clinal pattern to In(3R)Payne. These results suggest strong ongoing selection on In(3R)Payne over the last 100 years since the colonization of Australia that is partly independent of hsr-omega.},
	Author = {Anderson, Alisha R and Hoffmann, Ary A and McKechnie, Stephen W and Umina, Paul A and Weeks, Andrew R},
	Date-Added = {2009-11-19 10:14:33 -0500},
	Date-Modified = {2009-11-19 10:14:33 -0500},
	Doi = {10.1111/j.1365-294X.2005.02445.x},
	Journal = {Mol Ecol},
	Journal-Full = {Molecular ecology},
	Mesh = {Animals; Australia; DNA Primers; Demography; Drosophila melanogaster; Genetic Markers; Genetics, Population; Genotype; Geography; Heat-Shock Proteins; Inversion, Chromosome; Linkage Disequilibrium; Polymorphism, Single Nucleotide; Population Dynamics; Regression Analysis},
	Month = {Mar},
	Number = {3},
	Pages = {851-8},
	Pmid = {15723676},
	Title = {The latitudinal cline in the In(3R)Payne inversion polymorphism has shifted in the last 20 years in Australian Drosophila melanogaster populations},
	Volume = {14},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1111/j.1365-294X.2005.02445.x}}

@article{Anderson:2003ya,
	Abstract = {Drosophila melanogaster occurs in diverse climatic regions and shows opposing clinal changes in resistance to heat and resistance to cold along a 3000 km latitudinal transect on the eastern coast of Australia. We report here on variation at a polymorphic 8 bp-indel site in the heat shock hsr-omega gene that maps to the right arm of chromosome 3. The frequency of the genetic element marked by the L form of the gene was strongly and positively associated with latitude along this transect, and latitudinal differences in L frequency were robustly associated with latitudinal differences in maximum temperature for the hottest month. On a genetic background mixed for genes from each end of the cline a set of 10 lines was derived, five of which were fixed for the L marker, the absence of In(3R)P and 12 kb of repeats at a second polymorphic site at the 3' end of hsr-omega, and five that were fixed for the S marker, In(3R)P and 15 kb of hsr-omega repeats. For two different measures of heat tolerance S lines outperformed L lines, and for two different measures of cold tolerance L lines outperformed S lines. These data suggest that an element on the right arm of chromosome 3, possibly In(3R)P, confers heat resistance but carries the trade-off of also conferring susceptibility to cold. This element occurs at high frequency near the equator. The alternate element on the other hand, at high frequency at temperate latitudes, confers cold resistance at the cost of heat susceptibility.},
	Author = {Anderson, A R and Collinge, J E and Hoffmann, A A and Kellett, M and McKechnie, S W},
	Date-Added = {2009-11-19 10:14:27 -0500},
	Date-Modified = {2009-11-19 10:14:27 -0500},
	Doi = {10.1038/sj.hdy.6800220},
	Journal = {Heredity},
	Journal-Full = {Heredity},
	Mesh = {Acclimatization; Animals; Chromosome Mapping; Cold Temperature; Drosophila melanogaster; Female; Genotype; Hot Temperature; Male; Polymorphism, Genetic},
	Month = {Feb},
	Number = {2},
	Pages = {195-202},
	Pmid = {12634827},
	Title = {Thermal tolerance trade-offs associated with the right arm of chromosome 3 and marked by the hsr-omega gene in Drosophila melanogaster},
	Volume = {90},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/sj.hdy.6800220}}

@article{McColl:1999oa,
	Abstract = {The hsr-omega gene of Drosophila melanogaster produces RNA products both constitutively and at elevated levels in response to heat stress. A single-nucleotide difference in this gene that has been detected using denaturing gradient gel electrophoresis (DGGE) is responsible for an hsr-omegaa/b polymorphism, and selection experiments have indicated an association between the hsr-omegaa allele and susceptibility to heat stress. Since allele frequency estimates for population surveys using PCR and DGGE for single flies would be relatively time-consuming and expensive, we here develop a quantitative competitive-PCR method using mass-grind genomic DNA preparations for this purpose. Geographical and temporal variation of allele frequency at the hsr-omega locus in Australian populations of D. melanogaster are examined. Regular samples from a southern population through a summer season suggested stability of hsr-omegaa frequency. Field populations sampled from a approximately 2,250 km north-south transect along eastern Australia revealed a strong positive association between the frequency of hsr-omegaa and latitude, and marked spatial autocorrelation. Using appropriate analyses, strong association between population differences in hsr-omegaa frequencies and differences in temperature and rainfall measures, after controlling for latitudinal differences, support the idea that the cline in hsr-omegaa frequency may be attributable to some form of climatic selection.},
	Author = {McColl, G and McKechnie, S W},
	Date-Added = {2009-11-19 10:14:22 -0500},
	Date-Modified = {2009-11-19 10:14:22 -0500},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Alleles; Animals; Drosophila melanogaster; Gene Frequency; Heat-Shock Proteins; Polymerase Chain Reaction},
	Month = {Nov},
	Number = {11},
	Pages = {1568-74},
	Pmid = {10555288},
	Title = {The Drosophila heat shock hsr-omega gene: an allele frequency cline detected by quantitative PCR},
	Volume = {16},
	Year = {1999}}

@article{McKechnie:1998ct,
	Abstract = {Inducible heat shock genes are considered a major component of the molecular mechanisms that confer cellular protection against a variety of environmental stresses, in particular high temperature extremes. We have tested the association between expression of the heat shock RNA gene hsr-omega and thermoresistance by generating thermoresistant lines of Drosophila melanogaster after application of two distinct regimes of laboratory selection. One set of lines was selected for resistance to knockdown by heat stress and the other was similarly selected but before selection a mild heat exposure known to increase resistance (heat hardening) was applied. A cross between resistant and susceptible lines confirmed our earlier observation that increased thermal tolerance cosegregates with allelic variation in the hsr-omega gene. This cosegregating variation is attributed largely to two haplotype groups. Using quantitative reverse transcription-PCR, we find evidence for divergent phenotypic responses in the two selection regimes, involving both structural and regulatory changes in hsr-omega. Lines selected after hardening showed increased levels of the cytoplasmic transcript but decreased levels of the nuclear transcript. Lines selected without hardening showed decreased levels of the cytoplasmic transcript. The allelic frequency changes at hsr-omega could not by themselves account for the altered transcription patterns. Our results support the idea that the functional RNA molecules transcribed from hsr-omega are an important and polymorphic regulatory component of an insect thermoresistance phenotype.},
	Author = {McKechnie, S W and Halford, M M and McColl, G and Hoffmann, A A},
	Date-Added = {2009-11-19 10:14:15 -0500},
	Date-Modified = {2009-11-19 10:14:15 -0500},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Alleles; Animals; Base Sequence; Cell Nucleus; Cytoplasm; Drosophila melanogaster; Gene Expression Regulation; Genes, Insect; Genetic Variation; Hot Temperature; Phenotype; Polymerase Chain Reaction; Selection (Genetics); Stress, Physiological; Temperature; Transcription, Genetic},
	Month = {Mar},
	Number = {5},
	Pages = {2423-8},
	Pmid = {9482901},
	Title = {Both allelic variation and expression of nuclear and cytoplasmic transcripts of Hsr-omega are closely associated with thermal phenotype in Drosophila},
	Volume = {95},
	Year = {1998}}

@article{Collinge:2008rf,
	Abstract = {An 8-bp deletion in the hsr-omega heat-stress gene of Drosophila melanogaster has previously been associated with latitude, and with heat tolerance that decreases with latitude. Here we report a second polymorphic site, at the 3'-end of hsr-omega, at which multiple alleles segregate in natural populations for copy number of a approximately 280 bp tandem repeat. On each of 3 consecutive years (2000, 2001 and 2002) among populations sampled along the Australian eastern coast, repeat number was negatively associated with latitude. Neither altitudinal association was detected in 2002 when five high-altitude sites were included, nor was a robust association detected with local temperature or rainfall measures. Although in a large number of family lines, derived from a population located centrally in the latitudinal transect, no association between hsr-omega repeat number and heat tolerance occurred, a negative association of repeat number with cold tolerance was detected. As cold tolerance also exhibits latitudinal clines we examined a set of cold-tolerant populations derived by selection and found both reduced repeat number and low constitutive levels of the omega-n repeat-bearing transcript. In a sample from the central population, linkage disequilibrium was measured between repeat number and linked markers that also cline latitudinally. However, such disequilibrium could not account for the cline in repeat number or tolerance associations. Finally, during adult recovery from cold exposure a large increase occurred in tissue levels of the omega-c transcript. Together these data suggest that a latitudinal cline in hsr-omega repeat number influences cold-tolerance variation in this species.},
	Author = {Collinge, J E and Anderson, A R and Weeks, A R and Johnson, T K and McKechnie, S W},
	Date-Added = {2009-11-19 10:11:08 -0500},
	Date-Modified = {2009-11-19 10:11:08 -0500},
	Doi = {10.1038/hdy.2008.57},
	Journal = {Heredity},
	Journal-Full = {Heredity},
	Mesh = {Animals; Base Sequence; Cold Climate; DNA; DNA Primers; Drosophila melanogaster; Female; Genes, Insect; Genetic Variation; Hot Temperature; Linkage Disequilibrium; Male; Minisatellite Repeats},
	Month = {Sep},
	Number = {3},
	Pages = {260-70},
	Pmid = {18560441},
	Title = {Latitudinal and cold-tolerance variation associate with DNA repeat-number variation in the hsr-omega RNA gene of Drosophila melanogaster},
	Volume = {101},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/hdy.2008.57}}

@article{Turner:2008zh,
	Abstract = {Drosophila melanogaster shows clinal variation along latitudinal transects on multiple continents for several phenotypes, allozyme variants, sequence variants, and chromosome inversions. Previous investigation suggests that many such clines are due to spatially varying selection rather than demographic history, but the genomic extent of such selection is unknown. To map differentiation throughout the genome, we hybridized DNA from temperate and subtropical populations to Affymetrix tiling arrays. The dense genomic sampling of variants and low level of linkage disequilibrium in D. melanogaster enabled identification of many small, differentiated regions. Many regions are differentiated in parallel in the United States and Australia, strongly supporting the idea that they are influenced by spatially varying selection. Genomic differentiation is distributed nonrandomly with respect to gene function, even in regions differentiated on only one continent, providing further evidence for the role of selection. These data provide candidate genes for phenotypes known to vary clinally and implicate interesting new processes in genotype-by-environment interactions, including chorion proteins, proteins regulating meiotic recombination and segregation, gustatory and olfactory receptors, and proteins affecting synaptic function and behavior. This portrait of differentiation provides a genomic perspective on adaptation and the maintenance of variation through spatially varying selection.},
	Author = {Turner, Thomas L and Levine, Mia T and Eckert, Melissa L and Begun, David J},
	Date-Added = {2009-11-19 10:04:43 -0500},
	Date-Modified = {2009-11-19 10:04:43 -0500},
	Doi = {10.1534/genetics.107.083659},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Australia; Base Sequence; Drosophila melanogaster; Evolution, Molecular; Genetic Variation; Genetics, Population; Genome; Geography; Linkage Disequilibrium; Molecular Sequence Data; Oligonucleotide Array Sequence Analysis; Selection (Genetics); Sequence Analysis, DNA; United States},
	Month = {May},
	Number = {1},
	Pages = {455-73},
	Pmid = {18493064},
	Title = {Genomic analysis of adaptive differentiation in Drosophila melanogaster},
	Volume = {179},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.107.083659}}

@article{Bischof:2007yf,
	Abstract = {Germ-line transformation via transposable elements is a powerful tool to study gene function in Drosophila melanogaster. However, some inherent characteristics of transposon-mediated transgenesis limit its use for transgene analysis. Here, we circumvent these limitations by optimizing a phiC31-based integration system. We generated a collection of lines with precisely mapped attP sites that allow the insertion of transgenes into many different predetermined intergenic locations throughout the fly genome. By using regulatory elements of the nanos and vasa genes, we established endogenous sources of the phiC31 integrase, eliminating the difficulties of coinjecting integrase mRNA and raising the transformation efficiency. Moreover, to discriminate between specific and rare nonspecific integration events, a white gene-based reconstitution system was generated that enables visual selection for precise attP targeting. Finally, we demonstrate that our chromosomal attP sites can be modified in situ, extending their scope while retaining their properties as landing sites. The efficiency, ease-of-use, and versatility obtained here with the phiC31-based integration system represents an important advance in transgenesis and opens up the possibility of systematic, high-throughput screening of large cDNA sets and regulatory elements.},
	Author = {Bischof, Johannes and Maeda, Robert K and Hediger, Monika and Karch, Fran{\c c}ois and Basler, Konrad},
	Date-Added = {2009-11-17 10:03:11 -0500},
	Date-Modified = {2009-11-17 10:03:11 -0500},
	Doi = {10.1073/pnas.0611511104},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Animals; Attachment Sites, Microbiological; Base Sequence; Computational Biology; Cytogenetic Analysis; Drosophila melanogaster; Gene Targeting; Gene Transfer Techniques; Integrases; Molecular Sequence Data; Polymerase Chain Reaction; Sequence Analysis, DNA; Transformation, Genetic; Transgenes; Virus Integration},
	Month = {Feb},
	Number = {9},
	Pages = {3312-7},
	Pmid = {17360644},
	Title = {An optimized transgenesis system for Drosophila using germ-line-specific phiC31 integrases},
	Volume = {104},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0611511104}}

@article{Adams:2000ht,
	Abstract = {The fly Drosophila melanogaster is one of the most intensively studied organisms in biology and serves as a model system for the investigation of many developmental and cellular processes common to higher eukaryotes, including humans. We have determined the nucleotide sequence of nearly all of the approximately 120-megabase euchromatic portion of the Drosophila genome using a whole-genome shotgun sequencing strategy supported by extensive clone-based sequence and a high-quality bacterial artificial chromosome physical map. Efforts are under way to close the remaining gaps; however, the sequence is of sufficient accuracy and contiguity to be declared substantially complete and to support an initial analysis of genome structure and preliminary gene annotation and interpretation. The genome encodes approximately 13,600 genes, somewhat fewer than the smaller Caenorhabditis elegans genome, but with comparable functional diversity.},
	Author = {Adams, M D and Celniker, S E and Holt, R A and Evans, C A and Gocayne, J D and Amanatides, P G and Scherer, S E and Li, P W and Hoskins, R A and Galle, R F and George, R A and Lewis, S E and Richards, S and Ashburner, M and Henderson, S N and Sutton, G G and Wortman, J R and Yandell, M D and Zhang, Q and Chen, L X and Brandon, R C and Rogers, Y H and Blazej, R G and Champe, M and Pfeiffer, B D and Wan, K H and Doyle, C and Baxter, E G and Helt, G and Nelson, C R and Gabor, G L and Abril, J F and Agbayani, A and An, H J and Andrews-Pfannkoch, C and Baldwin, D and Ballew, R M and Basu, A and Baxendale, J and Bayraktaroglu, L and Beasley, E M and Beeson, K Y and Benos, P V and Berman, B P and Bhandari, D and Bolshakov, S and Borkova, D and Botchan, M R and Bouck, J and Brokstein, P and Brottier, P and Burtis, K C and Busam, D A and Butler, H and Cadieu, E and Center, A and Chandra, I and Cherry, J M and Cawley, S and Dahlke, C and Davenport, L B and Davies, P and de Pablos, B and Delcher, A and Deng, Z and Mays, A D and Dew, I and Dietz, S M and Dodson, K and Doup, L E and Downes, M and Dugan-Rocha, S and Dunkov, B C and Dunn, P and Durbin, K J and Evangelista, C C and Ferraz, C and Ferriera, S and Fleischmann, W and Fosler, C and Gabrielian, A E and Garg, N S and Gelbart, W M and Glasser, K and Glodek, A and Gong, F and Gorrell, J H and Gu, Z and Guan, P and Harris, M and Harris, N L and Harvey, D and Heiman, T J and Hernandez, J R and Houck, J and Hostin, D and Houston, K A and Howland, T J and Wei, M H and Ibegwam, C and Jalali, M and Kalush, F and Karpen, G H and Ke, Z and Kennison, J A and Ketchum, K A and Kimmel, B E and Kodira, C D and Kraft, C and Kravitz, S and Kulp, D and Lai, Z and Lasko, P and Lei, Y and Levitsky, A A and Li, J and Li, Z and Liang, Y and Lin, X and Liu, X and Mattei, B and McIntosh, T C and McLeod, M P and McPherson, D and Merkulov, G and Milshina, N V and Mobarry, C and Morris, J and Moshrefi, A and Mount, S M and Moy, M and Murphy, B and Murphy, L and Muzny, D M and Nelson, D L and Nelson, D R and Nelson, K A and Nixon, K and Nusskern, D R and Pacleb, J M and Palazzolo, M and Pittman, G S and Pan, S and Pollard, J and Puri, V and Reese, M G and Reinert, K and Remington, K and Saunders, R D and Scheeler, F and Shen, H and Shue, B C and Sid{\'e}n-Kiamos, I and Simpson, M and Skupski, M P and Smith, T and Spier, E and Spradling, A C and Stapleton, M and Strong, R and Sun, E and Svirskas, R and Tector, C and Turner, R and Venter, E and Wang, A H and Wang, X and Wang, Z Y and Wassarman, D A and Weinstock, G M and Weissenbach, J and Williams, S M and WoodageT and Worley, K C and Wu, D and Yang, S and Yao, Q A and Ye, J and Yeh, R F and Zaveri, J S and Zhan, M and Zhang, G and Zhao, Q and Zheng, L and Zheng, X H and Zhong, F N and Zhong, W and Zhou, X and Zhu, S and Zhu, X and Smith, H O and Gibbs, R A and Myers, E W and Rubin, G M and Venter, J C},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Animals; Biological Transport; Chromatin; Cloning, Molecular; Computational Biology; Contig Mapping; Cytochrome P-450 Enzyme System; DNA Repair; DNA Replication; Drosophila melanogaster; Euchromatin; Gene Library; Genes, Insect; Genome; Heterochromatin; Insect Proteins; Nuclear Proteins; Protein Biosynthesis; Sequence Analysis, DNA; Transcription, Genetic},
	Month = {Mar},
	Number = {5461},
	Pages = {2185-95},
	Pmid = {10731132},
	Title = {The genome sequence of Drosophila melanogaster},
	Volume = {287},
	Year = {2000}}

@article{Akeyetal2002,
	Abstract = {Identifying genomic regions that have been targets of natural selection remains one of the most important and challenging areas of research in genetics. To this end, we report an analysis of 26,530 single nucleotide polymorphisms (SNPs) with allele frequencies that were determined in three populations. Specifically, we calculated a measure of genetic differentiation, F(ST), for each locus and examined its distribution at the level of the genome, the chromosome, and individual genes. Through a variety of analyses, we have found statistically significant evidence supporting the hypothesis that selection has influenced extant patterns of human genetic variation. Importantly, by contrasting the F(ST) of individual SNPs to the empirical genome-wide distribution of F(ST), our results are not confounded by tenuous assumptions of population demographic history. Furthermore, we have identified 174 candidate genes with distribution of genetic variation that indicates that they have been targets of selection. Our work provides a first generation natural selection map of the human genome and provides compelling evidence that selection has shaped extant patterns of human genomic variation.},
	Author = {Akey, JM and Zhang, G and Zhang, k and Jin, L and Shriver, MD.},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {Genome Res.},
	Month = {Dec},
	Number = {12},
	Pages = {1805-14},
	Title = {Interrogating a high-density SNP map for signatures of natural selection.},
	Volume = {12},
	Year = {2002}}

@article{Begun:2005eu,
	Abstract = {Unusual properties of molecular evolution in reproduction-related Drosophila genes, including atypically rapid rates of protein evolution, support the idea that natural selection plays an important role in divergence of reproductive function in Drosophila. We used subtractive hybridization to investigate another potential side of evolution of the male reproductive transcriptome. We carried out a screen for genes with much greater transcript abundance in Drosophila simulans reproductive tracts than in Drosophila melanogaster reproductive tracts. Such genes could be present in both species but diverged dramatically in transcript abundance or could be present in D. simulans but absent from D. melanogaster. Here we report data from melanogaster subgroup species for three previously unknown accessory gland protein genes (Acps) identified in this screen. We found multiple Acps that were present in some lineages yet absent from other closely related melanogaster subgroup lineages, representing several losses of genes. An Acp that may have been lost in D. melanogaster and Drosophila erecta is segregating a null allele in Drosophila yakuba, yet shows evidence of adaptive protein evolution in contrasts of polymorphism and divergence within and between D. yakuba and its close relative, Drosophila teissieri. These data suggest that turnover of Acps occurs rapidly in Drosophila, consistent with rapid evolution of seminal fluid function.},
	Author = {Begun, David J and Lindfors, Heather A},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1093/molbev/msi201},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Amino Acid Sequence; Animals; Codon; Consensus Sequence; Drosophila; Drosophila Proteins; Drosophila melanogaster; Evolution, Molecular; Male; Molecular Sequence Data; Polymerase Chain Reaction; Reproduction; Sequence Alignment; Sequence Homology, Amino Acid; Transcription, Genetic},
	Month = {Oct},
	Number = {10},
	Pages = {2010-21},
	Pmid = {15987879},
	Title = {Rapid evolution of genomic Acp complement in the melanogaster subgroup of Drosophila},
	Volume = {22},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msi201}}

@article{Begunetal2007b,
	Author = {Begun, DJ and Holloway, AK and Stevens, K and Hillier, LW and Poh, YP and Hahn, MW and Nista, PM and Jones, CD and Kern, AD and Dewey, CN and Pachter, L and Myers, E and Langley, CH.},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {PLoS Biol.},
	Month = {Nov},
	Number = {11},
	Pages = {e310},
	Title = {Population genomics: whole-genome analysis of polymorphism and divergence in Drosophila simulans.},
	Volume = {5},
	Year = {2007}}

@article{Bentley:2008la,
	Abstract = {DNA sequence information underpins genetic research, enabling discoveries of important biological or medical benefit. Sequencing projects have traditionally used long (400-800 base pair) reads, but the existence of reference sequences for the human and many other genomes makes it possible to develop new, fast approaches to re-sequencing, whereby shorter reads are compared to a reference to identify intraspecies genetic variation. Here we report an approach that generates several billion bases of accurate nucleotide sequence per experiment at low cost. Single molecules of DNA are attached to a flat surface, amplified in situ and used as templates for synthetic sequencing with fluorescent reversible terminator deoxyribonucleotides. Images of the surface are analysed to generate high-quality sequence. We demonstrate application of this approach to human genome sequencing on flow-sorted X chromosomes and then scale the approach to determine the genome sequence of a male Yoruba from Ibadan, Nigeria. We build an accurate consensus sequence from >30x average depth of paired 35-base reads. We characterize four million single-nucleotide polymorphisms and four hundred thousand structural variants, many of which were previously unknown. Our approach is effective for accurate, rapid and economical whole-genome re-sequencing and many other biomedical applications.},
	Author = {Bentley, David R and Balasubramanian, Shankar and Swerdlow, Harold P and Smith, Geoffrey P and Milton, John and Brown, Clive G and Hall, Kevin P and Evers, Dirk J and Barnes, Colin L and Bignell, Helen R and Boutell, Jonathan M and Bryant, Jason and Carter, Richard J and Keira Cheetham, R and Cox, Anthony J and Ellis, Darren J and Flatbush, Michael R and Gormley, Niall A and Humphray, Sean J and Irving, Leslie J and Karbelashvili, Mirian S and Kirk, Scott M and Li, Heng and Liu, Xiaohai and Maisinger, Klaus S and Murray, Lisa J and Obradovic, Bojan and Ost, Tobias and Parkinson, Michael L and Pratt, Mark R and Rasolonjatovo, Isabelle M J and Reed, Mark T and Rigatti, Roberto and Rodighiero, Chiara and Ross, Mark T and Sabot, Andrea and Sankar, Subramanian V and Scally, Aylwyn and Schroth, Gary P and Smith, Mark E and Smith, Vincent P and Spiridou, Anastassia and Torrance, Peta E and Tzonev, Svilen S and Vermaas, Eric H and Walter, Klaudia and Wu, Xiaolin and Zhang, Lu and Alam, Mohammed D and Anastasi, Carole and Aniebo, Ify C and Bailey, David M D and Bancarz, Iain R and Banerjee, Saibal and Barbour, Selena G and Baybayan, Primo A and Benoit, Vincent A and Benson, Kevin F and Bevis, Claire and Black, Phillip J and Boodhun, Asha and Brennan, Joe S and Bridgham, John A and Brown, Rob C and Brown, Andrew A and Buermann, Dale H and Bundu, Abass A and Burrows, James C and Carter, Nigel P and Castillo, Nestor and Chiara E Catenazzi, Maria and Chang, Simon and Neil Cooley, R and Crake, Natasha R and Dada, Olubunmi O and Diakoumakos, Konstantinos D and Dominguez-Fernandez, Belen and Earnshaw, David J and Egbujor, Ugonna C and Elmore, David W and Etchin, Sergey S and Ewan, Mark R and Fedurco, Milan and Fraser, Louise J and Fuentes Fajardo, Karin V and Scott Furey, W and George, David and Gietzen, Kimberley J and Goddard, Colin P and Golda, George S and Granieri, Philip A and Green, David E and Gustafson, David L and Hansen, Nancy F and Harnish, Kevin and Haudenschild, Christian D and Heyer, Narinder I and Hims, Matthew M and Ho, Johnny T and Horgan, Adrian M and Hoschler, Katya and Hurwitz, Steve and Ivanov, Denis V and Johnson, Maria Q and James, Terena and Huw Jones, T A and Kang, Gyoung-Dong and Kerelska, Tzvetana H and Kersey, Alan D and Khrebtukova, Irina and Kindwall, Alex P and Kingsbury, Zoya and Kokko-Gonzales, Paula I and Kumar, Anil and Laurent, Marc A and Lawley, Cynthia T and Lee, Sarah E and Lee, Xavier and Liao, Arnold K and Loch, Jennifer A and Lok, Mitch and Luo, Shujun and Mammen, Radhika M and Martin, John W and McCauley, Patrick G and McNitt, Paul and Mehta, Parul and Moon, Keith W and Mullens, Joe W and Newington, Taksina and Ning, Zemin and Ling Ng, Bee and Novo, Sonia M and O'Neill, Michael J and Osborne, Mark A and Osnowski, Andrew and Ostadan, Omead and Paraschos, Lambros L and Pickering, Lea and Pike, Andrew C and Pike, Alger C and Chris Pinkard, D and Pliskin, Daniel P and Podhasky, Joe and Quijano, Victor J and Raczy, Come and Rae, Vicki H and Rawlings, Stephen R and Chiva Rodriguez, Ana and Roe, Phyllida M and Rogers, John and Rogert Bacigalupo, Maria C and Romanov, Nikolai and Romieu, Anthony and Roth, Rithy K and Rourke, Natalie J and Ruediger, Silke T and Rusman, Eli and Sanches-Kuiper, Raquel M and Schenker, Martin R and Seoane, Josefina M and Shaw, Richard J and Shiver, Mitch K and Short, Steven W and Sizto, Ning L and Sluis, Johannes P and Smith, Melanie A and Ernest Sohna Sohna, Jean and Spence, Eric J and Stevens, Kim and Sutton, Neil and Szajkowski, Lukasz and Tregidgo, Carolyn L and Turcatti, Gerardo and Vandevondele, Stephanie and Verhovsky, Yuli and Virk, Selene M and Wakelin, Suzanne and Walcott, Gregory C and Wang, Jingwen and Worsley, Graham J and Yan, Juying and Yau, Ling and Zuerlein, Mike and Rogers, Jane and Mullikin, James C and Hurles, Matthew E and McCooke, Nick J and West, John S and Oaks, Frank L and Lundberg, Peter L and Klenerman, David and Durbin, Richard and Smith, Anthony J},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1038/nature07517},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Chromosomes, Human, X; Consensus Sequence; Genome, Human; Genomics; Genotype; Humans; Male; Nigeria; Polymorphism, Single Nucleotide; Sensitivity and Specificity; Sequence Analysis, DNA},
	Month = {Nov},
	Number = {7218},
	Pages = {53-9},
	Pmid = {18987734},
	Title = {Accurate whole human genome sequencing using reversible terminator chemistry},
	Volume = {456},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature07517}}

@article{Biswas:2006tx,
	Abstract = {The traditional way of identifying targets of adaptive evolution has been to study a few loci that one hypothesizes a priori to have been under selection. This approach is complicated because of the confounding effects that population demographic history and selection have on patterns of DNA sequence variation. In principle, multilocus analyses can facilitate robust inferences of selection at individual loci. The deluge of large-scale catalogs of genetic variation has stimulated many genome-wide scans for positive selection in several species. Here, we review some of the salient observations of these studies, identify important challenges ahead, consider the limitations of genome-wide scans for selection and discuss the potential significance of a comprehensive understanding of genomic patterns of selection for disease-related research.},
	Author = {Biswas, Shameek and Akey, Joshua M},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1016/j.tig.2006.06.005},
	Journal = {Trends Genet},
	Journal-Full = {Trends in genetics : TIG},
	Mesh = {Animals; Evolution, Molecular; Genetic Variation; Genetics, Population; Humans; Models, Genetic; Selection (Genetics); Species Specificity},
	Month = {Aug},
	Number = {8},
	Pages = {437-46},
	Pmid = {16808986},
	Title = {Genomic insights into positive selection},
	Volume = {22},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.tig.2006.06.005}}

@article{Blanchette:2004kn,
	Abstract = {We define a "threaded blockset," which is a novel generalization of the classic notion of a multiple alignment. A new computer program called TBA (for "threaded blockset aligner") builds a threaded blockset under the assumption that all matching segments occur in the same order and orientation in the given sequences; inversions and duplications are not addressed. TBA is designed to be appropriate for aligning many, but by no means all, megabase-sized regions of multiple mammalian genomes. The output of TBA can be projected onto any genome chosen as a reference, thus guaranteeing that different projections present consistent predictions of which genomic positions are orthologous. This capability is illustrated using a new visualization tool to view TBA-generated alignments of vertebrate Hox clusters from both the mammalian and fish perspectives. Experimental evaluation of alignment quality, using a program that simulates evolutionary change in genomic sequences, indicates that TBA is more accurate than earlier programs. To perform the dynamic-programming alignment step, TBA runs a stand-alone program called MULTIZ, which can be used to align highly rearranged or incompletely sequenced genomes. We describe our use of MULTIZ to produce the whole-genome multiple alignments at the Santa Cruz Genome Browser.},
	Author = {Blanchette, Mathieu and Kent, W James and Riemer, Cathy and Elnitski, Laura and Smit, Arian F A and Roskin, Krishna M and Baertsch, Robert and Rosenbloom, Kate and Clawson, Hiram and Green, Eric D and Haussler, David and Miller, Webb},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1101/gr.1933104},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Animals; Base Sequence; Cats; Cattle; Computational Biology; Computer Simulation; Dogs; Evaluation Studies as Topic; Evolution, Molecular; Genes, Homeobox; Genes, fos; Genome; Genome, Human; Humans; Mice; Molecular Sequence Data; Multigene Family; Rats; Ribosomal Proteins; Sequence Alignment; Software},
	Month = {Apr},
	Number = {4},
	Pages = {708-15},
	Pmid = {15060014},
	Title = {Aligning multiple genomic sequences with the threaded blockset aligner},
	Volume = {14},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.1933104}}

@article{Coop:2004pj,
	Abstract = {The extent to which natural selection shapes diversity within populations is a key question for population genetics. Thus, there is considerable interest in quantifying the strength of selection. A full likelihood approach for inference about selection at a single site within an otherwise neutral fully linked sequence of sites is described here. A coalescent model of evolution is used to model the ancestry of a sample of DNA sequences which have the selected site segregating. The mutation model, for the selected and neutral sites, is the infinitely many-sites model where there is no back or parallel mutation at sites. A unique perfect phylogeny, a gene tree, can be constructed from the configuration of mutations on the sample sequences under this model of mutation. The approach is general and can be used for any bi-allelic selection scheme. Selection is incorporated through modelling the frequency of the selected and neutral allelic classes stochastically back in time, then using a subdivided population model considering the population frequencies through time as variable population sizes. An importance sampling algorithm is then used to explore over coalescent tree space consistent with the data. The method is applied to a simulated data set and the gene tree presented in Verrelli et al. (2002).},
	Address = {Department of Statistics, University of Oxford, 1 South Parks Road, Oxford OX1 3TG, UK. coop@stats.ox.ac.uk},
	Au = {Coop, G and Griffiths, RC},
	Author = {Coop, Graham and Griffiths, Robert C},
	Crdt = {2004/10/07 09:00},
	Da = {20041006},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {20050127},
	Doi = {10.1016/j.tpb.2004.06.006},
	Edat = {2004/10/07 09:00},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology},
	Keywords = {Genetic Variation; Likelihood Functions; Mutation; *Selection (Genetics)},
	Language = {eng},
	Lr = {20081121},
	Mhda = {2005/01/28 09:00},
	Number = {3},
	Own = {NLM},
	Pages = {219--232},
	Phst = {2004/01/26 {$[$}received{$]$}},
	Pii = {S0040-5809(04)00082-6},
	Pl = {United States},
	Pmid = {15465123},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Sb = {IM},
	So = {Theor Popul Biol. 2004 Nov;66(3):219-32.},
	Stat = {MEDLINE},
	Title = {Ancestral inference on gene trees under selection.},
	Volume = {66},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.tpb.2004.06.006}}

@article{Drosophila-12-Genomes-Consortium:2007gf,
	Abstract = {Comparative analysis of multiple genomes in a phylogenetic framework dramatically improves the precision and sensitivity of evolutionary inference, producing more robust results than single-genome analyses can provide. The genomes of 12 Drosophila species, ten of which are presented here for the first time (sechellia, simulans, yakuba, erecta, ananassae, persimilis, willistoni, mojavensis, virilis and grimshawi), illustrate how rates and patterns of sequence divergence across taxa can illuminate evolutionary processes on a genomic scale. These genome sequences augment the formidable genetic tools that have made Drosophila melanogaster a pre-eminent model for animal genetics, and will further catalyse fundamental research on mechanisms of development, cell biology, genetics, disease, neurobiology, behaviour, physiology and evolution. Despite remarkable similarities among these Drosophila species, we identified many putatively non-neutral changes in protein-coding genes, non-coding RNA genes, and cis-regulatory regions. These may prove to underlie differences in the ecology and behaviour of these diverse species.},
	Author = {{Drosophila 12 Genomes Consortium} and Clark, Andrew G and Eisen, Michael B and Smith, Douglas R and Bergman, Casey M and Oliver, Brian and Markow, Therese A and Kaufman, Thomas C and Kellis, Manolis and Gelbart, William and Iyer, Venky N and Pollard, Daniel A and Sackton, Timothy B and Larracuente, Amanda M and Singh, Nadia D and Abad, Jose P and Abt, Dawn N and Adryan, Boris and Aguade, Montserrat and Akashi, Hiroshi and Anderson, Wyatt W and Aquadro, Charles F and Ardell, David H and Arguello, Roman and Artieri, Carlo G and Barbash, Daniel A and Barker, Daniel and Barsanti, Paolo and Batterham, Phil and Batzoglou, Serafim and Begun, Dave and Bhutkar, Arjun and Blanco, Enrico and Bosak, Stephanie A and Bradley, Robert K and Brand, Adrianne D and Brent, Michael R and Brooks, Angela N and Brown, Randall H and Butlin, Roger K and Caggese, Corrado and Calvi, Brian R and Bernardo de Carvalho, A and Caspi, Anat and Castrezana, Sergio and Celniker, Susan E and Chang, Jean L and Chapple, Charles and Chatterji, Sourav and Chinwalla, Asif and Civetta, Alberto and Clifton, Sandra W and Comeron, Josep M and Costello, James C and Coyne, Jerry A and Daub, Jennifer and David, Robert G and Delcher, Arthur L and Delehaunty, Kim and Do, Chuong B and Ebling, Heather and Edwards, Kevin and Eickbush, Thomas and Evans, Jay D and Filipski, Alan and Findeiss, Sven and Freyhult, Eva and Fulton, Lucinda and Fulton, Robert and Garcia, Ana C L and Gardiner, Anastasia and Garfield, David A and Garvin, Barry E and Gibson, Greg and Gilbert, Don and Gnerre, Sante and Godfrey, Jennifer and Good, Robert and Gotea, Valer and Gravely, Brenton and Greenberg, Anthony J and Griffiths-Jones, Sam and Gross, Samuel and Guigo, Roderic and Gustafson, Erik A and Haerty, Wilfried and Hahn, Matthew W and Halligan, Daniel L and Halpern, Aaron L and Halter, Gillian M and Han, Mira V and Heger, Andreas and Hillier, LaDeana and Hinrichs, Angie S and Holmes, Ian and Hoskins, Roger A and Hubisz, Melissa J and Hultmark, Dan and Huntley, Melanie A and Jaffe, David B and Jagadeeshan, Santosh and Jeck, William R and Johnson, Justin and Jones, Corbin D and Jordan, William C and Karpen, Gary H and Kataoka, Eiko and Keightley, Peter D and Kheradpour, Pouya and Kirkness, Ewen F and Koerich, Leonardo B and Kristiansen, Karsten and Kudrna, Dave and Kulathinal, Rob J and Kumar, Sudhir and Kwok, Roberta and Lander, Eric and Langley, Charles H and Lapoint, Richard and Lazzaro, Brian P and Lee, So-Jeong and Levesque, Lisa and Li, Ruiqiang and Lin, Chiao-Feng and Lin, Michael F and Lindblad-Toh, Kerstin and Llopart, Ana and Long, Manyuan and Low, Lloyd and Lozovsky, Elena and Lu, Jian and Luo, Meizhong and Machado, Carlos A and Makalowski, Wojciech and Marzo, Mar and Matsuda, Muneo and Matzkin, Luciano and McAllister, Bryant and McBride, Carolyn S and McKernan, Brendan and McKernan, Kevin and Mendez-Lago, Maria and Minx, Patrick and Mollenhauer, Michael U and Montooth, Kristi and Mount, Stephen M and Mu, Xu and Myers, Eugene and Negre, Barbara and Newfeld, Stuart and Nielsen, Rasmus and Noor, Mohamed A F and O'Grady, Patrick and Pachter, Lior and Papaceit, Montserrat and Parisi, Matthew J and Parisi, Michael and Parts, Leopold and Pedersen, Jakob S and Pesole, Graziano and Phillippy, Adam M and Ponting, Chris P and Pop, Mihai and Porcelli, Damiano and Powell, Jeffrey R and Prohaska, Sonja and Pruitt, Kim and Puig, Marta and Quesneville, Hadi and Ram, Kristipati Ravi and Rand, David and Rasmussen, Matthew D and Reed, Laura K and Reenan, Robert and Reily, Amy and Remington, Karin A and Rieger, Tania T and Ritchie, Michael G and Robin, Charles and Rogers, Yu-Hui and Rohde, Claudia and Rozas, Julio and Rubenfield, Marc J and Ruiz, Alfredo and Russo, Susan and Salzberg, Steven L and Sanchez-Gracia, Alejandro and Saranga, David J and Sato, Hajime and Schaeffer, Stephen W and Schatz, Michael C and Schlenke, Todd and Schwartz, Russell and Segarra, Carmen and Singh, Rama S and Sirot, Laura and Sirota, Marina and Sisneros, Nicholas B and Smith, Chris D and Smith, Temple F and Spieth, John and Stage, Deborah E and Stark, Alexander and Stephan, Wolfgang and Strausberg, Robert L and Strempel, Sebastian and Sturgill, David and Sutton, Granger and Sutton, Granger G and Tao, Wei and Teichmann, Sarah and Tobari, Yoshiko N and Tomimura, Yoshihiko and Tsolas, Jason M and Valente, Vera L S and Venter, Eli and Venter, J Craig and Vicario, Saverio and Vieira, Filipe G and Vilella, Albert J and Villasante, Alfredo and Walenz, Brian and Wang, Jun and Wasserman, Marvin and Watts, Thomas and Wilson, Derek and Wilson, Richard K and Wing, Rod A and Wolfner, Mariana F and Wong, Alex and Wong, Gane Ka-Shu and Wu, Chung-I and Wu, Gabriel and Yamamoto, Daisuke and Yang, Hsiao-Pei and Yang, Shiaw-Pyng and Yorke, James A and Yoshida, Kiyohito and Zdobnov, Evgeny and Zhang, Peili and Zhang, Yu and Zimin, Aleksey V and Baldwin, Jennifer and Abdouelleil, Amr and Abdulkadir, Jamal and Abebe, Adal and Abera, Brikti and Abreu, Justin and Acer, St Christophe and Aftuck, Lynne and Alexander, Allen and An, Peter and Anderson, Erica and Anderson, Scott and Arachi, Harindra and Azer, Marc and Bachantsang, Pasang and Barry, Andrew and Bayul, Tashi and Berlin, Aaron and Bessette, Daniel and Bloom, Toby and Blye, Jason and Boguslavskiy, Leonid and Bonnet, Claude and Boukhgalter, Boris and Bourzgui, Imane and Brown, Adam and Cahill, Patrick and Channer, Sheridon and Cheshatsang, Yama and Chuda, Lisa and Citroen, Mieke and Collymore, Alville and Cooke, Patrick and Costello, Maura and D'Aco, Katie and Daza, Riza and De Haan, Georgius and DeGray, Stuart and DeMaso, Christina and Dhargay, Norbu and Dooley, Kimberly and Dooley, Erin and Doricent, Missole and Dorje, Passang and Dorjee, Kunsang and Dupes, Alan and Elong, Richard and Falk, Jill and Farina, Abderrahim and Faro, Susan and Ferguson, Diallo and Fisher, Sheila and Foley, Chelsea D and Franke, Alicia and Friedrich, Dennis and Gadbois, Loryn and Gearin, Gary and Gearin, Christina R and Giannoukos, Georgia and Goode, Tina and Graham, Joseph and Grandbois, Edward and Grewal, Sharleen and Gyaltsen, Kunsang and Hafez, Nabil and Hagos, Birhane and Hall, Jennifer and Henson, Charlotte and Hollinger, Andrew and Honan, Tracey and Huard, Monika D and Hughes, Leanne and Hurhula, Brian and Husby, M Erii and Kamat, Asha and Kanga, Ben and Kashin, Seva and Khazanovich, Dmitry and Kisner, Peter and Lance, Krista and Lara, Marcia and Lee, William and Lennon, Niall and Letendre, Frances and LeVine, Rosie and Lipovsky, Alex and Liu, Xiaohong and Liu, Jinlei and Liu, Shangtao and Lokyitsang, Tashi and Lokyitsang, Yeshi and Lubonja, Rakela and Lui, Annie and MacDonald, Pen and Magnisalis, Vasilia and Maru, Kebede and Matthews, Charles and McCusker, William and McDonough, Susan and Mehta, Teena and Meldrim, James and Meneus, Louis and Mihai, Oana and Mihalev, Atanas and Mihova, Tanya and Mittelman, Rachel and Mlenga, Valentine and Montmayeur, Anna and Mulrain, Leonidas and Navidi, Adam and Naylor, Jerome and Negash, Tamrat and Nguyen, Thu and Nguyen, Nga and Nicol, Robert and Norbu, Choe and Norbu, Nyima and Novod, Nathaniel and O'Neill, Barry and Osman, Sahal and Markiewicz, Eva and Oyono, Otero L and Patti, Christopher and Phunkhang, Pema and Pierre, Fritz and Priest, Margaret and Raghuraman, Sujaa and Rege, Filip and Reyes, Rebecca and Rise, Cecil and Rogov, Peter and Ross, Keenan and Ryan, Elizabeth and Settipalli, Sampath and Shea, Terry and Sherpa, Ngawang and Shi, Lu and Shih, Diana and Sparrow, Todd and Spaulding, Jessica and Stalker, John and Stange-Thomann, Nicole and Stavropoulos, Sharon and Stone, Catherine and Strader, Christopher and Tesfaye, Senait and Thomson, Talene and Thoulutsang, Yama and Thoulutsang, Dawa and Topham, Kerri and Topping, Ira and Tsamla, Tsamla and Vassiliev, Helen and Vo, Andy and Wangchuk, Tsering and Wangdi, Tsering and Weiand, Michael and Wilkinson, Jane and Wilson, Adam and Yadav, Shailendra and Young, Geneva and Yu, Qing and Zembek, Lisa and Zhong, Danni and Zimmer, Andrew and Zwirko, Zac and Jaffe, David B and Alvarez, Pablo and Brockman, Will and Butler, Jonathan and Chin, CheeWhye and Gnerre, Sante and Grabherr, Manfred and Kleber, Michael and Mauceli, Evan and MacCallum, Iain},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1038/nature06341},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Codon; DNA Transposable Elements; Drosophila; Drosophila Proteins; Evolution, Molecular; Gene Order; Genes, Insect; Genome, Insect; Genome, Mitochondrial; Genomics; Immunity; Multigene Family; Phylogeny; RNA, Untranslated; Reproduction; Sequence Alignment; Sequence Analysis, DNA; Synteny},
	Month = {Nov},
	Number = {7167},
	Pages = {203-18},
	Pmid = {17994087},
	Title = {Evolution of genes and genomes on the Drosophila phylogeny},
	Volume = {450},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature06341}}

@article{Griffith:2008eu,
	Abstract = {ORegAnno is an open-source, open-access database and literature curation system for community-based annotation of experimentally identified DNA regulatory regions, transcription factor binding sites and regulatory variants. The current release comprises 30 145 records curated from 922 publications and describing regulatory sequences for over 3853 genes and 465 transcription factors from 19 species. A new feature called the 'publication queue' allows users to input relevant papers from scientific literature as targets for annotation. The queue contains 4438 gene regulation papers entered by experts and another 54 351 identified by text-mining methods. Users can enter or 'check out' papers from the queue for manual curation using a series of user-friendly annotation pages. A typical record entry consists of species, sequence type, sequence, target gene, binding factor, experimental outcome and one or more lines of experimental evidence. An evidence ontology was developed to describe and categorize these experiments. Records are cross-referenced to Ensembl or Entrez gene identifiers, PubMed and dbSNP and can be visualized in the Ensembl or UCSC genome browsers. All data are freely available through search pages, XML data dumps or web services at: http://www.oreganno.org.},
	Author = {Griffith, Obi L and Montgomery, Stephen B and Bernier, Bridget and Chu, Bryan and Kasaian, Katayoon and Aerts, Stein and Mahony, Shaun and Sleumer, Monica C and Bilenky, Mikhail and Haeussler, Maximilian and Griffith, Malachi and Gallo, Steven M and Giardine, Belinda and Hooghe, Bart and Van Loo, Peter and Blanco, Enrique and Ticoll, Amy and Lithwick, Stuart and Portales-Casamar, Elodie and Donaldson, Ian J and Robertson, Gordon and Wadelius, Claes and De Bleser, Pieter and Vlieghe, Dominique and Halfon, Marc S and Wasserman, Wyeth and Hardison, Ross and Bergman, Casey M and Jones, Steven J M and {Open Regulatory Annotation Consortium}},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1093/nar/gkm967},
	Journal = {Nucleic Acids Res},
	Journal-Full = {Nucleic acids research},
	Mesh = {Access to Information; Animals; Binding Sites; Databases, Nucleic Acid; Humans; Internet; Regulatory Elements, Transcriptional; Transcription Factors; User-Computer Interface},
	Month = {Jan},
	Number = {Database issue},
	Pages = {D107-13},
	Pmid = {18006570},
	Title = {ORegAnno: an open-access community-driven resource for regulatory annotation},
	Volume = {36},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gkm967}}

@article{Hasegawa:1985gy,
	Abstract = {A new statistical method for estimating divergence dates of species from DNA sequence data by a molecular clock approach is developed. This method takes into account effectively the information contained in a set of DNA sequence data. The molecular clock of mitochondrial DNA (mtDNA) was calibrated by setting the date of divergence between primates and ungulates at the Cretaceous-Tertiary boundary (65 million years ago), when the extinction of dinosaurs occurred. A generalized least-squares method was applied in fitting a model to mtDNA sequence data, and the clock gave dates of 92.3 +/- 11.7, 13.3 +/- 1.5, 10.9 +/- 1.2, 3.7 +/- 0.6, and 2.7 +/- 0.6 million years ago (where the second of each pair of numbers is the standard deviation) for the separation of mouse, gibbon, orangutan, gorilla, and chimpanzee, respectively, from the line leading to humans. Although there is some uncertainty in the clock, this dating may pose a problem for the widely believed hypothesis that the pipedal creature Australopithecus afarensis, which lived some 3.7 million years ago at Laetoli in Tanzania and at Hadar in Ethiopia, was ancestral to man and evolved after the human-ape splitting. Another likelier possibility is that mtDNA was transferred through hybridization between a proto-human and a proto-chimpanzee after the former had developed bipedalism.},
	Author = {Hasegawa, M and Kishino, H and Yano, T},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {J Mol Evol},
	Journal-Full = {Journal of molecular evolution},
	Mesh = {Animals; DNA, Mitochondrial; Evolution; Genes; Haplorhini; Humans; Mathematics; Models, Genetic; Nucleic Acid Hybridization; Primates; Proteins; Species Specificity},
	Number = {2},
	Pages = {160-74},
	Pmid = {3934395},
	Title = {Dating of the human-ape splitting by a molecular clock of mitochondrial DNA},
	Volume = {22},
	Year = {1985}}

@article{Hinrichs:2006hm,
	Abstract = {The University of California Santa Cruz Genome Browser Database (GBD) contains sequence and annotation data for the genomes of about a dozen vertebrate species and several major model organisms. Genome annotations typically include assembly data, sequence composition, genes and gene predictions, mRNA and expressed sequence tag evidence, comparative genomics, regulation, expression and variation data. The database is optimized to support fast interactive performance with web tools that provide powerful visualization and querying capabilities for mining the data. The Genome Browser displays a wide variety of annotations at all scales from single nucleotide level up to a full chromosome. The Table Browser provides direct access to the database tables and sequence data, enabling complex queries on genome-wide datasets. The Proteome Browser graphically displays protein properties. The Gene Sorter allows filtering and comparison of genes by several metrics including expression data and several gene properties. BLAT and In Silico PCR search for sequences in entire genomes in seconds. These tools are highly integrated and provide many hyperlinks to other databases and websites. The GBD, browsing tools, downloadable data files and links to documentation and other information can be found at http://genome.ucsc.edu/.},
	Author = {Hinrichs, A S and Karolchik, D and Baertsch, R and Barber, G P and Bejerano, G and Clawson, H and Diekhans, M and Furey, T S and Harte, R A and Hsu, F and Hillman-Jackson, J and Kuhn, R M and Pedersen, J S and Pohl, A and Raney, B J and Rosenbloom, K R and Siepel, A and Smith, K E and Sugnet, C W and Sultan-Qurraie, A and Thomas, D J and Trumbower, H and Weber, R J and Weirauch, M and Zweig, A S and Haussler, D and Kent, W J},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1093/nar/gkj144},
	Journal = {Nucleic Acids Res},
	Journal-Full = {Nucleic acids research},
	Mesh = {Amino Acid Sequence; Animals; California; Computer Graphics; Databases, Genetic; Dogs; Gene Expression; Genes; Genomics; Humans; Internet; Mice; Polymorphism, Single Nucleotide; Proteins; Proteomics; Rats; Sequence Alignment; Software; User-Computer Interface},
	Month = {Jan},
	Number = {Database issue},
	Pages = {D590-8},
	Pmid = {16381938},
	Title = {The UCSC Genome Browser Database: update 2006},
	Volume = {34},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/nar/gkj144}}

@article{Jordan:2007ly,
	Abstract = {BACKGROUND: Locomotion is an integral component of most animal behaviors, and many human health problems are associated with locomotor deficits. Locomotor behavior is a complex trait, with population variation attributable to many interacting loci with small effects that are sensitive to environmental conditions. However, the genetic basis of this complex behavior is largely uncharacterized. RESULTS: We quantified locomotor behavior of Drosophila melanogaster in a large population of inbred lines derived from a single natural population, and derived replicated selection lines with different levels of locomotion. Estimates of broad-sense and narrow-sense heritabilities were 0.52 and 0.16, respectively, indicating substantial non-additive genetic variance for locomotor behavior. We used whole genome expression analysis to identify 1,790 probe sets with different expression levels between the selection lines when pooled across replicates, at a false discovery rate of 0.001. The transcriptional responses to selection for locomotor, aggressive and mating behavior from the same base population were highly overlapping, but the magnitude of the expression differences between selection lines for increased and decreased levels of behavior was uncorrelated. We assessed the locomotor behavior of ten mutations in candidate genes with altered transcript abundance between selection lines, and identified seven novel genes affecting this trait. CONCLUSION: Expression profiling of genetically divergent lines is an effective strategy for identifying genes affecting complex behaviors, and reveals that a large number of pleiotropic genes exhibit correlated transcriptional responses to multiple behaviors.},
	Author = {Jordan, Katherine W and Carbone, Mary Anna and Yamamoto, Akihiko and Morgan, Theodore J and Mackay, Trudy F C},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1186/gb-2007-8-8-r172},
	Journal = {Genome Biol},
	Journal-Full = {Genome biology},
	Mesh = {Animals; Drosophila melanogaster; Gene Expression Profiling; Genes, Insect; Genetic Variation; Genome, Insect; Genomics; Motor Activity; Phenotype; Transcription, Genetic},
	Number = {8},
	Pages = {R172},
	Pmid = {17708775},
	Title = {Quantitative genomics of locomotor behavior in Drosophila melanogaster},
	Volume = {8},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/gb-2007-8-8-r172}}

@article{Kernetal2002,
	Abstract = {Selective fixation of beneficial mutations reduces levels of linked, neutral variation. The magnitude of this "hitchhiking effect" is determined by the strength of selection and the recombination rate between selected and neutral sites. Thus, depending on the values of these parameters and the frequency with which directional selection occurs, the genomic scale over which directional selection reduces levels of linked variation may vary widely. Here we present a permutation-based analysis of nucleotide polymorphisms and fixations in Drosophila simulans. We show evidence of pervasive small-scale hitchhiking effects in this lineage. Furthermore, our results reveal that different types of fixations are associated with different levels of linked variation.},
	Address = {Center for Population Biology, University of California, Davis, California 95616, USA. adkerm@ucdavis.edu},
	Au = {Kern AD and Jones CD and Begun DJ},
	Author = {Kern, Andrew D and Jones, Corbin D and Begun, David J},
	Da = {20030113},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {20030721},
	Edat = {2003/01/14 04:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, DNA/genetics, Drosophila/*genetics, Genes, Insect, Genome, Loss of Heterozygosity, Molecular Sequence Data, Mutation, Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Selection (Genetics), Variation (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2003/07/23 05:00},
	Number = {4},
	Own = {NLM},
	Pages = {1753-61},
	Pl = {United States},
	Pmid = {12524346},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	Si = {GENBANK/AF544231, GENBANK/AF544232, GENBANK/AF544233, GENBANK/AF544234, GENBANK/AF544235, GENBANK/AF544236, GENBANK/AF544237, GENBANK/AF544238, GENBANK/AF544239},
	So = {Genetics. 2002 Dec;162(4):1753-61.},
	Stat = {MEDLINE},
	Title = {Genomic effects of nucleotide substitutions in Drosophila simulans.},
	Volume = {162},
	Year = {2002}}

@article{Kim:2002wd,
	Abstract = {The theory of genetic hitchhiking predicts that the level of genetic variation is greatly reduced at the site of strong directional selection and increases as the recombinational distance from the site of selection increases. This characteristic pattern can be used to detect recent directional selection on the basis of DNA polymorphism data. However, the large variance of nucleotide diversity in samples of moderate size imposes difficulties in detecting such patterns. We investigated the patterns of genetic variation along a recombining chromosome by constructing ancestral recombination graphs that are modified to incorporate the effect of genetic hitchhiking. A statistical method is proposed to test the significance of a local reduction of variation and a skew of the frequency spectrum caused by a hitchhiking event. This method also allows us to estimate the strength and the location of directional selection from DNA sequence data.},
	Author = {Kim, Yuseob and Stephan, Wolfgang},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Chromosomes; Evolution, Molecular; Heterozygote; Likelihood Functions; Linkage (Genetics); Models, Theoretical; Mutation; Polymorphism, Genetic; Recombination, Genetic},
	Month = {Feb},
	Number = {2},
	Pages = {765-77},
	Pmid = {11861577},
	Title = {Detecting a local signature of genetic hitchhiking along a recombining chromosome},
	Volume = {160},
	Year = {2002}}

@article{Li:2008fe,
	Abstract = {New sequencing technologies promise a new era in the use of DNA sequence. However, some of these technologies produce very short reads, typically of a few tens of base pairs, and to use these reads effectively requires new algorithms and software. In particular, there is a major issue in efficiently aligning short reads to a reference genome and handling ambiguity or lack of accuracy in this alignment. Here we introduce the concept of mapping quality, a measure of the confidence that a read actually comes from the position it is aligned to by the mapping algorithm. We describe the software MAQ that can build assemblies by mapping shotgun short reads to a reference genome, using quality scores to derive genotype calls of the consensus sequence of a diploid genome, e.g., from a human sample. MAQ makes full use of mate-pair information and estimates the error probability of each read alignment. Error probabilities are also derived for the final genotype calls, using a Bayesian statistical model that incorporates the mapping qualities, error probabilities from the raw sequence quality scores, sampling of the two haplotypes, and an empirical model for correlated errors at a site. Both read mapping and genotype calling are evaluated on simulated data and real data. MAQ is accurate, efficient, versatile, and user-friendly. It is freely available at http://maq.sourceforge.net.},
	Author = {Li, Heng and Ruan, Jue and Durbin, Richard},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1101/gr.078212.108},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Algorithms; Bayes Theorem; Chromosome Mapping; Computer Simulation; DNA; DNA, Bacterial; Diploidy; Genome, Bacterial; Genome, Human; Humans; Polymorphism, Single Nucleotide; Reproducibility of Results; Salmonella paratyphi A; Sequence Alignment; Sequence Analysis, DNA; Software},
	Month = {Nov},
	Number = {11},
	Pages = {1851-8},
	Pmid = {18714091},
	Title = {Mapping short DNA sequencing reads and calling variants using mapping quality scores},
	Volume = {18},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.078212.108}}

@article{MacArthur:2009ly,
	Abstract = {BACKGROUND: We previously established that six sequence-specific transcription factors that initiate anterior/posterior patterning in Drosophila bind to overlapping sets of thousands of genomic regions in blastoderm embryos. While regions bound at high levels include known and probable functional targets, more poorly bound regions are preferentially associated with housekeeping genes and/or genes not transcribed in the blastoderm, and are frequently found in protein coding sequences or in less conserved non-coding DNA, suggesting that many are likely non-functional. RESULTS: Here we show that an additional 15 transcription factors that regulate other aspects of embryo patterning show a similar quantitative continuum of function and binding to thousands of genomic regions in vivo. Collectively, the 21 regulators show a surprisingly high overlap in the regions they bind given that they belong to 11 DNA binding domain families, specify distinct developmental fates, and can act via different cis-regulatory modules. We demonstrate, however, that quantitative differences in relative levels of binding to shared targets correlate with the known biological and transcriptional regulatory specificities of these factors. CONCLUSIONS: It is likely that the overlap in binding of biochemically and functionally unrelated transcription factors arises from the high concentrations of these proteins in nuclei, which, coupled with their broad DNA binding specificities, directs them to regions of open chromatin. We suggest that most animal transcription factors will be found to show a similar broad overlapping pattern of binding in vivo, with specificity achieved by modulating the amount, rather than the identity, of bound factor.},
	Author = {MacArthur, Stewart and Li, Xiao-Yong and Li, Jingyi and Brown, James B and Chu, Hou Cheng and Zeng, Lucy and Grondona, Brandi P and Hechmer, Aaron and Simirenko, Lisa and Ker{\"a}nen, Soile V E and Knowles, David W and Stapleton, Mark and Bickel, Peter and Biggin, Mark D and Eisen, Michael B},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1186/gb-2009-10-7-r80},
	Journal = {Genome Biol},
	Journal-Full = {Genome biology},
	Number = {7},
	Pages = {R80},
	Pmid = {19627575},
	Title = {Developmental roles of 21 Drosophila transcription factors are determined by quantitative differences in binding to an overlapping set of thousands of genomic regions},
	Volume = {10},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/gb-2009-10-7-r80}}

@article{MaynardSmithHaigh1974,
	Author = {Maynard Smith, JM. and Haigh, J.},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {Genetical Research},
	Number = {23},
	Pages = {23--35},
	Title = {The hitch-hiking effect of a favourable gene},
	Year = {1974}}

@article{Nielsenetal2005b,
	Abstract = {Since the divergence of humans and chimpanzees about 5 million years ago, these species have undergone a remarkable evolution with drastic divergence in anatomy and cognitive abilities. At the molecular level, despite the small overall magnitude of DNA sequence divergence, we might expect such evolutionary changes to leave a noticeable signature throughout the genome. We here compare 13,731 annotated genes from humans to their chimpanzee orthologs to identify genes that show evidence of positive selection. Many of the genes that present a signature of positive selection tend to be involved in sensory perception or immune defenses. However, the group of genes that show the strongest evidence for positive selection also includes a surprising number of genes involved in tumor suppression and apoptosis, and of genes involved in spermatogenesis. We hypothesize that positive selection in some of these genes may be driven by genomic conflict due to apoptosis during spermatogenesis. Genes with maximal expression in the brain show little or no evidence for positive selection, while genes with maximal expression in the testis tend to be enriched with positively selected genes. Genes on the X chromosome also tend to show an elevated tendency for positive selection. We also present polymorphism data from 20 Caucasian Americans and 19 African Americans for the 50 annotated genes showing the strongest evidence for positive selection. The polymorphism analysis further supports the presence of positive selection in these genes by showing an excess of high-frequency derived nonsynonymous mutations.},
	Address = {Biological Statistics and Computational Biology, Cornell University, Ithaca, New York, USA. rasmus@binf.ku.dk},
	Aid = {04-PLBI-RA-0748R3 {$[$}pii{$]$}, 10.1371/journal.pbio.0030170 {$[$}doi{$]$}},
	Au = {Nielsen R and Bustamante C and Clark AG and Glanowski S and Sackton TB and Hubisz MJ and Fledel-Alon A and Tanenbaum DM and Civello D and White TJ and J Sninsky J and Adams MD and Cargill M},
	Author = {Nielsen, Rasmus and Bustamante, Carlos and Clark, Andrew G and Glanowski, Stephen and Sackton, Timothy B and Hubisz, Melissa J and Fledel-Alon, Adi and Tanenbaum, David M and Civello, Daniel and White, Thomas J and J Sninsky, John and Adams, Mark D and Cargill, Michele},
	Da = {20050608},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {20060303},
	Dep = {20050503},
	Edat = {2005/05/05 09:00},
	Issn = {1545-7885 (Electronic)},
	Jid = {101183755},
	Journal = {PLoS Biol},
	Jt = {PLoS biology},
	Keywords = {Animals, Evolution, Molecular, *Genome, *Genome, Human, Humans, Likelihood Functions, Pan troglodytes/*genetics, Polymerase Chain Reaction, Selection (Genetics), Zinc Fingers/genetics},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2006/03/04 09:00},
	Number = {6},
	Own = {NLM},
	Pages = {e170},
	Phst = {2004/09/30 {$[$}received{$]$}, 2005/03/14 {$[$}accepted{$]$}, 2005/05/03 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15869325},
	Pst = {ppublish},
	Pt = {Comparative Study, Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {PLoS Biol. 2005 Jun;3(6):e170. Epub 2005 May 3.},
	Stat = {MEDLINE},
	Title = {A scan for positively selected genes in the genomes of humans and chimpanzees.},
	Volume = {3},
	Year = {2005}}

@article{Nielsen:2005zr,
	Abstract = {Detecting selective sweeps from genomic SNP data is complicated by the intricate ascertainment schemes used to discover SNPs, and by the confounding influence of the underlying complex demographics and varying mutation and recombination rates. Current methods for detecting selective sweeps have little or no robustness to the demographic assumptions and varying recombination rates, and provide no method for correcting for ascertainment biases. Here, we present several new tests aimed at detecting selective sweeps from genomic SNP data. Using extensive simulations, we show that a new parametric test, based on composite likelihood, has a high power to detect selective sweeps and is surprisingly robust to assumptions regarding recombination rates and demography (i.e., has low Type I error). Our new test also provides estimates of the location of the selective sweep(s) and the magnitude of the selection coefficient. To illustrate the method, we apply our approach to data from the Seattle SNP project and to Chromosome 2 data from the HapMap project. In Chromosome 2, the most extreme signal is found in the lactase gene, which previously has been shown to be undergoing positive selection. Evidence for selective sweeps is also found in many other regions, including genes known to be associated with disease risk such as DPP10 and COL4A3.},
	Author = {Nielsen, Rasmus and Williamson, Scott and Kim, Yuseob and Hubisz, Melissa J and Clark, Andrew G and Bustamante, Carlos},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1101/gr.4252305},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {African Americans; Computer Simulation; European Continental Ancestry Group; Genome, Human; Genomics; Haplotypes; Humans; Models, Genetic; Polymorphism, Single Nucleotide; Selection (Genetics)},
	Month = {Nov},
	Number = {11},
	Pages = {1566-75},
	Pmid = {16251466},
	Title = {Genomic scans for selective sweeps using SNP data},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.4252305}}

@article{Pollardetal2006,
	Abstract = {Comparative genomics allow us to search the human genome for segments that were extensively changed in the last ~5 million years since divergence from our common ancestor with chimpanzee, but are highly conserved in other species and thus are likely to be functional. We found 202 genomic elements that are highly conserved in vertebrates but show evidence of significantly accelerated substitution rates in human. These are mostly in non-coding DNA, often near genes associated with transcription and DNA binding. Resequencing confirmed that the five most accelerated elements are dramatically changed in human but not in other primates, with seven times more substitutions in human than in chimp. The accelerated elements, and in particular the top five, show a strong bias for adenine and thymine to guanine and cytosine nucleotide changes and are disproportionately located in high recombination and high guanine and cytosine content environments near telomeres, suggesting either biased gene conversion or isochore selection. In addition, there is some evidence of directional selection in the regions containing the two most accelerated regions. A combination of evolutionary forces has contributed to accelerated evolution of the fastest evolving elements in the human genome.},
	Aid = {05-PLGE-RA-0435R4 {$[$}pii{$]$}, 10.1371/journal.pgen.0020168 {$[$}doi{$]$}},
	Author = {Pollard, KS and Salama, SR and King, B and Kern, AD and Dreszer, T and Katzman, S and Siepel, A and Pedersen, JS and Bejerano, G and Baertsch, R and Rosenbloom, KR and Kent, J and Haussler, D},
	Da = {20061016},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dep = {20061013},
	Edat = {2006/10/17 09:00},
	Issn = {1553-7404 (Electronic)},
	Jid = {101239074},
	Journal = {PLoS Genet},
	Language = {ENG},
	Mhda = {2006/10/17 09:00},
	Number = {10},
	Own = {NLM},
	Phst = {2005/12/27 {$[$}received{$]$}, 2006/08/23 {$[$}accepted{$]$}},
	Pmid = {17040131},
	Pst = {aheadofprint},
	Pt = {JOURNAL ARTICLE},
	Pubm = {Print-Electronic},
	So = {PLoS Genet. 2006 Oct 13;2(10).},
	Stat = {Publisher},
	Title = {Forces Shaping the Fastest Evolving Regions in the Human Genome.},
	Volume = {2},
	Year = {2006}}

@article{Przeworski:2005bk,
	Abstract = {Considerable interest is focused on the use of polymorphism data to identify regions of the genome that underlie recent adaptations. These searches are guided by a simple model of positive selection, in which a mutation is favored as soon as it arises. This assumption may not be realistic, as environmental changes and range expansions may lead previously neutral or deleterious alleles to become beneficial. We examine what effect this mode of selection has on patterns of variation at linked neutral sites by implementing a new coalescent model of positive directional selection on standing variation. In this model, a neutral allele arises and drifts in the population, then at frequency f becomes beneficial, and eventually reaches fixation. Depending on the value of f, this scenario can lead to a large variance in allele frequency spectra and in levels of linkage disequilibrium at linked, neutral sites. In particular, for intermediate f, the beneficial substitution often leads to a loss of rare alleles--a pattern that differs markedly from the signature of directional selection currently relied on by researchers. These findings highlight the importance of an accurate characterization of the effects of positive selection, if we are to reliably identify recent adaptations from polymorphism data.},
	Address = {Department of Human Genetics, University of Chicago, Illinois 60637, USA. mfp@uchicago.edu},
	Au = {Przeworski, M and Coop, G and Wall, JD},
	Author = {Przeworski, Molly and Coop, Graham and Wall, Jeffrey D},
	Crdt = {2006/01/07 09:00},
	Da = {20060106},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {20060203},
	Edat = {2006/01/07 09:00},
	Gr = {GM72861/GM/NIGMS NIH HHS/United States; HG002772/HG/NHGRI NIH HHS/United States},
	Issn = {0014-3820 (Print)},
	Jid = {0373224},
	Journal = {Evolution},
	Jt = {Evolution; international journal of organic evolution},
	Keywords = {Evolution; Gene Frequency; *Genetic Variation; Linkage Disequilibrium; *Models, Genetic; *Selection (Genetics)},
	Language = {eng},
	Lr = {20081121},
	Mhda = {2006/02/04 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {2312--2323},
	Pl = {United States},
	Pmid = {16396172},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Sb = {IM},
	So = {Evolution. 2005 Nov;59(11):2312-23.},
	Stat = {MEDLINE},
	Title = {The signature of positive selection on standing genetic variation.},
	Volume = {59},
	Year = {2005}}

@article{Sella:2009px,
	Abstract = {Over the past four decades, the predominant view of molecular evolution saw little connection between natural selection and genome evolution, assuming that the functionally constrained fraction of the genome is relatively small and that adaptation is sufficiently infrequent to play little role in shaping patterns of variation within and even between species. Recent evidence from Drosophila, reviewed here, suggests that this view may be invalid. Analyses of genetic variation within and between species reveal that much of the Drosophila genome is under purifying selection, and thus of functional importance, and that a large fraction of coding and noncoding differences between species are adaptive. The findings further indicate that, in Drosophila, adaptations may be both common and strong enough that the fate of neutral mutations depends on their chance linkage to adaptive mutations as much as on the vagaries of genetic drift. The emerging evidence has implications for a wide variety of fields, from conservation genetics to bioinformatics, and presents challenges to modelers and experimentalists alike.},
	Author = {Sella, Guy and Petrov, Dmitri A and Przeworski, Molly and Andolfatto, Peter},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1371/journal.pgen.1000495},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Drosophila; Evolution, Molecular; Genetic Variation; Genome, Insect; Mutation; Selection (Genetics)},
	Month = {Jun},
	Number = {6},
	Pages = {e1000495},
	Pmid = {19503600},
	Title = {Pervasive natural selection in the Drosophila genome?},
	Volume = {5},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000495}}

@article{Singh:2005yf,
	Abstract = {Mutation is the underlying force that provides the variation upon which evolutionary forces can act. It is important to understand how mutation rates vary within genomes and how the probabilities of fixation of new mutations vary as well. If substitutional processes across the genome are heterogeneous, then examining patterns of coding sequence evolution without taking these underlying variations into account may be misleading. Here we present the first rigorous test of substitution rate heterogeneity in the Drosophila melanogaster genome using almost 1500 nonfunctional fragments of the transposable element DNAREP1_DM. Not only do our analyses suggest that substitutional patterns in heterochromatic and euchromatic sequences are different, but also they provide support in favor of a recombination-associated substitutional bias toward G and C in this species. The magnitude of this bias is entirely sufficient to explain recombination-associated patterns of codon usage on the autosomes of the D. melanogaster genome. We also document a bias toward lower GC content in the pattern of small insertions and deletions (indels). In addition, the GC content of noncoding DNA in Drosophila is higher than would be predicted on the basis of the pattern of nucleotide substitutions and small indels. However, we argue that the fast turnover of noncoding sequences in Drosophila makes it difficult to assess the importance of the GC biases in nucleotide substitutions and small indels in shaping the base composition of noncoding sequences.},
	Author = {Singh, Nadia D and Arndt, Peter F and Petrov, Dmitri A},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1534/genetics.104.032250},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Base Composition; Base Pairing; Chromosome Mapping; Codon; DNA Transposable Elements; Drosophila melanogaster; Euchromatin; Evolution, Molecular; Genetic Heterogeneity; Genetic Variation; Genome; Heterochromatin; Kinetics; Models, Genetic; Mutation; Recombination, Genetic},
	Month = {Feb},
	Number = {2},
	Pages = {709-22},
	Pmid = {15520267},
	Title = {Genomic heterogeneity of background substitutional patterns in Drosophila melanogaster},
	Volume = {169},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.104.032250}}

@article{Stephan:2007ss,
	Abstract = {Population genetic analyses of the past two decades confirmed an earlier hypothesis by L Tsacas and D Lachaise that the cosmopolitan species Drosophila melanogaster has an Afrotropical origin, and that it colonized the rest of the world only very recently. Maximum likelihood analyses based on multilocus data suggest that the putative ancestral African population expanded its size about 60,000 years ago (ya). These demographic changes were accompanied by the fixation of numerous beneficial mutations, as revealed by signatures of positive directional selection in the genome (selective sweeps). The estimated rate of adaptive substitution on the X chromosome is in the order of 10(-11) per nucleotide site per generation. Comparable (but not significantly higher) substitution rates are found in derived populations that colonized new habitats outside Africa, such as in a European population that branched off from the African lineage about 16,000 ya.},
	Author = {Stephan, W and Li, H},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1038/sj.hdy.6800901},
	Journal = {Heredity},
	Journal-Full = {Heredity},
	Mesh = {Adaptation, Physiological; Africa; Animals; Drosophila melanogaster; Europe; Evolution, Molecular; Genetic Variation; Genetics, Population; Selection (Genetics); Species Specificity; X Chromosome},
	Month = {Feb},
	Number = {2},
	Pages = {65-8},
	Pmid = {17006533},
	Title = {The recent demographic and adaptive history of Drosophila melanogaster},
	Volume = {98},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/sj.hdy.6800901}}

@article{Storey:2002ly,
	Abstract = {Multiple-hypothesis testing involves guarding against much more complicated errors than single-hypothesis testing. Whereas we typically control the type I error rate for a single-hypothesis test, a compound error rate is controlled for multiple-hypothesis tests. For example, controlling the false discovery rate FDR traditionally involves intricate sequential p-value rejection methods based on the observed data. Whereas a sequential p-value method fixes the error rate and estimates its corresponding rejection region, we propose the opposite approach-we fix the rejection region and then estimate its corresponding error rate. This new approach offers increased applicability, accuracy and power. We apply the methodology to both the positive false discovery rate pFDR and FDR, and provide evidence for its benefits. It is shown that pFDR is probably the quantity of interest over FDR. Also discussed is the calculation of the q-value, the pFDR analogue of the p-value, which eliminates the need to set the error rate beforehand as is traditionally done. Some simple numerical examples are presented that show that this new approach can yield an increase of over eight times in power compared with the Benjamini-Hochberg FDR method.},
	Address = {108 COWLEY RD, OXFORD OX4 1JF, OXON, ENGLAND},
	Author = {Storey, JD},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Isi = {000177425500009},
	Isi-Recid = {126051257},
	Isi-Ref-Recids = {112504863 90155838 115373815 122784094 87253760 119531800 126051258 126051259 119668320 112504865},
	Journal = {Journal of the Royal Statistical Society Series B-Statistical Methodology},
	Keywords = {false discovery rate; multiple comparisons; positive false discovery rate; p-values; q-values; sequential p-value methods; simultaneous inference},
	Pages = {479-498},
	Publisher = {BLACKWELL PUBL LTD},
	Times-Cited = {715},
	Title = {A direct approach to false discovery rates},
	Volume = {64},
	Year = {2002},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=000177425500009}}

@article{Tajima:1990fx,
	Abstract = {When there is no recombination among nucleotide sites in DNA sequences, DNA polymorphism and fixation of mutants at nucleotide sites are mutually related. Using the method of gene genealogy, the relationship between the DNA polymorphism and the fixation of mutant nucleotide was quantitatively investigated under the assumption that mutants are selectively neutral, that there is no recombination among nucleotide sites, and that the population is a random mating population with N diploid individuals. The results obtained indicate that the expected number of nucleotide differences between two DNA sequences randomly sampled from the population is 42% less when a mutant at a particular nucleotide site reaches fixation than at a random time, and that heterozygosity is also expected to be less when fixation takes place than at a random time, but the amount of reduction depends on the value of 4Nv in this case, where v is the mutation rate per DNA sequence per generation. The formula for obtaining the expected number of nucleotide differences between the two DNA sequences for a given fixation time is also derived, and indicates that, even when it takes a large number of generations for a mutant to reach fixation, this number is 33% less than at a random time. The computer simulation conducted suggests that the expected number of nucleotide differences between the two DNA sequences at the time when an advantageous mutant becomes fixed is essentially the same as that of neutral mutant if the fixation time is the same. The effect of recombination on the amount of DNA polymorphism was also investigated by using computer simulation.},
	Address = {National Institute of Genetics, Mishima, Japan.},
	Au = {Tajima, F},
	Author = {Tajima, F},
	Crdt = {1990/06/01 00:00},
	Da = {19900912},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {19900912},
	Edat = {1990/06/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {Base Sequence; Computer Simulation; DNA/*genetics; Kinetics; Mathematics; *Models, Genetic; Mutation; *Polymorphism, Genetic; Recombination, Genetic},
	Language = {eng},
	Lr = {20081120},
	Mhda = {1990/06/01 00:01},
	Number = {2},
	Oid = {NLM: PMC1204032},
	Own = {NLM},
	Pages = {447--454},
	Pl = {UNITED STATES},
	Pmc = {PMC1204032},
	Pmid = {2379822},
	Pst = {ppublish},
	Pt = {Journal Article},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Genetics. 1990 Jun;125(2):447-54.},
	Stat = {MEDLINE},
	Title = {Relationship between DNA polymorphism and fixation time.},
	Volume = {125},
	Year = {1990}}

@article{Tribolium-Genome-Sequencing-Consortium:2008gf,
	Abstract = {Tribolium castaneum is a member of the most species-rich eukaryotic order, a powerful model organism for the study of generalized insect development, and an important pest of stored agricultural products. We describe its genome sequence here. This omnivorous beetle has evolved the ability to interact with a diverse chemical environment, as shown by large expansions in odorant and gustatory receptors, as well as P450 and other detoxification enzymes. Development in Tribolium is more representative of other insects than is Drosophila, a fact reflected in gene content and function. For example, Tribolium has retained more ancestral genes involved in cell-cell communication than Drosophila, some being expressed in the growth zone crucial for axial elongation in short-germ development. Systemic RNA interference in T. castaneum functions differently from that in Caenorhabditis elegans, but nevertheless offers similar power for the elucidation of gene function and identification of targets for selective insect control.},
	Author = {{Tribolium Genome Sequencing Consortium} and Richards, Stephen and Gibbs, Richard A and Weinstock, George M and Brown, Susan J and Denell, Robin and Beeman, Richard W and Gibbs, Richard and Beeman, Richard W and Brown, Susan J and Bucher, Gregor and Friedrich, Markus and Grimmelikhuijzen, Cornelis J P and Klingler, Martin and Lorenzen, Marce and Richards, Stephen and Roth, Siegfried and Schr{\"o}der, Reinhard and Tautz, Diethard and Zdobnov, Evgeny M and Muzny, Donna and Gibbs, Richard A and Weinstock, George M and Attaway, Tony and Bell, Stephanie and Buhay, Christian J and Chandrabose, Mimi N and Chavez, Dean and Clerk-Blankenburg, Kerstin P and Cree, Andrew and Dao, Marvin and Davis, Clay and Chacko, Joseph and Dinh, Huyen and Dugan-Rocha, Shannon and Fowler, Gerald and Garner, Toni T and Garnes, Jeffrey and Gnirke, Andreas and Hawes, Alica and Hernandez, Judith and Hines, Sandra and Holder, Michael and Hume, Jennifer and Jhangiani, Shalini N and Joshi, Vandita and Khan, Ziad Mohid and Jackson, LaRonda and Kovar, Christie and Kowis, Andrea and Lee, Sandra and Lewis, Lora R and Margolis, Jon and Morgan, Margaret and Nazareth, Lynne V and Nguyen, Ngoc and Okwuonu, Geoffrey and Parker, David and Richards, Stephen and Ruiz, San-Juana and Santibanez, Jireh and Savard, Jo{\"e}l and Scherer, Steven E and Schneider, Brian and Sodergren, Erica and Tautz, Diethard and Vattahil, Selina and Villasana, Donna and White, Courtney S and Wright, Rita and Park, Yoonseong and Beeman, Richard W and Lord, Jeff and Oppert, Brenda and Lorenzen, Marce and Brown, Susan and Wang, Liangjiang and Savard, Jo{\"e}l and Tautz, Diethard and Richards, Stephen and Weinstock, George and Gibbs, Richard A and Liu, Yue and Worley, Kim and Weinstock, George and Elsik, Christine G and Reese, Justin T and Elhaik, Eran and Landan, Giddy and Graur, Dan and Arensburger, Peter and Atkinson, Peter and Beeman, Richard W and Beidler, Jim and Brown, Susan J and Demuth, Jeffery P and Drury, Douglas W and Du, Yu-Zhou and Fujiwara, Haruhiko and Lorenzen, Marce and Maselli, Vincenza and Osanai, Mizuko and Park, Yoonseong and Robertson, Hugh M and Tu, Zhijian and Wang, Jian-jun and Wang, Suzhi and Richards, Stephen and Song, Henry and Zhang, Lan and Sodergren, Erica and Werner, Doreen and Stanke, Mario and Morgenstern, Burkhard and Solovyev, Victor and Kosarev, Peter and Brown, Garth and Chen, Hsiu-Chuan and Ermolaeva, Olga and Hlavina, Wratko and Kapustin, Yuri and Kiryutin, Boris and Kitts, Paul and Maglott, Donna and Pruitt, Kim and Sapojnikov, Victor and Souvorov, Alexandre and Mackey, Aaron J and Waterhouse, Robert M and Wyder, Stefan and Zdobnov, Evgeny M and Zdobnov, Evgeny M and Wyder, Stefan and Kriventseva, Evgenia V and Kadowaki, Tatsuhiko and Bork, Peer and Aranda, Manuel and Bao, Riyue and Beermann, Anke and Berns, Nicola and Bolognesi, Renata and Bonneton, Fran{\c c}ois and Bopp, Daniel and Brown, Susan J and Bucher, Gregor and Butts, Thomas and Chaumot, Arnaud and Denell, Robin E and Ferrier, David E K and Friedrich, Markus and Gordon, Cassondra M and Jindra, Marek and Klingler, Martin and Lan, Que and Lattorff, H Michael G and Laudet, Vincent and von Levetsow, Cornelia and Liu, Zhenyi and Lutz, Rebekka and Lynch, Jeremy A and da Fonseca, Rodrigo Nunes and Posnien, Nico and Reuter, Rolf and Roth, Siegfried and Savard, Jo{\"e}l and Schinko, Johannes B and Schmitt, Christian and Schoppmeier, Michael and Schr{\"o}der, Reinhard and Shippy, Teresa D and Simonnet, Franck and Marques-Souza, Henrique and Tautz, Diethard and Tomoyasu, Yoshinori and Trauner, Jochen and Van der Zee, Maurijn and Vervoort, Michel and Wittkopp, Nadine and Wimmer, Ernst A and Yang, Xiaoyun and Jones, Andrew K and Sattelle, David B and Ebert, Paul R and Nelson, David and Scott, Jeffrey G and Beeman, Richard W and Muthukrishnan, Subbaratnam and Kramer, Karl J and Arakane, Yasuyuki and Beeman, Richard W and Zhu, Qingsong and Hogenkamp, David and Dixit, Radhika and Oppert, Brenda and Jiang, Haobo and Zou, Zhen and Marshall, Jeremy and Elpidina, Elena and Vinokurov, Konstantin and Oppert, Cris and Zou, Zhen and Evans, Jay and Lu, Zhiqiang and Zhao, Picheng and Sumathipala, Niranji and Altincicek, Boran and Vilcinskas, Andreas and Williams, Michael and Hultmark, Dan and Hetru, Charles and Jiang, Haobo and Grimmelikhuijzen, Cornelis J P and Hauser, Frank and Cazzamali, Giuseppe and Williamson, Michael and Park, Yoonseong and Li, Bin and Tanaka, Yoshiaki and Predel, Reinhard and Neupert, Susanne and Schachtner, Joachim and Verleyen, Peter and Raible, Florian and Bork, Peer and Friedrich, Markus and Walden, Kimberly K O and Robertson, Hugh M and Angeli, Sergio and For{\^e}t, Sylvain and Bucher, Gregor and Schuetz, Stefan and Maleszka, Ryszard and Wimmer, Ernst A and Beeman, Richard W and Lorenzen, Marce and Tomoyasu, Yoshinori and Miller, Sherry C and Grossmann, Daniela and Bucher, Gregor},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1038/nature06784},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Base Composition; Body Patterning; Cytochrome P-450 Enzyme System; DNA Transposable Elements; Genes, Insect; Genome, Insect; Growth and Development; Humans; Insecticides; Neurotransmitter Agents; Oogenesis; Phylogeny; Proteome; RNA Interference; Receptors, G-Protein-Coupled; Receptors, Odorant; Repetitive Sequences, Nucleic Acid; Taste; Telomere; Tribolium; Vision, Ocular},
	Month = {Apr},
	Number = {7190},
	Pages = {949-55},
	Pmid = {18362917},
	Title = {The genome of the model beetle and pest Tribolium castaneum},
	Volume = {452},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature06784}}

@article{voightetal2006,
	Author = {Voight, BF and Kudaravalli, S and Wen, X and Pritchard, JK},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {PLoS Biol.},
	Number = {3},
	Pages = {e72},
	Title = {A map of recent positive selection in the human genome.},
	Volume = {4},
	Year = {2006}}

@article{Williamson:2007hh,
	Abstract = {Identifying genomic locations that have experienced selective sweeps is an important first step toward understanding the molecular basis of adaptive evolution. Using statistical methods that account for the confounding effects of population demography, recombination rate variation, and single-nucleotide polymorphism ascertainment, while also providing fine-scale estimates of the position of the selected site, we analyzed a genomic dataset of 1.2 million human single-nucleotide polymorphisms genotyped in African-American, European-American, and Chinese samples. We identify 101 regions of the human genome with very strong evidence (p < 10(-5)) of a recent selective sweep and where our estimate of the position of the selective sweep falls within 100 kb of a known gene. Within these regions, genes of biological interest include genes in pigmentation pathways, components of the dystrophin protein complex, clusters of olfactory receptors, genes involved in nervous system development and function, immune system genes, and heat shock genes. We also observe consistent evidence of selective sweeps in centromeric regions. In general, we find that recent adaptation is strikingly pervasive in the human genome, with as much as 10% of the genome affected by linkage to a selective sweep.},
	Address = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York, United States of America. sw292@cornell.edu},
	Au = {Williamson, SH and Hubisz, MJ and Clark, AG and Payseur, BA and Bustamante, CD and Nielsen, R},
	Author = {Williamson, Scott H and Hubisz, Melissa J and Clark, Andrew G and Payseur, Bret A and Bustamante, Carlos D and Nielsen, Rasmus},
	Crdt = {2007/06/05 09:00},
	Da = {20070816},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Dcom = {20071127},
	Dep = {20070420},
	Doi = {10.1371/journal.pgen.0030090},
	Edat = {2007/06/05 09:00},
	Gr = {1R01HG003229/HG/NHGRI NIH HHS/United States},
	Issn = {1553-7404 (Electronic)},
	Jid = {101239074},
	Journal = {PLoS Genet},
	Jt = {PLoS genetics},
	Keywords = {Adaptation, Biological/*genetics; *Evolution, Molecular; *Genome, Human; Humans; Polymorphism, Single Nucleotide},
	Language = {eng},
	Lr = {20081120},
	Mhda = {2007/12/06 09:00},
	Number = {6},
	Oid = {NLM: PMC1885279},
	Own = {NLM},
	Pages = {e90},
	Phst = {2006/08/30 {$[$}received{$]$}; 2007/04/20 {$[$}accepted{$]$}; 2007/04/20 {$[$}aheadofprint{$]$}},
	Pii = {06-PLGE-RA-0365R2},
	Pl = {United States},
	Pmc = {PMC1885279},
	Pmid = {17542651},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S.},
	Sb = {IM},
	So = {PLoS Genet. 2007 Jun;3(6):e90. Epub 2007 Apr 20.},
	Stat = {MEDLINE},
	Title = {Localizing recent adaptive evolution in the human genome.},
	Volume = {3},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.0030090}}

@article{Williamson:2005ay,
	Abstract = {Natural selection and demographic forces can have similar effects on patterns of DNA polymorphism. Therefore, to infer selection from samples of DNA sequences, one must simultaneously account for demographic effects. Here we take a model-based approach to this problem by developing predictions for patterns of polymorphism in the presence of both population size change and natural selection. If data are available from different functional classes of variation, and a priori information suggests that mutations in one of those classes are selectively neutral, then the putatively neutral class can be used to infer demographic parameters, and inferences regarding selection on other classes can be performed given demographic parameter estimates. This procedure is more robust to assumptions regarding the true underlying demography than previous approaches to detecting and analyzing selection. We apply this method to a large polymorphism data set from 301 human genes and find (i) widespread negative selection acting on standing nonsynonymous variation, (ii) that the fitness effects of nonsynonymous mutations are well predicted by several measures of amino acid exchangeability, especially site-specific methods, and (iii) strong evidence for very recent population growth.},
	Author = {Williamson, Scott H and Hernandez, Ryan and Fledel-Alon, Adi and Zhu, Lan and Nielsen, Rasmus and Bustamante, Carlos D},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1073/pnas.0502300102},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Computational Biology; Genes; Genome, Human; Genomics; Humans; Likelihood Functions; Models, Genetic; Mutation; Polymorphism, Genetic; Population Growth; Selection (Genetics)},
	Month = {May},
	Number = {22},
	Pages = {7882-7},
	Pmid = {15905331},
	Title = {Simultaneous inference of selection and population growth from patterns of variation in the human genome},
	Volume = {102},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0502300102}}

@article{Yang:1995wn,
	Abstract = {A statistical method was developed for reconstructing the nucleotide or amino acid sequences of extinct ancestors, given the phylogeny and sequences of the extant species. A model of nucleotide or amino acid substitution was employed to analyze data of the present-day sequences, and maximum likelihood estimates of parameters such as branch lengths were used to compare the posterior probabilities of assignments of character states (nucleotides or amino acids) to interior nodes of the tree; the assignment having the highest probability was the best reconstruction at the site. The lysozyme c sequences of six mammals were analyzed by using the likelihood and parsimony methods. The new likelihood-based method was found to be superior to the parsimony method. The probability that the amino acids for all interior nodes at a site reconstructed by the new method are correct was calculated to be 0.91, 0.86, and 0.73 for all, variable, and parsimony-informative sites, respectively, whereas the corresponding probabilities for the parsimony method were 0.84, 0.76, and 0.51, respectively. The probability that an amino acid in an ancestral sequence is correctly reconstructed by the likelihood analysis ranged from 91.3 to 98.7\% for the four ancestral sequences.},
	Author = {Yang, Z and Kumar, S and Nei, M},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Amino Acid Sequence; Animals; Base Sequence; Humans; Likelihood Functions; Molecular Sequence Data; Phylogeny; Selection (Genetics); Sequence Alignment},
	Month = {Dec},
	Number = {4},
	Pages = {1641-50},
	Pmid = {8601501},
	Title = {A new method of inference of ancestral nucleotide and amino acid sequences},
	Volume = {141},
	Year = {1995}}

@article{Yang:1996ol,
	Abstract = {Although several decades of study have revealed the ubiquity of variation of evolutionary rates among sites, reliable methods for studying rate variation were not developed until very recently. Early methods fit theoretical distributions to the numbers of changes at sites inferred by parsimony and substantially underestimate the rate variation. Recent analyses show that failure to account for rate variation can have drastic effects, leading to biased dating of speciation events, biased estimation of the transition:transversion rate ratio, and incorrect reconstruction of phylogenies.},
	Address = {THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD, OXON, ENGLAND OX5 1GB},
	Author = {Yang, ZH},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Isi = {A1996VC82300007},
	Isi-Recid = {97090834},
	Isi-Ref-Recids = {91496515 94813562 17174079 92572062 17421711 94203001 15413015 89818489 60939136 52276181 91858246 57684838 84765867 97090835 90983278 71151850 79944488 95240695 16311110 87135898 94795939 95624868 57733928 94882664 69760211 93007753 86414678 95230585 93361728 83481386 86599936 19965926 85302229 87135894 95139482 72423924 88167307 86599948 95661809 93866287 87386291 92189600 90119541 88167305 91496539 93534134 85384143},
	Journal = {Trends In Ecology \& Evolution},
	Month = sep,
	Number = {9},
	Pages = {367-372},
	Publisher = {ELSEVIER SCI LTD},
	Times-Cited = {594},
	Title = {Among-site rate variation and its impact on phylogenetic analyses},
	Volume = {11},
	Year = {1996},
	Bdsk-Url-1 = {http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS&DestLinkType=FullRecord;KeyUT=A1996VC82300007}}

@article{Yang:2007zh,
	Abstract = {PAML, currently in version 4, is a package of programs for phylogenetic analyses of DNA and protein sequences using maximum likelihood (ML). The programs may be used to compare and test phylogenetic trees, but their main strengths lie in the rich repertoire of evolutionary models implemented, which can be used to estimate parameters in models of sequence evolution and to test interesting biological hypotheses. Uses of the programs include estimation of synonymous and nonsynonymous rates (d(N) and d(S)) between two protein-coding DNA sequences, inference of positive Darwinian selection through phylogenetic comparison of protein-coding genes, reconstruction of ancestral genes and proteins for molecular restoration studies of extinct life forms, combined analysis of heterogeneous data sets from multiple gene loci, and estimation of species divergence times incorporating uncertainties in fossil calibrations. This note discusses some of the major applications of the package, which includes example data sets to demonstrate their use. The package is written in ANSI C, and runs under Windows, Mac OSX, and UNIX systems. It is available at -- (http://abacus.gene.ucl.ac.uk/software/paml.html).},
	Author = {Yang, Ziheng},
	Date-Added = {2009-11-16 09:39:20 -0500},
	Date-Modified = {2009-11-16 09:39:20 -0500},
	Doi = {10.1093/molbev/msm088},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Animals; Computer Simulation; Genetic Variation; Likelihood Functions; Models, Genetic; Phylogeny; Selection (Genetics); Software; Species Specificity},
	Month = {Aug},
	Number = {8},
	Pages = {1586-91},
	Pmid = {17483113},
	Title = {PAML 4: phylogenetic analysis by maximum likelihood},
	Volume = {24},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msm088}}

@article{Williamson:2007bs,
	Abstract = {Identifying genomic locations that have experienced selective sweeps is an important first step toward understanding the molecular basis of adaptive evolution. Using statistical methods that account for the confounding effects of population demography, recombination rate variation, and single-nucleotide polymorphism ascertainment, while also providing fine-scale estimates of the position of the selected site, we analyzed a genomic dataset of 1.2 million human single-nucleotide polymorphisms genotyped in African-American, European-American, and Chinese samples. We identify 101 regions of the human genome with very strong evidence (p < 10(-5)) of a recent selective sweep and where our estimate of the position of the selective sweep falls within 100 kb of a known gene. Within these regions, genes of biological interest include genes in pigmentation pathways, components of the dystrophin protein complex, clusters of olfactory receptors, genes involved in nervous system development and function, immune system genes, and heat shock genes. We also observe consistent evidence of selective sweeps in centromeric regions. In general, we find that recent adaptation is strikingly pervasive in the human genome, with as much as 10\% of the genome affected by linkage to a selective sweep.},
	Author = {Williamson, Scott H and Hubisz, Melissa J and Clark, Andrew G and Payseur, Bret A and Bustamante, Carlos D and Nielsen, Rasmus},
	Date-Added = {2009-11-16 09:04:28 -0500},
	Date-Modified = {2009-11-16 09:04:28 -0500},
	Doi = {10.1371/journal.pgen.0030090},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Adaptation, Biological; Evolution, Molecular; Genome, Human; Humans; Polymorphism, Single Nucleotide},
	Month = {Jun},
	Number = {6},
	Pages = {e90},
	Pmid = {17542651},
	Title = {Localizing recent adaptive evolution in the human genome},
	Volume = {3},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.0030090}}

@article{Andres:2009vy,
	Abstract = {Balancing selection is potentially an important biological force for maintaining advantageous genetic diversity in populations, including variation that is responsible for long-term adaptation to the environment. By serving as a means to maintain genetic variation, it may be particularly relevant to maintaining phenotypic variation in natural populations. Nevertheless, its prevalence and specific targets in the human genome remain largely unknown. We have analyzed the patterns of diversity and divergence of 13,400 genes in two human populations using an unbiased single-nucleotide polymorphism data set, a genome-wide approach, and a method that incorporates demography in neutrality tests. We identified an unbiased catalog of genes with signatures of long-term balancing selection, which includes immunity genes as well as genes encoding keratins and membrane channels; the catalog also shows enrichment in functional categories involved in cellular structure. Patterns are mostly concordant in the two populations, with a small fraction of genes showing population-specific signatures of selection. Power considerations indicate that our findings represent a subset of all targets in the genome, suggesting that although balancing selection may not have an obvious impact on a large proportion of human genes, it is a key force affecting the evolution of a number of genes in humans.},
	Author = {Andr{\'e}s, Aida M and Hubisz, Melissa J and Indap, Amit and Torgerson, Dara G and Degenhardt, Jeremiah D and Boyko, Adam R and Gutenkunst, Ryan N and White, Thomas J and Green, Eric D and Bustamante, Carlos D and Clark, Andrew G and Nielsen, Rasmus},
	Date-Added = {2009-11-16 09:04:17 -0500},
	Date-Modified = {2009-11-16 09:04:17 -0500},
	Doi = {10.1093/molbev/msp190},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Month = {Dec},
	Number = {12},
	Pages = {2755-64},
	Pmid = {19713326},
	Title = {Targets of balancing selection in the human genome},
	Volume = {26},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msp190}}

@article{Aminetzach:2005jn,
	Abstract = {To study adaptation, it is essential to identify multiple adaptive mutations and to characterize their molecular, phenotypic, selective, and ecological consequences. Here we describe a genomic screen for adaptive insertions of transposable elements in Drosophila. Using a pilot application of this screen, we have identified an adaptive transposable element insertion, which truncates a gene and apparently generates a functional protein in the process. The insertion of this transposable element confers increased resistance to an organophosphate pesticide and has spread in D. melanogaster recently.},
	Author = {Aminetzach, Yael T and Macpherson, J Michael and Petrov, Dmitri A},
	Date-Added = {2009-11-13 14:30:55 -0500},
	Date-Modified = {2009-11-13 14:30:55 -0500},
	Doi = {10.1126/science.1112699},
	Journal = {Science},
	Journal-Full = {Science (New York, N.Y.)},
	Mesh = {Adaptation, Physiological; Alleles; Amino Acid Substitution; Animals; Azinphosmethyl; Base Sequence; Choline; Crosses, Genetic; DNA Transposable Elements; Drosophila; Drosophila Proteins; Drosophila melanogaster; Evolution, Molecular; Exons; Female; Gene Expression; Genes, Insect; Haplotypes; Insecticide Resistance; Insecticides; Introns; Long Interspersed Nucleotide Elements; Molecular Sequence Data; Mutation; Polymorphism, Genetic; Recombination, Genetic; Selection (Genetics)},
	Month = {Jul},
	Number = {5735},
	Pages = {764-7},
	Pmid = {16051794},
	Title = {Pesticide resistance via transposition-mediated adaptive gene truncation in Drosophila},
	Volume = {309},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1112699}}

@article{Boitard:2009gx,
	Abstract = {Detecting and localizing selective sweeps on the basis of SNP data has recently received considerable attention. Here we introduce the use of hidden Markov models (HMMs) for the detection of selective sweeps in DNA sequences. Like previously published methods, our HMMs use the site frequency spectrum, and the spatial pattern of diversity along the sequence, to identify selection. In contrast to earlier approaches, our HMMs explicitly model the correlation structure between linked sites. The detection power of our methods, and their accuracy for estimating the selected site location, is similar to that of competing methods for constant size populations. In the case of population bottlenecks, however, our methods frequently showed fewer false positives.},
	Author = {Boitard, Simon and Schl{\"o}tterer, Christian and Futschik, Andreas},
	Date-Added = {2009-11-13 13:44:00 -0500},
	Date-Modified = {2009-11-13 13:44:00 -0500},
	Doi = {10.1534/genetics.108.100032},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Algorithms; Computer Simulation; Demography; Evolution, Molecular; Genetic Variation; Genetics, Population; Genomic Instability; Humans; Markov Chains; Models, Genetic; Selection (Genetics); Sequence Alignment},
	Month = {Apr},
	Number = {4},
	Pages = {1567-78},
	Pmid = {19204373},
	Title = {Detecting selective sweeps: a new approach based on hidden markov models},
	Volume = {181},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.108.100032}}

@article{Wiehe:2007ur,
	Abstract = {There is currently large interest in distinguishing the signatures of genetic variation produced by demographic events from those produced by natural selection. We propose a simple multilocus statistical test to identify candidate sites of selective sweeps with high power. The test is based on the variability profile measured in an array of linked microsatellites. We also show that the analysis of flanking markers drastically reduces the number of false positives among the candidates that are identified in a genomewide survey of unlinked loci and find that this property is maintained in many population-bottleneck scenarios. However, for a certain range of intermediately severe population bottlenecks we find genomic signatures that are very similar to those produced by a selective sweep. While in these worst-case scenarios the power of the proposed test remains high, the false-positive rate reaches values close to 50\%. Hence, selective sweeps may be hard to identify even if multiple linked loci are analyzed. Nevertheless, the integration of information from multiple linked loci always leads to a considerable reduction of the false-positive rate compared to a genome scan of unlinked loci. We discuss the application of this test to experimental data from Drosophila melanogaster.},
	Author = {Wiehe, Thomas and Nolte, Viola and Zivkovic, Daniel and Schl{\"o}tterer, Christian},
	Date-Added = {2009-11-13 13:43:13 -0500},
	Date-Modified = {2009-11-13 13:43:13 -0500},
	Doi = {10.1534/genetics.106.063677},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Animals; Computer Simulation; Demography; Drosophila melanogaster; Genetic Variation; Genetics, Population; Genome; Microsatellite Repeats; Mutation; Polymorphism, Genetic; Selection (Genetics)},
	Month = {Jan},
	Number = {1},
	Pages = {207-18},
	Pmid = {17057237},
	Title = {Identification of selective sweeps using a dynamically adjusted number of linked microsatellites},
	Volume = {175},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.106.063677}}

@article{Li:2006mm,
	Abstract = {An important goal of population genetics is to determine the forces that have shaped the pattern of genetic variation in natural populations. We developed a maximum likelihood method that allows us to infer demographic changes and detect recent positive selection (selective sweeps) in populations of varying size from DNA polymorphism data. Applying this approach to single nucleotide polymorphism data at more than 250 noncoding loci on the X chromosome of Drosophila melanogaster from an (ancestral) African population and a (derived) European, we found that the African population expanded about 60,000 y ago and that the European population split off from the African lineage about 15,800 y ago, thereby suffering a severe population size bottleneck. We estimated that about 160 beneficial mutations (with selection coefficients s between 0.05\% and 0.5\%) were fixed in the euchromatic portion of the X in the African population since population size expansion, and about 60 mutations (with s around 0.5\%) in the diverging European lineage.},
	Author = {Li, Haipeng and Stephan, Wolfgang},
	Date-Added = {2009-11-13 13:30:46 -0500},
	Date-Modified = {2009-11-13 13:30:46 -0500},
	Doi = {10.1371/journal.pgen.0020166},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Adaptation, Physiological; Africa; Animals; Drosophila melanogaster; Europe; Evolution, Molecular; Genetics, Population; Models, Genetic; Molecular Sequence Data; Mutagenesis; Selection (Genetics)},
	Month = {Oct},
	Number = {10},
	Pages = {e166},
	Pmid = {17040129},
	Title = {Inferring the demographic history and rate of adaptive substitution in Drosophila},
	Volume = {2},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.0020166}}

@article{Andolfatto:2007co,
	Abstract = {Several recent studies have estimated that a large fraction of amino acid divergence between species of Drosophila was fixed by positive selection, using statistical approaches based on the McDonald-Kreitman test. However, little is known about associated selection coefficients of beneficial amino acid mutations. Recurrent selective sweeps associated with adaptive substitutions should leave a characteristic signature in genome variability data that contains information about the frequency and strength of selection. Here, I document a significant negative correlation between the level and the frequency of synonymous site polymorphism and the rate of protein evolution in highly recombining regions of the X chromosome of D. melanogaster. This pattern is predicted by recurrent adaptive protein evolution and suggests that adaptation is an important determinant of patterns of neutral variation genome-wide. Using a maximum likelihood approach, I estimate the product of the rate and strength of selection under a recurrent genetic hitchhiking model, lambda2N(e)s approximately 3 x 10(-8). Using an approach based on the McDonald-Kreitman test, I estimate that approximately 50\% of divergent amino acids were driven to fixation by positive selection, implying that beneficial amino acid substitutions are of weak effect on average, on the order of 10(-5) (i.e., 2N(e)s approximately 40). Two implications of these results are that most adaptive substitutions will be difficult to detect in genome scans of selection and that population size (and genetic drift) may be an important determinant of the evolutionary dynamics of protein adaptation.},
	Author = {Andolfatto, Peter},
	Date-Added = {2009-11-13 13:14:21 -0500},
	Date-Modified = {2009-11-13 13:14:21 -0500},
	Doi = {10.1101/gr.6691007},
	Journal = {Genome Res},
	Journal-Full = {Genome research},
	Mesh = {Amino Acid Substitution; Animals; Codon; Drosophila melanogaster; Evolution, Molecular; Genetic Variation; Genome, Insect; Insect Proteins; Male; Models, Genetic; Molecular Sequence Data; Selection (Genetics); X Chromosome},
	Month = {Dec},
	Number = {12},
	Pages = {1755-62},
	Pmid = {17989248},
	Title = {Hitchhiking effects of recurrent beneficial amino acid substitutions in the Drosophila melanogaster genome},
	Volume = {17},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.6691007}}

@article{Cai:2009mw,
	Abstract = {Much effort and interest have focused on assessing the importance of natural selection, particularly positive natural selection, in shaping the human genome. Although scans for positive selection have identified candidate loci that may be associated with positive selection in humans, such scans do not indicate whether adaptation is frequent in general in humans. Studies based on the reasoning of the MacDonald-Kreitman test, which, in principle, can be used to evaluate the extent of positive selection, suggested that adaptation is detectable in the human genome but that it is less common than in Drosophila or Escherichia coli. Both positive and purifying natural selection at functional sites should affect levels and patterns of polymorphism at linked nonfunctional sites. Here, we search for these effects by analyzing patterns of neutral polymorphism in humans in relation to the rates of recombination, functional density, and functional divergence with chimpanzees. We find that the levels of neutral polymorphism are lower in the regions of lower recombination and in the regions of higher functional density or divergence. These correlations persist after controlling for the variation in GC content, density of simple repeats, selective constraint, mutation rate, and depth of sequencing coverage. We argue that these results are most plausibly explained by the effects of natural selection at functional sites -- either recurrent selective sweeps or background selection -- on the levels of linked neutral polymorphism. Natural selection at both coding and regulatory sites appears to affect linked neutral polymorphism, reducing neutral polymorphism by 6\% genome-wide and by 11\% in the gene-rich half of the human genome. These findings suggest that the effects of natural selection at linked sites cannot be ignored in the study of neutral human polymorphism.},
	Author = {Cai, James J and Macpherson, J Michael and Sella, Guy and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:12:26 -0500},
	Date-Modified = {2009-11-13 13:12:26 -0500},
	Doi = {10.1371/journal.pgen.1000336},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Evolution, Molecular; Genetic Variation; Genome, Human; Humans; Polymorphism, Genetic; Recombination, Genetic; Regulatory Sequences, Nucleic Acid; Selection (Genetics)},
	Month = {Jan},
	Number = {1},
	Pages = {e1000336},
	Pmid = {19148272},
	Title = {Pervasive hitchhiking at coding and regulatory sites in humans},
	Volume = {5},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000336}}

@article{Gonzalez:2009oj,
	Abstract = {A recent genomewide screen identified 13 transposable elements that are likely to have been adaptive during or after the spread of Drosophila melanogaster out of Africa. One of these insertions, Bari-Juvenile hormone epoxy hydrolase (Bari-Jheh), was associated with the selective sweep of its flanking neutral variation and with reduction of expression of one of its neighboring genes: Jheh3. Here, we provide further evidence that Bari-Jheh insertion is adaptive. We delimit the extent of the selective sweep and show that Bari-Jheh is the only mutation linked to the sweep. Bari-Jheh also lowers the expression of its other flanking gene, Jheh2. Subtle consequences of Bari-Jheh insertion on life-history traits are consistent with the effects of reduced expression of the Jheh genes. Finally, we analyze molecular evolution of Jheh genes in both the long- and the short-term and conclude that Bari-Jheh appears to be a very rare adaptive event in the history of these genes. We discuss the implications of these findings for the detection and understanding of adaptation.},
	Author = {Gonz{\'a}lez, Josefa and Macpherson, J Michael and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:12:18 -0500},
	Date-Modified = {2009-11-13 13:12:18 -0500},
	Doi = {10.1093/molbev/msp107},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Month = {Sep},
	Number = {9},
	Pages = {1949-61},
	Pmid = {19458110},
	Title = {A recent adaptive transposable element insertion near highly conserved developmental loci in Drosophila melanogaster},
	Volume = {26},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msp107}}

@article{Gonzalez:2008ql,
	Abstract = {Although transposable elements (TEs) are known to be potent sources of mutation, their contribution to the generation of recent adaptive changes has never been systematically assessed. In this work, we conduct a genome-wide screen for adaptive TE insertions in Drosophila melanogaster that have taken place during or after the spread of this species out of Africa. We determine population frequencies of 902 of the 1,572 TEs in Release 3 of the D. melanogaster genome and identify a set of 13 putatively adaptive TEs. These 13 TEs increased in population frequency sharply after the spread out of Africa. We argue that many of these TEs are in fact adaptive by demonstrating that the regions flanking five of these TEs display signatures of partial selective sweeps. Furthermore, we show that eight out of the 13 putatively adaptive elements show population frequency heterogeneity consistent with these elements playing a role in adaptation to temperate climates. We conclude that TEs have contributed considerably to recent adaptive evolution (one TE-induced adaptation every 200-1,250 y). The majority of these adaptive insertions are likely to be involved in regulatory changes. Our results also suggest that TE-induced adaptations arise more often from standing variants than from new mutations. Such a high rate of TE-induced adaptation is inconsistent with the number of fixed TEs in the D. melanogaster genome, and we discuss possible explanations for this discrepancy.},
	Author = {Gonz{\'a}lez, Josefa and Lenkov, Kapa and Lipatov, Mikhail and Macpherson, J Michael and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:11:58 -0500},
	Date-Modified = {2009-11-13 13:11:58 -0500},
	Doi = {10.1371/journal.pbio.0060251},
	Journal = {PLoS Biol},
	Journal-Full = {PLoS biology},
	Mesh = {Adaptation, Physiological; Animals; DNA Transposable Elements; Drosophila melanogaster; Evolution, Molecular; Genome, Insect; Mutagenesis, Insertional; Mutation; Polymerase Chain Reaction},
	Month = {Oct},
	Number = {10},
	Pages = {e251},
	Pmid = {18942889},
	Title = {High rate of recent transposable element-induced adaptation in Drosophila melanogaster},
	Volume = {6},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pbio.0060251}}

@article{Gonzalez:2009xg,
	Abstract = {Transposable elements (TEs) constitute a substantial fraction of the genomes of many species, and it is thus important to understand their population dynamics. The strength of natural selection against TEs is a key parameter in understanding these dynamics. In principle, the strength of selection can be inferred from the frequencies of a sample of TEs. However, complicated demographic histories, such as found in Drosophila melanogaster, could lead to a substantial distortion of the TE frequency distribution compared with that expected for a panmictic, constant-sized population. The current methodology for the estimation of selection intensity acting against TEs does not take into account demographic history and might generate erroneous estimates especially for TE families under weak selection. Here, we develop a flexible maximum likelihood methodology that explicitly accounts both for demographic history and for the ascertainment biases of identifying TEs. We apply this method to the newly generated frequency data of the BS family of non-long terminal repeat retrotransposons in D. melanogaster in concert with two recent models of the demographic history of the species to infer the intensity of selection against this family. We find the estimate to differ substantially compared with a prior estimate that was made assuming a model of constant population size. Further, we find there to be relatively little information about selection intensity present in the derived non-African frequency data and that the ancestral African subpopulation is much more informative in this respect. These findings highlight the importance of accounting for demographic history and bear on study design for the inference of selection coefficients generally.},
	Author = {Gonz{\'a}lez, Josefa and Macpherson, J Michael and Messer, Philipp W and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:11:56 -0500},
	Date-Modified = {2009-11-13 13:11:56 -0500},
	Doi = {10.1093/molbev/msn270},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Animals; DNA Transposable Elements; Drosophila melanogaster; Genetics, Population; Methods; Models, Genetic; Selection (Genetics)},
	Month = {Mar},
	Number = {3},
	Pages = {513-26},
	Pmid = {19033258},
	Title = {Inferring the strength of selection in Drosophila under complex demographic models},
	Volume = {26},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msn270}}

@article{Macpherson:2008qf,
	Abstract = {A beneficial mutation that has nearly but not yet fixed in a population produces a characteristic haplotype configuration, called a partial selective sweep. Whether nonadaptive processes might generate similar haplotype configurations has not been extensively explored. Here, we consider 5 population genetic data sets taken from regions flanking high-frequency transposable elements in North American strains of Drosophila melanogaster, each of which appears to be consistent with the expectations of a partial selective sweep. We use coalescent simulations to explore whether incorporation of the species' demographic history, purifying selection against the element, or suppression of recombination caused by the element could generate putatively adaptive haplotype configurations. Whereas most of the data sets would be rejected as nonneutral under the standard neutral null model, only the data set for which there is strong external evidence in support of an adaptive transposition appears to be nonneutral under the more complex null model and in particular when demography is taken into account. High-frequency, derived mutations from a recently bottlenecked population, such as we study here, are of great interest to evolutionary genetics in the context of scans for adaptive events; we discuss the broader implications of our findings in this context.},
	Author = {Macpherson, J Michael and Gonz{\'a}lez, Josefa and Witten, Daniela M and Davis, Jerel C and Rosenberg, Noah A and Hirsh, Aaron E and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:11:53 -0500},
	Date-Modified = {2009-11-13 13:11:53 -0500},
	Doi = {10.1093/molbev/msn007},
	Journal = {Mol Biol Evol},
	Journal-Full = {Molecular biology and evolution},
	Mesh = {Adaptation, Biological; Animals; Base Sequence; Computer Simulation; DNA Transposable Elements; Drosophila melanogaster; Genomics; Models, Genetic; Molecular Sequence Data; Mutation; Recombination, Genetic},
	Month = {Jun},
	Number = {6},
	Pages = {1025-42},
	Pmid = {18199829},
	Title = {Nonadaptive explanations for signatures of partial selective sweeps in Drosophila},
	Volume = {25},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msn007}}

@article{Macpherson:2007jv,
	Abstract = {The effect of recurrent selective sweeps is a spatially heterogeneous reduction in neutral polymorphism throughout the genome. The pattern of reduction depends on the selective advantage and recurrence rate of the sweeps. Because many adaptive substitutions responsible for these sweeps also contribute to nonsynonymous divergence, the spatial distribution of nonsynonymous divergence also reflects the distribution of adaptive substitutions. Thus, the spatial correspondence between neutral polymorphism and nonsynonymous divergence may be especially informative about the process of adaptation. Here we study this correspondence using genomewide polymorphism data from Drosophila simulans and the divergence between D. simulans and D. melanogaster. Focusing on highly recombining portions of the autosomes, at a spatial scale appropriate to the study of selective sweeps, we find that neutral polymorphism is both lower and, as measured by a new statistic Q(S), less homogeneous where nonsynonymous divergence is higher and that the spatial structure of this correlation is best explained by the action of strong recurrent selective sweeps. We introduce a method to infer, from the spatial correspondence between polymorphism and divergence, the rate and selective strength of adaptation. Our results independently confirm a high rate of adaptive substitution (approximately 1/3000 generations) and newly suggest that many adaptations are of surprisingly great selective effect (approximately 1\%), reducing the effective population size by approximately 15\% even in highly recombining regions of the genome.},
	Author = {Macpherson, J Michael and Sella, Guy and Davis, Jerel C and Petrov, Dmitri A},
	Date-Added = {2009-11-13 13:11:34 -0500},
	Date-Modified = {2009-11-13 13:11:34 -0500},
	Doi = {10.1534/genetics.107.080226},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Adaptation, Physiological; Animals; Data Collection; Drosophila; Drosophila melanogaster; Genome, Insect; Genomics; Polymorphism, Genetic; Recombination, Genetic},
	Month = {Dec},
	Number = {4},
	Pages = {2083-99},
	Pmid = {18073425},
	Title = {Genomewide spatial correspondence between nonsynonymous divergence and neutral polymorphism reveals extensive adaptation in Drosophila},
	Volume = {177},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.107.080226}}

@article{Sawyer:2007sh,
	Abstract = {We have estimated the selective effects of amino acid replacements in natural populations by comparing levels of polymorphism in 91 genes in African populations of Drosophila melanogaster with their divergence from Drosophila simulans. The genes include about equal numbers whose level of expression in adults is greater in males, greater in females, or approximately equal in the sexes. Markov chain Monte Carlo methods were used to sample key parameters in the stationary distribution of polymorphism and divergence in a model in which the selective effect of each nonsynonymous mutation is regarded as a random sample from some underlying normal distribution whose mean may differ from one gene to the next. Our analysis suggests that approximately 95\% of all nonsynonymous mutations that could contribute to polymorphism or divergence are deleterious, and that the average proportion of deleterious amino acid polymorphisms in samples is approximately 70\%. On the other hand, approximately 95\% of fixed differences between species are positively selected, although the scaled selection coefficient (N(e)s) is very small. We estimate that approximately 46\% of amino acid replacements have N(e)s < 2, approximately 84\% have N(e)s < 4, and approximately 99\% have N(e)s < 7. Although positive selection among amino acid differences between species seems pervasive, most of the selective effects could be regarded as nearly neutral. There are significant differences in selection between sex-biased and unbiased genes, which relate primarily to the mean of the distributions of mutational effects and the fraction of slightly deleterious and weakly beneficial mutations that are fixed.},
	Author = {Sawyer, Stanley A and Parsch, John and Zhang, Zhi and Hartl, Daniel L},
	Date-Added = {2009-11-13 12:58:51 -0500},
	Date-Modified = {2009-11-13 12:58:51 -0500},
	Doi = {10.1073/pnas.0701572104},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Amino Acid Substitution; Amino Acids, Neutral; Animals; Drosophila Proteins; Drosophila melanogaster; Evolution, Molecular; Female; Male; Markov Chains; Monte Carlo Method; Mutation; Polymorphism, Genetic; Selection (Genetics); Species Specificity},
	Month = {Apr},
	Number = {16},
	Pages = {6504-10},
	Pmid = {17409186},
	Title = {Prevalence of positive selection among nearly neutral amino acid replacements in Drosophila},
	Volume = {104},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.0701572104}}

@article{Sella:2009pw,
	Abstract = {Over the past four decades, the predominant view of molecular evolution saw little connection between natural selection and genome evolution, assuming that the functionally constrained fraction of the genome is relatively small and that adaptation is sufficiently infrequent to play little role in shaping patterns of variation within and even between species. Recent evidence from Drosophila, reviewed here, suggests that this view may be invalid. Analyses of genetic variation within and between species reveal that much of the Drosophila genome is under purifying selection, and thus of functional importance, and that a large fraction of coding and noncoding differences between species are adaptive. The findings further indicate that, in Drosophila, adaptations may be both common and strong enough that the fate of neutral mutations depends on their chance linkage to adaptive mutations as much as on the vagaries of genetic drift. The emerging evidence has implications for a wide variety of fields, from conservation genetics to bioinformatics, and presents challenges to modelers and experimentalists alike.},
	Author = {Sella, Guy and Petrov, Dmitri A and Przeworski, Molly and Andolfatto, Peter},
	Date-Added = {2009-11-13 12:42:42 -0500},
	Date-Modified = {2009-11-13 12:42:42 -0500},
	Doi = {10.1371/journal.pgen.1000495},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Drosophila; Evolution, Molecular; Genetic Variation; Genome, Insect; Mutation; Selection (Genetics)},
	Month = {Jun},
	Number = {6},
	Pages = {e1000495},
	Pmid = {19503600},
	Title = {Pervasive natural selection in the Drosophila genome?},
	Volume = {5},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.1000495}}

@article{McKay:2008wv,
	Abstract = {Despite compelling evidence that adaptation to local climate is common in plant populations, little is known about the evolutionary genetics of traits that contribute to climatic adaptation. A screen of natural accessions of Arabidopsis thaliana revealed Tsu-1 and Kas-1 to be opposite extremes for water-use efficiency and climate at collection sites for these accessions differs greatly. To provide a tool to understand the genetic basis of this putative adaptation, Kas-1 and Tsu-1 were reciprocally crossed to create a new mapping population. Analysis of F(3) families showed segregating variation in both delta(13)C and transpiration rate, and as expected these traits had a negative genetic correlation (r(g)=- 0.3). 346 RILs, 148 with Kas-1 cytoplasm and 198 with Tsu-1 cytoplasm, were advanced to the F(9) and genotyped using 48 microsatellites and 55 SNPs for a total of 103 markers. This mapping population was used for QTL analysis of delta(13)C using F(9) RIL means. Analysis of this reciprocal cross showed a large effect of cytoplasmic background, as well as two QTL for delta(13)C. The Kas-1 x Tsu-1 mapping population provides a powerful new resource for mapping QTL underlying natural variation and for dissecting the genetic basis of water-use efficiency differences.},
	Author = {McKay, John K and Richards, James H and Nemali, Krishna S and Sen, Saunak and Mitchell-Olds, Thomas and Boles, Sandra and Stahl, Eli A and Wayne, Tierney and Juenger, Thomas E},
	Date-Added = {2009-11-12 11:15:26 -0500},
	Date-Modified = {2009-11-12 11:15:26 -0500},
	Doi = {10.1111/j.1558-5646.2008.00474.x},
	Journal = {Evolution},
	Journal-Full = {Evolution; international journal of organic evolution},
	Mesh = {Adaptation, Biological; Analysis of Variance; Arabidopsis; Crosses, Genetic; Droughts; Genetic Markers; Genotype; Microsatellite Repeats; Polymorphism, Single Nucleotide; Quantitative Trait Loci; Species Specificity},
	Month = {Dec},
	Number = {12},
	Pages = {3014-26},
	Pmid = {18691264},
	Title = {Genetics of drought adaptation in Arabidopsis thaliana II. QTL analysis of a new mapping population, KAS-1 x TSU-1},
	Volume = {62},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1111/j.1558-5646.2008.00474.x}}

@article{Jones:2005sw,
	Abstract = {Drosophila sechellia is an island endemic of the Seychelles. After its geographic isolation on these islands, D. sechellia evolved into a host specialist on the fruit of Morinda citrifolia--a fruit often noxious and repulsive to Drosophila. Specialization on M. citrifolia required the evolution of a suite of adaptations, including resistance to and preference for some of the toxins found in this fruit. Several of these adaptive traits have been studied genetically. Here, I summarize what is known about the genetics of these traits and briefly describe the ecological and geographical context that shaped the evolution of these characters. The data from D. sechellia suggest that adaptations are not as genetically complex as historically thought, although almost all of the adaptations of D. sechellia involve several genes.},
	Author = {Jones, Corbin D},
	Date-Added = {2009-11-12 09:51:02 -0500},
	Date-Modified = {2009-11-12 09:51:02 -0500},
	Journal = {Genetica},
	Journal-Full = {Genetica},
	Mesh = {Adaptation, Biological; Animals; Drosophila; Fruit; Larva; Morinda; Ovum; Smell},
	Month = {Feb},
	Number = {1-2},
	Pages = {137-45},
	Pmid = {15881686},
	Title = {The genetics of adaptation in Drosophila sechellia},
	Volume = {123},
	Year = {2005}}

@article{McDonald:1991pt,
	Abstract = {Proteins often differ in amino-acid sequence across species. This difference has evolved by the accumulation of neutral mutations by random drift, the fixation of adaptive mutations by selection, or a mixture of the two. Here we propose a simple statistical test of the neutral protein evolution hypothesis based on a comparison of the number of amino-acid replacement substitutions to synonymous substitutions in the coding region of a locus. If the observed substitutions are neutral, the ratio of replacement to synonymous fixed differences between species should be the same as the ratio of replacement to synonymous polymorphisms within species. DNA sequence data on the Adh locus (encoding alcohol dehydrogenase, EC 1.1.1.1) in three species in the Drosophila melanogaster species subgroup do not fit this expectation; instead, there are more fixed replacement differences between species than expected. We suggest that these excess replacement substitutions result from adaptive fixation of selectively advantageous mutations.},
	Author = {McDonald, J H and Kreitman, M},
	Date-Added = {2009-11-10 14:57:33 -0500},
	Date-Modified = {2009-11-10 14:57:33 -0500},
	Doi = {10.1038/351652a0},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Alcohol Dehydrogenase; Animals; Base Sequence; DNA; Drosophila; Drosophila melanogaster; Evolution; Molecular Sequence Data; Polymorphism, Genetic; Sequence Homology, Nucleic Acid},
	Month = {Jun},
	Number = {6328},
	Pages = {652-4},
	Pmid = {1904993},
	Title = {Adaptive protein evolution at the Adh locus in Drosophila},
	Volume = {351},
	Year = {1991},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/351652a0}}

@article{Begun:1992pb,
	Abstract = {Two genomic regions with unusually low recombination rates in Drosophila melanogaster have normal levels of divergence but greatly reduced nucleotide diversity, apparently resulting from the fixation of advantageous mutations and the associated hitch-hiking effect. Here we show that for 20 gene regions from across the genome, the amount of nucleotide diversity in natural populations of D. melanogaster is positively correlated with the regional rate of recombination. This cannot be explained by variation in mutation rates and/or functional constraint, because we observe no correlation between recombination rates and DNA sequence divergence between D. melanogaster and its sibling species, D. simulans. We suggest that the correlation may result from genetic hitch-hiking associated with the fixation of advantageous mutants. Hitch-hiking thus seems to occur over a large fraction of the Drosophila genome and may constitute a major constraint on levels of genetic variation in nature.},
	Author = {Begun, D J and Aquadro, C F},
	Date-Added = {2009-11-10 14:54:58 -0500},
	Date-Modified = {2009-11-10 14:54:58 -0500},
	Doi = {10.1038/356519a0},
	Journal = {Nature},
	Journal-Full = {Nature},
	Mesh = {Animals; Drosophila melanogaster; Female; Male; Polymorphism, Genetic; Recombination, Genetic},
	Month = {Apr},
	Number = {6369},
	Pages = {519-20},
	Pmid = {1560824},
	Title = {Levels of naturally occurring DNA polymorphism correlate with recombination rates in D. melanogaster},
	Volume = {356},
	Year = {1992},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/356519a0}}

@book{Ewens:2004ty,
	Address = {New York},
	Annote = {LDR    01412cam  22003134a 4500
001    13365844
005    20080310093334.0
008    031007m20049999nyua     b    001 0 eng  
906    $a7$bcbc$corignew$d1$eocip$f20$gy-gencatlg
925 0  $aacquire$b2 shelf copies$xpolicy default
955    $apc11 2003-10-07 to ASCD;$djc15 2003-10-14$ejc13 2003-10-15 to Dewey$aaa07 2003-10-17$apv17 2004-06-08 to ASCD$ajb00 2004-06-09 bk. rec.;$fjc09 2004-08-16;$gjc13 2004-09-15 to BCCD$ajb18 2004-10-01 Copy 2 to BCCD
010    $a  2003065728
020    $a0387201912 (acid-free paper)
040    $aDLC$cDLC$dDLC
042    $apcc
050 00 $aQH455$b.M367 2004
082 00 $a576.5/8/0151$222
100 1  $aEwens, W. J.$q(Warren John),$d1937-
245 10 $aMathematical population genetics /$cWarren J. Ewens.
250    $a2nd ed.
260    $aNew York :$bSpringer,$c<c2004-     >.
300    $av. <1-   > :$bill. ;$c25 cm.
440  0 $aInterdisciplinary applied mathematics ;$vv. 27
505 1  $av. 1. Theoretical introduction.
650  0 $aPopulation genetics$xMathematics.
650  0 $aPopulation$xMathematical models.
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/enhancements/fy0818/2003065728-d.html
856 41 $3Table of contents only$uhttp://www.loc.gov/catdir/enhancements/fy0818/2003065728-t.html
952    $av. 1 (xix, 417 p.); "First of a  planned 2-vol. sequence"--Pref. of v. 1.
},
	Author = {Ewens, W. J},
	Call-Number = {QH455},
	Date-Added = {2009-10-28 09:44:08 -0400},
	Date-Modified = {2009-10-28 09:44:08 -0400},
	Dewey-Call-Number = {576.5/8/0151},
	Edition = {2nd ed},
	Genre = {Population genetics},
	Isbn = {0387201912 (acid-free paper)},
	Library-Id = {2003065728},
	Publisher = {Springer},
	Title = {Mathematical population genetics},
	Url = {http://www.loc.gov/catdir/enhancements/fy0818/2003065728-d.html},
	Volume = {v. 27},
	Year = {2004},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/enhancements/fy0818/2003065728-d.html}}

@article{Hobolthetal2007,
	Abstract = {The genealogical relationship of human, chimpanzee, and gorilla varies along the genome. We develop a hidden Markov model (HMM) that incorporates this variation and relate the model parameters to population genetics quantities such as speciation times and ancestral population sizes. Our HMM is an analytically tractable approximation to the coalescent process with recombination, and in simulations we see no apparent bias in the HMM estimates. We apply the HMM to four autosomal contiguous human-chimp-gorilla-orangutan alignments comprising a total of 1.9 million base pairs. We find a very recent speciation time of human-chimp (4.1 +/- 0.4 million years), and fairly large ancestral effective population sizes (65,000 +/- 30,000 for the human-chimp ancestor and 45,000 +/- 10,000 for the human-chimp-gorilla ancestor). Furthermore, around 50\% of the human genome coalesces with chimpanzee after speciation with gorilla. We also consider 250,000 base pairs of X-chromosome alignments and find an effective population size much smaller than 75\% of the autosomal effective population sizes. Finally, we find that the rate of transitions between different genealogies correlates well with the region-wide present-day human recombination rate, but does not correlate with the fine-scale recombination rates and recombination hot spots, suggesting that the latter are evolutionarily transient.},
	Author = {Hobolth, Asger and Christensen, Ole F and Mailund, Thomas and Schierup, Mikkel H},
	Date-Added = {2009-08-11 09:25:59 -0400},
	Date-Modified = {2009-08-11 09:26:10 -0400},
	Doi = {10.1371/journal.pgen.0030007},
	Journal = {PLoS Genet},
	Journal-Full = {PLoS genetics},
	Mesh = {Animals; Base Sequence; Computer Simulation; Genetic Speciation; Genetics, Population; Genome, Human; Gorilla gorilla; Hominidae; Humans; Markov Chains; Models, Theoretical; Molecular Sequence Data; Pan troglodytes; Phylogeny; Sequence Homology, Nucleic Acid},
	Month = {Feb},
	Number = {2},
	Pages = {e7},
	Pmid = {17319744},
	Title = {Genomic relationships and speciation times of human, chimpanzee, and gorilla inferred from a coalescent hidden Markov model},
	Volume = {3},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pgen.0030007}}

@article{Boitard2009,
	Abstract = {Detecting and localizing selective sweeps on the basis of SNP data has recently received considerable attention. Here we introduce the use of hidden Markov models (HMMs) for the detection of selective sweeps in DNA sequences. Like previously published methods, our HMMs use the site frequency spectrum, and the spatial pattern of diversity along the sequence, to identify selection. In contrast to earlier approaches, our HMMs explicitly model the correlation structure between linked sites. The detection power of our methods, and their accuracy for estimating the selected site location, is similar to that of competing methods for constant size populations. In the case of population bottlenecks, however, our methods frequently showed fewer false positives.},
	Author = {Boitard, Simon and Schl{\"o}tterer, Christian and Futschik, Andreas},
	Date-Added = {2009-08-11 09:21:51 -0400},
	Date-Modified = {2009-08-11 09:22:07 -0400},
	Doi = {10.1534/genetics.108.100032},
	Journal = {Genetics},
	Journal-Full = {Genetics},
	Mesh = {Algorithms; Computer Simulation; Demography; Evolution, Molecular; Genetic Variation; Genetics, Population; Genomic Instability; Humans; Markov Chains; Models, Genetic; Selection (Genetics); Sequence Alignment},
	Month = {Apr},
	Number = {4},
	Pages = {1567-78},
	Pmid = {19204373},
	Title = {Detecting selective sweeps: a new approach based on hidden markov models},
	Volume = {181},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.108.100032}}

@article{Kern2009,
	Abstract = {Comparative genomics based on sequenced referenced genomes is essential to hypothesis generation and testing within population genetics. However, selection of candidate regions for further study on the basis of elevated or depressed divergence between species leads to a divergence-based ascertainment bias in the site frequency spectrum within selected candidate loci. Here, a method to correct this problem is developed that obtains maximum-likelihood estimates of the unascertained allele frequency distribution using numerical optimization. I show how divergence-based ascertainment may mimic the effects of natural selection and offer correction formulae for performing proper estimation into the strength of selection in candidate regions in a maximum-likelihood setting.},
	Author = {Kern, Andrew D},
	Date-Added = {2009-07-27 09:01:21 -0400},
	Date-Modified = {2009-07-27 09:01:30 -0400},
	Doi = {10.1371/journal.pone.0005152},
	Journal = {PLoS One},
	Journal-Full = {PloS one},
	Number = {4},
	Pages = {e5152},
	Pmid = {19370150},
	Title = {Correcting the site frequency spectrum for divergence-based ascertainment},
	Volume = {4},
	Year = {2009},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pone.0005152}}

@article{Przeworskietal2005,
	Abstract = {Considerable interest is focused on the use of polymorphism data to identify regions of the genome that underlie recent adaptations. These searches are guided by a simple model of positive selection, in which a mutation is favored as soon as it arises. This assumption may not be realistic, as environmental changes and range expansions may lead previously neutral or deleterious alleles to become beneficial. We examine what effect this mode of selection has on patterns of variation at linked neutral sites by implementing a new coalescent model of positive directional selection on standing variation. In this model, a neutral allele arises and drifts in the population, then at frequency f becomes beneficial, and eventually reaches fixation. Depending on the value of f, this scenario can lead to a large variance in allele frequency spectra and in levels of linkage disequilibrium at linked, neutral sites. In particular, for intermediate f, the beneficial substitution often leads to a loss of rare alleles--a pattern that differs markedly from the signature of directional selection currently relied on by researchers. These findings highlight the importance of an accurate characterization of the effects of positive selection, if we are to reliably identify recent adaptations from polymorphism data.},
	Author = {Przeworski, Molly and Coop, Graham and Wall, Jeffrey D},
	Date-Added = {2009-07-22 16:40:26 -0400},
	Date-Modified = {2009-07-22 16:40:38 -0400},
	Journal = {Evolution},
	Journal-Full = {Evolution; international journal of organic evolution},
	Mesh = {Evolution; Gene Frequency; Genetic Variation; Linkage Disequilibrium; Models, Genetic; Selection (Genetics)},
	Month = {Nov},
	Number = {11},
	Pages = {2312-23},
	Pmid = {16396172},
	Title = {The signature of positive selection on standing genetic variation},
	Volume = {59},
	Year = {2005}}

@book{Skelton2006,
	Address = {Thousand Oaks, CA},
	Annote = {LDR    01375cam  2200349 a 4500
001    14260642
005    20071120182340.0
008    060210s2006    cau      b    001 0 eng  
906    $a7$bcbc$corignew$d2$eepcn$f20$gy-gencatlg
925 0  $aacquire$b2 shelf copies$xpolicy default
955    $apc21 2006-02-10;$ise15 2007-01-08$ese39 2007-01-16 to Dewey$aaa05 2007-03-19
010    $a  2006922117
020    $a1412907926
040    $aDLC$cDLC$dDLC
042    $apcc
050 00 $aLC212.9$b.S24 2006
082 00 $a371.822$222
245 04 $aThe Sage handbook of gender and education /$cedited by Christine Skelton, Becky Francis, and Lisa Smulyan.
246 3  $aGender and education
260    $aThousand Oaks, CA :$bSage Publications,$c2006.
300    $axxiii, 536 p. ;$c25 cm.
504    $aIncludes bibliographical references and index.
650  0 $aSex differences in education.
650  0 $aFeminism and education.
650  0 $aSex discrimination in education.
650  0 $aGender identity in education.
700 1  $aSkelton, Christine.
700 1  $aFrancis, Becky.
700 1  $aSmulyan, Lisa.
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/enhancements/fy0659/2006922117-d.html
856 41 $3Table of contents$uhttp://www.loc.gov/catdir/enhancements/fy0659/2006922117-t.html
991    $br-MRR$hLC212.9$i.S24 2006$tCopy 1$mAlc$wGenBib
},
	Author = {Skelton, Christine and Francis, Becky and Smulyan, Lisa},
	Call-Number = {LC212.9},
	Date-Added = {2009-07-07 15:13:53 -0400},
	Date-Modified = {2009-07-07 15:14:13 -0400},
	Dewey-Call-Number = {371.822},
	Genre = {Sex differences in education},
	Isbn = {1412907926},
	Library-Id = {2006922117},
	Publisher = {Sage Publications},
	Title = {The Sage handbook of gender and education},
	Url = {http://www.loc.gov/catdir/enhancements/fy0659/2006922117-d.html},
	Year = {2006},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/enhancements/fy0659/2006922117-d.html}}

@book{Margolis2002,
	Address = {Cambridge, Mass.},
	Annote = {LDR    01848cam  22002894a 4500
001    12401066
005    20050308181415.0
008    010507s2002    maua     b    001 0 eng  
906    $a7$bcbc$corignew$d1$eocip$f20$gy-gencatlg
925 0  $aacquire$b2 shelf copies$xpolicy default
955    $apc20 to sa00 05-07-01;jf05 (desc) 05/15/01; jf01 to SSCD  5-16-01; se10 to ASCD/Tech II 05-23-01; jf01 to sl 5-30-01; jf12 to Dewey 05-30-01; aa20 05-31-01$aps16 2002-05-10 bk rec'd, to CIP ver.$ajf00 2002-05-14$fjf25 2002-05-21 CIP ver$gjf25 2002-05-21 to BCCD; copy 2 added jf16 to BCCD 01-28-03
010    $a  2001034296
020    $a0262133989 (hc.)
040    $aDLC$cDLC$dDLC
042    $apcc
050 00 $aQA76.25$b.M35 2002
082 00 $a004/.023$221
100 1  $aMargolis, Jane.
245 10 $aUnlocking the clubhouse :$bwomen in computing /$cJane Margolis and Allan Fisher.
260    $aCambridge, Mass. :$bMIT Press,$cc2002.
300    $aviii, 172 p. :$bill. ;$c24 cm.
504    $aIncludes bibliographical references (p. [155]-164) and index.
505 8  $aMachine generated contents note: Introduction: Women out of the Loop 1 -- 1 The Magnetic Attraction 15 -- 2 Middle and High School: A Room of His Own 33 -- 3 Computing with a Purpose 49 -- 4 Geek Mythology 61 -- 5 Living among the Programming Gods: The Nexus of Confidence and Interest 77 -- 6 Persistence and Resistance: Staying in Computer Science 93 -- 7 A Tale of 240 Teachers 109 -- 8 Changing the University 129 -- Epilogue: Changing the Conversation in Computer Science 143 -- Appendix: Research Methodology 145 -- Sources and Further Reading 155 -- Index 165.
650  0 $aComputer science$xVocational guidance.
650  0 $aWomen in computer science.
700 1  $aFisher, Allan,$d1956-
856 41 $3Table of contents$uhttp://www.loc.gov/catdir/toc/fy032/2001034296.html
},
	Author = {Margolis, Jane and Fisher, Allan},
	Call-Number = {QA76.25},
	Date-Added = {2009-07-07 15:10:20 -0400},
	Date-Modified = {2009-07-07 15:10:35 -0400},
	Dewey-Call-Number = {004/.023},
	Genre = {Computer science},
	Isbn = {0262133989 (hc.)},
	Library-Id = {2001034296},
	Publisher = {MIT Press},
	Title = {Unlocking the clubhouse: women in computing},
	Url = {http://www.loc.gov/catdir/toc/fy032/2001034296.html},
	Year = {2002},
	Bdsk-Url-1 = {http://www.loc.gov/catdir/toc/fy032/2001034296.html}}

@article{Bellenetal1989,
	Abstract = {We generated and characterized greater than 500 Drosophila strains that carry single copies of a novel P-element enhancer detector. In the majority of the strains, the beta-galactosidase reporter gene in the P-transposon responds to nearby transcriptional regulatory sequences in the genome. A remarkable diversity of spatially and temporally regulated staining patterns is observed in embryos carrying different insertions. We selected numerous strains as markers for different embryonic organs, tissues, and cells. Many of these strains should allow the study of complex developmental processes, such as nervous system development, which have not been convenient to analyze previously. Also, we present genetic evidence that some of the detected regulatory elements control nearby Drosophila genes. In light of our results, we discuss the diversity and complexity of cis-acting regulatory elements in the genome and the general applications of the enhancer detector method for the study of Drosophila development.},
	Author = {Bellen, H J and O'Kane, C J and Wilson, C and Grossniklaus, U and Pearson, R K and Gehring, W J},
	Date-Added = {2009-07-07 14:07:38 -0400},
	Date-Modified = {2009-07-07 14:07:46 -0400},
	Journal = {Genes Dev},
	Journal-Full = {Genes \& development},
	Mesh = {Animals; Biological Markers; DNA Transposable Elements; Drosophila melanogaster; Embryo, Nonmammalian; Enhancer Elements, Genetic; Gene Expression Regulation; Genetic Vectors; Recombinant Fusion Proteins; beta-Galactosidase},
	Month = {Sep},
	Number = {9},
	Pages = {1288-300},
	Pmid = {2558050},
	Title = {P-element-mediated enhancer detection: a versatile method to study development in Drosophila},
	Volume = {3},
	Year = {1989}}

@article{Drewelletal2002,
	Abstract = {The extensive infraabdominal (iab) region contains a number of cis-regulatory elements, including enhancers, silencers, and insulators responsible for directing the developmental expression of the abdominal-A and Abdominal-B homeotic genes at the Drosophila bithorax complex. It is unclear how these regulatory elements are primed for activity early in embryogenesis, but the 100-kb intergenic region is subject to a complex transcriptional program. Here, we use molecular and genetic methods to examine the functional activity of the RNAs produced from this region and their role in cis regulation. We show that a subset of these transcripts demonstrates a distinct pattern of cellular localization. Furthermore, the transcripts from each iab region are discrete and the transcripts do not spread across the insulator elements that delineate the iab regions. In embryos carrying a Mcp deletion, the intergenic transcription pattern is disrupted in the iab4 region and the fourth abdominal segment is transformed into the fifth. We propose that intergenic transcription is required early in embryogenesis to initiate the activation of the Drosophila bithorax complex and define the domains of activity for the iab cis-regulatory elements. We also discuss a possible mechanism by which this may occur.},
	Author = {Drewell, Robert A and Bae, Esther and Burr, John and Lewis, Edward B},
	Date-Added = {2009-07-07 14:05:04 -0400},
	Date-Modified = {2009-07-07 14:05:13 -0400},
	Doi = {10.1073/pnas.222671199},
	Journal = {Proc Natl Acad Sci U S A},
	Journal-Full = {Proceedings of the National Academy of Sciences of the United States of America},
	Mesh = {Animals; Drosophila; Drosophila Proteins; Enhancer Elements, Genetic; Genes, Homeobox; Genes, Insect; Genes, Regulator; Homeodomain Proteins; Multigene Family; Nuclear Proteins; Promoter Regions, Genetic; Transcription Factors; Transcription, Genetic},
	Month = {Dec},
	Number = {26},
	Pages = {16853-8},
	Pmid = {12477928},
	Title = {Transcription defines the embryonic domains of cis-regulatory activity at the Drosophila bithorax complex},
	Volume = {99},
	Year = {2002},
	Bdsk-Url-1 = {http://dx.doi.org/10.1073/pnas.222671199}}

@article{TautzPfeifle1989,
	Abstract = {We have developed a non-radioactive in situ hybridization technique for the localization of RNA in whole mount Drosophila embryos. After fixation, whole embryos are hybridized in situ with a DNA probe which has been labeled with digoxygenin. The hybridization products are detected by using a phosphatase-coupled antibody against digoxygenin. In parallel experiments, embryos can be treated with an antibody directed against the corresponding protein product to allow the detection of its distribution using standard immunochemical techniques. We have used this approach to compare the spatial and temporal distribution patterns of the RNA and protein products of the segmentation gene hunchback (hb) during the early stages of embryogenesis. This comparison revealed translational control of the maternally derived hb mRNA, which was difficult to detect by conventional techniques. The non-radioactive in situ hybridization method is as sensitive as conventional methods, but is faster and easier to perform. This may make it a useful tool for a variety of other systems.},
	Author = {Tautz, D and Pfeifle, C},
	Date-Added = {2009-07-07 11:12:53 -0400},
	Date-Modified = {2009-07-07 11:13:11 -0400},
	Journal = {Chromosoma},
	Journal-Full = {Chromosoma},
	Mesh = {Animals; DNA Probes; Drosophila; Gene Expression Regulation; Genes; Insect Hormones; Nucleic Acid Hybridization; Promoter Regions, Genetic; Protein Biosynthesis; RNA; RNA, Messenger; Transcription, Genetic},
	Month = {Aug},
	Number = {2},
	Pages = {81-5},
	Pmid = {2476281},
	Title = {A non-radioactive in situ hybridization method for the localization of specific RNAs in Drosophila embryos reveals translational control of the segmentation gene hunchback},
	Volume = {98},
	Year = {1989}}

@article{Barolo2000,
	Author = {Barolo, S and Carver, L A and Posakony, J W},
	Date-Added = {2009-07-07 11:04:54 -0400},
	Date-Modified = {2009-07-07 11:05:11 -0400},
	Journal = {Biotechniques},
	Journal-Full = {BioTechniques},
	Mesh = {Animals; Drosophila; Enhancer Elements, Genetic; Genetic Vectors; Green Fluorescent Proteins; Lac Operon; Luminescent Proteins; Promoter Regions, Genetic},
	Month = {Oct},
	Number = {4},
	Pages = {726, 728, 730, 732},
	Pmid = {11056799},
	Title = {GFP and beta-galactosidase transformation vectors for promoter/enhancer analysis in Drosophila},
	Volume = {29},
	Year = {2000}}

@article{Jiangetal1991,
	Abstract = {A gradient of the maternal morphogen dorsal (dl) initiates the differentiation of various tissues along the dorsal-ventral axis of early Drosophila embryos. dl is a sequence-specific DNA-binding protein that is related to the mammalian regulatory factor NF-kappa B. Previous studies suggest that dl can function as a transcriptional repressor. To determine how dl functions as an activator we have examined the promoter of the mesoderm determinant gene twist (twi). Genetic studies suggest that peak levels of dl protein in ventral regions of early embryos initiate twi expression. Using a combination of promoter fusion-P-transformation assays, and in vitro DNA-binding assays coupled with site-directed mutagenesis, we establish a direct link between dl-binding sites and twi expression in the early embryo. We also present evidence that the dorsal-ventral limits of twi expression depend on the number and affinity of dl-binding sites present in its promoter. A comparison of twi with a second dl target gene, zen, suggests a correlation between the affinities of dl-binding sites and response to different thresholds of dl morphogen.},
	Author = {Jiang, J and Kosman, D and Ip, Y T and Levine, M},
	Date-Added = {2009-07-07 11:01:55 -0400},
	Date-Modified = {2009-07-07 11:02:08 -0400},
	Journal = {Genes Dev},
	Journal-Full = {Genes \& development},
	Mesh = {Animals; Base Sequence; DNA; DNA Transposable Elements; DNA-Binding Proteins; Deoxyribonuclease I; Drosophila; Drosophila Proteins; Embryo, Nonmammalian; Feedback; Mesoderm; Molecular Sequence Data; Morphogenesis; Mutagenesis, Site-Directed; NF-kappa B; Nuclear Proteins; Oligonucleotide Probes; Phosphoproteins; Promoter Regions, Genetic; Recombinant Fusion Proteins; Transcription Factors; beta-Galactosidase},
	Month = {Oct},
	Number = {10},
	Pages = {1881-91},
	Pmid = {1655572},
	Title = {The dorsal morphogen gradient regulates the mesoderm determinant twist in early Drosophila embryos},
	Volume = {5},
	Year = {1991}}

@article{Marthetal2004,
	Abstract = {We have studied a genome-wide set of single-nucleotide polymorphism (SNP) allele frequency measures for African-American, East Asian, and European-American samples. For this analysis we derived a simple, closed mathematical formulation for the spectrum of expected allele frequencies when the sampled populations have experienced nonstationary demographic histories. The direct calculation generates the spectrum orders of magnitude faster than coalescent simulations do and allows us to generate spectra for a large number of alternative histories on a multidimensional parameter grid. Model-fitting experiments using this grid reveal significant population-specific differences among the demographic histories that best describe the observed allele frequency spectra. European and Asian spectra show a bottleneck-shaped history: a reduction of effective population size in the past followed by a recent phase of size recovery. In contrast, the African-American spectrum shows a history of moderate but uninterrupted population expansion. These differences are expected to have profound consequences for the design of medical association studies. The analytical methods developed for this study, i.e., a closed mathematical formulation for the allele frequency spectrum, correcting the ascertainment bias introduced by shallow SNP sampling, and dealing with variable sample sizes provide a general framework for the analysis of public variation data.},
	Address = {National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland 20894, USA. marth@bc.edu},
	Author = {Marth, Gabor T and Czabarka, Eva and Murvai, Janos and Sherry, Stephen T},
	Crdt = {2004/03/17 05:00},
	Da = {20040315},
	Date = {2004 Jan},
	Date-Added = {2009-06-26 14:09:32 -0400},
	Date-Modified = {2009-06-26 14:09:45 -0400},
	Dcom = {20041026},
	Edat = {2004/03/17 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Lr = {20081121},
	Mh = {African Americans/genetics; Alleles; Americas; Asia; Biometry; Europe; Gene Frequency; *Genetic Variation; Genetics, Population; *Genome, Human; Humans; Linkage Disequilibrium; Models, Genetic; Polymorphism, Single Nucleotide; Population Density},
	Mhda = {2004/10/27 09:00},
	Month = {Jan},
	Number = {1},
	Oid = {NLM: PMC1470693},
	Own = {NLM},
	Pages = {351--372},
	Pii = {166/1/351},
	Pl = {United States},
	Pmc = {PMC1470693},
	Pmid = {15020430},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article},
	Sb = {IM},
	Source = {Genetics. 2004 Jan;166(1):351-72.},
	Status = {MEDLINE},
	Title = {The allele frequency spectrum in genome-wide human variation data reveals signals of differential demographic history in three large world populations.},
	Volume = {166},
	Year = {2004}}

@article{Hudson2002,
	Abstract = {A Monte Carlo computer program is available to generate samples drawn from a population evolving according to a Wright-Fisher neutral model. The program assumes an infinite-sites model of mutation, and allows recombination, gene conversion, symmetric migration among subpopulations, and a variety of demographic histories. The samples produced can be used to investigate the sampling properties of any sample statistic under these neutral models.},
	Address = {Department of Ecology and Evolution, University of Chicago, 1101 E. 57th Street, Chicago, IL 60637, USA. rr-hudson@uchicago.edu},
	Author = {Hudson, Richard R},
	Crdt = {2002/02/16 10:00},
	Da = {20020215},
	Date = {2002 Feb},
	Date-Added = {2009-06-24 15:35:10 -0400},
	Date-Modified = {2009-06-24 15:35:26 -0400},
	Dcom = {20020722},
	Edat = {2002/02/16 10:00},
	Issn = {1367-4803 (Print)},
	Jid = {9808944},
	Journal = {Bioinformatics},
	Jt = {Bioinformatics (Oxford, England)},
	Language = {eng},
	Lr = {20081121},
	Mh = {Computational Biology; Gene Conversion; *Genetic Variation; Genetics, Population; *Models, Genetic; Monte Carlo Method; Recombination, Genetic; *Software},
	Mhda = {2002/07/23 10:01},
	Month = {Feb},
	Number = {2},
	Own = {NLM},
	Pages = {337--338},
	Pl = {England},
	Pmid = {11847089},
	Pst = {ppublish},
	Pt = {Journal Article},
	Sb = {IM},
	Status = {MEDLINE},
	Title = {Generating samples under a Wright-Fisher neutral model of genetic variation.},
	Volume = {18},
	Year = {2002}}

@article{Chiangetal2008,
	Abstract = {Ultraconserved elements (UCEs) are sequences that are identical between reference genomes of distantly related species. As they are under negative selection and enriched near or in specific classes of genes, one explanation for their ultraconservation may be their involvement in important functions. Indeed, many UCEs can drive tissue-specific gene expression. We have demonstrated that nonexonic UCEs are depleted among segmental duplications (SDs) and copy number variants (CNVs) and proposed that their ultraconservation may reflect a mechanism of copy counting via comparison. Here, we report that nonexonic UCEs are also depleted among 10 of 11 recent genomewide data sets of human CNVs, including 3 obtained with strategies permitting greater precision in determining the extents of CNVs. We further present observations suggesting that nonexonic UCEs per se may contribute to this depletion and that their apparent dosage sensitivity was in effect when they became fixed in the last common ancestor of mammals, birds, and reptiles, consistent with dosage sensitivity contributing to ultraconservation. Finally, in searching for the mechanism(s) underlying the function of nonexonic UCEs, we have found that they are enriched in TAATTA, which is also the recognition sequence for the homeodomain DNA-binding module, and bounded by a change in A + T frequency.},
	Address = {Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, Massachusetts 02115.},
	Au = {Chiang, CW and Derti, A and Schwartz, D and Chou, MF and Hirschhorn, JN and Wu, CT},
	Author = {Chiang, Charleston W K and Derti, Adnan and Schwartz, Daniel and Chou, Michael F and Hirschhorn, Joel N and Wu, C-Ting},
	Crdt = {2008/10/30 09:00},
	Da = {20081217},
	Date-Added = {2009-02-02 13:09:37 -0500},
	Date-Modified = {2009-07-07 11:21:13 -0400},
	Dep = {20081028},
	Doi = {10.1534/genetics.108.096537},
	Edat = {2008/10/30 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Mhda = {2008/10/30 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {2277--2293},
	Phst = {2008/10/28 {$[$}aheadofprint{$]$}},
	Pii = {genetics.108.096537},
	Pl = {United States},
	Pmc = {PMC2600958},
	Pmcr = {2009/03/01},
	Pmid = {18957701},
	Pst = {ppublish},
	Pt = {Journal Article},
	Sb = {IM},
	So = {Genetics. 2008 Dec;180(4):2277-93. Epub 2008 Oct 28.},
	Stat = {In-Data-Review},
	Title = {Ultraconserved elements: analyses of dosage sensitivity, motifs and boundaries.},
	Volume = {180},
	Year = 2008,
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.108.096537}}

@article{ThummelPirrotta1991,
	Author = {Carl S. Thummel and Vincenzo Pirrotta},
	Date-Added = {2009-02-01 13:26:25 -0500},
	Date-Modified = {2009-02-01 13:28:16 -0500},
	Journal = {Drosophila Information Newsletter},
	Title = {New pCaSpeR P element vectors},
	Volume = {2},
	Year = {1999}}

@article{BrandPerrimon1993,
	Abstract = {We have designed a system for targeted gene expression that allows the selective activation of any cloned gene in a wide variety of tissue- and cell-specific patterns. The gene encoding the yeast transcriptional activator GAL4 is inserted randomly into the Drosophila genome to drive GAL4 expression from one of a diverse array of genomic enhancers. It is then possible to introduce a gene containing GAL4 binding sites within its promoter, to activate it in those cells where GAL4 is expressed, and to observe the effect of this directed misexpression on development. We have used GAL4-directed transcription to expand the domain of embryonic expression of the homeobox protein even-skipped. We show that even-skipped represses wingless and transforms cells that would normally secrete naked cuticle into denticle secreting cells. The GAL4 system can thus be used to study regulatory interactions during embryonic development. In adults, targeted expression can be used to generate dominant phenotypes for use in genetic screens. We have directed expression of an activated form of the Dras2 protein, resulting in dominant eye and wing defects that can be used in screens to identify other members of the Dras2 signal transduction pathway.},
	Address = {Department of Genetics, Harvard Medical School, Boston, Massachusetts 02115.},
	Au = {Brand, AH and Perrimon, N},
	Author = {Brand, A H and Perrimon, N},
	Crdt = {1993/06/01 00:00},
	Da = {19931209},
	Date-Added = {2009-01-31 15:24:22 -0500},
	Date-Modified = {2009-01-31 15:24:47 -0500},
	Dcom = {19931209},
	Edat = {1993/06/01},
	Issn = {0950-1991 (Print)},
	Jid = {8701744},
	Journal = {Development},
	Jt = {Development (Cambridge, England)},
	Language = {eng},
	Lr = {20081121},
	Mh = {Animals; Base Sequence; Drosophila/*genetics; Enhancer Elements, Genetic/*physiology; Eye/ultrastructure; Gene Expression Regulation/*physiology; Genes, Dominant/*genetics; Microscopy, Electron, Scanning; Molecular Sequence Data; Mutagenesis, Insertional/*methods; Phenotype},
	Mhda = {1993/06/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {401--415},
	Pl = {ENGLAND},
	Pmid = {8223268},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Sb = {IM},
	So = {Development. 1993 Jun;118(2):401-15.},
	Stat = {MEDLINE},
	Title = {Targeted gene expression as a means of altering cell fates and generating dominant phenotypes.},
	Volume = {118},
	Year = {1993 Jun}}

@article{Brandetal1994,
	Address = {Wellcome/CRC Institute, Cambridge, United Kingdom.},
	Au = {Brand, AH and Manoukian, AS and Perrimon, N},
	Author = {Brand, A H and Manoukian, A S and Perrimon, N},
	Crdt = {1994/01/01 00:00},
	Da = {19950511},
	Date-Added = {2009-01-31 15:24:17 -0500},
	Date-Modified = {2009-01-31 15:24:38 -0500},
	Dcom = {19950511},
	Edat = {1994/01/01},
	Issn = {0091-679X (Print)},
	Jid = {0373334},
	Journal = {Methods Cell Biol},
	Jt = {Methods in cell biology},
	Language = {eng},
	Lr = {20081121},
	Mh = {Animals; Base Sequence; Drosophila melanogaster/embryology/*genetics; Embryo, Nonmammalian; Female; Gene Expression Regulation/physiology; Genes, Insect/*physiology; Heat-Shock Proteins/genetics; Hot Temperature; Male; Molecular Sequence Data; beta-Galactosidase/genetics},
	Mhda = {1994/01/01 00:01},
	Own = {NLM},
	Pages = {635--654},
	Pl = {UNITED STATES},
	Pmid = {7707973},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Review},
	Rf = {51},
	Rn = {0 (Heat-Shock Proteins); EC 3.2.1.23 (beta-Galactosidase)},
	Sb = {IM},
	So = {Methods Cell Biol. 1994;44:635-54.},
	Stat = {MEDLINE},
	Title = {Ectopic expression in Drosophila.},
	Volume = {44},
	Year = {1994}}

@article{Fischer1988,
	Abstract = {GAL4 is a yeast regulatory protein that binds to specific sites within a DNA sequence called UASG (galactose upstream activating sequence) and activates transcription of linked genes. This activation requires two functions of the protein: a DNA binding domain located near the amino terminus, and one or more 'activating regions'. The 'activating regions' are highly acidic (see also ref. 12) and can be replaced, for example, by a short peptide designed to form a negatively charged, amphipathic alpha-helix. GAL4, as well as deletion derivatives bearing one or more 'activating regions' attached to the DNA binding domain, activates transcription in cultured mammalian cells from mammalian promoters linked to a UASG (refs 14, 15). Here we show that GAL4, when expressed in particular tissues of Drosophila larvae, stimulates tissue-specific transcription of a Drosophila promoter linked to GAL4 binding sites.},
	Address = {Department of Biochemistry and Molecular Biology, Harvard University, Cambridge, Massachusetts 02138.},
	Au = {Fischer, JA and Giniger, E and Maniatis, T and Ptashne, M},
	Author = {Fischer, J A and Giniger, E and Maniatis, T and Ptashne, M},
	Crdt = {1988/04/28 00:00},
	Da = {19880526},
	Date-Added = {2009-01-31 15:19:01 -0500},
	Date-Modified = {2009-07-07 10:46:28 -0400},
	Dcom = {19880526},
	Doi = {10.1038/332853a0},
	Edat = {1988/04/28},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20061115},
	Mh = {Animals; Binding Sites; Chromosome Deletion; DNA/metabolism; Drosophila melanogaster/genetics; Fungal Proteins/genetics/*pharmacology; *Saccharomyces cerevisiae Proteins; *Transcription Factors; Transcription, Genetic/*drug effects; beta-Galactosidase/metabolism},
	Mhda = {1988/04/28 00:01},
	Number = {6167},
	Own = {NLM},
	Pages = {853--856},
	Pl = {ENGLAND},
	Pmid = {3128741},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (Fungal Proteins); 0 (GAL4 protein, S cerevisiae); 0 (Saccharomyces cerevisiae Proteins); 0 (Transcription Factors); 9007-49-2 (DNA); EC 3.2.1.23 (beta-Galactosidase)},
	Sb = {IM},
	So = {Nature. 1988 Apr 28;332(6167):853-6.},
	Stat = {MEDLINE},
	Title = {GAL4 activates transcription in Drosophila.},
	Volume = {332},
	Year = {1988},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/332853a0}}

@article{Reenan:2005uk,
	Abstract = {Most RNA editing systems are mechanistically diverse, informationally restorative, and scattershot in eukaryotic lineages. In contrast, genetic recoding by adenosine-to-inosine RNA editing seems common in animals; usually, altering highly conserved or invariant coding positions in proteins. Here I report striking variation between species in the recoding of synaptotagmin I (sytI). Fruitflies, mosquitoes and butterflies possess shared and species-specific sytI editing sites, all within a single exon. Honeybees, beetles and roaches do not edit sytI. The editing machinery is usually directed to modify particular adenosines by information stored in intron-mediated RNA structures. Combining comparative genomics of 34 species with mutational analysis reveals that complex, multi-domain, pre-mRNA structures solely determine species-appropriate RNA editing. One of these is a previously unreported long-range pseudoknot. I show that small changes to intronic sequences, far removed from an editing site, can transfer the species specificity of editing between RNA substrates. Taken together, these data support a phylogeny of sytI gene editing spanning more than 250 million years of hexapod evolution. The results also provide models for the genesis of RNA editing sites through the stepwise addition of structural domains, or by short walks through sequence space from ancestral structures.},
	Address = {Department of Genetics and Developmental Biology, University of Connecticut Health Center, Farmington, Connecticut 06030, USA. rreenan@neuron.uchc.edu},
	Au = {Reenan, RA},
	Author = {Reenan, Robert A},
	Crdt = {2005/03/18 09:00},
	Da = {20050317},
	Date-Added = {2009-01-31 14:01:32 -0500},
	Date-Modified = {2009-01-31 14:01:32 -0500},
	Dcom = {20050330},
	Doi = {10.1038/nature03364},
	Edat = {2005/03/18 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20061115},
	Mh = {Adenosine/genetics; Amino Acid Sequence; Animals; Base Sequence; Calcium-Binding Proteins/*genetics; *Evolution, Molecular; Exons/genetics; *Genomics; Inosine/genetics; Introns/genetics; Membrane Glycoproteins/*genetics; Models, Molecular; Molecular Sequence Data; Mutation/genetics; Nerve Tissue Proteins/*genetics; Phylogeny; RNA Editing/*genetics; RNA Precursors/genetics/metabolism; Species Specificity; Synaptotagmin I; Synaptotagmins; Time Factors},
	Mhda = {2005/03/31 09:00},
	Number = {7031},
	Own = {NLM},
	Pages = {409--413},
	Phst = {2004/10/25 {$[$}received{$]$}; 2005/01/14 {$[$}accepted{$]$}},
	Pii = {nature03364},
	Pl = {England},
	Pmid = {15772668},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (Calcium-Binding Proteins); 0 (Membrane Glycoproteins); 0 (Nerve Tissue Proteins); 0 (RNA Precursors); 0 (Synaptotagmin I); 134193-27-4 (Synaptotagmins); 58-61-7 (Adenosine); 58-63-9 (Inosine)},
	Sb = {IM},
	So = {Nature. 2005 Mar 17;434(7031):409-13.},
	Stat = {MEDLINE},
	Title = {Molecular determinants and guided evolution of species-specific RNA editing.},
	Volume = {434},
	Year = {2005 Mar 17},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature03364}}

@article{Willinghametal2005,
	Abstract = {Noncoding RNA molecules (ncRNAs) have been implicated in numerous biological processes including transcriptional regulation and the modulation of protein function. Yet, in spite of the apparent abundance of ncRNA, little is known about the biological role of the projected thousands of ncRNA genes present in the human genome. To facilitate functional analysis of these RNAs, we have created an arrayed library of short hairpin RNAs (shRNAs) directed against 512 evolutionarily conserved putative ncRNAs and, via cell-based assays, we have begun to determine their roles in cellular pathways. Using this system, we have identified an ncRNA repressor of the nuclear factor of activated T cells (NFAT), which interacts with multiple proteins including members of the importin-beta superfamily and likely functions as a specific regulator of NFAT nuclear trafficking.},
	Address = {Department of Chemistry, Scripps Research Institute, 10550 North Torrey Pines Road, La Jolla, CA 92037, USA.},
	Au = {Willingham, AT and Orth, AP and Batalov, S and Peters, EC and Wen, BG and Aza-Blanc, P and Hogenesch, JB and Schultz, PG},
	Author = {Willingham, A T and Orth, A P and Batalov, S and Peters, E C and Wen, B G and Aza-Blanc, P and Hogenesch, J B and Schultz, P G},
	Cin = {Science. 2005 Sep 2;309(5740):1527-8. PMID: 16141063},
	Crdt = {2005/09/06 09:00},
	Da = {20050905},
	Date-Added = {2009-01-26 20:36:23 -0500},
	Date-Modified = {2009-01-26 20:36:35 -0500},
	Dcom = {20050914},
	Doi = {10.1126/science.1115901},
	Edat = {2005/09/06 09:00},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Keywords = {Animals; Cell Line; DNA-Binding Proteins/*antagonists \& inhibitors; Humans; Mice; NFATC Transcription Factors; Nuclear Proteins/*antagonists \& inhibitors; *RNA Interference; RNA, Untranslated/antagonists \& inhibitors/genetics/*physiology; Transcription Factors/*antagonists \& inhibitors; beta Karyopherins/metabolism},
	Language = {eng},
	Lr = {20070319},
	Mhda = {2005/09/15 09:00},
	Number = {5740},
	Own = {NLM},
	Pages = {1570--1573},
	Pii = {309/5740/1570},
	Pl = {United States},
	Pmid = {16141075},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (DNA-Binding Proteins); 0 (NFATC Transcription Factors); 0 (NRON RNA, mouse); 0 (Nuclear Proteins); 0 (RNA, Untranslated); 0 (Transcription Factors); 0 (beta Karyopherins)},
	Sb = {IM},
	So = {Science. 2005 Sep 2;309(5740):1570-3.},
	Stat = {MEDLINE},
	Title = {A strategy for probing the function of noncoding RNAs finds a repressor of NFAT.},
	Volume = {309},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1115901}}

@article{Aza-Blancetal2003,
	Abstract = {New opportunities in mammalian functional genomics are emerging through the combination of high throughput technology and methods that allow manipulation of gene expression in living cells. Here we describe the application of an RNAi-based forward genomics approach toward understanding the biology and mechanism of TRAIL-induced apoptosis. TRAIL is a TNF superfamily member that induces selective cytotoxicity of tumor cells when bound to its cognate receptors. In addition to detecting well-characterized genes in the apoptosis pathway, we uncover several modulators including DOBI, a gene required for progression of the apoptotic signal through the intrinsic mitochondrial cell death pathway, and MIRSA, a gene that acts to limit TRAIL-induced apoptosis. Moreover, our data suggest a role for MYC and the WNT pathway in maintaining susceptibility to TRAIL. Collectively, these observations offer several insights on how TRAIL mediates the selective killing of tumor cells and demonstrate the utility of large-scale RNAi screens in mammalian cells.},
	Address = {Genomics Institute of the Novartis Research Foundation, 10675 John J. Hopkins Drive, San Diego, CA 92121, USA. aza-blanc@gnf.org},
	Au = {Aza-Blanc, P and Cooper, CL and Wagner, K and Batalov, S and Deveraux, QL and Cooke, MP},
	Author = {Aza-Blanc, Pedro and Cooper, Christopher L and Wagner, Klaus and Batalov, Serge and Deveraux, Quinn L and Cooke, Michael P},
	Crdt = {2003/10/07 05:00},
	Da = {20031006},
	Date-Added = {2009-01-26 20:24:35 -0500},
	Date-Modified = {2009-01-26 20:24:51 -0500},
	Dcom = {20031106},
	Edat = {2003/10/07 05:00},
	Issn = {1097-2765 (Print)},
	Jid = {9802571},
	Journal = {Mol Cell},
	Jt = {Molecular cell},
	Keywords = {Apoptosis/*genetics/*immunology; Apoptosis Regulatory Proteins; Gene Expression Regulation/genetics; Genetic Screening/*methods; Hela Cells; Humans; Immunologic Surveillance/*immunology; Membrane Glycoproteins/*immunology; Mitochondria/genetics/metabolism; Neoplasms/*immunology; Proto-Oncogene Proteins/metabolism; Proto-Oncogene Proteins c-myc/metabolism; RNA Interference/*immunology; Signal Transduction/genetics; TNF-Related Apoptosis-Inducing Ligand; Tumor Necrosis Factor-alpha/*immunology; Wnt Proteins; *Zebrafish Proteins},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2003/11/07 05:00},
	Number = {3},
	Own = {NLM},
	Pages = {627--637},
	Pii = {S1097276503003484},
	Pl = {United States},
	Pmid = {14527409},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Rn = {0 (Apoptosis Regulatory Proteins); 0 (Membrane Glycoproteins); 0 (Proto-Oncogene Proteins); 0 (Proto-Oncogene Proteins c-myc); 0 (TNF-Related Apoptosis-Inducing Ligand); 0 (TNFSF10 protein, human); 0 (Tumor Necrosis Factor-alpha); 0 (Wnt Proteins); 0 (Zebrafish Proteins)},
	Sb = {IM},
	So = {Mol Cell. 2003 Sep;12(3):627-37.},
	Stat = {MEDLINE},
	Title = {Identification of modulators of TRAIL-induced apoptosis via RNAi-based phenotypic screening.},
	Volume = {12},
	Year = {2003}}

@article{Kondoetal2006,
	Abstract = {RNAi is a gene-silencing phenomenon mediated by double-stranded RNA (dsRNA) and has become a powerful tool to elucidate gene function. To accomplish rapid construction of transgenes expressing dsRNA in Drosophila, we developed a novel transformation vector, pRISE, which contains an inverted repeat of the attR1-ccdB-attR2 cassette for in vitro recombination and a pentameric GAL4 binding site for conditional expression. These features enabled us to construct RNAi transgenes without a complicated cloning scheme. In cultured cells and transgenic flies, pRISE constructs carrying dsRNA transgenes induced effective RNAi against an EGFP transgene and the endogenous white gene, respectively. These results indicate that pRISE is a convenient transformation vector for studies of multiple Drosophila genes for which functional information is lacking.},
	Address = {Graduate School of Biological Sciences, Nara Institute of Science and Technology, Ikoma, Japan.},
	Au = {Kondo, T and Inagaki, S and Yasuda, K and Kageyama, Y},
	Author = {Kondo, Takefumi and Inagaki, Sachi and Yasuda, Kunio and Kageyama, Yuji},
	Crdt = {2006/06/07 09:00},
	Da = {20060606},
	Date-Added = {2009-01-26 20:23:20 -0500},
	Date-Modified = {2009-01-26 20:23:45 -0500},
	Dcom = {20061013},
	Edat = {2006/06/07 09:00},
	Issn = {1341-7568 (Print)},
	Jid = {9607822},
	Journal = {Genes Genet Syst},
	Jt = {Genes \& genetic systems},
	Keywords = {ATP-Binding Cassette Transporters/metabolism; Animals; Animals, Genetically Modified; Cells, Cultured; DNA Transposable Elements/*genetics; Drosophila/*genetics; Drosophila Proteins/deficiency/metabolism; Eye Proteins/metabolism; Genetic Vectors/*chemical synthesis; RNA Interference; RNA, Small Interfering/*genetics; Recombination, Genetic; Transformation, Genetic; *Transgenes},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2006/10/14 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {129--134},
	Pii = {JST.JSTAGE/ggs/81.129},
	Pl = {Japan},
	Pmid = {16755136},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Rn = {0 (ATP-Binding Cassette Transporters); 0 (DNA Transposable Elements); 0 (Drosophila Proteins); 0 (Eye Proteins); 0 (RNA, Small Interfering); 0 (white protein, Drosophila)},
	Sb = {IM},
	So = {Genes Genet Syst. 2006 Apr;81(2):129-34.},
	Stat = {MEDLINE},
	Title = {Rapid construction of Drosophila RNAi transgenes using pRISE, a P-element-mediated transformation vector exploiting an in vitro recombination system.},
	Volume = {81},
	Year = {2006}}

@article{Albertetal2007,
	Abstract = {We applied high-density microarrays to the enrichment of specific sequences from the human genome for high-throughput sequencing. After capture of 6,726 approximately 500-base 'exon' segments, and of 'locus-specific' regions ranging in size from 200 kb to 5 Mb, followed by sequencing on a 454 Life Sciences FLX sequencer, most sequence reads represented selection targets. These direct selection methods supersede multiplex PCR for the large-scale analysis of genomic regions.},
	Address = {NimbleGen Systems Inc., 1 Science Court, Madison, Wisconsin 53711, USA. talbert@nimblegen.com},
	Au = {Albert, TJ and Molla, MN and Muzny, DM and Nazareth, L and Wheeler, D and Song, X and Richmond, TA and Middle, CM and Rodesch, MJ and Packard, CJ and Weinstock, GM and Gibbs, RA},
	Author = {Albert, Thomas J and Molla, Michael N and Muzny, Donna M and Nazareth, Lynne and Wheeler, David and Song, Xingzhi and Richmond, Todd A and Middle, Chris M and Rodesch, Matthew J and Packard, Charles J and Weinstock, George M and Gibbs, Richard A},
	Cin = {Nat Methods. 2007 Nov;4(11):891-2. PMID: 17971778},
	Crdt = {2007/10/16 09:00},
	Da = {20071031},
	Date-Added = {2009-01-22 12:31:06 -0500},
	Date-Modified = {2009-07-07 08:37:08 -0400},
	Dcom = {20080115},
	Dep = {20071014},
	Doi = {10.1038/nmeth1111},
	Edat = {2007/10/16 09:00},
	Gr = {R21HG004553/HG/NHGRI NIH HHS/United States; U54 HG 003273/HG/NHGRI NIH HHS/United States},
	Issn = {1548-7091 (Print)},
	Jid = {101215604},
	Journal = {Nat Methods},
	Jt = {Nature methods},
	Language = {eng},
	Mh = {BRCA1 Protein/genetics; Cell Line, Tumor; Gene Library; Genome, Human/*genetics; Humans; Nucleic Acid Hybridization/methods; Oligodeoxyribonucleotides/genetics; Oligonucleotide Array Sequence Analysis/*methods; Polymerase Chain Reaction; Polymorphism, Single Nucleotide; Sequence Analysis, DNA/methods},
	Mhda = {2008/01/16 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {903--905},
	Phst = {2007/07/26 {$[$}received{$]$}; 2007/09/24 {$[$}accepted{$]$}; 2007/10/14 {$[$}aheadofprint{$]$}},
	Pii = {nmeth1111},
	Pl = {United States},
	Pmid = {17934467},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural},
	Rn = {0 (BRCA1 Protein); 0 (Oligodeoxyribonucleotides)},
	Sb = {IM},
	So = {Nat Methods. 2007 Nov;4(11):903-5. Epub 2007 Oct 14.},
	Stat = {MEDLINE},
	Title = {Direct selection of human genomic loci by microarray hybridization.},
	Volume = {4},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nmeth1111}}

@article{Bravermanetal1995,
	Abstract = {The level of DNA sequence variation is reduced in regions of the Drosophila melanogaster genome where the rate of crossing over per physical distance is also reduced. This observation has been interpreted as support for the simple model of genetic hitchhiking, in which directional selection on rare variants, e.g., newly arising advantageous mutants, sweeps linked neutral alleles to fixation, thus eliminating polymorphisms near the selected site. However, the frequency spectra of segregating sites of several loci from some populations exhibiting reduced levels of nucleotide diversity and reduced numbers of segregating sites did not appear different from what would be expected under a neutral equilibrium model. Specifically, a skew toward an excess of rare sites was not observed in these samples, as measured by Tajima's D. Because this skew was predicted by a simple hitchhiking model, yet it had never been expressed quantitatively and compared directly to DNA polymorphism data, this paper investigates the hitchhiking effect on the site frequency spectrum, as measured by Tajima's D and several other statistics, using a computer simulation model based on the coalescent process and recurrent hitchhiking events. The results presented here demonstrate that under the simple hitchhiking model (1) the expected value of Tajima's D is large and negative (indicating a skew toward rare variants), (2) that Tajima's test has reasonable power to detect a skew in the frequency spectrum for parameters comparable to those from actual data sets, and (3) that the Tajima's Ds observed in several data sets are very unlikely to have been the result of simple hitchhiking. Consequently, the simple hitchhiking model is not a sufficient explanation for the DNA polymorphism at those loci exhibiting a decreased number of segregating sites yet not exhibiting a skew in the frequency spectrum.},
	Address = {Center for Population Biology, University of California, Davis 95616, USA.},
	Au = {Braverman, JM and Hudson, RR and Kaplan, NL and Langley, CH and Stephan, W},
	Author = {Braverman, J M and Hudson, R R and Kaplan, N L and Langley, C H and Stephan, W},
	Crdt = {1995/06/01 00:00},
	Da = {19960117},
	Date-Added = {2009-01-22 08:59:17 -0500},
	Date-Modified = {2010-02-04 11:33:14 -0500},
	Dcom = {19960117},
	Edat = {1995/06/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Lr = {20081121},
	Mh = {Animals; DNA/*genetics; Drosophila melanogaster/*genetics; Genetic Variation; Models, Genetic; *Polymorphism, Genetic},
	Mhda = {1995/06/01 00:01},
	Month = {Jun},
	Number = {2},
	Oid = {NLM: PMC1206652},
	Own = {NLM},
	Pages = {783--796},
	Pl = {UNITED STATES},
	Pmc = {PMC1206652},
	Pmid = {7498754},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, U.S. Gov't, Non-P.H.S.},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Genetics. 1995 Jun;140(2):783-96.},
	Stat = {MEDLINE},
	Title = {The hitchhiking effect on the site frequency spectrum of DNA polymorphisms.},
	Volume = {140},
	Year = {1995}}

@article{StephanLi2007,
	Abstract = {Population genetic analyses of the past two decades confirmed an earlier hypothesis by L Tsacas and D Lachaise that the cosmopolitan species Drosophila melanogaster has an Afrotropical origin, and that it colonized the rest of the world only very recently. Maximum likelihood analyses based on multilocus data suggest that the putative ancestral African population expanded its size about 60,000 years ago (ya). These demographic changes were accompanied by the fixation of numerous beneficial mutations, as revealed by signatures of positive directional selection in the genome (selective sweeps). The estimated rate of adaptive substitution on the X chromosome is in the order of 10(-11) per nucleotide site per generation. Comparable (but not significantly higher) substitution rates are found in derived populations that colonized new habitats outside Africa, such as in a European population that branched off from the African lineage about 16,000 ya.},
	Address = {Section of Evolutionary Biology, Department of Biology II, University of Munich, Planegg-Martinsried, Germany. stephan@zi.biologie.uni-muenchen.de},
	Au = {Stephan, W and Li, H},
	Author = {Stephan, W and Li, H},
	Crdt = {2006/09/29 09:00},
	Da = {20070126},
	Date-Added = {2009-01-22 08:24:57 -0500},
	Date-Modified = {2009-07-07 08:36:31 -0400},
	Dcom = {20070409},
	Dep = {20060927},
	Doi = {10.1038/sj.hdy.6800901},
	Edat = {2006/09/29 09:00},
	Issn = {0018-067X (Print)},
	Jid = {0373007},
	Journal = {Heredity},
	Jt = {Heredity},
	Language = {eng},
	Lr = {20081121},
	Mh = {Adaptation, Physiological/*genetics; Africa; Animals; Drosophila melanogaster/*genetics; Europe; *Evolution, Molecular; Genetic Variation; *Genetics, Population; *Selection (Genetics); Species Specificity; X Chromosome/metabolism},
	Mhda = {2007/04/10 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {65--68},
	Phst = {2006/09/27 {$[$}aheadofprint{$]$}},
	Pii = {6800901},
	Pl = {England},
	Pmid = {17006533},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Review},
	Rf = {29},
	Sb = {IM},
	So = {Heredity. 2007 Feb;98(2):65-8. Epub 2006 Sep 27.},
	Stat = {MEDLINE},
	Title = {The recent demographic and adaptive history of Drosophila melanogaster.},
	Volume = {98},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/sj.hdy.6800901}}

@article{BegunAquadro1993,
	Abstract = {Understanding genetic evolution within species requires an accurate description of variation within and between populations and the ability to distinguish between the potential causes of an observed distribution of variation. In the cosmopolitan species Drosophila melanogaster, previous studies suggested that gene flow within and between continents is extensive and that most of the nuclear gene variation is found within, rather than among, populations. Here we present evidence that a population from Zimbabwe is more than twice as variable as those from the United States of America at the DNA sequence level, that most variants are not shared between the two geographic regions, and that there are nearly fixed differences between the Zimbabwe and USA samples in genomic regions experiencing low recombination rates. It appears that there is an unappreciated degree of population structure in D. melanogaster and that equilibrium models of molecular evolution are inappropriate for this species.},
	Address = {Cornell University, Section of Genetics and Development, Ithaca, New York 14853.},
	Au = {Begun, DJ and Aquadro, CF},
	Author = {Begun, D J and Aquadro, C F},
	Cin = {Nature. 1994 Jun 9;369(6480):450. PMID: 8202135; Nature. 1994 Sep 1;371(6492):25. PMID: 8072523},
	Crdt = {1993/10/07 00:00},
	Da = {19931109},
	Date-Added = {2009-01-22 08:23:53 -0500},
	Date-Modified = {2009-07-07 08:36:46 -0400},
	Dcom = {19931109},
	Doi = {10.1038/365548a0},
	Edat = {1993/10/07},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20081121},
	Mh = {Animals; DNA/*genetics; DNA Restriction Enzymes; Drosophila melanogaster/*genetics; Genetic Variation; Isoenzymes/genetics; Species Specificity; United States; X Chromosome; Zimbabwe},
	Mhda = {1993/10/07 00:01},
	Number = {6446},
	Own = {NLM},
	Pages = {548--550},
	Pl = {ENGLAND},
	Pmid = {8413609},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (Isoenzymes); 9007-49-2 (DNA); EC 3.1.21.- (DNA Restriction Enzymes)},
	Sb = {IM},
	So = {Nature. 1993 Oct 7;365(6446):548-50.},
	Stat = {MEDLINE},
	Title = {African and North American populations of Drosophila melanogaster are very different at the DNA level.},
	Volume = {365},
	Year = {1993},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/365548a0}}

@article{Thornton2006,
	Abstract = {Genome-wide nucleotide variation in non-African populations of Drosophila melanogaster is a subset of variation found in East sub-Saharan African populations, suggesting a bottleneck in the history of the former. We implement an approximate Bayesian approach to infer the timing, duration, and severity of this putative bottleneck and ask whether this inferred model is sufficient to account for patterns of variability observed at 115 loci scattered across the X chromosome. We estimate a recent bottleneck 0.006N(e) generations ago, somewhat further in the past than suggested by biogeographical evidence. Using various proposed statistical tests, we find that this bottleneck model is able to predict the majority of observed features of diversity and linkage disequilibrium in the data. Thus, while precise estimates of bottleneck parameters (like inferences of selection) are sensitive to model assumptions, our results imply that it may be unnecessary to invoke frequent selective sweeps associated with the dispersal of D. melanogaster from Africa to explain patterns of variability in non-African populations.},
	Address = {Department of Molecular Biology and Genetics, Cornell University, Ithaca, New York 14853, USA. kt234@cornell.edu},
	Au = {Thornton, K and Andolfatto, P},
	Author = {Thornton, Kevin and Andolfatto, Peter},
	Crdt = {2005/11/22 09:00},
	Da = {20060323},
	Date-Added = {2009-01-21 15:01:38 -0500},
	Date-Modified = {2009-07-07 08:36:19 -0400},
	Dep = {20051119},
	Doi = {10.1534/genetics.105.048223},
	Edat = {2005/11/22 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Mhda = {2005/11/22 09:00},
	Number = {3},
	Oid = {NLM: PMC1456302},
	Own = {NLM},
	Pages = {1607--1619},
	Phst = {2005/11/19 {$[$}aheadofprint{$]$}},
	Pii = {genetics.105.048223},
	Pl = {United States},
	Pmc = {PMC1456302},
	Pmid = {16299396},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Sb = {IM},
	So = {Genetics. 2006 Mar;172(3):1607-19. Epub 2005 Nov 19.},
	Stat = {In-Process},
	Title = {Approximate Bayesian inference reveals evidence for a recent, severe bottleneck in a Netherlands population of Drosophila melanogaster.},
	Volume = {172},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.105.048223}}

@article{Haddrilletal2005,
	Abstract = {Uncertainty about the demographic history of populations can hamper genome-wide scans for selection based on population genetic models. To obtain a portrait of the effects of demographic history on genome variability patterns in Drosophila melanogaster populations, we surveyed noncoding DNA polymorphism at 10 X-linked loci in large samples from three African and two non-African populations. All five populations show significant departures from expectations under the standard neutral model. We detect weak but significant differentiation between East (Kenya and Zimbabwe) and West/Central sub-Saharan (Gabon) African populations. A skew toward high-frequency-derived polymorphisms, elevated levels of linkage disequilibrium (LD) and significant heterogeneity in levels of polymorphism and divergence in the Gabon sample suggest that this population is further from mutation-drift equilibrium than the two Eastern African populations. Both non-African populations harbor significantly higher levels of LD, a large excess of high-frequency-derived mutations and extreme heterogeneity among loci in levels of polymorphism and divergence. Rejections of the neutral model in D. melanogaster populations using these and similar features have been interpreted as evidence for an important role for natural selection in shaping genome variability patterns. Based on simulations, we conclude that simple bottleneck models are sufficient to account for most, if not all, polymorphism features of both African and non-African populations. In contrast, we show that a steady-state recurrent hitchhiking model fails to account for several aspects of the data. Demographic departures from equilibrium expectations in both ancestral and derived populations thus represent a serious challenge to detecting positive selection in genome-wide scans using current methodologies.},
	Address = {Institute of Evolutionary Biology, School of Biological Sciences, University of Edinburgh, Edinburgh, EH9 3JT, United Kingdom.},
	Au = {Haddrill, PR and Thornton, KR and Charlesworth, B and Andolfatto, P},
	Author = {Haddrill, Penelope R and Thornton, Kevin R and Charlesworth, Brian and Andolfatto, Peter},
	Crdt = {2005/06/03 09:00},
	Da = {20050602},
	Date-Added = {2009-01-21 15:01:31 -0500},
	Date-Modified = {2009-07-07 08:36:05 -0400},
	Dcom = {20050815},
	Doi = {10.1101/gr.3541005},
	Edat = {2005/06/03 09:00},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research},
	Language = {eng},
	Lr = {20081120},
	Mh = {Animals; Base Sequence; Drosophila melanogaster; *Genes, Insect; Genetics, Population; *Linkage Disequilibrium; Molecular Sequence Data; *Polymorphism, Genetic; Quantitative Trait Loci/*genetics; *Selection (Genetics); X Chromosome/*genetics},
	Mhda = {2005/08/16 09:00},
	Number = {6},
	Oid = {NLM: PMC1142469},
	Own = {NLM},
	Pages = {790--799},
	Pii = {15/6/790},
	Pl = {United States},
	Pmc = {PMC1142469},
	Pmid = {15930491},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, Non-U.S. Gov't},
	Sb = {IM},
	Si = {GENBANK/AY925214; GENBANK/AY925215; GENBANK/AY925216; GENBANK/AY925217; GENBANK/AY925218; GENBANK/AY925219; GENBANK/AY925220; GENBANK/AY925221; GENBANK/AY925222; GENBANK/AY925223; GENBANK/AY925224; GENBANK/AY925225; GENBANK/AY925226; GENBANK/AY925227; GENBANK/AY925228; GENBANK/AY925229; GENBANK/AY925230; GENBANK/AY925231; GENBANK/AY925232; GENBANK/AY925233; GENBANK/AY925234; GENBANK/AY925235; GENBANK/AY925236; GENBANK/AY925237; GENBANK/AY925238; GENBANK/AY925239; GENBANK/AY925240; GENBANK/AY925241; GENBANK/AY925242; GENBANK/AY925243; GENBANK/AY925244; GENBANK/AY925245; GENBANK/AY925246; GENBANK/AY925247; GENBANK/AY925248; GENBANK/AY925249; GENBANK/AY925250; GENBANK/AY925251; GENBANK/AY925252; GENBANK/AY925253; GENBANK/AY925254; GENBANK/AY925255; GENBANK/AY925256; GENBANK/AY925257; GENBANK/AY925258; GENBANK/AY925259; GENBANK/AY925260; GENBANK/AY925261; GENBANK/AY925262; GENBANK/AY925263; GENBANK/AY925264; GENBANK/AY925265; GENBANK/AY925266; GENBANK/AY925267; GENBANK/AY925268; GENBANK/AY925269; GENBANK/AY925270; GENBANK/AY925271; GENBANK/AY925272; GENBANK/AY925273; GENBANK/AY925274; GENBANK/AY925275; GENBANK/AY925276; GENBANK/AY925277; GENBANK/AY925278; GENBANK/AY925279; GENBANK/AY925280; GENBANK/AY925281; GENBANK/AY925282; GENBANK/AY925283; GENBANK/AY925284; GENBANK/AY925285; GENBANK/AY925286; GENBANK/AY925287; GENBANK/AY925288; GENBANK/AY925289; GENBANK/AY925290; GENBANK/AY925291; GENBANK/AY925292; GENBANK/AY925293; GENBANK/AY925294; GENBANK/AY925295; GENBANK/AY925296; GENBANK/AY925297; GENBANK/AY925298; GENBANK/AY925299; GENBANK/AY925300; GENBANK/AY925301; GENBANK/AY925302; GENBANK/AY925303; GENBANK/AY925304; GENBANK/AY925305; GENBANK/AY925306; GENBANK/AY925307; GENBANK/AY925308; GENBANK/AY925309; GENBANK/AY925310; GENBANK/AY925311; GENBANK/AY925312; GENBANK/AY925313; GENBANK/AY925314; GENBANK/AY925315; GENBANK/AY925316; GENBANK/AY925317; GENBANK/AY925318; GENBANK/AY925319; GENBANK/AY925320; GENBANK/AY925321; GENBANK/AY925322; GENBANK/AY925323; GENBANK/AY925324; GENBANK/AY925325; GENBANK/AY925326; GENBANK/AY925327; GENBANK/AY925328; GENBANK/AY925329; GENBANK/AY925330; GENBANK/AY925331; GENBANK/AY925332; GENBANK/AY925333; GENBANK/AY925334; GENBANK/AY925335; GENBANK/AY925336; GENBANK/AY925337; GENBANK/AY925338; GENBANK/AY925339; GENBANK/AY925340; GENBANK/AY925341; GENBANK/AY925342; GENBANK/AY925343; GENBANK/AY925344; GENBANK/AY925345; GENBANK/AY925346; GENBANK/AY925347; GENBANK/AY925348; GENBANK/AY925349; GENBANK/AY925350; GENBANK/AY925351; GENBANK/AY925352; GENBANK/AY925353; GENBANK/AY925354; GENBANK/AY925355; GENBANK/AY925356; GENBANK/AY925357; GENBANK/AY925358; GENBANK/AY925359; GENBANK/AY925360; GENBANK/AY925361; GENBANK/AY925362; GENBANK/AY925363; GENBANK/AY925364; GENBANK/AY925365; GENBANK/AY925366; GENBANK/AY925367; GENBANK/AY925368; GENBANK/AY925369; GENBANK/AY925370; GENBANK/AY925371; GENBANK/AY925372; GENBANK/AY925373; GENBANK/AY925374; GENBANK/AY925375; GENBANK/AY925376; GENBANK/AY925377; GENBANK/AY925378; GENBANK/AY925379; GENBANK/AY925380; GENBANK/AY925381; GENBANK/AY925382; GENBANK/AY925383; GENBANK/AY925384; GENBANK/AY925385; GENBANK/AY925386; GENBANK/AY925387; GENBANK/AY925388; GENBANK/AY925389; GENBANK/AY925390; GENBANK/AY925391; GENBANK/AY925392; GENBANK/AY925393; GENBANK/AY925394; GENBANK/AY925395; GENBANK/AY925396; GENBANK/AY925397; GENBANK/AY925398; GENBANK/AY925399; GENBANK/AY925400; GENBANK/AY925401; GENBANK/AY925402; GENBANK/AY925403; GENBANK/AY925404; GENBANK/AY925405; GENBANK/AY925406; GENBANK/AY925407; GENBANK/AY925408; GENBANK/AY925409; GENBANK/AY925410; GENBANK/AY925411; GENBANK/AY925412; GENBANK/AY925413; GENBANK/AY925414; GENBANK/AY925415; GENBANK/AY925416; GENBANK/AY925417; GENBANK/AY925418; GENBANK/AY925419; GENBANK/AY925420; GENBANK/AY925421; GENBANK/AY925422; GENBANK/AY925423; GENBANK/AY925424; GENBANK/AY925425; GENBANK/AY925426; GENBANK/AY925427; GENBANK/AY925428; GENBANK/AY925429; GENBANK/AY925430; GENBANK/AY925431; GENBANK/AY925432; GENBANK/AY925433; GENBANK/AY925434; GENBANK/AY925435; GENBANK/AY925436; GENBANK/AY925437; GENBANK/AY925438; GENBANK/AY925439; GENBANK/AY925440; GENBANK/AY925441; GENBANK/AY925442; GENBANK/AY925443; GENBANK/AY925444; GENBANK/AY925445; GENBANK/AY925446; GENBANK/AY925447; GENBANK/AY925448; GENBANK/AY925449; GENBANK/AY925450; GENBANK/AY925451; GENBANK/AY925452; GENBANK/AY925453; GENBANK/AY925454; GENBANK/AY925455; GENBANK/AY925456; GENBANK/AY925457; GENBANK/AY925458; GENBANK/AY925459; GENBANK/AY925460; GENBANK/AY925461; GENBANK/AY925462; GENBANK/AY925463; GENBANK/AY925464; GENBANK/AY925465; GENBANK/AY925466; GENBANK/AY925467; GENBANK/AY925468; GENBANK/AY925469; GENBANK/AY925470; GENBANK/AY925471; GENBANK/AY925472; GENBANK/AY925473; GENBANK/AY925474; GENBANK/AY925475; GENBANK/AY925476; GENBANK/AY925477; GENBANK/AY925478; GENBANK/AY925479; GENBANK/AY925480; GENBANK/AY925481; GENBANK/AY925482; GENBANK/AY925483; GENBANK/AY925484; GENBANK/AY925485; GENBANK/AY925486; GENBANK/AY925487; GENBANK/AY925488; GENBANK/AY925489; GENBANK/AY925490; GENBANK/AY925491; GENBANK/AY925492; GENBANK/AY925493; GENBANK/AY925494; GENBANK/AY925495; GENBANK/AY925496; GENBANK/AY925497; GENBANK/AY925498; GENBANK/AY925499; GENBANK/AY925500; GENBANK/AY925501; GENBANK/AY925502; GENBANK/AY925503; GENBANK/AY925504; GENBANK/AY925505; GENBANK/AY925506; GENBANK/AY925507; GENBANK/AY925508; GENBANK/AY925509; GENBANK/AY925510; GENBANK/AY925511; GENBANK/AY925512; GENBANK/AY925513; GENBANK/AY925514; GENBANK/AY925515; GENBANK/AY925516; GENBANK/AY925517; GENBANK/AY925518; GENBANK/AY925519; GENBANK/AY925520; GENBANK/AY925521; GENBANK/AY925522; GENBANK/AY925523; GENBANK/AY925524; GENBANK/AY925525; GENBANK/AY925526; GENBANK/AY925527; GENBANK/AY925528; GENBANK/AY925529; GENBANK/AY925530; GENBANK/AY925531; GENBANK/AY925532; GENBANK/AY925533; GENBANK/AY925534; GENBANK/AY925535; GENBANK/AY925536; GENBANK/AY925537; GENBANK/AY925538; GENBANK/AY925539; GENBANK/AY925540; GENBANK/AY925541; GENBANK/AY925542; GENBANK/AY925543; GENBANK/AY925544; GENBANK/AY925545; GENBANK/AY925546; GENBANK/AY925547; GENBANK/AY925548; GENBANK/AY925549; GENBANK/AY925550; GENBANK/AY925551; GENBANK/AY925552; GENBANK/AY925553; GENBANK/AY925554; GENBANK/AY925555; GENBANK/AY925556; GENBANK/AY925557; GENBANK/AY925558; GENBANK/AY925559; GENBANK/AY925560; GENBANK/AY925561; GENBANK/AY925562; GENBANK/AY925563; GENBANK/AY925564; GENBANK/AY925565; GENBANK/AY925566; GENBANK/AY925567; GENBANK/AY925568; GENBANK/AY925569; GENBANK/AY925570; GENBANK/AY925571; GENBANK/AY925572; GENBANK/AY925573; GENBANK/AY925574; GENBANK/AY925575; GENBANK/AY925576; GENBANK/AY925577; GENBANK/AY925578; GENBANK/AY925579; GENBANK/AY925580; GENBANK/AY925581; GENBANK/AY925582; GENBANK/AY925583; GENBANK/AY925584; GENBANK/AY925585; GENBANK/AY925586; GENBANK/AY925587; GENBANK/AY925588; GENBANK/AY925589; GENBANK/AY925590; GENBANK/AY925591; GENBANK/AY925592; GENBANK/AY925593; GENBANK/AY925594; GENBANK/AY925595; GENBANK/AY925596; GENBANK/AY925597; GENBANK/AY925598; GENBANK/AY925599; GENBANK/AY925600; GENBANK/AY925601; GENBANK/AY925602; GENBANK/AY925603; GENBANK/AY925604; GENBANK/AY925605; GENBANK/AY925606; GENBANK/AY925607; GENBANK/AY925608; GENBANK/AY925609; GENBANK/AY925610; GENBANK/AY925611; GENBANK/AY925612; GENBANK/AY925613; GENBANK/AY925614; GENBANK/AY925615; GENBANK/AY925616; GENBANK/AY925617; GENBANK/AY925618; GENBANK/AY925619; GENBANK/AY925620; GENBANK/AY925621; GENBANK/AY925622; GENBANK/AY925623; GENBANK/AY925624; GENBANK/AY925625; GENBANK/AY925626; GENBANK/AY925627; GENBANK/AY925628; GENBANK/AY925629; GENBANK/AY925630; GENBANK/AY925631; GENBANK/AY925632; GENBANK/AY925633; GENBANK/AY925634; GENBANK/AY925635; GENBANK/AY925636; GENBANK/AY925637; GENBANK/AY925638; GENBANK/AY925639; GENBANK/AY925640; GENBANK/AY925641; GENBANK/AY925642; GENBANK/AY925643; GENBANK/AY925644; GENBANK/AY925645; GENBANK/AY925646; GENBANK/AY925647; GENBANK/AY925648; GENBANK/AY925649; GENBANK/AY925650; GENBANK/AY925651; GENBANK/AY925652; GENBANK/AY925653; GENBANK/AY925654; GENBANK/AY925655; GENBANK/AY925656; GENBANK/AY925657; GENBANK/AY925658; GENBANK/AY925659; GENBANK/AY925660; GENBANK/AY925661; GENBANK/AY925662; GENBANK/AY925663; GENBANK/AY925664; GENBANK/AY925665; GENBANK/AY925666; GENBANK/AY925667; GENBANK/AY925668; GENBANK/AY925669; GENBANK/AY925670; GENBANK/AY925671; GENBANK/AY925672; GENBANK/AY925673; GENBANK/AY925674; GENBANK/AY925675; GENBANK/AY925676; GENBANK/AY925677; GENBANK/AY925678; GENBANK/AY925679; GENBANK/AY925680; GENBANK/AY925681; GENBANK/AY925682; GENBANK/AY925683; GENBANK/AY925684; GENBANK/AY925685; GENBANK/AY925686; GENBANK/AY925687; GENBANK/AY925688; GENBANK/AY925689; GENBANK/AY925690; GENBANK/AY925691; GENBANK/AY925692; GENBANK/AY925693; GENBANK/AY925694; GENBANK/AY925695; GENBANK/AY925696; GENBANK/AY925697; GENBANK/AY925698; GENBANK/AY925699; GENBANK/AY925700; GENBANK/AY925701; GENBANK/AY925702; GENBANK/AY925703; GENBANK/AY925704; GENBANK/AY925705; GENBANK/AY925706; GENBANK/AY925707; GENBANK/AY925708; GENBANK/AY925709; GENBANK/AY925710; GENBANK/AY925711; GENBANK/AY925712; GENBANK/AY925713; GENBANK/AY925714; GENBANK/AY925715; GENBANK/AY925716; GENBANK/AY925717; GENBANK/AY925718; GENBANK/AY925719; GENBANK/AY925720; GENBANK/AY925721; GENBANK/AY925722; GENBANK/AY925723; GENBANK/AY925724; GENBANK/AY925725; GENBANK/AY925726; GENBANK/AY925727; GENBANK/AY925728; GENBANK/AY925729; GENBANK/AY925730; GENBANK/AY925731; GENBANK/AY925732; GENBANK/AY925733; GENBANK/AY925734; GENBANK/AY925735; GENBANK/AY925736; GENBANK/AY925737; GENBANK/AY925738; GENBANK/AY925739; GENBANK/AY925740; GENBANK/AY925741; GENBANK/AY925742; GENBANK/AY925743; GENBANK/AY925744; GENBANK/AY925745; GENBANK/AY925746; GENBANK/AY925747; GENBANK/AY925748; GENBANK/AY925749; GENBANK/AY925750; GENBANK/AY925751; GENBANK/AY925752; GENBANK/AY925753; GENBANK/AY925754; GENBANK/AY925755; GENBANK/AY925756; GENBANK/AY925757; GENBANK/AY925758; GENBANK/AY925759; GENBANK/AY925760; GENBANK/AY925761; GENBANK/AY925762; GENBANK/AY925763; GENBANK/AY925764; GENBANK/AY925765; GENBANK/AY925766; GENBANK/AY925767; GENBANK/AY925768; GENBANK/AY925769; GENBANK/AY925770; GENBANK/AY925771; GENBANK/AY925772; GENBANK/AY925773; GENBANK/AY925774; GENBANK/AY925775; GENBANK/AY925776; GENBANK/AY925777; GENBANK/AY925778; GENBANK/AY925779; GENBANK/AY925780; GENBANK/AY925781; GENBANK/AY925782; GENBANK/AY925783; GENBANK/AY925784; GENBANK/AY925785; GENBANK/AY925786; GENBANK/AY925787; GENBANK/AY925788; GENBANK/AY925789; GENBANK/AY925790; GENBANK/AY925791; GENBANK/AY925792; GENBANK/AY925793; GENBANK/AY925794; GENBANK/AY925795; GENBANK/AY925796; GENBANK/AY925797; GENBANK/AY925798; GENBANK/AY925799; GENBANK/AY925800; GENBANK/AY925801; GENBANK/AY925802; GENBANK/AY925803; GENBANK/AY925804; GENBANK/AY925805; GENBANK/AY925806; GENBANK/AY925807; GENBANK/AY925808; GENBANK/AY925809; GENBANK/AY925810; GENBANK/AY925811; GENBANK/AY925812; GENBANK/AY925813; GENBANK/AY925814; GENBANK/AY925815; GENBANK/AY925816; GENBANK/AY925817; GENBANK/AY925818; GENBANK/AY925819; GENBANK/AY925820; GENBANK/AY925821; GENBANK/AY925822; GENBANK/AY925823; GENBANK/AY925824; GENBANK/AY925825; GENBANK/AY925826; GENBANK/AY925827; GENBANK/AY925828; GENBANK/AY925829; GENBANK/AY925830; GENBANK/AY925831; GENBANK/AY925832; GENBANK/AY925833; GENBANK/AY925834; GENBANK/AY925835; GENBANK/AY925836; GENBANK/AY925837; GENBANK/AY925838; GENBANK/AY925839; GENBANK/AY925840; GENBANK/AY925841; GENBANK/AY925842; GENBANK/AY925843; GENBANK/AY925844; GENBANK/AY925845; GENBANK/AY925846; GENBANK/AY925847; GENBANK/AY925848; GENBANK/AY925849; GENBANK/AY925850; GENBANK/AY925851; GENBANK/AY925852; GENBANK/AY925853; GENBANK/AY925854; GENBANK/AY925855; GENBANK/AY925856; GENBANK/AY925857; GENBANK/AY925858; GENBANK/AY925859; GENBANK/AY925860; GENBANK/AY925861; GENBANK/AY925862; GENBANK/AY925863; GENBANK/AY925864; GENBANK/AY925865; GENBANK/AY925866; GENBANK/AY925867; GENBANK/AY925868; GENBANK/AY925869; GENBANK/AY925870; GENBANK/AY925871; GENBANK/AY925872; GENBANK/AY925873; GENBANK/AY925874; GENBANK/AY925875; GENBANK/AY925876; GENBANK/AY925877; GENBANK/AY925878; GENBANK/AY925879; GENBANK/AY925880; GENBANK/AY925881; GENBANK/AY925882; GENBANK/AY925883; GENBANK/AY925884; GENBANK/AY925885; GENBANK/AY925886; GENBANK/AY925887; GENBANK/AY925888; GENBANK/AY925889; GENBANK/AY925890; GENBANK/AY925891; GENBANK/AY925892; GENBANK/AY925893; GENBANK/AY925894; GENBANK/AY925895; GENBANK/AY925896; GENBANK/AY925897; GENBANK/AY925898; GENBANK/AY925899; GENBANK/AY925900; GENBANK/AY925901; GENBANK/AY925902; GENBANK/AY925903; GENBANK/AY925904; GENBANK/AY925905; GENBANK/AY925906; GENBANK/AY925907; GENBANK/AY925908; GENBANK/AY925909; GENBANK/AY925910; GENBANK/AY925911; GENBANK/AY925912; GENBANK/AY925913; GENBANK/AY925914; GENBANK/AY925915; GENBANK/AY925916; GENBANK/AY925917; GENBANK/AY925918; GENBANK/AY925919; GENBANK/AY925920; GENBANK/AY925921; GENBANK/AY925922; GENBANK/AY925923; GENBANK/AY925924; GENBANK/AY925925; GENBANK/AY925926; GENBANK/AY925927; GENBANK/AY925928; GENBANK/AY925929; GENBANK/AY925930; GENBANK/AY925931; GENBANK/AY925932; GENBANK/AY925933; GENBANK/AY925934; GENBANK/AY925935; GENBANK/AY925936; GENBANK/AY925937; GENBANK/AY925938; GENBANK/AY925939; GENBANK/AY925940; GENBANK/AY925941; GENBANK/AY925942; GENBANK/AY925943; GENBANK/AY925944; GENBANK/AY925945; GENBANK/AY925946; GENBANK/AY925947; GENBANK/AY925948; GENBANK/AY925949; GENBANK/AY925950; GENBANK/AY925951; GENBANK/AY925952; GENBANK/AY925953; GENBANK/AY925954; GENBANK/AY925955; GENBANK/AY925956; GENBANK/AY925957; GENBANK/AY925958; GENBANK/AY925959; GENBANK/AY925960; GENBANK/AY925961; GENBANK/AY925962; GENBANK/AY925963; GENBANK/AY925964; GENBANK/AY925965; GENBANK/AY925966; GENBANK/AY925967; GENBANK/AY925968; GENBANK/AY925969; GENBANK/AY925970; GENBANK/AY925971; GENBANK/AY925972; GENBANK/AY925973; GENBANK/AY925974; GENBANK/AY925975; GENBANK/AY925976; GENBANK/AY925977; GENBANK/AY925978; GENBANK/AY925979; GENBANK/AY925980; GENBANK/AY925981; GENBANK/AY925982; GENBANK/AY925983; GENBANK/AY925984; GENBANK/AY925985; GENBANK/AY925986; GENBANK/AY925987; GENBANK/AY925988; GENBANK/AY925989; GENBANK/AY925990; GENBANK/AY925991; GENBANK/AY925992; GENBANK/AY925993; GENBANK/AY925994; GENBANK/AY925995; GENBANK/AY925996; GENBANK/AY925997; GENBANK/AY925998; GENBANK/AY925999; GENBANK/AY926000; GENBANK/AY926001; GENBANK/AY926002; GENBANK/AY926003; GENBANK/AY926004; GENBANK/AY926005; GENBANK/AY926006; GENBANK/AY926007; GENBANK/AY926008; GENBANK/AY926009; GENBANK/AY926010; GENBANK/AY926011; GENBANK/AY926012; GENBANK/AY926013; GENBANK/AY926014; GENBANK/AY926015; GENBANK/AY926016; GENBANK/AY926017; GENBANK/AY926018; GENBANK/AY926019; GENBANK/AY926020; GENBANK/AY926021; GENBANK/AY926022; GENBANK/AY926023; GENBANK/AY926024; GENBANK/AY926025; GENBANK/AY926026; GENBANK/AY926027; GENBANK/AY926028; GENBANK/AY926029; GENBANK/AY926030; GENBANK/AY926031; GENBANK/AY926032; GENBANK/AY926033; GENBANK/AY926034; GENBANK/AY926035; GENBANK/AY926036; GENBANK/AY926037; GENBANK/AY926038; GENBANK/AY926039; GENBANK/AY926040; GENBANK/AY926041; GENBANK/AY926042; GENBANK/AY926043; GENBANK/AY926044; GENBANK/AY926045; GENBANK/AY926046; GENBANK/AY926047; GENBANK/AY926048; GENBANK/AY926049; GENBANK/AY926050; GENBANK/AY926051; GENBANK/AY926052; GENBANK/AY926053; GENBANK/AY926054; GENBANK/AY926055; GENBANK/AY926056; GENBANK/AY926057; GENBANK/AY926058; GENBANK/AY926059; GENBANK/AY926060; GENBANK/AY926061; GENBANK/AY926062; GENBANK/AY926063; GENBANK/AY926064; GENBANK/AY926065; GENBANK/AY926066; GENBANK/AY926067; GENBANK/AY926068; GENBANK/AY926069; GENBANK/AY926070; GENBANK/AY926071; GENBANK/AY926072; GENBANK/AY926073; GENBANK/AY926074; GENBANK/AY926075; GENBANK/AY926076; GENBANK/AY926077; GENBANK/AY926078; GENBANK/AY926079; GENBANK/AY926080; GENBANK/AY926081; GENBANK/AY926082; GENBANK/AY926083; GENBANK/AY926084; GENBANK/AY926085; GENBANK/AY926086; GENBANK/AY926087; GENBANK/AY926088; GENBANK/AY926089; GENBANK/AY926090; GENBANK/AY926091; GENBANK/AY926092; GENBANK/AY926093; GENBANK/AY926094; GENBANK/AY926095; GENBANK/AY926096; GENBANK/AY926097; GENBANK/AY926098; GENBANK/AY926099; GENBANK/AY926100; GENBANK/AY926101; GENBANK/AY926102; GENBANK/AY926103; GENBANK/AY926104; GENBANK/AY926105; GENBANK/AY926106; GENBANK/AY926107; GENBANK/AY926108; GENBANK/AY926109; GENBANK/AY926110; GENBANK/AY926111; GENBANK/AY926112; GENBANK/AY926113; GENBANK/AY926114; GENBANK/AY926115; GENBANK/AY926116; GENBANK/AY926117; GENBANK/AY926118; GENBANK/AY926119; GENBANK/AY926120; GENBANK/AY926121; GENBANK/AY926122; GENBANK/AY926123; GENBANK/AY926124; GENBANK/AY926125; GENBANK/AY926126; GENBANK/AY926127; GENBANK/AY926128; GENBANK/AY926129; GENBANK/AY926130; GENBANK/AY926131; GENBANK/AY926132; GENBANK/AY926133; GENBANK/AY926134; GENBANK/AY926135; GENBANK/AY926136; GENBANK/AY926137; GENBANK/AY926138; GENBANK/AY926139; GENBANK/AY926140; GENBANK/AY926141; GENBANK/AY926142; GENBANK/AY926143; GENBANK/AY926144; GENBANK/AY926145; GENBANK/AY926146; GENBANK/AY926147; GENBANK/AY926148; GENBANK/AY926149; GENBANK/AY926150; GENBANK/AY926151; GENBANK/AY926152; GENBANK/AY926153; GENBANK/AY926154; GENBANK/AY926155; GENBANK/AY926156; GENBANK/AY926157; GENBANK/AY926158; GENBANK/AY926159; GENBANK/AY926160; GENBANK/AY926161; GENBANK/AY926162; GENBANK/AY926163; GENBANK/AY926164; GENBANK/AY926165; GENBANK/AY926166; GENBANK/AY926167; GENBANK/AY926168; GENBANK/AY926169; GENBANK/AY926170; GENBANK/AY926171; GENBANK/AY926172; GENBANK/AY926173; GENBANK/AY926174; GENBANK/AY926175; GENBANK/AY926176; GENBANK/AY926177; GENBANK/AY926178; GENBANK/AY926179; GENBANK/AY926180; GENBANK/AY926181; GENBANK/AY926182; GENBANK/AY926183; GENBANK/AY926184; GENBANK/AY926185; GENBANK/AY926186; GENBANK/AY926187; GENBANK/AY926188; GENBANK/AY926189; GENBANK/AY926190; GENBANK/AY926191; GENBANK/AY926192; GENBANK/AY926193; GENBANK/AY926194; GENBANK/AY926195; GENBANK/AY926196; GENBANK/AY926197; GENBANK/AY926198; GENBANK/AY926199; GENBANK/AY926200; GENBANK/AY926201; GENBANK/AY926202; GENBANK/AY926203; GENBANK/AY926204; GENBANK/AY926205; GENBANK/AY926206; GENBANK/AY926207; GENBANK/AY926208; GENBANK/AY926209; GENBANK/AY926210; GENBANK/AY926211; GENBANK/AY926212; GENBANK/AY926213},
	So = {Genome Res. 2005 Jun;15(6):790-9.},
	Stat = {MEDLINE},
	Title = {Multilocus patterns of nucleotide variability and the demographic and selection history of Drosophila melanogaster populations.},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.3541005}}

@article{Hanrahanetal2000,
	Abstract = {Post-transcriptional editing of pre-mRNAs through the action of dsRNA adenosine deaminases results in the modification of particular adenosine (A) residues to inosine (I), which can alter the coding potential of the modified transcripts. We describe here three sites in the para transcript, which encodes the major voltage-activated Na(+) channel polypeptide in Drosophila, where RNA editing occurs. The occurrence of RNA editing at the three sites was found to be developmentally regulated. Editing at two of these sites was also conserved across species between the D. melanogaster and D. virilis. In each case, a highly conserved region was found in the intron downstream of the editing site and this region was shown to be complementary to the region of the exonic editing site. Thus, editing at these sites would appear to involve a mechanism whereby the edited exon forms a base-paired secondary structure with the distant conserved noncoding sequences located in adjacent downstream introns, similar to the mechanism shown for A-to-I RNA editing of mammalian glutamate receptor subunits (GluRs). For the third site, neither RNA editing nor the predicted RNA secondary structures were evolutionarily conserved. Transcripts from transgenic Drosophila expressing a minimal editing site construct for this site were shown to faithfully undergo RNA editing. These results demonstrate that Na(+) channel diversity in Drosophila is increased by RNA editing via a mechanism analogous to that described for transcripts encoding mammalian GluRs.},
	Address = {Department of Genetics and Developmental Biology, University of Connecticut Health Center, Farmington, Connecticut 06030, USA.},
	Au = {Hanrahan, CJ and Palladino, MJ and Ganetzky, B and Reenan, RA},
	Author = {Hanrahan, C J and Palladino, M J and Ganetzky, B and Reenan, R A},
	Crdt = {2000/07/06 11:00},
	Da = {20000821},
	Date-Added = {2009-01-15 16:29:26 -0500},
	Date-Modified = {2009-07-07 08:41:25 -0400},
	Dcom = {20000821},
	Edat = {2000/07/06 11:00},
	Gr = {GM43100/GM/NIGMS NIH HHS/United States; NS15390/NS/NINDS NIH HHS/United States},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Lr = {20081120},
	Mh = {Alternative Splicing; Animals; Base Pairing; Base Sequence; Binding Sites; Conserved Sequence/*genetics; Drosophila/*genetics/metabolism; Gene Expression Regulation, Developmental; Insect Proteins/genetics/metabolism; Introns; Molecular Sequence Data; Nucleic Acid Conformation; Protein Structure, Secondary; RNA Editing/*genetics; RNA, Messenger/*metabolism; Reverse Transcriptase Polymerase Chain Reaction; Sodium Channels/*genetics/metabolism},
	Mhda = {2000/08/29 11:01},
	Number = {3},
	Oid = {NLM: PMC1461140},
	Own = {NLM},
	Pages = {1149--1160},
	Pl = {UNITED STATES},
	Pmc = {PMC1461140},
	Pmid = {10880477},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (Insect Proteins); 0 (RNA, Messenger); 0 (Sodium Channels)},
	Sb = {IM},
	So = {Genetics. 2000 Jul;155(3):1149-60.},
	Stat = {MEDLINE},
	Title = {RNA editing of the Drosophila para Na(+) channel transcript. Evolutionary conservation and developmental regulation.},
	Volume = {155},
	Year = {2000}}

@article{KumarCarmichael1997,
	Abstract = {Antisense RNA may regulate the expression of a number of eukaryotic genes, but little is known about its prevalence or mechanism of action. We have used a model system in which antisense control can be studied both genetically and biochemically. Late in polyoma virus infection, early-strand mRNA levels are down-regulated by nuclear antisense RNA from the late strand. Analysis of early-strand transcripts isolated late in infection revealed extensive base modifications. In many transcripts almost half of the adenosines were altered to inosines or guanosines. These results suggest modification of RNA duplexes by double-stranded RNA adenosine deaminase or a related enzyme. Probes that detect only modified RNAs revealed that these molecules are not highly unstable, but accumulate within the nucleus and are thus inert for gene expression. Antisense-induced modifications can account for most or all of the observed regulation, with the lowered levels of early-strand RNAs commonly observed late in infection resulting from the fact that many transcripts are invisible to standard hybridization probes. This work suggests that similar antisense-mediated control mechanisms may also operate under physiological conditions in uninfected eukaryotic cells, and leads to the proposal that there is a novel pool of nuclear RNAs that cannot be seen with many molecular probes heretofore used.},
	Address = {Department of Microbiology, University of Connecticut Health Center, Farmington 06030-3205, USA.},
	Au = {Kumar, M and Carmichael, GG},
	Author = {Kumar, M and Carmichael, G G},
	Crdt = {1997/04/15 00:00},
	Da = {19970522},
	Date-Added = {2009-01-15 14:22:51 -0500},
	Date-Modified = {2009-07-07 08:40:57 -0400},
	Dcom = {19970522},
	Edat = {1997/04/15},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America},
	Language = {eng},
	Lr = {20081120},
	Mh = {3T3 Cells; Adenosine/genetics; Animals; Base Sequence; Cell Nucleus/genetics; Mice; Molecular Sequence Data; Papillomavirus Infections/*genetics; *Polyomavirus; RNA, Antisense/*genetics; RNA, Viral/*genetics; *Transcription, Genetic},
	Mhda = {1997/04/15 00:01},
	Number = {8},
	Oid = {NLM: PMC20475},
	Own = {NLM},
	Pages = {3542--3547},
	Pl = {UNITED STATES},
	Pmc = {PMC20475},
	Pmid = {9108012},
	Pst = {ppublish},
	Pt = {Journal Article},
	Rn = {0 (RNA, Antisense); 0 (RNA, Viral); 58-61-7 (Adenosine)},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 1997 Apr 15;94(8):3542-7.},
	Stat = {MEDLINE},
	Title = {Nuclear antisense RNA induces extensive adenosine modifications and nuclear retention of target transcripts.},
	Volume = {94},
	Year = {1997}}

@article{BassWeintraub1988,
	Abstract = {An activity that unwinds double-stranded RNA has been reported to exist in several organisms. We have analyzed the RNA intermediates and final products of the unwinding reaction. Although the RNA becomes sensitive to single strand-specific ribonucleases during the reaction, the duplex is never completely unwound. Furthermore, the base pairing properties of the RNA are permanently altered; the reacted RNA cannot rehybridize to form the original duplex. We demonstrate that during the reaction many, but not all, of the adenosine residues are converted to inosine residues, and we propose that the covalent modification is responsible for the irreversible change in base pairing properties. Possible biological roles for the unwinding/modifying activity, as well as its relevance to antisense RNA experiments, are discussed.},
	Address = {Hutchinson Cancer Research Center, Seattle, Washington 98104.},
	Au = {Bass, BL and Weintraub, H},
	Author = {Bass, B L and Weintraub, H},
	Crdt = {1988/12/23 00:00},
	Da = {19890203},
	Date-Added = {2009-01-15 14:21:56 -0500},
	Date-Modified = {2009-07-07 08:40:46 -0400},
	Dcom = {19890203},
	Edat = {1988/12/23},
	Issn = {0092-8674 (Print)},
	Jid = {0413066},
	Journal = {Cell},
	Jt = {Cell},
	Language = {eng},
	Lr = {20061115},
	Mh = {Adenosine; Animals; Inosine; Nucleic Acid Conformation; RNA, Double-Stranded/*metabolism; Ribonucleases/metabolism; Xenopus},
	Mhda = {1988/12/23 00:01},
	Number = {6},
	Own = {NLM},
	Pages = {1089--1098},
	Pii = {0092-8674(88)90253-X},
	Pl = {UNITED STATES},
	Pmid = {3203381},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Rn = {0 (RNA, Double-Stranded); 58-61-7 (Adenosine); 58-63-9 (Inosine); EC 3.1.- (Ribonucleases)},
	Sb = {IM},
	So = {Cell. 1988 Dec 23;55(6):1089-98.},
	Stat = {MEDLINE},
	Title = {An unwinding activity that covalently modifies its double-stranded RNA substrate.},
	Volume = {55},
	Year = {1988}}

@article{Bass1997,
	Abstract = {Double-stranded RNA adenosine deaminase (dsRAD) was discovered ten years ago. In the intervening decade, research on dsRAD has progressed not only predictably, such as with the purification of the enzyme and identification of cDNAs, but also in some quite surprising ways. This review covers both areas of progress, but will concentrate on the surprises, which include the discovery that dsRAD is a member of a larger family of deaminases and the identification of RNAs that appear to be targets for these deaminases in vivo.},
	Address = {Department of Biochemistry, University of Utah, Salt Lake City 84112, USA. bass@msscc.med.utah.edu},
	Au = {Bass, BL},
	Author = {Bass, B L},
	Crdt = {1997/05/01 00:00},
	Da = {19970701},
	Date-Added = {2009-01-15 14:06:32 -0500},
	Date-Modified = {2009-07-07 08:40:31 -0400},
	Dcom = {19970701},
	Edat = {1997/05/01},
	Ein = {Trends Biochem Sci 1997 Jul;22(7):278},
	Issn = {0968-0004 (Print)},
	Jid = {7610674},
	Journal = {Trends Biochem Sci},
	Jt = {Trends in biochemical sciences},
	Language = {eng},
	Lr = {20061115},
	Mh = {Adenosine Deaminase/*metabolism; Animals; Base Sequence; DNA, Complementary; Hepatitis Delta Virus/genetics; Molecular Sequence Data; *Mutation; RNA/chemistry/genetics/metabolism; *RNA Editing; RNA, Viral; Receptors, Glutamate/genetics},
	Mhda = {1997/05/01 00:01},
	Number = {5},
	Own = {NLM},
	Pages = {157--162},
	Pii = {S0968000497010359},
	Pl = {ENGLAND},
	Pmid = {9175473},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, U.S. Gov't, P.H.S.; Review},
	Rf = {54},
	Rn = {0 (DNA, Complementary); 0 (RNA, Viral); 0 (Receptors, Glutamate); 63231-63-0 (RNA); EC 3.5.4.4 (Adenosine Deaminase)},
	Sb = {IM},
	So = {Trends Biochem Sci. 1997 May;22(5):157-62.},
	Stat = {MEDLINE},
	Title = {RNA editing and hypermutation by adenosine deamination.},
	Volume = {22},
	Year = {1997}}

@article{Benne1996,
	Au = {Benne, R},
	Author = {Benne, R},
	Con = {Nature. 1996 Apr 4;380(6573):454-6. PMID: 8602246},
	Crdt = {1996/04/04 00:00},
	Da = {19960503},
	Date-Added = {2009-01-15 14:05:46 -0500},
	Date-Modified = {2009-07-07 08:40:24 -0400},
	Dcom = {19960503},
	Doi = {10.1038/380391a0},
	Edat = {1996/04/04},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20060413},
	Mh = {Adenosine/metabolism; Adenosine Deaminase/*metabolism; Animals; Base Sequence; Hepatitis Delta Virus/*genetics; Humans; Inosine/metabolism; Molecular Sequence Data; Nucleic Acid Conformation; RNA/chemistry/*metabolism; *RNA Editing; RNA, Viral/metabolism; Receptors, Neurotransmitter/genetics/metabolism},
	Mhda = {1996/04/04 00:01},
	Number = {6573},
	Own = {NLM},
	Pages = {391--392},
	Pl = {ENGLAND},
	Pmid = {8602237},
	Pst = {ppublish},
	Pt = {Comment; News},
	Rn = {0 (RNA, Viral); 0 (Receptors, Neurotransmitter); 0 (glutamine receptor); 58-61-7 (Adenosine); 58-63-9 (Inosine); 63231-63-0 (RNA); EC 3.5.4.- (dsRNA adenosine deaminase); EC 3.5.4.4 (Adenosine Deaminase)},
	Sb = {IM},
	So = {Nature. 1996 Apr 4;380(6573):391-2.},
	Stat = {MEDLINE},
	Title = {RNA editing. The long and the short of it.},
	Volume = {380},
	Year = {1996},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/380391a0}}

@article{Hollowayetal2008,
	Abstract = {Recent genomic sequencing of 10 additional Drosophila genomes provides a rich resource for comparative genomics analyses aimed at understanding the similarities and differences between species and between Drosophila and mammals. Using a phylogenetic approach, we identified 64 genomic elements that have been highly conserved over most of the Drosophila tree, but that have experienced a recent burst of evolution along the Drosophila melanogaster lineage. Compared to similarly defined elements in humans, these regions of rapid lineage-specific evolution in Drosophila differ dramatically in location, mechanism of evolution, and functional properties of associated genes. Notably, the majority reside in protein-coding regions and primarily result from rapid adaptive synonymous site evolution. In fact, adaptive evolution appears to be driving substitutions to unpreferred codons. Our analysis also highlights interesting noncoding genomic regions, such as regulatory regions in the gene gooseberry-neuro and a putative novel miRNA.},
	Address = {Department of Evolution and Ecology and Center for Population Biology, University of California, Davis, California 95691, USA. akholloway@ucdavis.edu},
	Au = {Holloway, AK and Begun, DJ and Siepel, A and Pollard, KS},
	Author = {Holloway, Alisha K and Begun, David J and Siepel, Adam and Pollard, Katherine S},
	Crdt = {2008/06/28 09:00},
	Da = {20081003},
	Date-Added = {2009-01-08 09:36:27 -0500},
	Date-Modified = {2010-01-12 15:20:12 -0500},
	Dcom = {20081210},
	Dep = {20080626},
	Doi = {10.1101/gr.077131.108},
	Edat = {2008/06/28 09:00},
	Gr = {R01-GM071926/GM/NIGMS NIH HHS/United States},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research},
	Language = {eng},
	Mh = {Animals; Codon; Conserved Sequence; Drosophila melanogaster/*genetics; Evolution, Molecular; *Genome, Insect; MicroRNAs/genetics/metabolism; Models, Genetic; Molecular Sequence Data; Phylogeny; Regulatory Sequences, Nucleic Acid},
	Mhda = {2008/12/17 09:00},
	Number = {10},
	Oid = {NLM: PMC2556263},
	Own = {NLM},
	Pages = {1592--1601},
	Phst = {2008/06/26 {$[$}aheadofprint{$]$}; 2008/08/22 {$[$}aheadofprint{$]$}},
	Pii = {gr.077131.108},
	Pl = {United States},
	Pmc = {PMC2556263},
	Pmid = {18583644},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S.},
	Rn = {0 (Codon); 0 (MicroRNAs)},
	Sb = {IM},
	Si = {GENBANK/EU588685; GENBANK/EU588686; GENBANK/EU588687; GENBANK/EU588688; GENBANK/EU588689; GENBANK/EU588690; GENBANK/EU588691; GENBANK/EU588692; GENBANK/EU588693; GENBANK/EU588694; GENBANK/EU588695; GENBANK/EU588696; GENBANK/EU588697; GENBANK/EU588698; GENBANK/EU588699; GENBANK/EU588700; GENBANK/EU588701; GENBANK/EU588702; GENBANK/EU588703; GENBANK/EU588704; GENBANK/EU588705; GENBANK/EU588706; GENBANK/EU588707; GENBANK/EU588708; GENBANK/EU588709; GENBANK/EU588710; GENBANK/EU588711; GENBANK/EU588712; GENBANK/EU588713; GENBANK/EU588714},
	So = {Genome Res. 2008 Oct;18(10):1592-601. Epub 2008 Jun 26.},
	Stat = {MEDLINE},
	Title = {Accelerated sequence divergence of conserved genomic elements in Drosophila melanogaster.},
	Volume = {18},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.077131.108}}

@article{Prabhakaretal2008,
	Abstract = {Changes in gene regulation are thought to have contributed to the evolution of human development. However, in vivo evidence for uniquely human developmental regulatory function has remained elusive. In transgenic mice, a conserved noncoding sequence (HACNS1) that evolved extremely rapidly in humans acted as an enhancer of gene expression that has gained a strong limb expression domain relative to the orthologous elements from chimpanzee and rhesus macaque. This gain of function was consistent across two developmental stages in the mouse and included the presumptive anterior wrist and proximal thumb. In vivo analyses with synthetic enhancers, in which human-specific substitutions were introduced into the chimpanzee enhancer sequence or reverted in the human enhancer to the ancestral state, indicated that 13 substitutions clustered in an 81-base pair module otherwise highly constrained among terrestrial vertebrates were sufficient to confer the human-specific limb expression domain.},
	Address = {Genomics Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.},
	Au = {Prabhakar, S and Visel, A and Akiyama, JA and Shoukry, M and Lewis, KD and Holt, A and Plajzer-Frick, I and Morrison, H and Fitzpatrick, DR and Afzal, V and Pennacchio, LA and Rubin, EM and Noonan, JP},
	Author = {Prabhakar, Shyam and Visel, Axel and Akiyama, Jennifer A and Shoukry, Malak and Lewis, Keith D and Holt, Amy and Plajzer-Frick, Ingrid and Morrison, Harris and Fitzpatrick, David R and Afzal, Veena and Pennacchio, Len A and Rubin, Edward M and Noonan, James P},
	Cin = {Science. 2008 Sep 5;321(5894):1300-1. PMID: 18772422},
	Crdt = {2008/09/06 09:00},
	Da = {20080905},
	Date-Added = {2009-01-08 09:35:08 -0500},
	Date-Modified = {2010-01-12 15:21:24 -0500},
	Dcom = {20080909},
	Doi = {10.1126/science.1159974},
	Edat = {2008/09/06 09:00},
	Gr = {1-F32-GM074367/GM/NIGMS NIH HHS/United States; HG003988/HG/NHGRI NIH HHS/United States; HL066681/HL/NHLBI NIH HHS/United States},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Language = {eng},
	Lr = {20081121},
	Mh = {Animals; Base Sequence; Binding Sites; Body Patterning/*genetics; Conserved Sequence; Embryonic Development; *Enhancer Elements, Genetic; Evolution, Molecular; Extremities/*embryology; Gene Expression Profiling; *Gene Expression Regulation, Developmental; Humans; Limb Buds/embryology/metabolism; Macaca mulatta/genetics; Mice; Mice, Transgenic; Molecular Sequence Data; Mutation; PAX9 Transcription Factor/metabolism; Pan troglodytes/genetics; Transcription Factors/metabolism},
	Mhda = {2008/09/10 09:00},
	Number = {5894},
	Own = {NLM},
	Pages = {1346--1350},
	Pii = {321/5894/1346},
	Pl = {United States},
	Pmid = {18772437},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.},
	Rn = {0 (PAX9 Transcription Factor); 0 (Transcription Factors)},
	Sb = {IM},
	So = {Science. 2008 Sep 5;321(5894):1346-50.},
	Stat = {MEDLINE},
	Title = {Human-specific gain of function in a developmental enhancer.},
	Volume = {321},
	Year = {2008},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1159974}}

@article{Prabhakaretal2006,
	Abstract = {Changes in gene regulation likely influenced the profound phenotypic divergence of humans from other mammals, but the extent of adaptive substitution in human regulatory sequences remains unknown. We identified 992 conserved noncoding sequences (CNSs) with a significant excess of human-specific substitutions. These accelerated elements were disproportionately found near genes involved in neuronal cell adhesion. To assess the uniqueness of human noncoding evolution, we examined CNSs accelerated in chimpanzee and mouse. Although we observed a similar enrichment near neuronal adhesion genes in chimpanzee, the accelerated CNSs themselves exhibited almost no overlap with those in human, suggesting independent evolution toward different neuronal phenotypes in each species. CNSs accelerated in mouse showed no bias toward neuronal cell adhesion. Our results indicate that widespread cis-regulatory changes in human evolution may have contributed to uniquely human features of brain development and function.},
	Address = {U.S. Department of Energy (DOE) Joint Genome Institute, Walnut Creek, CA 94598, USA.},
	Au = {Prabhakar, S and Noonan, JP and Paabo, S and Rubin, EM},
	Author = {Prabhakar, Shyam and Noonan, James P and Paabo, Svante and Rubin, Edward M},
	Crdt = {2006/11/04 09:00},
	Da = {20061103},
	Date-Added = {2009-01-08 09:35:04 -0500},
	Date-Modified = {2010-01-12 15:21:31 -0500},
	Dcom = {20061120},
	Doi = {10.1126/science.1130738},
	Edat = {2006/11/04 09:00},
	Gr = {1-F32-GM074367/GM/NIGMS NIH HHS/United States; HL066681/HL/NHLBI NIH HHS/United States},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Language = {eng},
	Lr = {20071114},
	Mh = {Animals; Base Sequence; Brain/physiology; Cell Adhesion/*genetics; Cell Adhesion Molecules/genetics; Cognition; *Conserved Sequence; DNA, Intergenic/*genetics; *Evolution, Molecular; Genome, Human; Humans; Mice; Neurons/*physiology; Pan troglodytes/genetics; *Regulatory Sequences, Nucleic Acid},
	Mhda = {2006/12/09 09:00},
	Number = {5800},
	Own = {NLM},
	Pages = {786},
	Pii = {314/5800/786},
	Pl = {United States},
	Pmid = {17082449},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, Non-P.H.S.},
	Rn = {0 (Cell Adhesion Molecules); 0 (DNA, Intergenic)},
	Sb = {IM},
	So = {Science. 2006 Nov 3;314(5800):786.},
	Stat = {MEDLINE},
	Title = {Accelerated evolution of conserved noncoding sequences in humans.},
	Volume = {314},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1130738}}

@article{Glazovetal2006,
	Abstract = {In a recent study that identified highly evolutionary conserved sequences in three genomes of Diptera species we described an ultraconserved element found at an internal exon-intron junction of the Drosophila melanogaster homothorax (hth) gene that appeared to be involved in the control of hth pre-mRNA splicing. We also discussed a possible role of RNA secondary structure at this site in the regulation of hth pre-mRNA splicing. In this report we identify a shorter evolutionary conserved intronic element within the hth gene that is located downstream of the first element and has sequence complementarity to it. We demonstrate that intramolecular interactions between these two elements would give rise to alternative RNA secondary structures, which in turn may result in differential control of homothorax pre-mRNA splicing. We also provide additional comparative genomic data from several newly available insect genomes supporting our original conclusion that these conserved elements are important in the post-transcriptional regulation of homothorax gene expression in Diptera.},
	Address = {ARC Special Research Centre for Functional and Applied Genomics, Institute for Molecular Bioscience, University of Queensland, Brisbane, Australia.},
	Au = {Glazov, EA and Pheasant, M and Nahkuri, S and Mattick, JS},
	Author = {Glazov, Evgeny A and Pheasant, Michael and Nahkuri, Satu and Mattick, John S},
	Crdt = {2006/11/23 09:00},
	Da = {20070820},
	Date-Added = {2009-01-07 18:09:24 -0500},
	Date-Modified = {2009-01-07 18:10:38 -0500},
	Dcom = {20070914},
	Dep = {20060315},
	Edat = {2006/11/23 09:00},
	Issn = {1555-8584 (Electronic)},
	Jid = {101235328},
	Journal = {RNA Biol},
	Jt = {RNA biology},
	Keywords = {*Alternative Splicing; Animals; Base Sequence; Cell Lineage; Drosophila Proteins/*metabolism; Drosophila melanogaster; Exons; Gene Expression Regulation; Genomics; Homeodomain Proteins/*metabolism; Introns; Molecular Sequence Data; *Nucleic Acid Conformation; RNA/*chemistry; RNA Splicing; Sequence Homology, Nucleic Acid},
	Language = {eng},
	Mhda = {2007/09/15 09:00},
	Number = {1},
	Own = {NLM},
	Pages = {36--39},
	Phst = {2006/03/15 {$[$}aheadofprint{$]$}},
	Pii = {2719},
	Pl = {United States},
	Pmid = {17114937},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Rn = {0 (Drosophila Proteins); 0 (Homeodomain Proteins); 0 (homothorax protein, Drosophila); 63231-63-0 (RNA)},
	Sb = {IM},
	So = {RNA Biol. 2006 Jan-Mar;3(1):36-9. Epub 2006 Mar 15.},
	Stat = {MEDLINE},
	Title = {Evidence for control of splicing by alternative RNA secondary structures in Dipteran homothorax pre-mRNA.},
	Volume = {3},
	Year = {2006}}

@article{Glazovetal2005,
	Abstract = {Recently, we identified a large number of ultraconserved (uc) sequences in noncoding regions of human, mouse, and rat genomes that appear to be essential for vertebrate and amniote ontogeny. Here, we used similar methods to identify ultraconserved genomic regions between the insect species Drosophila melanogaster and Drosophila pseudoobscura, as well as the more distantly related Anopheles gambiae. As with vertebrates, ultraconserved sequences in insects appear to occur primarily in intergenic and intronic sequences, and at intron-exon junctions. The sequences are significantly associated with genes encoding developmental regulators and transcription factors, but are less frequent and are smaller in size than in vertebrates. The longest identical, nongapped orthologous match between the three genomes was found within the homothorax (hth) gene. This sequence spans an internal exon-intron junction, with the majority located within the intron, and is predicted to form a highly stable stem-loop RNA structure. Real-time quantitative PCR analysis of different hth splice isoforms and Northern blotting showed that the conserved element is associated with a high incidence of intron retention in hth pre-mRNA, suggesting that the conserved intronic element is critically important in the post-transcriptional regulation of hth expression in Diptera.},
	Address = {ARC Special Research Centre for Functional and Applied Genomics, Institute for Molecular Bioscience, University of Queensland, Brisbane, QLD 4072, Australia.},
	Au = {Glazov, EA and Pheasant, M and McGraw, EA and Bejerano, G and Mattick, JS},
	Author = {Glazov, Evgeny A and Pheasant, Michael and McGraw, Elizabeth A and Bejerano, Gill and Mattick, John S},
	Crdt = {2005/05/19 09:00},
	Da = {20050602},
	Date-Added = {2009-01-07 18:09:24 -0500},
	Date-Modified = {2009-01-07 18:10:31 -0500},
	Dcom = {20050815},
	Dep = {20050517},
	Doi = {10.1101/gr.3545105},
	Edat = {2005/05/19 09:00},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research},
	Keywords = {Animals; Anopheles gambiae/*genetics; Drosophila/*genetics; Drosophila Proteins/*genetics; Gene Expression Regulation; Homeodomain Proteins/*genetics; Molecular Sequence Data; *Phylogeny; RNA Splice Sites/*genetics; RNA Splicing/*genetics; RNA, Messenger/genetics},
	Language = {eng},
	Lr = {20081120},
	Mhda = {2005/08/16 09:00},
	Number = {6},
	Oid = {NLM: PMC1142470},
	Own = {NLM},
	Pages = {800--808},
	Phst = {2005/05/17 {$[$}aheadofprint{$]$}},
	Pii = {gr.3545105},
	Pl = {United States},
	Pmc = {PMC1142470},
	Pmid = {15899965},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Rn = {0 (Drosophila Proteins); 0 (Homeodomain Proteins); 0 (RNA Splice Sites); 0 (RNA, Messenger); 0 (homothorax protein, Drosophila)},
	Sb = {IM},
	So = {Genome Res. 2005 Jun;15(6):800-8. Epub 2005 May 17.},
	Stat = {MEDLINE},
	Title = {Ultraconserved elements in insect genomes: a highly conserved intronic sequence implicated in the control of homothorax mRNA splicing.},
	Volume = {15},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1101/gr.3545105}}

@article{Casillasetal2007,
	Abstract = {The majority of metazoan genomes consist of nonprotein-coding regions, although the functional significance of most noncoding DNA sequences remains unknown. Highly conserved noncoding sequences (CNSs) have proven to be reliable indicators of functionally constrained sequences such as cis-regulatory elements and noncoding RNA genes. However, CNSs may arise from nonselective evolutionary processes such as genomic regions with extremely low mutation rates known as mutation "cold spots." Here we combine comparative genomic data from recently completed insect genome projects with population genetic data in Drosophila melanogaster to test predictions of the mutational cold spot model of CNS evolution in the genus Drosophila. We find that point mutations in intronic and intergenic CNSs exhibit a significant reduction in levels of divergence relative to levels of polymorphism, as well as a significant excess of rare derived alleles, compared with either the nonconserved spacer regions between CNSs or with 4-fold silent sites in coding regions. Controlling for the effects of purifying selection, we find no evidence of positive selection acting on Drosophila CNSs, although we do find evidence for the action of recurrent positive selection in the spacer regions between CNSs. We estimate that approximately 85% of sites in Drosophila CNSs are under constraint with selection coefficients (N(e)s) on the order of 10-100, and thus, the estimated strength and number of sites under purifying selection is greater for Drosophila CNSs relative to those in the human genome. These patterns of nonneutral molecular evolution are incompatible with the mutational cold spot hypothesis to explain the existence of CNSs in Drosophila and, coupled with similar findings in mammals, argue against the general likelihood that CNSs are generated by mutational cold spots in any metazoan genome.},
	Address = {Faculty of Life Sciences, University of Manchester, Michael Smith Building, Manchester M13 9PT, UK.},
	Au = {Casillas, S and Barbadilla, A and Bergman, CM},
	Author = {Casillas, Sonia and Barbadilla, Antonio and Bergman, Casey M},
	Crdt = {2007/07/25 09:00},
	Da = {20071009},
	Date-Added = {2009-01-07 17:44:07 -0500},
	Date-Modified = {2009-01-07 17:44:39 -0500},
	Dcom = {20080414},
	Dep = {20070723},
	Doi = {10.1093/molbev/msm150},
	Edat = {2007/07/25 09:00},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution},
	Keywords = {Animals; Base Sequence; *Conserved Sequence; Drosophila melanogaster/*genetics; *Evolution, Molecular; Genome, Insect; Humans; Mutation; Polymorphism, Genetic; *Selection (Genetics); Sequence Alignment; Sequence Analysis, DNA},
	Language = {eng},
	Mhda = {2008/04/15 09:00},
	Number = {10},
	Own = {NLM},
	Pages = {2222--2234},
	Phst = {2007/07/23 {$[$}aheadofprint{$]$}},
	Pii = {msm150},
	Pl = {United States},
	Pmid = {17646256},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Sb = {IM},
	So = {Mol Biol Evol. 2007 Oct;24(10):2222-34. Epub 2007 Jul 23.},
	Stat = {MEDLINE},
	Title = {Purifying selection maintains highly conserved noncoding sequences in Drosophila.},
	Volume = {24},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/molbev/msm150}}

@article{Leeetal2006,
	Abstract = {Polycomb group proteins are essential for early development in metazoans, but their contributions to human development are not well understood. We have mapped the Polycomb Repressive Complex 2 (PRC2) subunit SUZ12 across the entire nonrepeat portion of the genome in human embryonic stem (ES) cells. We found that SUZ12 is distributed across large portions of over two hundred genes encoding key developmental regulators. These genes are occupied by nucleosomes trimethylated at histone H3K27, are transcriptionally repressed, and contain some of the most highly conserved noncoding elements in the genome. We found that PRC2 target genes are preferentially activated during ES cell differentiation and that the ES cell regulators OCT4, SOX2, and NANOG cooccupy a significant subset of these genes. These results indicate that PRC2 occupies a special set of developmental genes in ES cells that must be repressed to maintain pluripotency and that are poised for activation during ES cell differentiation.},
	Address = {Whitehead Institute for Biomedical Research, 9 Cambridge Center, Cambridge, MA 02142, USA.},
	Au = {Lee, TI and Jenner, RG and Boyer, LA and Guenther, MG and Levine, SS and Kumar, RM and Chevalier, B and Johnstone, SE and Cole, MF and Isono, K and Koseki, H and Fuchikami, T and Abe, K and Murray, HL and Zucker, JP and Yuan, B and Bell, GW and Herbolsheimer, E and Hannett, NM and Sun, K and Odom, DT and Otte, AP and Volkert, TL and Bartel, DP and Melton, DA and Gifford, DK and Jaenisch, R and Young, RA},
	Author = {Lee, Tong Ihn and Jenner, Richard G and Boyer, Laurie A and Guenther, Matthew G and Levine, Stuart S and Kumar, Roshan M and Chevalier, Brett and Johnstone, Sarah E and Cole, Megan F and Isono, Kyo-ichi and Koseki, Haruhiko and Fuchikami, Takuya and Abe, Kuniya and Murray, Heather L and Zucker, Jacob P and Yuan, Bingbing and Bell, George W and Herbolsheimer, Elizabeth and Hannett, Nancy M and Sun, Kaiming and Odom, Duncan T and Otte, Arie P and Volkert, Thomas L and Bartel, David P and Melton, Douglas A and Gifford, David K and Jaenisch, Rudolf and Young, Richard A},
	Cin = {Cell. 2006 Apr 21;125(2):233-6. PMID: 16630812},
	Crdt = {2006/04/25 09:00},
	Da = {20060424},
	Date-Added = {2009-01-07 11:45:58 -0500},
	Date-Modified = {2009-07-07 08:38:47 -0400},
	Dcom = {20060613},
	Doi = {10.1016/j.cell.2006.02.043},
	Edat = {2006/04/25 09:00},
	Gr = {DK070813/DK/NIDDK NIH HHS/United States; GM069400/GM/NIGMS NIH HHS/United States; HG002668/HG/NHGRI NIH HHS/United States},
	Issn = {0092-8674 (Print)},
	Jid = {0413066},
	Journal = {Cell},
	Jt = {Cell},
	Language = {eng},
	Lr = {20071115},
	Mh = {Animals; Carrier Proteins/genetics/*metabolism; Cells, Cultured; Gene Expression Profiling; *Gene Expression Regulation, Developmental; Humans; Multiprotein Complexes; Nuclear Proteins; Oligonucleotide Array Sequence Analysis; Protein Subunits/genetics/metabolism; RNA Polymerase II/genetics/metabolism; Signal Transduction/physiology; Stem Cells/cytology/*physiology; Transcription Factors/genetics/metabolism; Transcription, Genetic},
	Mhda = {2006/06/14 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {301--313},
	Phst = {2005/10/25 {$[$}received{$]$}; 2006/01/20 {$[$}revised{$]$}; 2006/02/23 {$[$}accepted{$]$}},
	Pii = {S0092-8674(06)00384-9},
	Pl = {United States},
	Pmid = {16630818},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Rn = {0 (Carrier Proteins); 0 (Multiprotein Complexes); 0 (Nuclear Proteins); 0 (Protein Subunits); 0 (SUZ12 protein, human); 0 (Transcription Factors); EC 2.7.7.- (RNA Polymerase II)},
	Sb = {IM},
	So = {Cell. 2006 Apr 21;125(2):301-13.},
	Stat = {MEDLINE},
	Title = {Control of developmental regulators by Polycomb in human embryonic stem cells.},
	Volume = {125},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.cell.2006.02.043}}

@article{Bernsteinetal2006,
	Abstract = {The most highly conserved noncoding elements (HCNEs) in mammalian genomes cluster within regions enriched for genes encoding developmentally important transcription factors (TFs). This suggests that HCNE-rich regions may contain key regulatory controls involved in development. We explored this by examining histone methylation in mouse embryonic stem (ES) cells across 56 large HCNE-rich loci. We identified a specific modification pattern, termed "bivalent domains," consisting of large regions of H3 lysine 27 methylation harboring smaller regions of H3 lysine 4 methylation. Bivalent domains tend to coincide with TF genes expressed at low levels. We propose that bivalent domains silence developmental genes in ES cells while keeping them poised for activation. We also found striking correspondences between genome sequence and histone methylation in ES cells, which become notably weaker in differentiated cells. These results highlight the importance of DNA sequence in defining the initial epigenetic landscape and suggest a novel chromatin-based mechanism for maintaining pluripotency.},
	Address = {Molecular Pathology Unit and Center for Cancer Research, Massachusetts General Hospital, Charlestown, MA 02129, USA. bbernstein@partners.org},
	Au = {Bernstein, BE and Mikkelsen, TS and Xie, X and Kamal, M and Huebert, DJ and Cuff, J and Fry, B and Meissner, A and Wernig, M and Plath, K and Jaenisch, R and Wagschal, A and Feil, R and Schreiber, SL and Lander, ES},
	Author = {Bernstein, Bradley E and Mikkelsen, Tarjei S and Xie, Xiaohui and Kamal, Michael and Huebert, Dana J and Cuff, James and Fry, Ben and Meissner, Alex and Wernig, Marius and Plath, Kathrin and Jaenisch, Rudolf and Wagschal, Alexandre and Feil, Robert and Schreiber, Stuart L and Lander, Eric S},
	Cin = {Cell. 2006 Apr 21;125(2):233-6. PMID: 16630812},
	Crdt = {2006/04/25 09:00},
	Da = {20060424},
	Date-Added = {2009-01-07 11:44:21 -0500},
	Date-Modified = {2009-07-07 08:38:27 -0400},
	Dcom = {20060613},
	Doi = {10.1016/j.cell.2006.02.041},
	Edat = {2006/04/25 09:00},
	Gr = {CA84198/CA/NCI NIH HHS/United States; GM38627/GM/NIGMS NIH HHS/United States; HD045022/HD/NICHD NIH HHS/United States},
	Issn = {0092-8674 (Print)},
	Jid = {0413066},
	Journal = {Cell},
	Jt = {Cell},
	Language = {eng},
	Lr = {20071114},
	Mh = {Animals; Cell Differentiation; Cells, Cultured; Chromatin/*chemistry/metabolism; DNA-Binding Proteins/genetics/metabolism; Epigenesis, Genetic; Gene Expression Profiling; *Gene Expression Regulation, Developmental; Histones/chemistry/*metabolism; Homeodomain Proteins/genetics/metabolism; Male; Methylation; Mice; Mice, Inbred C57BL; *Nucleic Acid Conformation; Octamer Transcription Factor-3/genetics/metabolism; Oligonucleotide Array Sequence Analysis; Stem Cells/cytology/*physiology},
	Mhda = {2006/06/14 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {315--326},
	Phst = {2005/11/04 {$[$}received{$]$}; 2006/01/18 {$[$}revised{$]$}; 2006/02/23 {$[$}accepted{$]$}},
	Pii = {S0092-8674(06)00380-1},
	Pl = {United States},
	Pmid = {16630819},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Rn = {0 (Chromatin); 0 (DNA-Binding Proteins); 0 (Histones); 0 (Homeodomain Proteins); 0 (Nanog protein, mouse); 0 (Octamer Transcription Factor-3); 0 (Pou5f1 protein, mouse)},
	Sb = {IM},
	So = {Cell. 2006 Apr 21;125(2):315-26.},
	Stat = {MEDLINE},
	Title = {A bivalent chromatin structure marks key developmental genes in embryonic stem cells.},
	Volume = {125},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1016/j.cell.2006.02.041}}

@article{CarterDurbin2006,
	Abstract = {BACKGROUND: One way in which the accuracy of gene structure prediction in vertebrate DNA sequences can be improved is by analyzing alignments with multiple related species, since functional regions of genes tend to be more conserved. RESULTS: We describe DOGFISH, a vertebrate gene finder consisting of a cleanly separated site classifier and structure predictor. The classifier scores potential splice sites and other features, using sequence alignments between multiple vertebrate species, while the structure predictor hypothesizes coding transcripts by combining these scores using a simple model of gene structure. This also identifies and assigns confidence scores to possible additional exons. Performance is assessed on the ENCODE regions. We predict transcripts and exons across the whole human genome, and identify over 10,000 high confidence new coding exons not in the Ensembl gene set. CONCLUSION: We present a practical multiple species gene prediction method. Accuracy improves as additional species, up to at least eight, are introduced. The novel predictions of the whole-genome scan should support efficient experimental verification.},
	Address = {Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SA, UK. dmc@sanger.ac.uk},
	Au = {Carter, D and Durbin, R},
	Author = {Carter, David and Durbin, Richard},
	Crdt = {2006/08/24 09:00},
	Da = {20060823},
	Date-Added = {2009-01-07 10:33:05 -0500},
	Date-Modified = {2009-01-07 10:33:22 -0500},
	Dcom = {20060918},
	Dep = {20060807},
	Doi = {10.1186/gb-2006-7-s1-s6},
	Edat = {2006/08/24 09:00},
	Gr = {Wellcome Trust/United Kingdom},
	Issn = {1465-6914 (Electronic)},
	Jid = {100960660},
	Journal = {Genome Biol},
	Jt = {Genome biology},
	Language = {eng},
	Lr = {20081120},
	Mh = {Animals; Base Sequence; Computational Biology/methods; Exons; Genes; Genome, Human; Genomics/*methods; Humans; Models, Genetic; RNA Splice Sites; RNA, Messenger/analysis; Sequence Alignment/*methods; *Software; Vertebrates/*genetics},
	Mhda = {2006/09/19 09:00},
	Oid = {NLM: PMC1810555},
	Own = {NLM},
	Pages = {S6.1-12},
	Phst = {2006/08/07 {$[$}epublish{$]$}},
	Pii = {gb-2006-7-s1-s6},
	Pl = {England},
	Pmc = {PMC1810555},
	Pmid = {16925840},
	Pst = {ppublish},
	Pt = {Evaluation Studies; Journal Article; Research Support, Non-U.S. Gov't},
	Rn = {0 (RNA Splice Sites); 0 (RNA, Messenger)},
	Sb = {IM},
	So = {Genome Biol. 2006;7 Suppl 1:S6.1-12. Epub 2006 Aug 7.},
	Stat = {MEDLINE},
	Title = {Vertebrate gene finding from multiple-species alignments using a two-level strategy.},
	Volume = {7 Suppl 1},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1186/gb-2006-7-s1-s6}}

@article{Birney2007,
	Abstract = {We report the generation and analysis of functional data from multiple, diverse experiments performed on a targeted 1% of the human genome as part of the pilot phase of the ENCODE Project. These data have been further integrated and augmented by a number of evolutionary and computational analyses. Together, our results advance the collective knowledge about human genome function in several major areas. First, our studies provide convincing evidence that the genome is pervasively transcribed, such that the majority of its bases can be found in primary transcripts, including non-protein-coding transcripts, and those that extensively overlap one another. Second, systematic examination of transcriptional regulation has yielded new understanding about transcription start sites, including their relationship to specific regulatory sequences and features of chromatin accessibility and histone modification. Third, a more sophisticated view of chromatin structure has emerged, including its inter-relationship with DNA replication and transcriptional regulation. Finally, integration of these new sources of information, in particular with respect to mammalian evolution based on inter- and intra-species sequence comparisons, has yielded new mechanistic and evolutionary insights concerning the functional landscape of the human genome. Together, these studies are defining a path for pursuit of a more comprehensive characterization of human genome function.},
	Au = {Birney, E and Stamatoyannopoulos, JA and Dutta, A and Guigo, R and Gingeras, TR and Margulies, EH and Weng, Z and Snyder, M and Dermitzakis, ET and Thurman, RE and Kuehn, MS and Taylor, CM and Neph, S and Koch, CM and Asthana, S and Malhotra, A and Adzhubei, I and Greenbaum, JA and Andrews, RM and Flicek, P and Boyle, PJ and Cao, H and Carter, NP and Clelland, GK and Davis, S and Day, N and Dhami, P and Dillon, SC and Dorschner, MO and Fiegler, H and Giresi, PG and Goldy, J and Hawrylycz, M and Haydock, A and Humbert, R and James, KD and Johnson, BE and Johnson, EM and Frum, TT and Rosenzweig, ER and Karnani, N and Lee, K and Lefebvre, GC and Navas, PA and Neri, F and Parker, SC and Sabo, PJ and Sandstrom, R and Shafer, A and Vetrie, D and Weaver, M and Wilcox, S and Yu, M and Collins, FS and Dekker, J and Lieb, JD and Tullius, TD and Crawford, GE and Sunyaev, S and Noble, WS and Dunham, I and Denoeud, F and Reymond, A and Kapranov, P and Rozowsky, J and Zheng, D and Castelo, R and Frankish, A and Harrow, J and Ghosh, S and Sandelin, A and Hofacker, IL and Baertsch, R and Keefe, D and Dike, S and Cheng, J and Hirsch, HA and Sekinger, EA and Lagarde, J and Abril, JF and Shahab, A and Flamm, C and Fried, C and Hackermuller, J and Hertel, J and Lindemeyer, M and Missal, K and Tanzer, A and Washietl, S and Korbel, J and Emanuelsson, O and Pedersen, JS and Holroyd, N and Taylor, R and Swarbreck, D and Matthews, N and Dickson, MC and Thomas, DJ and Weirauch, MT and Gilbert, J and Drenkow, J and Bell, I and Zhao, X and Srinivasan, KG and Sung, WK and Ooi, HS and Chiu, KP and Foissac, S and Alioto, T and Brent, M and Pachter, L and Tress, ML and Valencia, A and Choo, SW and Choo, CY and Ucla, C and Manzano, C and Wyss, C and Cheung, E and Clark, TG and Brown, JB and Ganesh, M and Patel, S and Tammana, H and Chrast, J and Henrichsen, CN and Kai, C and Kawai, J and Nagalakshmi, U and Wu, J and Lian, Z and Lian, J and Newburger, P and Zhang, X and Bickel, P and Mattick, JS and Carninci, P and Hayashizaki, Y and Weissman, S and Hubbard, T and Myers, RM and Rogers, J and Stadler, PF and Lowe, TM and Wei, CL and Ruan, Y and Struhl, K and Gerstein, M and Antonarakis, SE and Fu, Y and Green, ED and Karaoz, U and Siepel, A and Taylor, J and Liefer, LA and Wetterstrand, KA and Good, PJ and Feingold, EA and Guyer, MS and Cooper, GM and Asimenos, G and Dewey, CN and Hou, M and Nikolaev, S and Montoya-Burgos, JI and Loytynoja, A and Whelan, S and Pardi, F and Massingham, T and Huang, H and Zhang, NR and Holmes, I and Mullikin, JC and Ureta-Vidal, A and Paten, B and Seringhaus, M and Church, D and Rosenbloom, K and Kent, WJ and Stone, EA and Batzoglou, S and Goldman, N and Hardison, RC and Haussler, D and Miller, W and Sidow, A and Trinklein, ND and Zhang, ZD and Barrera, L and Stuart, R and King, DC and Ameur, A and Enroth, S and Bieda, MC and Kim, J and Bhinge, AA and Jiang, N and Liu, J and Yao, F and Vega, VB and Lee, CW and Ng, P and Shahab, A and Yang, A and Moqtaderi, Z and Zhu, Z and Xu, X and Squazzo, S and Oberley, MJ and Inman, D and Singer, MA and Richmond, TA and Munn, KJ and Rada-Iglesias, A and Wallerman, O and Komorowski, J and Fowler, JC and Couttet, P and Bruce, AW and Dovey, OM and Ellis, PD and Langford, CF and Nix, DA and Euskirchen, G and Hartman, S and Urban, AE and Kraus, P and Van Calcar, S and Heintzman, N and Kim, TH and Wang, K and Qu, C and Hon, G and Luna, R and Glass, CK and Rosenfeld, MG and Aldred, SF and Cooper, SJ and Halees, A and Lin, JM and Shulha, HP and Zhang, X and Xu, M and Haidar, JN and Yu, Y and Ruan, Y and Iyer, VR and Green, RD and Wadelius, C and Farnham, PJ and Ren, B and Harte, RA and Hinrichs, AS and Trumbower, H and Clawson, H and Hillman-Jackson, J and Zweig, AS and Smith, K and Thakkapallayil, A and Barber, G and Kuhn, RM and Karolchik, D and Armengol, L and Bird, CP and de Bakker, PI and Kern, AD and Lopez-Bigas, N and Martin, JD and Stranger, BE and Woodroffe, A and Davydov, E and Dimas, A and Eyras, E and Hallgrimsdottir, IB and Huppert, J and Zody, MC and Abecasis, GR and Estivill, X and Bouffard, GG and Guan, X and Hansen, NF and Idol, JR and Maduro, VV and Maskeri, B and McDowell, JC and Park, M and Thomas, PJ and Young, AC and Blakesley, RW and Muzny, DM and Sodergren, E and Wheeler, DA and Worley, KC and Jiang, H and Weinstock, GM and Gibbs, RA and Graves, T and Fulton, R and Mardis, ER and Wilson, RK and Clamp, M and Cuff, J and Gnerre, S and Jaffe, DB and Chang, JL and Lindblad-Toh, K and Lander, ES and Koriabine, M and Nefedov, M and Osoegawa, K and Yoshinaga, Y and Zhu, B and de Jong, PJ},
	Author = {Birney, Ewan and Stamatoyannopoulos, John A and Dutta, Anindya and Guigo, Roderic and Gingeras, Thomas R and Margulies, Elliott H and Weng, Zhiping and Snyder, Michael and Dermitzakis, Emmanouil T and Thurman, Robert E and Kuehn, Michael S and Taylor, Christopher M and Neph, Shane and Koch, Christoph M and Asthana, Saurabh and Malhotra, Ankit and Adzhubei, Ivan and Greenbaum, Jason A and Andrews, Robert M and Flicek, Paul and Boyle, Patrick J and Cao, Hua and Carter, Nigel P and Clelland, Gayle K and Davis, Sean and Day, Nathan and Dhami, Pawandeep and Dillon, Shane C and Dorschner, Michael O and Fiegler, Heike and Giresi, Paul G and Goldy, Jeff and Hawrylycz, Michael and Haydock, Andrew and Humbert, Richard and James, Keith D and Johnson, Brett E and Johnson, Ericka M and Frum, Tristan T and Rosenzweig, Elizabeth R and Karnani, Neerja and Lee, Kirsten and Lefebvre, Gregory C and Navas, Patrick A and Neri, Fidencio and Parker, Stephen C J and Sabo, Peter J and Sandstrom, Richard and Shafer, Anthony and Vetrie, David and Weaver, Molly and Wilcox, Sarah and Yu, Man and Collins, Francis S and Dekker, Job and Lieb, Jason D and Tullius, Thomas D and Crawford, Gregory E and Sunyaev, Shamil and Noble, William S and Dunham, Ian and Denoeud, France and Reymond, Alexandre and Kapranov, Philipp and Rozowsky, Joel and Zheng, Deyou and Castelo, Robert and Frankish, Adam and Harrow, Jennifer and Ghosh, Srinka and Sandelin, Albin and Hofacker, Ivo L and Baertsch, Robert and Keefe, Damian and Dike, Sujit and Cheng, Jill and Hirsch, Heather A and Sekinger, Edward A and Lagarde, Julien and Abril, Josep F and Shahab, Atif and Flamm, Christoph and Fried, Claudia and Hackermuller, Jorg and Hertel, Jana and Lindemeyer, Manja and Missal, Kristin and Tanzer, Andrea and Washietl, Stefan and Korbel, Jan and Emanuelsson, Olof and Pedersen, Jakob S and Holroyd, Nancy and Taylor, Ruth and Swarbreck, David and Matthews, Nicholas and Dickson, Mark C and Thomas, Daryl J and Weirauch, Matthew T and Gilbert, James and Drenkow, Jorg and Bell, Ian and Zhao, XiaoDong and Srinivasan, K G and Sung, Wing-Kin and Ooi, Hong Sain and Chiu, Kuo Ping and Foissac, Sylvain and Alioto, Tyler and Brent, Michael and Pachter, Lior and Tress, Michael L and Valencia, Alfonso and Choo, Siew Woh and Choo, Chiou Yu and Ucla, Catherine and Manzano, Caroline and Wyss, Carine and Cheung, Evelyn and Clark, Taane G and Brown, James B and Ganesh, Madhavan and Patel, Sandeep and Tammana, Hari and Chrast, Jacqueline and Henrichsen, Charlotte N and Kai, Chikatoshi and Kawai, Jun and Nagalakshmi, Ugrappa and Wu, Jiaqian and Lian, Zheng and Lian, Jin and Newburger, Peter and Zhang, Xueqing and Bickel, Peter and Mattick, John S and Carninci, Piero and Hayashizaki, Yoshihide and Weissman, Sherman and Hubbard, Tim and Myers, Richard M and Rogers, Jane and Stadler, Peter F and Lowe, Todd M and Wei, Chia-Lin and Ruan, Yijun and Struhl, Kevin and Gerstein, Mark and Antonarakis, Stylianos E and Fu, Yutao and Green, Eric D and Karaoz, Ulas and Siepel, Adam and Taylor, James and Liefer, Laura A and Wetterstrand, Kris A and Good, Peter J and Feingold, Elise A and Guyer, Mark S and Cooper, Gregory M and Asimenos, George and Dewey, Colin N and Hou, Minmei and Nikolaev, Sergey and Montoya-Burgos, Juan I and Loytynoja, Ari and Whelan, Simon and Pardi, Fabio and Massingham, Tim and Huang, Haiyan and Zhang, Nancy R and Holmes, Ian and Mullikin, James C and Ureta-Vidal, Abel and Paten, Benedict and Seringhaus, Michael and Church, Deanna and Rosenbloom, Kate and Kent, W James and Stone, Eric A and Batzoglou, Serafim and Goldman, Nick and Hardison, Ross C and Haussler, David and Miller, Webb and Sidow, Arend and Trinklein, Nathan D and Zhang, Zhengdong D and Barrera, Leah and Stuart, Rhona and King, David C and Ameur, Adam and Enroth, Stefan and Bieda, Mark C and Kim, Jonghwan and Bhinge, Akshay A and Jiang, Nan and Liu, Jun and Yao, Fei and Vega, Vinsensius B and Lee, Charlie W H and Ng, Patrick and Shahab, Atif and Yang, Annie and Moqtaderi, Zarmik and Zhu, Zhou and Xu, Xiaoqin and Squazzo, Sharon and Oberley, Matthew J and Inman, David and Singer, Michael A and Richmond, Todd A and Munn, Kyle J and Rada-Iglesias, Alvaro and Wallerman, Ola and Komorowski, Jan and Fowler, Joanna C and Couttet, Phillippe and Bruce, Alexander W and Dovey, Oliver M and Ellis, Peter D and Langford, Cordelia F and Nix, David A and Euskirchen, Ghia and Hartman, Stephen and Urban, Alexander E and Kraus, Peter and Van Calcar, Sara and Heintzman, Nate and Kim, Tae Hoon and Wang, Kun and Qu, Chunxu and Hon, Gary and Luna, Rosa and Glass, Christopher K and Rosenfeld, M Geoff and Aldred, Shelley Force and Cooper, Sara J and Halees, Anason and Lin, Jane M and Shulha, Hennady P and Zhang, Xiaoling and Xu, Mousheng and Haidar, Jaafar N S and Yu, Yong and Ruan, Yijun and Iyer, Vishwanath R and Green, Roland D and Wadelius, Claes and Farnham, Peggy J and Ren, Bing and Harte, Rachel A and Hinrichs, Angie S and Trumbower, Heather and Clawson, Hiram and Hillman-Jackson, Jennifer and Zweig, Ann S and Smith, Kayla and Thakkapallayil, Archana and Barber, Galt and Kuhn, Robert M and Karolchik, Donna and Armengol, Lluis and Bird, Christine P and de Bakker, Paul I W and Kern, Andrew D and Lopez-Bigas, Nuria and Martin, Joel D and Stranger, Barbara E and Woodroffe, Abigail and Davydov, Eugene and Dimas, Antigone and Eyras, Eduardo and Hallgrimsdottir, Ingileif B and Huppert, Julian and Zody, Michael C and Abecasis, Goncalo R and Estivill, Xavier and Bouffard, Gerard G and Guan, Xiaobin and Hansen, Nancy F and Idol, Jacquelyn R and Maduro, Valerie V B and Maskeri, Baishali and McDowell, Jennifer C and Park, Morgan and Thomas, Pamela J and Young, Alice C and Blakesley, Robert W and Muzny, Donna M and Sodergren, Erica and Wheeler, David A and Worley, Kim C and Jiang, Huaiyang and Weinstock, George M and Gibbs, Richard A and Graves, Tina and Fulton, Robert and Mardis, Elaine R and Wilson, Richard K and Clamp, Michele and Cuff, James and Gnerre, Sante and Jaffe, David B and Chang, Jean L and Lindblad-Toh, Kerstin and Lander, Eric S and Koriabine, Maxim and Nefedov, Mikhail and Osoegawa, Kazutoyo and Yoshinaga, Yuko and Zhu, Baoli and de Jong, Pieter J},
	Cin = {Nature. 2007 Jun 14;447(7146):760-1. PMID: 17568710; Nature. 2007 Jun 14;447(7146):782-3. PMID: 17568731},
	Cn = {ENCODE Project Consortium; NISC Comparative Sequencing Program; Baylor College of Medicine Human Genome Sequencing Center; Washington University Genome Sequencing Center; Broad Institute; Children's Hospital Oakland Research Institute},
	Crdt = {2007/06/16 09:00},
	Da = {20070614},
	Date-Added = {2009-01-07 10:12:27 -0500},
	Date-Modified = {2010-01-12 15:20:29 -0500},
	Dcom = {20070627},
	Edat = {2007/06/16 09:00},
	Gr = {077198/Wellcome Trust/United Kingdom; K22 HG003169-01A1/HG/NHGRI NIH HHS/United States; P41 HG002371-03S1/HG/NHGRI NIH HHS/United States; R01 HG002238-15/HG/NHGRI NIH HHS/United States; R01 HG003110-03/HG/NHGRI NIH HHS/United States; R01 HG003129-03/HG/NHGRI NIH HHS/United States; R01 HG003143-04/HG/NHGRI NIH HHS/United States; R01 HG003521-01/HG/NHGRI NIH HHS/United States; R01 HG003532-01/HG/NHGRI NIH HHS/United States; R01 HG003541-01/HG/NHGRI NIH HHS/United States; U01 HG002523-01/HG/NHGRI NIH HHS/United States; U01 HG003147-02/HG/NHGRI NIH HHS/United States; U01 HG003150-03/HG/NHGRI NIH HHS/United States; U01 HG003151-03/HG/NHGRI NIH HHS/United States; U01 HG003156-03/HG/NHGRI NIH HHS/United States; U01 HG003157-03/HG/NHGRI NIH HHS/United States; U01 HG003161-03/HG/NHGRI NIH HHS/United States; U01 HG003162-03/HG/NHGRI NIH HHS/United States; U01 HG003168-02/HG/NHGRI NIH HHS/United States; U54 HG003067-01/HG/NHGRI NIH HHS/United States; U54 HG003079-01/HG/NHGRI NIH HHS/United States; U54 HG003273-01/HG/NHGRI NIH HHS/United States; Wellcome Trust/United Kingdom},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20081121},
	Mh = {Chromatin/genetics/metabolism; Chromatin Immunoprecipitation; Conserved Sequence/genetics; DNA Replication; Evolution, Molecular; Exons/genetics; Genetic Variation/genetics; Genome, Human/*genetics; *Genomics; Heterozygote; Histones/metabolism; Humans; Pilot Projects; Protein Binding; RNA, Messenger/genetics; RNA, Untranslated/genetics; Regulatory Sequences, Nucleic Acid/*genetics; Transcription Factors/metabolism; Transcription Initiation Site; Transcription, Genetic/*genetics},
	Mhda = {2007/06/28 09:00},
	Mid = {NIHMS27513},
	Number = {7146},
	Oid = {NLM: NIHMS27513; NLM: PMC2212820},
	Own = {NLM},
	Pages = {799--816},
	Pl = {England},
	Pmc = {PMC2212820},
	Pmid = {17571346},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.},
	Rn = {0 (Chromatin); 0 (Histones); 0 (RNA, Messenger); 0 (RNA, Untranslated); 0 (Transcription Factors)},
	Sb = {IM},
	So = {Nature. 2007 Jun 14;447(7146):799-816.},
	Stat = {MEDLINE},
	Title = {Identification and analysis of functional elements in 1{\%} of the human genome by the ENCODE pilot project.},
	Volume = {447},
	Year = {2007}}

@article{riboswitch2004,
	Abstract = {We identified a previously unknown riboswitch class in bacteria that is selectively triggered by glycine. A representative of these glycine-sensing RNAs from Bacillus subtilis operates as a rare genetic on switch for the gcvT operon, which codes for proteins that form the glycine cleavage system. Most glycine riboswitches integrate two ligand-binding domains that function cooperatively to more closely approximate a two-state genetic switch. This advanced form of riboswitch may have evolved to ensure that excess glycine is efficiently used to provide carbon flux through the citric acid cycle and maintain adequate amounts of the amino acid for protein synthesis. Thus, riboswitches perform key regulatory roles and exhibit complex performance characteristics that previously had been observed only with protein factors.},
	Address = {Department of Molecular, Cellular, and Developmental Biology, Yale University, Post Office Box 208103, New Haven, CT 06520-8103, USA.},
	Au = {Mandal, M and Lee, M and Barrick, JE and Weinberg, Z and Emilsson, GM and Ruzzo, WL and Breaker, RR},
	Author = {Mandal, Maumita and Lee, Mark and Barrick, Jeffrey E and Weinberg, Zasha and Emilsson, Gail Mitchell and Ruzzo, Walter L and Breaker, Ronald R},
	Cin = {Science. 2004 Oct 8;306(5694):233-4. PMID: 15472064},
	Da = {20041008},
	Date-Added = {2008-09-23 09:32:18 -0400},
	Date-Modified = {2008-09-23 09:32:42 -0400},
	Dcom = {20041021},
	Doi = {10.1126/science.1100829},
	Edat = {2004/10/09 09:00},
	Ein = {Science. 2004 Nov 26;306(5701):1477},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Language = {eng},
	Lr = {20070319},
	Mh = {5' Untranslated Regions/chemistry/*metabolism; Allosteric Regulation; Allosteric Site; Bacillus subtilis/*genetics/metabolism; Base Pairing; Base Sequence; Binding Sites; *Gene Expression Regulation, Bacterial; Glycine/*metabolism; Ligands; Molecular Sequence Data; Mutation; Nucleic Acid Conformation; Operon; RNA, Bacterial/chemistry/*metabolism; RNA, Messenger/chemistry/*metabolism; Transcription, Genetic; Vibrio cholerae/*genetics/metabolism},
	Mhda = {2004/10/22 09:00},
	Number = {5694},
	Own = {NLM},
	Pages = {275--279},
	Pii = {306/5694/275},
	Pl = {United States},
	Pmid = {15472076},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Rn = {0 (5' Untranslated Regions); 0 (Ligands); 0 (RNA, Bacterial); 0 (RNA, Messenger); 56-40-6 (Glycine)},
	Sb = {IM},
	So = {Science. 2004 Oct 8;306(5694):275-9.},
	Stat = {MEDLINE},
	Title = {A glycine-dependent riboswitch that uses cooperative binding to control gene expression.},
	Volume = {306},
	Year = {2004 Oct 8},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1100829}}

@article{Zucker2003,
	Author = {M. Zucker},
	Date-Added = {2008-09-22 15:36:33 -0400},
	Date-Modified = {2008-09-22 15:37:45 -0400},
	Journal = {Nucleic Acids Res},
	Number = {13},
	Pages = {3406-3415},
	Title = {Mfold web server for nucleic acid folding and hybridization prediction.},
	Volume = {31},
	Year = {2003}}

@article{Pedersenetal2006,
	Abstract = {The discoveries of microRNAs and riboswitches, among others, have shown functional RNAs to be biologically more important and genomically more prevalent than previously anticipated. We have developed a general comparative genomics method based on phylogenetic stochastic context-free grammars for identifying functional RNAs encoded in the human genome and used it to survey an eight-way genome-wide alignment of the human, chimpanzee, mouse, rat, dog, chicken, zebra-fish, and puffer-fish genomes for deeply conserved functional RNAs. At a loose threshold for acceptance, this search resulted in a set of 48,479 candidate RNA structures. This screen finds a large number of known functional RNAs, including 195 miRNAs, 62 histone 3'UTR stem loops, and various types of known genetic recoding elements. Among the highest-scoring new predictions are 169 new miRNA candidates, as well as new candidate selenocysteine insertion sites, RNA editing hairpins, RNAs involved in transcript auto regulation, and many folds that form singletons or small functional RNA families of completely unknown function. While the rate of false positives in the overall set is difficult to estimate and is likely to be substantial, the results nevertheless provide evidence for many new human functional RNAs and present specific predictions to facilitate their further characterization.},
	Address = {Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California, USA. jsp@soe.ucsc.edu},
	Au = {Pedersen, JS and Bejerano, G and Siepel, A and Rosenbloom, K and Lindblad-Toh, K and Lander, ES and Kent, J and Miller, W and Haussler, D},
	Author = {Pedersen, Jakob Skou and Bejerano, Gill and Siepel, Adam and Rosenbloom, Kate and Lindblad-Toh, Kerstin and Lander, Eric S and Kent, Jim and Miller, Webb and Haussler, David},
	Da = {20060605},
	Date-Added = {2008-09-22 15:33:17 -0400},
	Date-Modified = {2009-07-07 08:34:43 -0400},
	Dcom = {20060728},
	Dep = {20060421},
	Doi = {10.1371/journal.pcbi.0020033},
	Edat = {2006/04/22 09:00},
	Gr = {1P41HG02371/HG/United States NHGRI},
	Issn = {1553-7358 (Electronic)},
	Jid = {101238922},
	Journal = {PLoS Comput Biol},
	Jt = {PLoS computational biology},
	Language = {eng},
	Lr = {20071114},
	Mh = {3' Untranslated Regions; Animals; Chickens; Computational Biology/methods; Conserved Sequence; Dogs; Genome; *Genome, Human; Humans; Mice; MicroRNAs/*chemistry; *Nucleic Acid Conformation; Rats; Sequence Analysis, RNA/*methods; Tetraodontiformes; Zebrafish},
	Mhda = {2006/07/29 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {e33},
	Phst = {2005/09/08 {$[$}received{$]$}; 2006/03/06 {$[$}accepted{$]$}; 2006/04/21 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmc = {PMC1440920},
	Pmid = {16628248},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Pubm = {Print-Electronic},
	Rn = {0 (3' Untranslated Regions); 0 (MicroRNAs)},
	Sb = {IM},
	So = {PLoS Comput Biol. 2006 Apr;2(4):e33. Epub 2006 Apr 21.},
	Stat = {MEDLINE},
	Title = {Identification and classification of conserved RNA secondary structures in the human genome.},
	Volume = {2},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pcbi.0020033}}

@article{Hoopengardneretal2003,
	Abstract = {An unknown number of precursor messenger RNAs undergo genetic recoding by modification of adenosine to inosine, a reaction catalyzed by the adenosine deaminases acting on RNA (ADARs). Discovery of these edited transcripts has always been serendipitous. Using comparative genomics, we identified a phylogenetic signature of RNA editing. We report the identification and experimental verification of 16 previously unknown ADAR target genes in the fruit fly Drosophila and one in humans-more than the sum total previously reported. All of these genes are involved in rapid electrical and chemical neurotransmission, and many of the edited sites recode conserved and functionally important amino acids. These results point to a pivotal role for RNA editing in nervous system function.},
	Address = {Department of Genetics and Developmental Biology, University of Connecticut Health Center, 263 Farmington Avenue, Farmington, CT 06030, USA.},
	Au = {Hoopengardner, B and Bhalla, T and Staber, C and Reenan, R},
	Author = {Hoopengardner, Barry and Bhalla, Tarun and Staber, Cynthia and Reenan, Robert},
	Da = {20030808},
	Date-Added = {2008-09-22 15:30:39 -0400},
	Date-Modified = {2009-07-07 08:40:09 -0400},
	Dcom = {20030822},
	Doi = {10.1126/science.1086763},
	Edat = {2003/08/09 05:00},
	Gr = {R01 GM062291/GM/United States NIGMS},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Language = {eng},
	Lr = {20071114},
	Mh = {Adenosine/metabolism; Adenosine Deaminase/*metabolism; Animals; Base Sequence; Drosophila/*genetics; Drosophila melanogaster/genetics; *Genes, Insect; Genomics; Humans; Inosine/metabolism; Ion Channel Gating; Ion Channels/*genetics/metabolism; Molecular Sequence Data; Nervous System/metabolism; Phylogeny; Potassium Channels/genetics/metabolism; *RNA Editing; Reverse Transcriptase Polymerase Chain Reaction; Synapses; *Synaptic Transmission},
	Mhda = {2003/08/23 05:00},
	Number = {5634},
	Own = {NLM},
	Pages = {832--836},
	Pii = {301/5634/832},
	Pl = {United States},
	Pmid = {12907802},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.; Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Rn = {0 (Ion Channels); 0 (Potassium Channels); 58-61-7 (Adenosine); 58-63-9 (Inosine); EC 3.5.4.- (dsRNA adenosine deaminase); EC 3.5.4.4 (Adenosine Deaminase)},
	Sb = {IM},
	So = {Science. 2003 Aug 8;301(5634):832-6.},
	Stat = {MEDLINE},
	Title = {Nervous system targets of RNA editing identified by comparative genomics.},
	Volume = {301},
	Year = {2003},
	Bdsk-Url-1 = {http://dx.doi.org/10.1126/science.1086763}}

@article{12Genomes,
	Abstract = {Comparative analysis of multiple genomes in a phylogenetic framework dramatically improves the precision and sensitivity of evolutionary inference, producing more robust results than single-genome analyses can provide. The genomes of 12 Drosophila species, ten of which are presented here for the first time (sechellia, simulans, yakuba, erecta, ananassae, persimilis, willistoni, mojavensis, virilis and grimshawi), illustrate how rates and patterns of sequence divergence across taxa can illuminate evolutionary processes on a genomic scale. These genome sequences augment the formidable genetic tools that have made Drosophila melanogaster a pre-eminent model for animal genetics, and will further catalyse fundamental research on mechanisms of development, cell biology, genetics, disease, neurobiology, behaviour, physiology and evolution. Despite remarkable similarities among these Drosophila species, we identified many putatively non-neutral changes in protein-coding genes, non-coding RNA genes, and cis-regulatory regions. These may prove to underlie differences in the ecology and behaviour of these diverse species.},
	Address = {Department of Molecular Biology and Genetics, Cornell University, Ithaca, New York 14853, USA. ac347@cornell.edu},
	Au = {Clark, AG and Eisen, MB and Smith, DR and Bergman, CM and Oliver, B and Markow, TA and Kaufman, TC and Kellis, M and Gelbart, W and Iyer, VN and Pollard, DA and Sackton, TB and Larracuente, AM and Singh, ND and Abad, JP and Abt, DN and Adryan, B and Aguade, M and Akashi, H and Anderson, WW and Aquadro, CF and Ardell, DH and Arguello, R and Artieri, CG and Barbash, DA and Barker, D and Barsanti, P and Batterham, P and Batzoglou, S and Begun, D and Bhutkar, A and Blanco, E and Bosak, SA and Bradley, RK and Brand, AD and Brent, MR and Brooks, AN and Brown, RH and Butlin, RK and Caggese, C and Calvi, BR and Bernardo de Carvalho, A and Caspi, A and Castrezana, S and Celniker, SE and Chang, JL and Chapple, C and Chatterji, S and Chinwalla, A and Civetta, A and Clifton, SW and Comeron, JM and Costello, JC and Coyne, JA and Daub, J and David, RG and Delcher, AL and Delehaunty, K and Do, CB and Ebling, H and Edwards, K and Eickbush, T and Evans, JD and Filipski, A and Findeiss, S and Freyhult, E and Fulton, L and Fulton, R and Garcia, AC and Gardiner, A and Garfield, DA and Garvin, BE and Gibson, G and Gilbert, D and Gnerre, S and Godfrey, J and Good, R and Gotea, V and Gravely, B and Greenberg, AJ and Griffiths-Jones, S and Gross, S and Guigo, R and Gustafson, EA and Haerty, W and Hahn, MW and Halligan, DL and Halpern, AL and Halter, GM and Han, MV and Heger, A and Hillier, L and Hinrichs, AS and Holmes, I and Hoskins, RA and Hubisz, MJ and Hultmark, D and Huntley, MA and Jaffe, DB and Jagadeeshan, S and Jeck, WR and Johnson, J and Jones, CD and Jordan, WC and Karpen, GH and Kataoka, E and Keightley, PD and Kheradpour, P and Kirkness, EF and Koerich, LB and Kristiansen, K and Kudrna, D and Kulathinal, RJ and Kumar, S and Kwok, R and Lander, E and Langley, CH and Lapoint, R and Lazzaro, BP and Lee, SJ and Levesque, L and Li, R and Lin, CF and Lin, MF and Lindblad-Toh, K and Llopart, A and Long, M and Low, L and Lozovsky, E and Lu, J and Luo, M and Machado, CA and Makalowski, W and Marzo, M and Matsuda, M and Matzkin, L and McAllister, B and McBride, CS and McKernan, B and McKernan, K and Mendez-Lago, M and Minx, P and Mollenhauer, MU and Montooth, K and Mount, SM and Mu, X and Myers, E and Negre, B and Newfeld, S and Nielsen, R and Noor, MA and O'Grady, P and Pachter, L and Papaceit, M and Parisi, MJ and Parisi, M and Parts, L and Pedersen, JS and Pesole, G and Phillippy, AM and Ponting, CP and Pop, M and Porcelli, D and Powell, JR and Prohaska, S and Pruitt, K and Puig, M and Quesneville, H and Ram, KR and Rand, D and Rasmussen, MD and Reed, LK and Reenan, R and Reily, A and Remington, KA and Rieger, TT and Ritchie, MG and Robin, C and Rogers, YH and Rohde, C and Rozas, J and Rubenfield, MJ and Ruiz, A and Russo, S and Salzberg, SL and Sanchez-Gracia, A and Saranga, DJ and Sato, H and Schaeffer, SW and Schatz, MC and Schlenke, T and Schwartz, R and Segarra, C and Singh, RS and Sirot, L and Sirota, M and Sisneros, NB and Smith, CD and Smith, TF and Spieth, J and Stage, DE and Stark, A and Stephan, W and Strausberg, RL and Strempel, S and Sturgill, D and Sutton, G and Sutton, GG and Tao, W and Teichmann, S and Tobari, YN and Tomimura, Y and Tsolas, JM and Valente, VL and Venter, E and Venter, JC and Vicario, S and Vieira, FG and Vilella, AJ and Villasante, A and Walenz, B and Wang, J and Wasserman, M and Watts, T and Wilson, D and Wilson, RK and Wing, RA and Wolfner, MF and Wong, A and Wong, GK and Wu, CI and Wu, G and Yamamoto, D and Yang, HP and Yang, SP and Yorke, JA and Yoshida, K and Zdobnov, E and Zhang, P and Zhang, Y and Zimin, AV and Baldwin, J and Abdouelleil, A and Abdulkadir, J and Abebe, A and Abera, B and Abreu, J and Acer, SC and Aftuck, L and Alexander, A and An, P and Anderson, E and Anderson, S and Arachi, H and Azer, M and Bachantsang, P and Barry, A and Bayul, T and Berlin, A and Bessette, D and Bloom, T and Blye, J and Boguslavskiy, L and Bonnet, C and Boukhgalter, B and Bourzgui, I and Brown, A and Cahill, P and Channer, S and Cheshatsang, Y and Chuda, L and Citroen, M and Collymore, A and Cooke, P and Costello, M and D'Aco, K and Daza, R and De Haan, G and DeGray, S and DeMaso, C and Dhargay, N and Dooley, K and Dooley, E and Doricent, M and Dorje, P and Dorjee, K and Dupes, A and Elong, R and Falk, J and Farina, A and Faro, S and Ferguson, D and Fisher, S and Foley, CD and Franke, A and Friedrich, D and Gadbois, L and Gearin, G and Gearin, CR and Giannoukos, G and Goode, T and Graham, J and Grandbois, E and Grewal, S and Gyaltsen, K and Hafez, N and Hagos, B and Hall, J and Henson, C and Hollinger, A and Honan, T and Huard, MD and Hughes, L and Hurhula, B and Husby, ME and Kamat, A and Kanga, B and Kashin, S and Khazanovich, D and Kisner, P and Lance, K and Lara, M and Lee, W and Lennon, N and Letendre, F and LeVine, R and Lipovsky, A and Liu, X and Liu, J and Liu, S and Lokyitsang, T and Lokyitsang, Y and Lubonja, R and Lui, A and MacDonald, P and Magnisalis, V and Maru, K and Matthews, C and McCusker, W and McDonough, S and Mehta, T and Meldrim, J and Meneus, L and Mihai, O and Mihalev, A and Mihova, T and Mittelman, R and Mlenga, V and Montmayeur, A and Mulrain, L and Navidi, A and Naylor, J and Negash, T and Nguyen, T and Nguyen, N and Nicol, R and Norbu, C and Norbu, N and Novod, N and O'Neill, B and Osman, S and Markiewicz, E and Oyono, OL and Patti, C and Phunkhang, P and Pierre, F and Priest, M and Raghuraman, S and Rege, F and Reyes, R and Rise, C and Rogov, P and Ross, K and Ryan, E and Settipalli, S and Shea, T and Sherpa, N and Shi, L and Shih, D and Sparrow, T and Spaulding, J and Stalker, J and Stange-Thomann, N and Stavropoulos, S and Stone, C and Strader, C and Tesfaye, S and Thomson, T and Thoulutsang, Y and Thoulutsang, D and Topham, K and Topping, I and Tsamla, T and Vassiliev, H and Vo, A and Wangchuk, T and Wangdi, T and Weiand, M and Wilkinson, J and Wilson, A and Yadav, S and Young, G and Yu, Q and Zembek, L and Zhong, D and Zimmer, A and Zwirko, Z and Jaffe, DB and Alvarez, P and Brockman, W and Butler, J and Chin, C and Gnerre, S and Grabherr, M and Kleber, M and Mauceli, E and MacCallum, I},
	Author = {Clark, Andrew G and Eisen, Michael B and Smith, Douglas R and others},
	Cin = {Nature. 2007 Nov 8;450(7167):184-5. PMID: 17994082},
	Cn = {Drosophila 12 Genomes Consortium},
	Da = {20071112},
	Date-Added = {2008-09-22 15:29:41 -0400},
	Date-Modified = {2009-07-07 08:39:30 -0400},
	Dcom = {20080103},
	Doi = {10.1038/nature06341},
	Edat = {2007/11/13 09:00},
	Gr = {R01 LM006845-08/LM/United States NLM},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Language = {eng},
	Lr = {20080428},
	Mh = {Animals; Codon/genetics; DNA Transposable Elements/genetics; Drosophila/*classification/*genetics/immunology/metabolism; Drosophila Proteins/genetics; *Evolution, Molecular; Gene Order/genetics; Genes, Insect/*genetics; Genome, Insect/*genetics; Genome, Mitochondrial/genetics; *Genomics; Immunity/genetics; Multigene Family/genetics; *Phylogeny; RNA, Untranslated/genetics; Reproduction/genetics; Sequence Alignment; Sequence Analysis, DNA; Synteny/genetics},
	Mhda = {2008/01/04 09:00},
	Number = {7167},
	Own = {NLM},
	Pages = {203--218},
	Phst = {2007/07/19 {$[$}received{$]$}; 2007/10/05 {$[$}accepted{$]$}},
	Pii = {nature06341},
	Pl = {England},
	Pmid = {17994087},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't},
	Pubm = {Print},
	Rn = {0 (Codon); 0 (DNA Transposable Elements); 0 (Drosophila Proteins); 0 (RNA, Untranslated)},
	Sb = {IM},
	So = {Nature. 2007 Nov 8;450(7167):203-18.},
	Stat = {MEDLINE},
	Title = {Evolution of genes and genomes on the Drosophila phylogeny.},
	Volume = {450},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature06341}}

@article{Ahituvetal2007,
	Abstract = {Ultraconserved elements have been suggested to retain extended perfect sequence identity between the human, mouse, and rat genomes due to essential functional properties. To investigate the necessities of these elements in vivo, we removed four noncoding ultraconserved elements (ranging in length from 222 to 731 base pairs) from the mouse genome. To maximize the likelihood of observing a phenotype, we chose to delete elements that function as enhancers in a mouse transgenic assay and that are near genes that exhibit marked phenotypes both when completely inactivated in the mouse and when their expression is altered due to other genomic modifications. Remarkably, all four resulting lines of mice lacking these ultraconserved elements were viable and fertile, and failed to reveal any critical abnormalities when assayed for a variety of phenotypes including growth, longevity, pathology, and metabolism. In addition, more targeted screens, informed by the abnormalities observed in mice in which genes in proximity to the investigated elements had been altered, also failed to reveal notable abnormalities. These results, while not inclusive of all the possible phenotypic impact of the deleted sequences, indicate that extreme sequence constraint does not necessarily reflect crucial functions required for viability.},
	Address = {Genomics Division, Lawrence Berkeley National Laboratory, Berkeley, California, United States of America.},
	Au = {Ahituv, N and Zhu, Y and Visel, A and Holt, A and Afzal, V and Pennacchio, LA and Rubin, EM},
	Author = {Ahituv, Nadav and Zhu, Yiwen and Visel, Axel and Holt, Amy and Afzal, Veena and Pennacchio, Len A and Rubin, Edward M},
	Da = {20070920},
	Date-Added = {2008-09-22 15:27:39 -0400},
	Date-Modified = {2009-07-07 08:39:04 -0400},
	Dcom = {20071231},
	Doi = {10.1371/journal.pbio.0050234},
	Edat = {2007/09/07 09:00},
	Gr = {HG003988/HG/United States NHGRI; HL066681/HL/United States NHLBI; R01 HG003988-02/HG/United States NHGRI},
	Issn = {1545-7885 (Electronic)},
	Jid = {101183755},
	Journal = {PLoS Biol},
	Jt = {PLoS biology},
	Language = {eng},
	Lr = {20080904},
	Mh = {Animals; Conserved Sequence/*physiology; Fertility; Genome; Mice; *Phenotype; Sequence Deletion/*physiology; Survival},
	Mhda = {2008/01/01 09:00},
	Number = {9},
	Own = {NLM},
	Pages = {e234},
	Phst = {2007/05/15 {$[$}received{$]$}; 2007/07/03 {$[$}accepted{$]$}},
	Pii = {07-PLBI-RA-1373},
	Pl = {United States},
	Pmc = {PMC1964772},
	Pmid = {17803355},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print},
	Sb = {IM},
	So = {PLoS Biol. 2007 Sep;5(9):e234.},
	Stat = {MEDLINE},
	Title = {Deletion of ultraconserved elements yields viable mice.},
	Volume = {5},
	Year = {2007},
	Bdsk-Url-1 = {http://dx.doi.org/10.1371/journal.pbio.0050234}}

@article{hodgesetal2007,
	Abstract = {Increasingly powerful sequencing technologies are ushering in an era of personal genome sequences and raising the possibility of using such information to guide medical decisions. Genome resequencing also promises to accelerate the identification of disease-associated mutations. Roughly 98% of the human genome is composed of repeats and intergenic or non-protein-coding sequences. Thus, it is crucial to focus resequencing on high-value genomic regions. Protein-coding exons represent one such type of high-value target. We have developed a method of using flexible, high-density microarrays to capture any desired fraction of the human genome, in this case corresponding to more than 200,000 protein-coding exons. Depending on the precise protocol, up to 55-85% of the captured fragments are associated with targeted regions and up to 98% of intended exons can be recovered. This methodology provides an adaptable route toward rapid and efficient resequencing of any sizeable, non-repeat portion of the human genome.},
	Address = {Howard Hughes Medical Institute, Watson School of Biological Sciences, Cold Spring Harbor Laboratory, 1 Bungtown Road, Cold Spring Harbor, New York 11724, USA.},
	Au = {Hodges, E and Xuan, Z and Balija, V and Kramer, M and Molla, MN and Smith, SW and Middle, CM and Rodesch, MJ and Albert, TJ and Hannon, GJ and McCombie, WR},
	Author = {Hodges, Emily and Xuan, Zhenyu and Balija, Vivekanand and Kramer, Melissa and Molla, Michael N and Smith, Steven W and Middle, Christina M and Rodesch, Matthew J and Albert, Thomas J and Hannon, Gregory J and McCombie, W Richard},
	Da = {20071129},
	Date-Added = {2008-08-08 09:38:26 -0400},
	Date-Modified = {2008-08-08 09:38:26 -0400},
	Dcom = {20071211},
	Dep = {20071104},
	Doi = {10.1038/ng.2007.42},
	Edat = {2007/11/06 09:00},
	Issn = {1546-1718 (Electronic)},
	Jid = {9216904},
	Journal = {Nat Genet},
	Jt = {Nature genetics},
	Language = {eng},
	Mh = {*Exons; *Genome, Human; Humans; Oligonucleotide Array Sequence Analysis/methods; Oligonucleotides/genetics; Sequence Analysis, DNA/*methods},
	Mhda = {2007/12/12 09:00},
	Number = {12},
	Own = {NLM},
	Pages = {1522--1527},
	Phst = {2007/08/01 {$[$}received{$]$}; 2007/10/15 {$[$}accepted{$]$}; 2007/11/04 {$[$}aheadofprint{$]$}},
	Pii = {ng.2007.42},
	Pl = {United States},
	Pmid = {17982454},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print-Electronic},
	Rn = {0 (Oligonucleotides)},
	Sb = {IM},
	So = {Nat Genet. 2007 Dec;39(12):1522-7. Epub 2007 Nov 4.},
	Stat = {MEDLINE},
	Title = {Genome-wide in situ exon capture for selective resequencing.},
	Volume = {39},
	Year = {2007 Dec},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/ng.2007.42}}

@article{Montgomery2006,
	Abstract = {MOTIVATION: Our understanding of gene regulation is currently limited by our ability to collectively synthesize and catalogue transcriptional regulatory elements stored in scientific literature. Over the past decade, this task has become increasingly challenging as the accrual of biologically validated regulatory sequences has accelerated. To meet this challenge, novel community-based approaches to regulatory element annotation are required. SUMMARY: Here, we present the Open Regulatory Annotation (ORegAnno) database as a dynamic collection of literature-curated regulatory regions, transcription factor binding sites and regulatory mutations (polymorphisms and haplotypes). ORegAnno has been designed to manage the submission, indexing and validation of new annotations from users worldwide. Submissions to ORegAnno are immediately cross-referenced to EnsEMBL, dbSNP, Entrez Gene, the NCBI Taxonomy database and PubMed, where appropriate. AVAILABILITY: ORegAnno is available directly through MySQL, Web services, and online at http://www.oreganno.org. All software is licensed under the Lesser GNU Public License (LGPL).},
	Address = {Canada's Michael Smith Genome Sciences Centre, British Columbia Cancer Agency, Vancouver, BC, Canada V5Z 4E6.},
	Au = {Montgomery, SB and Griffith, OL and Sleumer, MC and Bergman, CM and Bilenky, M and Pleasance, ED and Prychyna, Y and Zhang, X and Jones, SJ},
	Author = {Montgomery, S B and Griffith, O L and Sleumer, M C and Bergman, C M and Bilenky, M and Pleasance, E D and Prychyna, Y and Zhang, X and Jones, S J M},
	Da = {20060223},
	Date-Added = {2008-02-07 11:48:04 -0800},
	Date-Modified = {2008-02-07 11:48:26 -0800},
	Dcom = {20060418},
	Dep = {20060105},
	Doi = {10.1093/bioinformatics/btk027},
	Edat = {2006/01/07 09:00},
	Issn = {1367-4803 (Print)},
	Jid = {9808944},
	Journal = {Bioinformatics},
	Jt = {Bioinformatics (Oxford, England)},
	Keywords = {Binding Sites; *Database Management Systems; *Databases, Genetic; Documentation/*methods; Gene Expression Regulation/genetics; Internet; *Natural Language Processing; *Periodicals as Topic; Promoter Regions (Genetics)/*genetics; Protein Binding; Transcription Factors/*genetics; Variation (Genetics)/genetics},
	Language = {eng},
	Lr = {20071115},
	Mhda = {2006/04/19 09:00},
	Number = {5},
	Own = {NLM},
	Pages = {637--640},
	Phst = {2006/01/05 {$[$}aheadofprint{$]$}; 2006/01/24 {$[$}aheadofprint{$]$}},
	Pii = {btk027},
	Pl = {England},
	Pmid = {16397004},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't},
	Pubm = {Print-Electronic},
	Rn = {0 (Transcription Factors)},
	Sb = {IM},
	So = {Bioinformatics. 2006 Mar 1;22(5):637-40. Epub 2006 Jan 5.},
	Stat = {MEDLINE},
	Title = {ORegAnno: an open access database and curation system for literature-derived promoters, transcription factor binding sites and regulatory variation.},
	Volume = {22},
	Year = {2006},
	Bdsk-Url-1 = {http://dx.doi.org/10.1093/bioinformatics/btk027}}

@article{Ashburneretal2000,
	Address = {Department of Genetics, Stanford University School of Medicine, California, USA. cherry@stanford.edu},
	Au = {Ashburner, M and Ball, CA and Blake, JA and Botstein, D and Butler, H and Cherry, JM and Davis, AP and Dolinski, K and Dwight, SS and Eppig, JT and Harris, MA and Hill, DP and Issel-Tarver, L and Kasarskis, A and Lewis, S and Matese, JC and Richardson, JE and Ringwald, M and Rubin, GM and Sherlock, G},
	Author = {Ashburner, M and Ball, C A and Blake, J A and Botstein, D and Butler, H and Cherry, J M and Davis, A P and Dolinski, K and Dwight, S S and Eppig, J T and Harris, M A and Hill, D P and Issel-Tarver, L and Kasarskis, A and Lewis, S and Matese, J C and Richardson, J E and Ringwald, M and Rubin, G M and Sherlock, G},
	Da = {20000612},
	Date-Added = {2007-12-18 12:20:35 -0800},
	Date-Modified = {2007-12-18 12:20:35 -0800},
	Dcom = {20000612},
	Doi = {10.1038/75556},
	Edat = {2000/05/10 09:00},
	Gr = {HD33745/HD/United States NICHD; P41 HG00330/HG/United States NHGRI; P41 HG01315/HG/United States NHGRI; etc.},
	Issn = {1061-4036 (Print)},
	Jid = {9216904},
	Journal = {Nat Genet},
	Jt = {Nature genetics},
	Keywords = {Animals; Computer Communication Networks; Databases, Factual; Eukaryotic Cells/*physiology; *Genes; Humans; Metaphysics; Mice; Molecular Biology/*trends; *Sequence Analysis, DNA; *Terminology as Topic},
	Language = {eng},
	Lr = {20071115},
	Mhda = {2000/06/17 09:00},
	Number = {1},
	Own = {NLM},
	Pages = {25--29},
	Pl = {UNITED STATES},
	Pmid = {10802651},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Sb = {IM},
	So = {Nat Genet. 2000 May;25(1):25-9.},
	Stat = {MEDLINE},
	Title = {Gene ontology: tool for the unification of biology. The Gene Ontology Consortium.},
	Volume = {25},
	Year = {2000},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/75556}}

@article{Adamsetal2000,
	Abstract = {The fly Drosophila melanogaster is one of the most intensively studied organisms in biology and serves as a model system for the investigation of many developmental and cellular processes common to higher eukaryotes, including humans. We have determined the nucleotide sequence of nearly all of the approximately 120-megabase euchromatic portion of the Drosophila genome using a whole-genome shotgun sequencing strategy supported by extensive clone-based sequence and a high-quality bacterial artificial chromosome physical map. Efforts are under way to close the remaining gaps; however, the sequence is of sufficient accuracy and contiguity to be declared substantially complete and to support an initial analysis of genome structure and preliminary gene annotation and interpretation. The genome encodes approximately 13,600 genes, somewhat fewer than the smaller Caenorhabditis elegans genome, but with comparable functional diversity.},
	Address = {Celera Genomics, 45 West Gude Drive, Rockville, MD 20850, USA.},
	Au = {Adams, MD and Celniker, SE and Holt, RA and Evans, CA and Gocayne, JD and Amanatides, PG and Scherer, SE and Li, PW and Hoskins, RA and Galle, RF and George, RA and Lewis, SE and Richards, S and Ashburner, M and Henderson, SN and Sutton, GG and Wortman, JR and Yandell, MD and Zhang, Q and Chen, LX and Brandon, RC and Rogers, YH and Blazej, RG and Champe, M and Pfeiffer, BD and Wan, KH and Doyle, C and Baxter, EG and Helt, G and Nelson, CR and Gabor, GL and Abril, JF and Agbayani, A and An, HJ and Andrews-Pfannkoch, C and Baldwin, D and Ballew, RM and Basu, A and Baxendale, J and Bayraktaroglu, L and Beasley, EM and Beeson, KY and Benos, PV and Berman, BP and Bhandari, D and Bolshakov, S and Borkova, D and Botchan, MR and Bouck, J and Brokstein, P and Brottier, P and Burtis, KC and Busam, DA and Butler, H and Cadieu, E and Center, A and Chandra, I and Cherry, JM and Cawley, S and Dahlke, C and Davenport, LB and Davies, P and de Pablos, B and Delcher, A and Deng, Z and Mays, AD and Dew, I and Dietz, SM and Dodson, K and Doup, LE and Downes, M and Dugan-Rocha, S and Dunkov, BC and Dunn, P and Durbin, KJ and Evangelista, CC and Ferraz, C and Ferriera, S and Fleischmann, W and Fosler, C and Gabrielian, AE and Garg, NS and Gelbart, WM and Glasser, K and Glodek, A and Gong, F and Gorrell, JH and Gu, Z and Guan, P and Harris, M and Harris, NL and Harvey, D and Heiman, TJ and Hernandez, JR and Houck, J and Hostin, D and Houston, KA and Howland, TJ and Wei, MH and Ibegwam, C and Jalali, M and Kalush, F and Karpen, GH and Ke, Z and Kennison, JA and Ketchum, KA and Kimmel, BE and Kodira, CD and Kraft, C and Kravitz, S and Kulp, D and Lai, Z and Lasko, P and Lei, Y and Levitsky, AA and Li, J and Li, Z and Liang, Y and Lin, X and Liu, X and Mattei, B and McIntosh, TC and McLeod, MP and McPherson, D and Merkulov, G and Milshina, NV and Mobarry, C and Morris, J and Moshrefi, A and Mount, SM and Moy, M and Murphy, B and Murphy, L and Muzny, DM and Nelson, DL and Nelson, DR and Nelson, KA and Nixon, K and Nusskern, DR and Pacleb, JM and Palazzolo, M and Pittman, GS and Pan, S and Pollard, J and Puri, V and Reese, MG and Reinert, K and Remington, K and Saunders, RD and Scheeler, F and Shen, H and Shue, BC and Siden-Kiamos, I and Simpson, M and Skupski, MP and Smith, T and Spier, E and Spradling, AC and Stapleton, M and Strong, R and Sun, E and Svirskas, R and Tector, C and Turner, R and Venter, E and Wang, AH and Wang, X and Wang, ZY and Wassarman, DA and Weinstock, GM and Weissenbach, J and Williams, SM and WoodageT and Worley, KC and Wu, D and Yang, S and Yao, QA and Ye, J and Yeh, RF and Zaveri, JS and Zhan, M and Zhang, G and Zhao, Q and Zheng, L and Zheng, XH and Zhong, FN and Zhong, W and Zhou, X and Zhu, S and Zhu, X and Smith, HO and Gibbs, RA and Myers, EW and Rubin, GM and Venter, JC},
	Author = {Adams, M D and Celniker, S E and Holt, R A and Evans, C A and Gocayne, J D and Amanatides, P G and Scherer, S E and Li, P W and Hoskins, R A and Galle, R F and George, R A and Lewis, S E and Richards, S and Ashburner, M and Henderson, S N and Sutton, G G and Wortman, J R and Yandell, M D and Zhang, Q and Chen, L X and Brandon, R C and Rogers, Y H and Blazej, R G and Champe, M and Pfeiffer, B D and Wan, K H and Doyle, C and Baxter, E G and Helt, G and Nelson, C R and Gabor, G L and Abril, J F and Agbayani, A and An, H J and Andrews-Pfannkoch, C and Baldwin, D and Ballew, R M and Basu, A and Baxendale, J and Bayraktaroglu, L and Beasley, E M and Beeson, K Y and Benos, P V and Berman, B P and Bhandari, D and Bolshakov, S and Borkova, D and Botchan, M R and Bouck, J and Brokstein, P and Brottier, P and Burtis, K C and Busam, D A and Butler, H and Cadieu, E and Center, A and Chandra, I and Cherry, J M and Cawley, S and Dahlke, C and Davenport, L B and Davies, P and de Pablos, B and Delcher, A and Deng, Z and Mays, A D and Dew, I and Dietz, S M and Dodson, K and Doup, L E and Downes, M and Dugan-Rocha, S and Dunkov, B C and Dunn, P and Durbin, K J and Evangelista, C C and Ferraz, C and Ferriera, S and Fleischmann, W and Fosler, C and Gabrielian, A E and Garg, N S and Gelbart, W M and Glasser, K and Glodek, A and Gong, F and Gorrell, J H and Gu, Z and Guan, P and Harris, M and Harris, N L and Harvey, D and Heiman, T J and Hernandez, J R and Houck, J and Hostin, D and Houston, K A and Howland, T J and Wei, M H and Ibegwam, C and Jalali, M and Kalush, F and Karpen, G H and Ke, Z and Kennison, J A and Ketchum, K A and Kimmel, B E and Kodira, C D and Kraft, C and Kravitz, S and Kulp, D and Lai, Z and Lasko, P and Lei, Y and Levitsky, A A and Li, J and Li, Z and Liang, Y and Lin, X and Liu, X and Mattei, B and McIntosh, T C and McLeod, M P and McPherson, D and Merkulov, G and Milshina, N V and Mobarry, C and Morris, J and Moshrefi, A and Mount, S M and Moy, M and Murphy, B and Murphy, L and Muzny, D M and Nelson, D L and Nelson, D R and Nelson, K A and Nixon, K and Nusskern, D R and Pacleb, J M and Palazzolo, M and Pittman, G S and Pan, S and Pollard, J and Puri, V and Reese, M G and Reinert, K and Remington, K and Saunders, R D and Scheeler, F and Shen, H and Shue, B C and Siden-Kiamos, I and Simpson, M and Skupski, M P and Smith, T and Spier, E and Spradling, A C and Stapleton, M and Strong, R and Sun, E and Svirskas, R and Tector, C and Turner, R and Venter, E and Wang, A H and Wang, X and Wang, Z Y and Wassarman, D A and Weinstock, G M and Weissenbach, J and Williams, S M and Worley, K C and Wu, D and Yang, S and Yao, Q A and Ye, J and Yeh, R F and Zaveri, J S and Zhan, M and Zhang, G and Zhao, Q and Zheng, L and Zheng, X H and Zhong, F N and Zhong, W and Zhou, X and Zhu, S and Zhu, X and Smith, H O and Gibbs, R A and Myers, E W and Rubin, G M and Venter, J C},
	Da = {20000330},
	Date-Added = {2007-12-07 14:56:06 -0800},
	Date-Modified = {2007-12-07 14:56:15 -0800},
	Dcom = {20000330},
	Edat = {2000/03/25},
	Gr = {P50-HG00750/HG/United States NHGRI},
	Issn = {0036-8075 (Print)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Keywords = {Animals; Biological Transport/genetics; Chromatin/genetics; Cloning, Molecular; Computational Biology; Contig Mapping; Cytochrome P-450 Enzyme System/genetics; DNA Repair/genetics; DNA Replication/genetics; Drosophila melanogaster/*genetics/metabolism; Euchromatin; Gene Library; Genes, Insect; *Genome; Heterochromatin/genetics; Insect Proteins/chemistry/genetics/physiology; Nuclear Proteins/genetics; Protein Biosynthesis; *Sequence Analysis, DNA; Transcription, Genetic},
	Language = {eng},
	Lr = {20071114},
	Mhda = {2000/04/01},
	Number = {5461},
	Own = {NLM},
	Pages = {2185--2195},
	Pii = {8392},
	Pl = {UNITED STATES},
	Pmid = {10731132},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Rn = {0 (Chromatin); 0 (Euchromatin); 0 (Heterochromatin); 0 (Insect Proteins); 0 (Nuclear Proteins); 9035-51-2 (Cytochrome P-450 Enzyme System)},
	Sb = {IM},
	So = {Science. 2000 Mar 24;287(5461):2185-95.},
	Stat = {MEDLINE},
	Title = {The genome sequence of Drosophila melanogaster.},
	Volume = {287},
	Year = {2000}}

@article{Andolfatto2005,
	Abstract = {A large fraction of eukaryotic genomes consists of DNA that is not translated into protein sequence, and little is known about its functional significance. Here I show that several classes of non-coding DNA in Drosophila are evolving considerably slower than synonymous sites, and yet show an excess of between-species divergence relative to polymorphism when compared with synonymous sites. The former is a hallmark of selective constraint, but the latter is a signature of adaptive evolution, resembling general patterns of protein evolution in Drosophila. I estimate that about 40-70% of nucleotides in intergenic regions, untranslated portions of mature mRNAs (UTRs) and most intronic DNA are evolutionarily constrained relative to synonymous sites. However, I also use an extension to the McDonald-Kreitman test to show that a substantial fraction of the nucleotide divergence in these regions was driven to fixation by positive selection (about 20% for most intronic and intergenic DNA, and 60% for UTRs). On the basis of these observations, I suggest that a large fraction of the non-translated genome is functionally important and subject to both purifying selection and adaptive evolution. These results imply that, although positive selection is clearly an important facet of protein evolution, adaptive changes to non-coding DNA might have been considerably more common in the evolution of D. melanogaster.},
	Address = {Section of Ecology, Behavior and Evolution, Division of Biological Sciences, University of California San Diego, La Jolla, California 92093, USA. pandolfatto@ucsd.edu},
	Au = {Andolfatto, P},
	Author = {Andolfatto, Peter},
	Cin = {Nature. 2005 Oct 20;437(7062):1106. PMID: 16237433},
	Da = {20051020},
	Date-Added = {2007-12-07 14:54:07 -0800},
	Date-Modified = {2007-12-07 14:54:47 -0800},
	Dcom = {20051028},
	Doi = {10.1038/nature04107},
	Edat = {2005/10/21 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Keywords = {Adaptation, Physiological/*genetics; Animals; DNA, Intergenic/*genetics; Drosophila/genetics; Drosophila melanogaster/*genetics; *Evolution, Molecular; Genomics; Introns/*genetics; Models, Genetic; Mutagenesis/genetics; Nucleotides/genetics; Polymorphism, Genetic/genetics; *Selection (Genetics); Untranslated Regions/*genetics; Zimbabwe},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2005/10/29 09:00},
	Number = {7062},
	Own = {NLM},
	Pages = {1149--1152},
	Phst = {2005/05/23 {$[$}received{$]$}; 2005/08/02 {$[$}accepted{$]$}},
	Pii = {nature04107},
	Pl = {England},
	Pmid = {16237443},
	Pst = {ppublish},
	Pt = {Comparative Study; Journal Article; Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print},
	Rn = {0 (DNA, Intergenic); 0 (Nucleotides); 0 (Untranslated Regions)},
	Sb = {IM},
	So = {Nature. 2005 Oct 20;437(7062):1149-52.},
	Stat = {MEDLINE},
	Title = {Adaptive evolution of non-coding DNA in Drosophila.},
	Volume = {437},
	Year = {2005},
	Bdsk-Url-1 = {http://dx.doi.org/10.1038/nature04107}}

@article{Schwarz1978,
	Author = {G. Schwarz},
	Date-Added = {2007-12-06 12:13:24 -0800},
	Date-Modified = {2007-12-06 12:14:20 -0800},
	Journal = {Annals of Statistics},
	Number = {2},
	Pages = {461-464},
	Title = {Estimation the dimension of a model},
	Volume = {6},
	Year = {1978}}

@article{Betancourtetal2004,
	Abstract = {We study levels of X-linked vs. autosomal diversity using a model developed to analyze the hitchhiking effect. Repeated bouts of hitchhiking are thought to lower X-linked diversity for two reasons: first, because sojourn times of beneficial mutations are shorter on the X, and second, because adaptive substitutions may be more frequent on the X. We investigate whether each of these effects does, in fact, cause reduced X-linked diversity under hitchhiking. We study the strength of the hitchhiking effect on the X vs. autosomes when there is no recombination and under two different recombination schemes. When recombination occurs in both sexes, X-linked vs. autosomal diversity is reduced by hitchhiking under a broad range of conditions, but when there is no recombination in males, as in Drosophila, the required conditions are considerably more restrictive.},
	Address = {Department of Biology, University of Rochester, Rochester, New York 14627, USA. aabt@mail.rochester.edu <aabt@mail.rochester.edu>},
	Au = {Betancourt, AJ and Kim, Y and Orr, HA},
	Author = {Betancourt, Andrea J and Kim, Yuseob and Orr, H Allen},
	Da = {20041221},
	Date-Added = {2007-12-06 12:11:28 -0800},
	Date-Modified = {2007-12-06 12:11:28 -0800},
	Dcom = {20050621},
	Doi = {10.1534/genetics.104.030999},
	Edat = {2004/12/22 09:00},
	Gr = {GM-51932/GM/United States NIGMS},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {Animals; Drosophila/genetics; Female; Male; *Models, Genetic; Molecular Sequence Data; Recombination, Genetic; *Variation (Genetics); *X Chromosome},
	Language = {eng},
	Lr = {20071114},
	Mhda = {2005/06/23 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {2261--2269},
	Pii = {168/4/2261},
	Pl = {United States},
	Pmid = {15611190},
	Pst = {ppublish},
	Pt = {Journal Article; Research Support, N.I.H., Extramural; Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2004 Dec;168(4):2261-9.},
	Stat = {MEDLINE},
	Title = {A pseudohitchhiking model of X vs. autosomal diversity.},
	Volume = {168},
	Year = {2004},
	Bdsk-Url-1 = {http://dx.doi.org/10.1534/genetics.104.030999}}

@article{Dempsteretal1977,
	Author = {A. Dempster and N. Laird and D. Rubin},
	Date-Added = {2007-12-03 16:46:02 -0800},
	Date-Modified = {2007-12-03 16:47:09 -0800},
	Journal = {Journal of the Royal Statistical Society B},
	Pages = {1--38},
	Title = {Maximum likelihood from incomplete data via the EM algorithm (with discussion)},
	Volume = {39},
	Year = {1977}}

@book{durbin1998,
	Author = {R. Durbin and S. Eddy and A. Krogh and G. Mithison},
	Date-Added = {2007-12-03 11:47:44 -0800},
	Date-Modified = {2007-12-03 16:45:55 -0800},
	Publisher = {Cambridge University Press},
	Title = {Biological Sequence Analysis: Probabilistic models of proteins and nucleic acids},
	Year = {1998}}

@article{kim1971,
	Author = {M. Kimura},
	Date-Added = {2007-12-03 10:52:12 -0800},
	Date-Modified = {2007-12-03 10:53:14 -0800},
	Journal = {Theoretical Population Biology},
	Pages = {174--208},
	Title = {Theoretical foundation of population genetics at the molecular level},
	Volume = {2},
	Year = {1971}}

@article{Thomasetal2007,
	Abstract = {The variation resources within the University of California Santa Cruz Genome Browser include polymorphism data drawn from public collections and analyses of these data, along with their display in the context of other genomic annotations. Primary data from dbSNP is included for many organisms, with added information including genomic alleles and orthologous alleles for closely related organisms. Display filtering and coloring is available by variant type, functional class or other annotations. Annotation of potential errors is highlighted and a genomic alignment of the variant's flanking sequence is displayed. HapMap allele frequencies and linkage disequilibrium (LD) are available for each HapMap population, along with non-human primate alleles. The browsing and analysis tools, downloadable data files and links to documentation and other information can be found at http://genome.ucsc.edu/.},
	Address = {Department of Biomolecular Engineering, University of California at Santa Cruz, Santa Cruz, CA, USA. daryl@soe.ucsc.edu},
	Aid = {gkl953 {$[$}pii{$]$}, 10.1093/nar/gkl953 {$[$}doi{$]$}},
	Au = {Thomas DJ and Trumbower H and Kern AD and Rhead BL and Kuhn RM and Haussler D and Kent WJ},
	Author = {Thomas, Daryl J and Trumbower, Heather and Kern, Andrew D and Rhead, Brooke L and Kuhn, Robert M and Haussler, David and Kent, W James},
	Da = {20070104},
	Date-Added = {2007-09-03 07:07:01 -0700},
	Date-Modified = {2007-09-03 07:07:01 -0700},
	Dcom = {20070316},
	Dep = {20061206},
	Edat = {2006/12/08 09:00},
	Issn = {1362-4962 (Electronic)},
	Jid = {0411011},
	Journal = {Nucleic Acids Res},
	Jt = {Nucleic acids research},
	Keywords = {Alleles, Animals, *Databases, Nucleic Acid, Gene Frequency, Genomics, Genotype, Humans, Internet, Linkage Disequilibrium, Mice, *Polymorphism, Single Nucleotide, Rats, Recombination, Genetic, Sequence Alignment, User-Computer Interface},
	Language = {eng},
	Mhda = {2007/03/17 09:00},
	Number = {Database issue},
	Own = {NLM},
	Pages = {D716-20},
	Phst = {2006/12/06 {$[$}aheadofprint{$]$}},
	Pl = {England},
	Pmid = {17151077},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Nucleic Acids Res. 2007 Jan;35(Database issue):D716-20. Epub 2006 Dec 6.},
	Stat = {MEDLINE},
	Title = {Variation resources at UC Santa Cruz.},
	Volume = {35},
	Year = {2007}}

@article{Levineetal2006,
	Abstract = {Descriptions of recently evolved genes suggest several mechanisms of origin including exon shuffling, gene fission/fusion, retrotransposition, duplication-divergence, and lateral gene transfer, all of which involve recruitment of preexisting genes or genetic elements into new function. The importance of noncoding DNA in the origin of novel genes remains an open question. We used the well annotated genome of the genetic model system Drosophila melanogaster and genome sequences of related species to carry out a whole-genome search for new D. melanogaster genes that are derived from noncoding DNA. Here, we describe five such genes, four of which are X-linked. Our RT-PCR experiments show that all five putative novel genes are expressed predominantly in testes. These data support the idea that these novel genes are derived from ancestral noncoding sequence and that new, favored genes are likely to invade populations under selective pressures relating to male reproduction.},
	Address = {Center for Population Biology, University of California-Davis, Davis, CA 95616, USA. mialevine@ucdavis.edu},
	Aid = {0509809103 {$[$}pii{$]$}, 10.1073/pnas.0509809103 {$[$}doi{$]$}},
	Au = {Levine MT and Jones CD and Kern AD and Lindfors HA and Begun DJ},
	Author = {Levine, Mia T and Jones, Corbin D and Kern, Andrew D and Lindfors, Heather A and Begun, David J},
	Da = {20060628},
	Date-Added = {2007-09-03 07:06:50 -0700},
	Date-Modified = {2007-09-03 07:06:50 -0700},
	Dcom = {20060823},
	Dep = {20060615},
	Edat = {2006/06/17 09:00},
	Gr = {GM 071926/GM/NIGMS},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America},
	Keywords = {Animals, Base Sequence, DNA Shuffling, Drosophila melanogaster/*genetics, Gene Expression, Genes, Insect/*genetics, Introns/*genetics, Male, Molecular Sequence Data, RNA, Messenger/analysis/metabolism, Testis/*metabolism, X Chromosome/*genetics},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2006/08/24 09:00},
	Number = {26},
	Own = {NLM},
	Pages = {9935-9},
	Phst = {2006/06/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16777968},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print-Electronic},
	Rn = {0 (RNA, Messenger)},
	Sb = {IM},
	Si = {GENBANK/DQ657247, GENBANK/DQ657248, GENBANK/DQ657249, GENBANK/DQ657250, GENBANK/DQ657251, GENBANK/DQ657252, GENBANK/DQ657253, GENBANK/DQ657254, GENBANK/DQ657255, GENBANK/DQ657256, GENBANK/DQ657257, GENBANK/DQ657258, GENBANK/DQ657259, GENBANK/DQ657260, GENBANK/DQ657261, GENBANK/DQ657262, GENBANK/DQ657263, GENBANK/DQ657264, GENBANK/DQ657265, GENBANK/DQ657266, GENBANK/DQ657267, GENBANK/DQ657268, GENBANK/DQ657269, GENBANK/DQ657270, GENBANK/DQ657271, GENBANK/DQ657272, GENBANK/DQ657273, GENBANK/DQ657274, GENBANK/DQ657275, GENBANK/DQ657276, GENBANK/DQ657277, GENBANK/DQ657278, GENBANK/DQ657279, GENBANK/DQ657280, GENBANK/DQ657281, GENBANK/DQ657282, GENBANK/DQ657283, GENBANK/DQ657284, GENBANK/DQ657285, GENBANK/DQ657286, GENBANK/DQ657287, GENBANK/DQ657288, GENBANK/DQ657289, GENBANK/DQ657290, GENBANK/DQ657291, GENBANK/DQ657292, GENBANK/DQ657293, GENBANK/DQ657294, GENBANK/DQ657295, GENBANK/DQ657296, GENBANK/DQ657297, GENBANK/DQ657298, GENBANK/DQ657299, GENBANK/DQ657300, GENBANK/DQ657301, GENBANK/DQ657302, GENBANK/DQ657303, GENBANK/DQ657304, GENBANK/DQ657305, GENBANK/DQ657306, GENBANK/DQ657307, GENBANK/DQ657308, GENBANK/DQ657309, GENBANK/DQ657310, GENBANK/DQ657311, GENBANK/DQ657312, GENBANK/DQ657313, GENBANK/DQ657314, GENBANK/DQ657315, GENBANK/DQ657316, GENBANK/DQ657317, GENBANK/DQ657318, GENBANK/DQ657319, GENBANK/DQ657320, GENBANK/DQ657321, GENBANK/DQ657322, GENBANK/DQ657323, GENBANK/DQ657324, GENBANK/DQ657325, GENBANK/DQ657326, GENBANK/DQ657327, GENBANK/DQ657328, GENBANK/DQ657329, GENBANK/DQ657330, GENBANK/DQ657331, GENBANK/DQ657332, GENBANK/DQ657333, GENBANK/DQ657334, GENBANK/DQ657335, GENBANK/DQ657336, GENBANK/DQ657337, GENBANK/DQ657338, GENBANK/DQ657339, GENBANK/DQ657340, GENBANK/DQ657341, GENBANK/DQ657342, GENBANK/DQ657343, GENBANK/DQ657344, GENBANK/DQ657345, GENBANK/DQ657346, GENBANK/DQ657347},
	So = {Proc Natl Acad Sci U S A. 2006 Jun 27;103(26):9935-9. Epub 2006 Jun 15.},
	Stat = {MEDLINE},
	Title = {Novel genes derived from noncoding DNA in Drosophila melanogaster are frequently X-linked and exhibit testis-biased expression.},
	Volume = {103},
	Year = {2006}}

@article{macaque2007,
	Abstract = {The rhesus macaque (Macaca mulatta) is an abundant primate species that diverged from the ancestors of Homo sapiens about 25 million years ago. Because they are genetically and physiologically similar to humans, rhesus monkeys are the most widely used nonhuman primate in basic and applied biomedical research. We determined the genome sequence of an Indian-origin Macaca mulatta female and compared the data with chimpanzees and humans to reveal the structure of ancestral primate genomes and to identify evidence for positive selection and lineage-specific expansions and contractions of gene families. A comparison of sequences from individual animals was used to investigate their underlying genetic diversity. The complete description of the macaque genome blueprint enhances the utility of this animal model for biomedical research and improves our understanding of the basic biology of the species.},
	Address = {Human Genome Sequencing Center, Baylor College of Medicine, Houston, TX 77030, USA. agibbs@bcm.edu},
	Aid = {316/5822/222 {$[$}pii{$]$}, 10.1126/science.1139247 {$[$}doi{$]$}},
	Au = {Gibbs RA and Rogers J and Katze MG and Bumgarner R and Weinstock GM and Mardis ER and Remington KA and Strausberg RL and Venter JC and Wilson RK and Batzer MA and Bustamante CD and Eichler EE and Hahn MW and Hardison RC and Makova KD and Miller W and Milosavljevic A and Palermo RE and Siepel A and Sikela JM and Attaway T and Bell S and Bernard KE and Buhay CJ and Chandrabose MN and Dao M and Davis C and Delehaunty KD and Ding Y and Dinh HH and Dugan-Rocha S and Fulton LA and Gabisi RA and Garner TT and Godfrey J and Hawes AC and Hernandez J and Hines S and Holder M and Hume J and Jhangiani SN and Joshi V and Khan ZM and Kirkness EF and Cree A and Fowler RG and Lee S and Lewis LR and Li Z and Liu YS and Moore SM and Muzny D and Nazareth LV and Ngo DN and Okwuonu GO and Pai G and Parker D and Paul HA and Pfannkoch C and Pohl CS and Rogers YH and Ruiz SJ and Sabo A and Santibanez J and Schneider BW and Smith SM and Sodergren E and Svatek AF and Utterback TR and Vattathil S and Warren W and White CS and Chinwalla AT and Feng Y and Halpern AL and Hillier LW and Huang X and Minx P and Nelson JO and Pepin KH and Qin X and Sutton GG and Venter E and Walenz BP and Wallis JW and Worley KC and Yang SP and Jones SM and Marra MA and Rocchi M and Schein JE and Baertsch R and Clarke L and Csuros M and Glasscock J and Harris RA and Havlak P and Jackson AR and Jiang H and Liu Y and Messina DN and Shen Y and Song HX and Wylie T and Zhang L and Birney E and Han K and Konkel MK and Lee J and Smit AF and Ullmer B and Wang H and Xing J and Burhans R and Cheng Z and Karro JE and Ma J and Raney B and She X and Cox MJ and Demuth JP and Dumas LJ and Han SG and Hopkins J and Karimpour-Fard A and Kim YH and Pollack JR and Vinar T and Addo-Quaye C and Degenhardt J and Denby A and Hubisz MJ and Indap A and Kosiol C and Lahn BT and Lawson HA and Marklein A and Nielsen R and Vallender EJ and Clark AG and Ferguson B and Hernandez RD and Hirani K and Kehrer-Sawatzki H and Kolb J and Patil S and Pu LL and Ren Y and Smith DG and Wheeler DA and Schenck I and Ball EV and Chen R and Cooper DN and Giardine B and Hsu F and Kent WJ and Lesk A and Nelson DL and O'brien WE and Prufer K and Stenson PD and Wallace JC and Ke H and Liu XM and Wang P and Xiang AP and Yang F and Barber GP and Haussler D and Karolchik D and Kern AD and Kuhn RM and Smith KE and Zwieg AS},
	Author = {Gibbs, Richard A and Rogers, Jeffrey and Katze, Michael G and Bumgarner, Roger and Weinstock, George M and Mardis, Elaine R and Remington, Karin A and Strausberg, Robert L and Venter, J Craig and Wilson, Richard K and Batzer, Mark A and Bustamante, Carlos D and Eichler, Evan E and Hahn, Matthew W and Hardison, Ross C and Makova, Kateryna D and Miller, Webb and Milosavljevic, Aleksandar and Palermo, Robert E and Siepel, Adam and Sikela, James M and Attaway, Tony and Bell, Stephanie and Bernard, Kelly E and Buhay, Christian J and Chandrabose, Mimi N and Dao, Marvin and Davis, Clay and Delehaunty, Kimberly D and Ding, Yan and Dinh, Huyen H and Dugan-Rocha, Shannon and Fulton, Lucinda A and Gabisi, Ramatu Ayiesha and Garner, Toni T and Godfrey, Jennifer and Hawes, Alicia C and Hernandez, Judith and Hines, Sandra and Holder, Michael and Hume, Jennifer and Jhangiani, Shalini N and Joshi, Vandita and Khan, Ziad Mohid and Kirkness, Ewen F and Cree, Andrew and Fowler, R Gerald and Lee, Sandra and Lewis, Lora R and Li, Zhangwan and Liu, Yih-Shin and Moore, Stephanie M and Muzny, Donna and Nazareth, Lynne V and Ngo, Dinh Ngoc and Okwuonu, Geoffrey O and Pai, Grace and Parker, David and Paul, Heidie A and Pfannkoch, Cynthia and Pohl, Craig S and Rogers, Yu-Hui and Ruiz, San Juana and Sabo, Aniko and Santibanez, Jireh and Schneider, Brian W and Smith, Scott M and Sodergren, Erica and Svatek, Amanda F and Utterback, Teresa R and Vattathil, Selina and Warren, Wesley and White, Courtney Sherell and Chinwalla, Asif T and Feng, Yucheng and Halpern, Aaron L and Hillier, Ladeana W and Huang, Xiaoqiu and Minx, Pat and Nelson, Joanne O and Pepin, Kymberlie H and Qin, Xiang and Sutton, Granger G and Venter, Eli and Walenz, Brian P and Wallis, John W and Worley, Kim C and Yang, Shiaw-Pyng and Jones, Steven M and Marra, Marco A and Rocchi, Mariano and Schein, Jacqueline E and Baertsch, Robert and Clarke, Laura and Csuros, Miklos and Glasscock, Jarret and Harris, R Alan and Havlak, Paul and Jackson, Andrew R and Jiang, Huaiyang and Liu, Yue and Messina, David N and Shen, Yufeng and Song, Henry Xing-Zhi and Wylie, Todd and Zhang, Lan and Birney, Ewan and Han, Kyudong and Konkel, Miriam K and Lee, Jungnam and Smit, Arian F A and Ullmer, Brygg and Wang, Hui and Xing, Jinchuan and Burhans, Richard and Cheng, Ze and Karro, John E and Ma, Jian and Raney, Brian and She, Xinwei and Cox, Michael J and Demuth, Jeffery P and Dumas, Laura J and Han, Sang-Gook and Hopkins, Janet and Karimpour-Fard, Anis and Kim, Young H and Pollack, Jonathan R and Vinar, Tomas and Addo-Quaye, Charles and Degenhardt, Jeremiah and Denby, Alexandra and Hubisz, Melissa J and Indap, Amit and Kosiol, Carolin and Lahn, Bruce T and Lawson, Heather A and Marklein, Alison and Nielsen, Rasmus and Vallender, Eric J and Clark, Andrew G and Ferguson, Betsy and Hernandez, Ryan D and Hirani, Kashif and Kehrer-Sawatzki, Hildegard and Kolb, Jessica and Patil, Shobha and Pu, Ling-Ling and Ren, Yanru and Smith, David Glenn and Wheeler, David A and Schenck, Ian and Ball, Edward V and Chen, Rui and Cooper, David N and Giardine, Belinda and Hsu, Fan and Kent, W James and Lesk, Arthur and Nelson, David L and O'brien, William E and Prufer, Kay and Stenson, Peter D and Wallace, James C and Ke, Hui and Liu, Xiao-Ming and Wang, Peng and Xiang, Andy Peng and Yang, Fan and Barber, Galt P and Haussler, David and Karolchik, Donna and Kern, Andy D and Kuhn, Robert M and Smith, Kayla E and Zwieg, Ann S},
	Cin = {Science. 2007 Apr 13;316(5822):216-8. PMID: 17431165, Science. 2007 Apr 13;316(5822):218-21. PMID: 17431166},
	Cn = {Rhesus Macaque Genome Sequencing and Analysis Consortium},
	Da = {20070413},
	Date-Added = {2007-09-03 07:06:36 -0700},
	Date-Modified = {2007-09-03 07:06:36 -0700},
	Dcom = {20070426},
	Edat = {2007/04/14 09:00},
	Gr = {U54 HG003068/HG/NHGRI, U54 HG003079/HG/NHGRI, U54 HG003273/HG/NHGRI},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science (New York, N.Y.)},
	Keywords = {Animals, Biomedical Research, *Evolution, Molecular, Female, Gene Duplication, Gene Rearrangement, Genetic Diseases, Inborn, *Genome, Humans, Macaca mulatta/*genetics, Male, Multigene Family, Mutation, Pan troglodytes/genetics, Sequence Analysis, DNA, Species Specificity, Variation (Genetics)},
	Language = {eng},
	Mhda = {2007/04/27 09:00},
	Number = {5822},
	Own = {NLM},
	Pages = {222-34},
	Pl = {United States},
	Pmid = {17431167},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural},
	Pubm = {Print},
	Sb = {IM},
	So = {Science. 2007 Apr 13;316(5822):222-34.},
	Stat = {MEDLINE},
	Title = {Evolutionary and biomedical insights from the rhesus macaque genome.},
	Volume = {316},
	Year = {2007}}

@article{encode2007,
	Abstract = {We report the generation and analysis of functional data from multiple, diverse experiments performed on a targeted 1% of the human genome as part of the pilot phase of the ENCODE Project. These data have been further integrated and augmented by a number of evolutionary and computational analyses. Together, our results advance the collective knowledge about human genome function in several major areas. First, our studies provide convincing evidence that the genome is pervasively transcribed, such that the majority of its bases can be found in primary transcripts, including non-protein-coding transcripts, and those that extensively overlap one another. Second, systematic examination of transcriptional regulation has yielded new understanding about transcription start sites, including their relationship to specific regulatory sequences and features of chromatin accessibility and histone modification. Third, a more sophisticated view of chromatin structure has emerged, including its inter-relationship with DNA replication and transcriptional regulation. Finally, integration of these new sources of information, in particular with respect to mammalian evolution based on inter- and intra-species sequence comparisons, has yielded new mechanistic and evolutionary insights concerning the functional landscape of the human genome. Together, these studies are defining a path for pursuit of a more comprehensive characterization of human genome function.},
	Au = {Birney E and Stamatoyannopoulos JA and Dutta A and Guigo R and Gingeras TR and Margulies EH and Weng Z and Snyder M and Dermitzakis ET and Thurman RE and Kuehn MS and Taylor CM and Neph S and Koch CM and Asthana S and Malhotra A and Adzhubei I and Greenbaum JA and Andrews RM and Flicek P and Boyle PJ and Cao H and Carter NP and Clelland GK and Davis S and Day N and Dhami P and Dillon SC and Dorschner MO and Fiegler H and Giresi PG and Goldy J and Hawrylycz M and Haydock A and Humbert R and James KD and Johnson BE and Johnson EM and Frum TT and Rosenzweig ER and Karnani N and Lee K and Lefebvre GC and Navas PA and Neri F and Parker SC and Sabo PJ and Sandstrom R and Shafer A and Vetrie D and Weaver M and Wilcox S and Yu M and Collins FS and Dekker J and Lieb JD and Tullius TD and Crawford GE and Sunyaev S and Noble WS and Dunham I and Denoeud F and Reymond A and Kapranov P and Rozowsky J and Zheng D and Castelo R and Frankish A and Harrow J and Ghosh S and Sandelin A and Hofacker IL and Baertsch R and Keefe D and Dike S and Cheng J and Hirsch HA and Sekinger EA and Lagarde J and Abril JF and Shahab A and Flamm C and Fried C and Hackermuller J and Hertel J and Lindemeyer M and Missal K and Tanzer A and Washietl S and Korbel J and Emanuelsson O and Pedersen JS and Holroyd N and Taylor R and Swarbreck D and Matthews N and Dickson MC and Thomas DJ and Weirauch MT and Gilbert J and Drenkow J and Bell I and Zhao X and Srinivasan KG and Sung WK and Ooi HS and Chiu KP and Foissac S and Alioto T and Brent M and Pachter L and Tress ML and Valencia A and Choo SW and Choo CY and Ucla C and Manzano C and Wyss C and Cheung E and Clark TG and Brown JB and Ganesh M and Patel S and Tammana H and Chrast J and Henrichsen CN and Kai C and Kawai J and Nagalakshmi U and Wu J and Lian Z and Lian J and Newburger P and Zhang X and Bickel P and Mattick JS and Carninci P and Hayashizaki Y and Weissman S and Hubbard T and Myers RM and Rogers J and Stadler PF and Lowe TM and Wei CL and Ruan Y and Struhl K and Gerstein M and Antonarakis SE and Fu Y and Green ED and Karaoz U and Siepel A and Taylor J and Liefer LA and Wetterstrand KA and Good PJ and Feingold EA and Guyer MS and Cooper GM and Asimenos G and Dewey CN and Hou M and Nikolaev S and Montoya-Burgos JI and Loytynoja A and Whelan S and Pardi F and Massingham T and Huang H and Zhang NR and Holmes I and Mullikin JC and Ureta-Vidal A and Paten B and Seringhaus M and Church D and Rosenbloom K and Kent WJ and Stone EA and Batzoglou S and Goldman N and Hardison RC and Haussler D and Miller W and Sidow A and Trinklein ND and Zhang ZD and Barrera L and Stuart R and King DC and Ameur A and Enroth S and Bieda MC and Kim J and Bhinge AA and Jiang N and Liu J and Yao F and Vega VB and Lee CW and Ng P and Yang A and Moqtaderi Z and Zhu Z and Xu X and Squazzo S and Oberley MJ and Inman D and Singer MA and Richmond TA and Munn KJ and Rada-Iglesias A and Wallerman O and Komorowski J and Fowler JC and Couttet P and Bruce AW and Dovey OM and Ellis PD and Langford CF and Nix DA and Euskirchen G and Hartman S and Urban AE and Kraus P and Van Calcar S and Heintzman N and Kim TH and Wang K and Qu C and Hon G and Luna R and Glass CK and Rosenfeld MG and Aldred SF and Cooper SJ and Halees A and Lin JM and Shulha HP and Xu M and Haidar JN and Yu Y and Iyer VR and Green RD and Wadelius C and Farnham PJ and Ren B and Harte RA and Hinrichs AS and Trumbower H and Clawson H and Hillman-Jackson J and Zweig AS and Smith K and Thakkapallayil A and Barber G and Kuhn RM and Karolchik D and Armengol L and Bird CP and de Bakker PI and Kern AD and Lopez-Bigas N and Martin JD and Stranger BE and Woodroffe A and Davydov E and Dimas A and Eyras E and Hallgrimsdottir IB and Huppert J and Zody MC and Abecasis GR and Estivill X and Bouffard GG and Guan X and Hansen NF and Idol JR and Maduro VV and Maskeri B and McDowell JC and Park M and Thomas PJ and Young AC and Blakesley RW and Muzny DM and Sodergren E and Wheeler DA and Worley KC and Jiang H and Weinstock GM and Gibbs RA and Graves T and Fulton R and Mardis ER and Wilson RK and Clamp M and Cuff J and Gnerre S and Jaffe DB and Chang JL and Lindblad-Toh K and Lander ES and Koriabine M and Nefedov M and Osoegawa K and Yoshinaga Y and Zhu B and de Jong PJ},
	Author = {Birney, Ewan and Stamatoyannopoulos, John A and Dutta, Anindya and Guigo, Roderic and Gingeras, Thomas R and others},
	Cin = {Nature. 2007 Jun 14;447(7146):760-1. PMID: 17568710, Nature. 2007 Jun 14;447(7146):782-3. PMID: 17568731},
	Cn = {ENCODE Project Consortium, NISC Comparative Sequencing Program, Baylor College of Medicine Human Genome Sequencing Center, Washington University Genome Sequencing Center, Broad Institute, Children's Hospital Oakland Research Institute},
	Da = {20070614},
	Date-Added = {2007-09-03 07:06:23 -0700},
	Date-Modified = {2009-01-16 10:38:39 -0500},
	Dcom = {20070627},
	Edat = {2007/06/16 09:00},
	Gr = {United Kingdom Wellcome Trust},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Keywords = {Chromatin/genetics/metabolism, Chromatin Immunoprecipitation, Conserved Sequence/genetics, DNA Replication, Evolution, Molecular, Exons/genetics, Genome, Human/*genetics, *Genomics, Heterozygote, Histones/metabolism, Humans, Pilot Projects, Protein Binding, RNA, Messenger/genetics, RNA, Untranslated/genetics, Regulatory Sequences, Nucleic Acid/*genetics, Transcription Factors/metabolism, Transcription Initiation Site, Transcription, Genetic/*genetics, Variation (Genetics)/genetics},
	Language = {eng},
	Lr = {20070813},
	Mhda = {2007/06/28 09:00},
	Number = {7146},
	Own = {NLM},
	Pages = {799-816},
	Pl = {England},
	Pmid = {17571346},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print},
	Rn = {0 (Chromatin), 0 (Histones), 0 (RNA, Messenger), 0 (RNA, Untranslated), 0 (Transcription Factors)},
	Sb = {IM},
	So = {Nature. 2007 Jun 14;447(7146):799-816.},
	Stat = {MEDLINE},
	Title = {Identification and analysis of functional elements in 1{\%} of the human genome by the ENCODE pilot project.},
	Volume = {447},
	Year = {2007}}

@article{Begunetal2007,
	Abstract = {The mutational origin and subsequent evolution of de novo genes, which are hypothesized to be genes of recent origin that are not obviously related to ancestral coding sequence, are poorly understood. However, accumulating evidence suggests that such genes may often function in male reproduction. Here we use testis-derived expressed sequence tags (ESTs) from Drosophila yakuba to identify genes that have likely arisen either in D. yakuba or in the D. yakuba/D. erecta ancestor. We found several such genes, which show testis-biased expression and are often X-linked. Comparative data indicate that three of these genes have very short open reading frames, which suggests the possibility that a significant number of testis-biased de novo genes in the D. yakuba/D. erecta clade may be noncoding RNA genes. These data, along with previously published data from D. melanogaster, support the idea that many de novo Drosophila genes function in male reproduction and that a small region of the X chromosome in the melanogaster subgroup may be a hotspot for the evolution of novel testis-biased genes.},
	Address = {Section of Evolution and Ecology, University of California, Davis, California 95616, USA. djbegun@ucdavis.edu},
	Aid = {genetics.106.069245 {$[$}pii{$]$}, 10.1534/genetics.106.069245 {$[$}doi{$]$}},
	Au = {Begun DJ and Lindfors HA and Kern AD and Jones CD},
	Author = {Begun, David J and Lindfors, Heather A and Kern, Andrew D and Jones, Corbin D},
	Da = {20070620},
	Date-Added = {2007-09-03 07:06:09 -0700},
	Date-Modified = {2007-09-03 07:06:09 -0700},
	Dep = {20070415},
	Edat = {2007/04/17 09:00},
	Gr = {GM071926/GM/NIGMS},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Language = {eng},
	Mhda = {2007/04/17 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {1131-7},
	Phst = {2007/04/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {17435230},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print-Electronic},
	Sb = {IM},
	Si = {GENBANK/EF508208, GENBANK/EF508209, GENBANK/EF508210, GENBANK/EF508211, GENBANK/EF508212, GENBANK/EF508213, GENBANK/EF508214, GENBANK/EF508215, GENBANK/EF508216, GENBANK/EF508217, GENBANK/EF508218, GENBANK/EF508219, GENBANK/EF508220, GENBANK/EF508221, GENBANK/EF508222, GENBANK/EF508223, GENBANK/EF508224, GENBANK/EF508225, GENBANK/EF508226, GENBANK/EF508227, GENBANK/EF508228, GENBANK/EF508229, GENBANK/EF508230, GENBANK/EF508231, GENBANK/EF508232, GENBANK/EF508233, GENBANK/EF508234, GENBANK/EF508235, GENBANK/EF508236, GENBANK/EF508237, GENBANK/EF508238, GENBANK/EF508239, GENBANK/EF508240, GENBANK/EF508241, GENBANK/EF508242, GENBANK/EF508243, GENBANK/EF508244, GENBANK/EF508245, GENBANK/EF508246, GENBANK/EF508247, GENBANK/EF508248, GENBANK/EF508249, GENBANK/EF508250, GENBANK/EF508251, GENBANK/EF508252, GENBANK/EF508253, GENBANK/EF508254, GENBANK/EF508255, GENBANK/EF508256, GENBANK/EF508257, GENBANK/EF508258, GENBANK/EF508259, GENBANK/EF508260, GENBANK/EF508261, GENBANK/EF508262, GENBANK/EF508263, GENBANK/EF508264, GENBANK/EF508265, GENBANK/EF508266, GENBANK/EF508267, GENBANK/EF508268, GENBANK/EF508269, GENBANK/EF525530, GENBANK/EF525531, GENBANK/EF525532, GENBANK/EF525533, GENBANK/EF525534, GENBANK/EF525535},
	So = {Genetics. 2007 Jun;176(2):1131-7. Epub 2007 Apr 15.},
	Stat = {In-Process},
	Title = {Evidence for de novo evolution of testis-expressed genes in the Drosophila yakuba/Drosophila erecta clade.},
	Volume = {176},
	Year = {2007}}

@article{Hey1991,
	Abstract = {When two samples of DNA sequences are compared, one way in which they may differ is in the presence of fixed differences, which are defined as sites at which all of the sequences in one sample are different from all of the sequences in a second sample. The probability distribution of the number of fixed differences is developed. The theory employs Wright-Fisher genealogies and the infinite sites mutation model. For the case when both samples are drawn randomly from the same population it is found that genealogies permitting fixed differences are very unlikely. Thus the mere presence of fixed differences between samples is statistically significant, even for small samples. The theory is extended to samples from populations that have been separated for some time. The relationship between a simple Poisson distribution of mutations and the distribution of fixed differences is described as a function of the time since populations have been isolated. It is shown how these results may contribute to improved tests of recent balancing or directional selection.},
	Address = {Department of Biological Sciences, Rutgers University, Nelson Laboratories, Piscataway, New Jersey 08855.},
	Au = {Hey J},
	Author = {Hey, J},
	Da = {19911108},
	Date-Added = {2007-05-14 16:13:38 -0700},
	Date-Modified = {2007-05-14 16:13:38 -0700},
	Dcom = {19911108},
	Edat = {1991/08/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {*Base Sequence, Data Interpretation, Statistical, Evolution, Forecasting, *Genetics, Population, Mathematics, Models, Genetic, Mutation/*genetics, Pedigree, Probability, Sampling Studies},
	Language = {eng},
	Lr = {20061115},
	Mhda = {1991/08/01 00:01},
	Number = {4},
	Own = {NLM},
	Pages = {831-40},
	Pl = {UNITED STATES},
	Pmid = {1916247},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, U.S. Gov't, Non-P.H.S.},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 1991 Aug;128(4):831-40.},
	Stat = {MEDLINE},
	Title = {The structure of genealogies and the distribution of fixed differences between DNA sequence samples from natural populations.},
	Volume = {128},
	Year = {1991}}

@book{Pressetal1992,
	Author = {W. H. Press and S. A. Teukolsky and W. T. Vetterling and B. P. Flannery},
	Date-Added = {2007-05-11 14:27:02 -0700},
	Date-Modified = {2007-05-11 14:29:20 -0700},
	Publisher = {Cambridge University Press},
	Title = {Numerical Recipes in C},
	Year = {1992}}

@article{HapMap2005,
	Abstract = {Inherited genetic variation has a critical but as yet largely uncharacterized role in human disease. Here we report a public database of common variation in the human genome: more than one million single nucleotide polymorphisms (SNPs) for which accurate and complete genotypes have been obtained in 269 DNA samples from four populations, including ten 500-kilobase regions in which essentially all information about common DNA variation has been extracted. These data document the generality of recombination hotspots, a block-like structure of linkage disequilibrium and low haplotype diversity, leading to substantial correlations of SNPs with many of their neighbours. We show how the HapMap resource can guide the design and analysis of genetic association studies, shed light on structural variation and recombination, and identify loci that may have been subject to natural selection during human evolution.},
	Aid = {10.1038/nature04226 {$[$}doi{$]$}},
	Author = {International HapMap Consortium},
	Cin = {Nature. 2005 Oct 27;437(7063):1241-2. PMID: 16251937},
	Cn = {International HapMap Consortium},
	Da = {20051027},
	Date-Added = {2007-03-08 10:06:14 -0800},
	Date-Modified = {2007-03-08 11:35:53 -0800},
	Dcom = {20051123},
	Edat = {2005/10/29 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature},
	Keywords = {Chromosomes, Human, Y/genetics, DNA, Mitochondrial/genetics, Gene Frequency/genetics, *Genome, Human, Haplotypes/*genetics, Humans, Linkage Disequilibrium/genetics, Polymorphism, Single Nucleotide/*genetics, Recombination, Genetic/genetics, Selection (Genetics)},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2005/12/13 09:00},
	Number = {7063},
	Own = {NLM},
	Pages = {1299-320},
	Pl = {England},
	Pmid = {16255080},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print},
	Rn = {0 (DNA, Mitochondrial)},
	Sb = {IM},
	So = {Nature. 2005 Oct 27;437(7063):1299-320.},
	Stat = {MEDLINE},
	Title = {A haplotype map of the human genome.},
	Volume = {437},
	Year = {2005}}

@article{Nielsenetal2004,
	Abstract = {Most of the available SNP data have eluded valid population genetic analysis because most population genetical methods do not correctly accommodate the special discovery process used to identify SNPs. Most of the available SNP data have allele frequency distributions that are biased by the ascertainment protocol. We here show how this problem can be corrected by obtaining maximum-likelihood estimates of the true allele frequency distribution. In simple cases, the ML estimate of the true allele frequency distribution can be obtained analytically, but in other cases computational methods based on numerical optimization or the EM algorithm must be used. We illustrate the new correction method by analyzing some previously published SNP data from the SNP Consortium. Appropriate treatment of SNP ascertainment is vital to our ability to make correct inferences from the data of the International HapMap Project.},
	Address = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA. rasmus@binf.ku.dk <rasmus@binf.ku.dk>},
	Aid = {10.1534/genetics.104.031039 {$[$}doi{$]$}, genetics.104.031039 {$[$}pii{$]$}},
	Au = {Nielsen R and Hubisz MJ and Clark AG},
	Author = {Nielsen, Rasmus and Hubisz, Melissa J and Clark, Andrew G},
	Da = {20041221},
	Date-Added = {2007-02-07 13:12:39 -0800},
	Date-Modified = {2007-02-07 13:12:39 -0800},
	Dcom = {20050621},
	Dep = {20040915},
	Edat = {2004/09/17 05:00},
	Gr = {0201037/PHS, HG03229/HG/NHGRI},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {Alleles, Data Interpretation, Statistical, *Gene Frequency, Models, Genetic, *Polymorphism, Single Nucleotide, Variation (Genetics)},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2005/06/23 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {2373-82},
	Phst = {2004/09/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15371362},
	Pst = {ppublish},
	Pt = {Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S.},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genetics. 2004 Dec;168(4):2373-82. Epub 2004 Sep 15.},
	Stat = {MEDLINE},
	Title = {Reconstituting the frequency spectrum of ascertained single-nucleotide polymorphism data.},
	Volume = {168},
	Year = {2004}}

@article{Galtieretal2001,
	Au = {Galtier N and Piganeau G and Mouchiroud D and Duret L},
	Author = {Galtier, N and Piganeau, G and Mouchiroud, D and Duret, L},
	Da = {20011101},
	Date-Added = {2006-12-12 14:02:01 -0800},
	Date-Modified = {2006-12-12 14:02:01 -0800},
	Dcom = {20020115},
	Edat = {2001/11/06 10:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {Animals, Cytosine/*metabolism, *Evolution, Molecular, *Gene Conversion, *Genome, Guanine/*metabolism, Mammals/*genetics},
	Language = {eng},
	Lr = {20031114},
	Mhda = {2002/01/16 10:01},
	Number = {2},
	Own = {NLM},
	Pages = {907-11},
	Pl = {United States},
	Pmid = {11693127},
	Pst = {ppublish},
	Pt = {Letter},
	Pubm = {Print},
	Rn = {71-30-7 (Cytosine), 73-40-5 (Guanine)},
	Sb = {IM},
	So = {Genetics. 2001 Oct;159(2):907-11.},
	Stat = {MEDLINE},
	Title = {GC-content evolution in mammalian genomes: the biased gene conversion hypothesis.},
	Volume = {159},
	Year = {2001}}

@article{Zhangetal2002,
	Abstract = {Genes responsible for human-specific phenotypes may have been under altered selective pressures in human evolution and thus exhibit changes in substitution rate and pattern at the protein sequence level. Using comparative analysis of human, chimpanzee, and mouse protein sequences, we identified two genes (PRM2 and FOXP2) with significantly enhanced evolutionary rates in the hominid lineage. PRM2 is a histone-like protein essential to spermatogenesis and was previously reported to be a likely target of sexual selection in humans and chimpanzees. FOXP2 is a transcription factor involved in speech and language development. Human FOXP2 experienced a >60-fold increase in substitution rate and incorporated two fixed amino acid changes in a broadly defined transcription suppression domain. A survey of a diverse group of placental mammals reveals the uniqueness of the human FOXP2 sequence and a population genetic analysis indicates possible adaptive selection behind the accelerated evolution. Taken together, our results suggest an important role that FOXP2 may have played in the origin of human speech and demonstrate a strategy for identifying candidate genes underlying the emergences of human-specific features.},
	Address = {Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, Michigan 48109, USA. jianzhi@umich.edu},
	Au = {Zhang J and Webb DM and Podlaha O},
	Author = {Zhang, Jianzhi and Webb, David M and Podlaha, Ondrej},
	Da = {20030113},
	Date-Added = {2006-12-12 09:54:25 -0800},
	Date-Modified = {2006-12-12 09:54:25 -0800},
	Dcom = {20030721},
	Edat = {2003/01/14 04:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics},
	Keywords = {Alleles, Amino Acid Sequence, Amino Acid Substitution, Animals, *Evolution, Molecular, Forkhead Transcription Factors, Genetics, Population, Hominidae/*genetics, Humans, Male, Mice, Molecular Sequence Data, Pan troglodytes/genetics, Polymorphism, Genetic, Protamines/genetics, Repressor Proteins/genetics, Selection (Genetics), Sequence Homology, Amino Acid, Species Specificity, Transcription Factors/*genetics},
	Language = {eng},
	Lr = {20061115},
	Mhda = {2003/07/23 05:00},
	Number = {4},
	Own = {NLM},
	Pages = {1825-35},
	Pl = {United States},
	Pmid = {12524352},
	Pst = {ppublish},
	Pt = {Comparative Study, Journal Article, Research Support, Non-U.S. Gov't},
	Pubm = {Print},
	Rn = {0 (FOXP2 protein, human), 0 (Forkhead Transcription Factors), 0 (Foxp2 protein, mouse), 0 (Protamines), 0 (Repressor Proteins), 0 (Transcription Factors), 0 (protamine 2)},
	Sb = {IM},
	Si = {GENBANK/AF539547, GENBANK/AF539548, GENBANK/AF539549, GENBANK/AF539550, GENBANK/AY143178, GENBANK/AY143179, GENBANK/AY143180, GENBANK/AY143181},
	So = {Genetics. 2002 Dec;162(4):1825-35.},
	Stat = {MEDLINE},
	Title = {Accelerated protein evolution and origins of human-specific features: Foxp2 as an example.},
	Volume = {162},
	Year = {2002}}

@article{Bustamanteetal2005,
	Abstract = {Comparisons of DNA polymorphism within species to divergence between species enables the discovery of molecular adaptation in evolutionarily constrained genes as well as the differentiation of weak from strong purifying selection. The extent to which weak negative and positive darwinian selection have driven the molecular evolution of different species varies greatly, with some species, such as Drosophila melanogaster, showing strong evidence of pervasive positive selection, and others, such as the selfing weed Arabidopsis thaliana, showing an excess of deleterious variation within local populations. Here we contrast patterns of coding sequence polymorphism identified by direct sequencing of 39 humans for over 11,000 genes to divergence between humans and chimpanzees, and find strong evidence that natural selection has shaped the recent molecular evolution of our species. Our analysis discovered 304 (9.0%) out of 3,377 potentially informative loci showing evidence of rapid amino acid evolution. Furthermore, 813 (13.5%) out of 6,033 potentially informative loci show a paucity of amino acid differences between humans and chimpanzees, indicating weak negative selection and/or balancing selection operating on mutations at these loci. We find that the distribution of negatively and positively selected genes varies greatly among biological processes and molecular functions, and that some classes, such as transcription factors, show an excess of rapidly evolving genes, whereas others, such as cytoskeletal proteins, show an excess of genes with extensive amino acid polymorphism within humans and yet little amino acid divergence between humans and chimpanzees.},
	Address = {Department of Biological Statistics and Computational Biology, 101 Biotechnology Building, Cornell University, Ithaca, New York 14853, USA. cdb28@cornell.edu},
	Aid = {nature04240 {$[$}pii{$]$}, 10.1038/nature04240 {$[$}doi{$]$}},
	Au = {Bustamante CD and Fledel-Alon A and Williamson S and Nielsen R and Hubisz MT and Glanowski S and Tanenbaum DM and White TJ and Sninsky JJ and Hernandez RD and Civello D and Adams MD and Cargill M and Clark AG},
	Author = {Bustamante, Carlos D and Fledel-Alon, Adi and Williamson, Scott and Nielsen, Rasmus and Hubisz, Melissa Todd and Glanowski, Stephen and Tanenbaum, David M and White, Thomas J and Sninsky, John J and Hernandez, Ryan D and Civello, Daniel and Adams, Mark D and Cargill, Michele and Clark, Andrew G},
	Da = {20051020},
	Date-Added = {2006-11-21 09:26:39 -0800},
	Date-Modified = {2006-11-21 09:26:39 -0800},
	Dcom = {20051028},
	Edat = {2005/10/21 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Amino Acid Substitution/genetics, Animals, Comparative Study, Computational Biology, Continental Population Groups/genetics, Cytoskeleton/metabolism, Disease, *Evolution, Molecular, *Genes, Genetic Predisposition to Disease/genetics, *Genome, Human, Genomics, Humans, Male, Pan troglodytes/genetics, Polymorphism, Genetic/genetics, Proteins/*genetics, *Selection (Genetics)},
	Language = {eng},
	Mhda = {2005/10/29 09:00},
	Number = {7062},
	Own = {NLM},
	Pages = {1153-7},
	Phst = {2005/04/24 {$[$}received{$]$}, 2005/09/14 {$[$}accepted{$]$}},
	Pl = {England},
	Pmid = {16237444},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Proteins)},
	Sb = {IM},
	So = {Nature. 2005 Oct 20;437(7062):1153-7.},
	Stat = {MEDLINE},
	Title = {Natural selection on protein-coding genes in the human genome.},
	Volume = {437},
	Year = {2005}}

@article{HermissonPennings2005,
	Abstract = {A population can adapt to a rapid environmental change or habitat expansion in two ways. It may adapt either through new beneficial mutations that subsequently sweep through the population or by using alleles from the standing genetic variation. We use diffusion theory to calculate the probabilities for selective adaptations and find a large increase in the fixation probability for weak substitutions, if alleles originate from the standing genetic variation. We then determine the parameter regions where each scenario-standing variation vs. new mutations-is more likely. Adaptations from the standing genetic variation are favored if either the selective advantage is weak or the selection coefficient and the mutation rate are both high. Finally, we analyze the probability of "soft sweeps," where multiple copies of the selected allele contribute to a substitution, and discuss the consequences for the footprint of selection on linked neutral variation. We find that soft sweeps with weaker selective footprints are likely under both scenarios if the mutation rate and/or the selection coefficient is high.},
	Address = {Section of Evolutionary Biology, Department of Biology II, Ludwig-Maximilians-University Munich, Germany. joachim.hermission@lmu.de},
	Aid = {genetics.104.036947 {$[$}pii{$]$}, 10.1534/genetics.104.036947 {$[$}doi{$]$}},
	Au = {Hermisson J and Pennings PS},
	Author = {Hermisson, Joachim and Pennings, Pleuni S},
	Da = {20050509},
	Date-Added = {2006-11-21 09:06:39 -0800},
	Date-Modified = {2006-11-21 09:06:39 -0800},
	Dcom = {20050825},
	Dep = {20050216},
	Edat = {2005/02/18 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {*Adaptation, Physiological, Alleles, Animals, Evolution, Molecular, *Genetics, Population, Humans, Models, Genetic, Models, Statistical, Models, Theoretical, Mutation, Poisson Distribution, Research Support, Non-U.S. Gov't, *Variation (Genetics)},
	Language = {eng},
	Mhda = {2005/08/27 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {2335-52},
	Phst = {2005/02/16 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15716498},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genetics. 2005 Apr;169(4):2335-52. Epub 2005 Feb 16.},
	Stat = {MEDLINE},
	Title = {Soft sweeps: molecular population genetics of adaptation from standing genetic variation.},
	Volume = {169},
	Year = {2005}}

@article{PenningsHermisson2006,
	Abstract = {In the classical model of molecular adaptation, a favored allele derives from a single mutational origin. This ignores that beneficial alleles can enter a population recurrently, either by mutation or migration, during the selective phase. In this case, descendants of several of these independent origins may contribute to the fixation. As a consequence, all ancestral haplotypes that are linked to any of these copies will be retained in the population, affecting the pattern of a selective sweep on linked neutral variation. In this study, we use analytical calculations based on coalescent theory and computer simulations to analyze molecular adaptation from recurrent mutation or migration. Under the assumption of complete linkage, we derive a robust analytical approximation for the number of ancestral haplotypes and their distribution in a sample from the population. We find that so-called "soft sweeps," where multiple ancestral haplotypes appear in a sample, are likely for biologically realistic values of mutation or migration rates.},
	Address = {Section of Evolutionary Biology, Department of Biology II, Ludwig-Maximilians-University Munich, Planegg-Martinsried, Germany.},
	Aid = {msj117 {$[$}pii{$]$}, 10.1093/molbev/msj117 {$[$}doi{$]$}},
	Au = {Pennings PS and Hermisson J},
	Author = {Pennings, Pleuni S and Hermisson, Joachim},
	Da = {20060501},
	Date-Added = {2006-11-21 09:06:39 -0800},
	Date-Modified = {2006-11-21 09:06:39 -0800},
	Dcom = {20060821},
	Dep = {20060306},
	Edat = {2006/03/08 09:00},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {Alleles, Animals, Cell Movement, Computer Simulation, Diploidy, *Genetics, Population, Genomics, Models, Genetic, Models, Statistical, Molecular Biology, *Mutation, Research Support, Non-U.S. Gov't, Variation (Genetics)},
	Language = {eng},
	Mhda = {2006/08/22 09:00},
	Number = {5},
	Own = {NLM},
	Pages = {1076-84},
	Phst = {2006/03/06 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16520336},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Mol Biol Evol. 2006 May;23(5):1076-84. Epub 2006 Mar 6.},
	Stat = {MEDLINE},
	Title = {Soft sweeps II--molecular population genetics of adaptation from recurrent mutation or migration.},
	Volume = {23},
	Year = {2006}}

@article{Carlsonetal2005,
	Abstract = {The allele frequency spectrum of polymorphisms in DNA sequences can be used to test for signatures of natural selection that depart from the expected frequency spectrum under the neutral theory. We observed a significant (P = 0.001) correlation between the Tajima's D test statistic in full resequencing data and Tajima's D in a dense, genome-wide data set of genotyped polymorphisms for a set of 179 genes. Based on this, we used a sliding window analysis of Tajima's D across the human genome to identify regions putatively subject to strong, recent, selective sweeps. This survey identified seven Contiguous Regions of Tajima's D Reduction (CRTRs) in an African-descent population (AD), 23 in a European-descent population (ED), and 29 in a Chinese-descent population (XD). Only four CRTRs overlapped between populations: three between ED and XD and one between AD and ED. Full resequencing of eight genes within six CRTRs demonstrated frequency spectra inconsistent with neutral expectations for at least one gene within each CRTR. Identification of the functional polymorphism (and/or haplotype) responsible for the selective sweeps within each CRTR may provide interesting insights into the strongest selective pressures experienced by the human genome over recent evolutionary history.},
	Address = {Department of Genome Sciences, University of Washington, Seattle, Washington 98195-7730, USA. csc47@u.washington.edu},
	Aid = {15/11/1553 {$[$}pii{$]$}, 10.1101/gr.4326505 {$[$}doi{$]$}},
	Au = {Carlson CS and Thomas DJ and Eberle MA and Swanson JE and Livingston RJ and Rieder MJ and Nickerson DA},
	Author = {Carlson, Christopher S and Thomas, Daryl J and Eberle, Michael A and Swanson, Johanna E and Livingston, Robert J and Rieder, Mark J and Nickerson, Deborah A},
	Da = {20051027},
	Date-Added = {2006-11-21 08:56:29 -0800},
	Date-Modified = {2006-11-21 08:56:29 -0800},
	Dcom = {20060502},
	Edat = {2005/10/28 09:00},
	Gr = {HG02238/HG/NHGRI, HL66642/HL/NHLBI, HL66682/HL/NHLBI, IP41HG02371/HG/NHGRI},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research.},
	Keywords = {African Americans/genetics, Asian Americans/genetics, Base Sequence, Comparative Study, DNA Primers, European Continental Ancestry Group/genetics, *Evolution, Molecular, Gene Frequency, Genes/*genetics, Genome, Human/*genetics, Genomics/methods, Genotype, Humans, Molecular Sequence Data, *Polymorphism, Genetic, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, P.H.S., *Selection (Genetics), Sequence Analysis, DNA},
	Language = {eng},
	Mhda = {2006/05/04 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {1553-65},
	Pl = {United States},
	Pmid = {16251465},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (DNA Primers)},
	Sb = {IM},
	So = {Genome Res. 2005 Nov;15(11):1553-65.},
	Stat = {MEDLINE},
	Title = {Genomic regions exhibiting positive selection identified from dense genotype data.},
	Volume = {15},
	Year = {2005}}

@article{Kelleyetal2006,
	Abstract = {Identifying regions of the human genome that have been targets of positive selection will provide important insights into recent human evolutionary history and may facilitate the search for complex disease genes. However, the confounding effects of population demographic history and selection on patterns of genetic variation complicate inferences of selection when a small number of loci are studied. To this end, identifying outlier loci from empirical genome-wide distributions of genetic variation is a promising strategy to detect targets of selection. Here, we evaluate the power and efficiency of a simple outlier approach and describe a genome-wide scan for positive selection using a dense catalog of 1.58 million SNPs that were genotyped in three human populations. In total, we analyzed 14,589 genes, 385 of which possess patterns of genetic variation consistent with the hypothesis of positive selection. Furthermore, several extended genomic regions were found, spanning >500 kb, that contained multiple contiguous candidate selection genes. More generally, these data provide important practical insights into the limits of outlier approaches in genome-wide scans for selection, provide strong candidate selection genes to study in greater detail, and may have important implications for disease related research.},
	Address = {Department of Genome Sciences, University of Washington, Seattle, Washington 98195, USA.},
	Aid = {gr.5157306 {$[$}pii{$]$}, 10.1101/gr.5157306 {$[$}doi{$]$}},
	Au = {Kelley JL and Madeoy J and Calhoun JC and Swanson W and Akey JM},
	Author = {Kelley, Joanna L and Madeoy, Jennifer and Calhoun, John C and Swanson, Willie and Akey, Joshua M},
	Da = {20060802},
	Date-Added = {2006-11-21 08:50:05 -0800},
	Date-Modified = {2006-11-21 08:50:05 -0800},
	Dcom = {20060927},
	Dep = {20060706},
	Edat = {2006/07/11 09:00},
	Gr = {HD42563/HD/NICHD},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research.},
	Keywords = {*Genome, Human, Humans, Multigene Family, Polymorphism, Single Nucleotide, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2006/09/28 09:00},
	Number = {8},
	Own = {NLM},
	Pages = {980-9},
	Phst = {2006/07/06 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16825663},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genome Res. 2006 Aug;16(8):980-9. Epub 2006 Jul 6.},
	Stat = {MEDLINE},
	Title = {Genomic signatures of positive selection in humans and the limits of outlier approaches.},
	Volume = {16},
	Year = {2006}}

@article{Hahn2004,
	Abstract = {The abundance of cis-regulatory polymorphisms in humans suggests that many may have been important in human evolution, but evidence for their role is relatively rare. Four common polymorphisms in the 5' promoter region of factor VII (F7), a coagulation factor, have been shown to affect its transcription and protein abundance both in vitro and in vivo. Three of these polymorphisms have low-frequency alleles that decrease expression of F7 and may provide protection against myocardial infarction (heart attacks). The fourth polymorphism has a minor allele that increases the level of transcription. To look for evidence of natural selection on the cis-regulatory variants flanking F7, we genotyped three of the polymorphisms in six Old World populations for which we also have data from a group of putatively neutral SNPs. Our population genetic analysis shows evidence for selection within humans; surprisingly, the strongest evidence is due to a large increase in frequency of the high-expression variant in Singaporean Chinese. Further characterization of a Japanese population shows that at least part of the increase in frequency of the high-expression allele is found in other East Asian populations. In addition, to examine interspecific patterns of selection we sequenced the homologous 5' noncoding region in chimpanzees, bonobos, a gorilla, an orangutan, and a baboon. Analysis of these data reveals an excess of fixed differences within transcription factor binding sites along the human lineage. Our results thus further support the hypothesis that regulatory mutations have been important in human evolution.},
	Address = {Department of Biology, Duke University, Durham, North Carolina 27708, USA. mwhahn@ucdavis.edu},
	Aid = {10.1534/genetics.103.025726 {$[$}doi{$]$}, 167/2/867 {$[$}pii{$]$}},
	Au = {Hahn MW and Rockman MV and Soranzo N and Goldstein DB and Wray GA},
	Author = {Hahn, Matthew W and Rockman, Matthew V and Soranzo, Nicole and Goldstein, David B and Wray, Gregory A},
	Da = {20040707},
	Date-Added = {2006-11-21 08:41:13 -0800},
	Date-Modified = {2006-11-21 08:41:13 -0800},
	Dcom = {20050426},
	Edat = {2004/07/09 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Base Sequence, DNA/genetics/isolation \& purification, Factor VII/*genetics, *Genetics, Population, Gorilla gorilla/genetics, Humans, Molecular Sequence Data, Mutation/*genetics, Pan troglodytes/genetics, Papio/genetics, Phylogeny, Polymorphism, Genetic, Pongo pygmaeus/genetics, Primates/classification/*genetics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Selection (Genetics), Sequence Alignment, Sequence Homology, Nucleic Acid},
	Language = {eng},
	Mhda = {2005/04/27 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {867-77},
	Pl = {United States},
	Pmid = {15238535},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {9001-25-6 (Factor VII), 9007-49-2 (DNA)},
	Sb = {IM},
	Si = {GENBANK/AY493422, GENBANK/AY493423, GENBANK/AY493424, GENBANK/AY493425, GENBANK/AY493426, GENBANK/AY493427, GENBANK/AY493428, GENBANK/AY493429, GENBANK/AY493430, GENBANK/AY493431, GENBANK/AY493432, GENBANK/AY493433},
	So = {Genetics. 2004 Jun;167(2):867-77.},
	Stat = {MEDLINE},
	Title = {Population genetic and phylogenetic evidence for positive selection on regulatory mutations at the factor VII locus in humans.},
	Volume = {167},
	Year = {2004}}

@article{Rockmanetal2005,
	Abstract = {Changes in the cis-regulation of neural genes likely contributed to the evolution of our species' unique attributes, but evidence of a role for natural selection has been lacking. We found that positive natural selection altered the cis-regulation of human prodynorphin, the precursor molecule for a suite of endogenous opioids and neuropeptides with critical roles in regulating perception, behavior, and memory. Independent lines of phylogenetic and population genetic evidence support a history of selective sweeps driving the evolution of the human prodynorphin promoter. In experimental assays of chimpanzee-human hybrid promoters, the selected sequence increases transcriptional inducibility. The evidence for a change in the response of the brain's natural opioids to inductive stimuli points to potential human-specific characteristics favored during evolution. In addition, the pattern of linked nucleotide and microsatellite variation among and within modern human populations suggests that recent selection, subsequent to the fixation of the human-specific mutations and the peopling of the globe, has favored different prodynorphin cis-regulatory alleles in different parts of the world.},
	Address = {Department of Biology, Duke University, Durham, North Carolina, USA. mrockman@princeton.edu},
	Aid = {05-PLBI-RA-0636R2 {$[$}pii{$]$}, 10.1371/journal.pbio.0030387 {$[$}doi{$]$}},
	Au = {Rockman MV and Hahn MW and Soranzo N and Zimprich F and Goldstein DB and Wray GA},
	Author = {Rockman, Matthew V and Hahn, Matthew W and Soranzo, Nicole and Zimprich, Fritz and Goldstein, David B and Wray, Gregory A},
	Da = {20051220},
	Date-Added = {2006-11-21 08:41:13 -0800},
	Date-Modified = {2006-11-21 08:43:24 -0800},
	Edat = {2005/11/09 09:00},
	Issn = {1545-7885 (Electronic)},
	Jid = {101183755},
	Journal = {PLoS Biol},
	Jt = {PLoS biology.},
	Language = {eng},
	Mhda = {2005/11/09 09:00},
	Number = {12},
	Own = {NLM},
	Pages = {e387},
	Phst = {2005/07/19 {$[$}received{$]$}, 2005/09/13 {$[$}accepted{$]$}},
	Pl = {United States},
	Pmid = {16274263},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	Si = {GENBANK/AY902542, GENBANK/AY902543, GENBANK/AY902544, GENBANK/AY902545, GENBANK/AY902546, GENBANK/AY902547, GENBANK/AY902548, GENBANK/AY902549, GENBANK/AY902550, GENBANK/AY902551, GENBANK/AY902552, GENBANK/AY902553, GENBANK/AY902554, GENBANK/AY902555, GENBANK/AY902556, GENBANK/AY902557, GENBANK/AY902558, GENBANK/AY902559, GENBANK/AY902560, GENBANK/AY902561, GENBANK/AY902562, GENBANK/AY902563, GENBANK/AY902564, GENBANK/AY902565, GENBANK/AY902566, GENBANK/AY902567, GENBANK/AY902568, GENBANK/AY902569, GENBANK/AY902570, GENBANK/AY902571, GENBANK/AY902572, GENBANK/AY902573, GENBANK/AY902574, GENBANK/AY902575, GENBANK/AY902576, GENBANK/AY902577, GENBANK/AY902578, GENBANK/AY902579, GENBANK/AY902580, GENBANK/AY902581, GENBANK/AY902582, GENBANK/AY902583, GENBANK/AY902584, GENBANK/AY902585, GENBANK/AY902586, GENBANK/AY902587, GENBANK/AY902588, GENBANK/AY902589, GENBANK/AY902590, GENBANK/AY902591, GENBANK/AY902592, GENBANK/AY902593, GENBANK/AY902594, GENBANK/AY902595, GENBANK/AY902596, GENBANK/AY902597, GENBANK/AY902598, GENBANK/AY902599, GENBANK/AY902600, GENBANK/AY902601, GENBANK/AY902602, GENBANK/AY902603, GENBANK/AY902604, GENBANK/AY902605, GENBANK/AY902606, GENBANK/AY902607, GENBANK/AY902608, GENBANK/AY902609, GENBANK/AY902610, GENBANK/AY902611, GENBANK/AY902612, GENBANK/AY902613, GENBANK/AY902614, GENBANK/AY902615, GENBANK/AY902616, GENBANK/AY902617, GENBANK/AY902618, GENBANK/AY902619, GENBANK/AY902620, GENBANK/AY902621, GENBANK/AY902622, GENBANK/AY902623, GENBANK/AY902624, GENBANK/AY902625, GENBANK/AY902626, GENBANK/AY902627, GENBANK/AY902628, GENBANK/AY902629, GENBANK/AY902630, GENBANK/AY902631, GENBANK/AY902632, GENBANK/AY902633, GENBANK/AY902634, GENBANK/AY902635, GENBANK/AY902636, GENBANK/AY902637, GENBANK/AY902638, GENBANK/AY902639, GENBANK/AY902640, GENBANK/AY902641, GENBANK/AY902642, GENBANK/AY902643, GENBANK/AY902644, GENBANK/AY902645, GENBANK/AY902646, GENBANK/AY902647, GENBANK/AY902648, GENBANK/AY902649, GENBANK/AY902650, GENBANK/AY902651, GENBANK/AY902652, GENBANK/AY902653, GENBANK/AY902654, GENBANK/AY902655, GENBANK/AY902656, GENBANK/AY902657, GENBANK/AY902658, GENBANK/AY902659, GENBANK/AY902660, GENBANK/AY902661, GENBANK/AY902662, GENBANK/AY902663, GENBANK/AY902664, GENBANK/AY902665, GENBANK/AY902666, GENBANK/AY902667, GENBANK/AY902668, GENBANK/AY902669, GENBANK/AY902670, GENBANK/AY902671, GENBANK/AY902672, GENBANK/AY902673, GENBANK/AY902674, GENBANK/AY902675, GENBANK/AY902676, GENBANK/AY902677, GENBANK/AY902678, GENBANK/AY902679},
	So = {PLoS Biol. 2005 Dec;3(12):e387.},
	Stat = {In-Process},
	Title = {Ancient and recent positive selection transformed opioid cis-regulation in humans.},
	Volume = {3},
	Year = {2005}}

@article{AndolfattoPrzeworski2001,
	Abstract = {A correlation between diversity levels and rates of recombination is predicted both by models of positive selection, such as hitchhiking associated with the rapid fixation of advantageous mutations, and by models of purifying selection against strongly deleterious mutations (commonly referred to as "background selection"). With parameter values appropriate for Drosophila populations, only the first class of models predicts a marked skew in the frequency spectrum of linked neutral variants, relative to a neutral model. Here, we consider 29 loci scattered throughout the Drosophila melanogaster genome. We show that, in African populations, a summary of the frequency spectrum of polymorphic mutations is positively correlated with the meiotic rate of crossing over. This pattern is demonstrated to be unlikely under a model of background selection. Models of weakly deleterious selection are not expected to produce both the observed correlation and the extent to which nucleotide diversity is reduced in regions of low (but nonzero) recombination. Thus, of existing models, hitchhiking due to the recurrent fixation of advantageous variants is the most plausible explanation for the data.},
	Address = {Institute of Cell and Animal Population Biology, Ashworth Labs, University of Edinburgh, Edinburgh, EH9 3JT, United Kingdom. peter.andolfatto@ed.ac.uk},
	Au = {Andolfatto P and Przeworski M},
	Author = {Andolfatto, P and Przeworski, M},
	Da = {20010613},
	Date-Added = {2006-11-21 08:38:48 -0800},
	Date-Modified = {2006-11-21 08:38:48 -0800},
	Dcom = {20010927},
	Edat = {2001/06/19 10:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Africa, Animals, *Crossing Over, Genetic, Drosophila melanogaster/*genetics, Evolution, Evolution, Molecular, Genome, Mutation, Polymerase Chain Reaction, *Recombination, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Variation (Genetics), X Chromosome},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2001/09/28 10:01},
	Number = {2},
	Own = {NLM},
	Pages = {657-65},
	Pl = {United States},
	Pmid = {11404330},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2001 Jun;158(2):657-65.},
	Stat = {MEDLINE},
	Title = {Regions of lower crossing over harbor more rare variants in African populations of Drosophila melanogaster.},
	Volume = {158},
	Year = {2001}}

@article{Enardetal2002,
	Abstract = {Language is a uniquely human trait likely to have been a prerequisite for the development of human culture. The ability to develop articulate speech relies on capabilities, such as fine control of the larynx and mouth, that are absent in chimpanzees and other great apes. FOXP2 is the first gene relevant to the human ability to develop language. A point mutation in FOXP2 co-segregates with a disorder in a family in which half of the members have severe articulation difficulties accompanied by linguistic and grammatical impairment. This gene is disrupted by translocation in an unrelated individual who has a similar disorder. Thus, two functional copies of FOXP2 seem to be required for acquisition of normal spoken language. We sequenced the complementary DNAs that encode the FOXP2 protein in the chimpanzee, gorilla, orang-utan, rhesus macaque and mouse, and compared them with the human cDNA. We also investigated intraspecific variation of the human FOXP2 gene. Here we show that human FOXP2 contains changes in amino-acid coding and a pattern of nucleotide polymorphism, which strongly suggest that this gene has been the target of selection during recent human evolution.},
	Address = {Max Planck Institute for Evolutionary Anthropology, Inselstrasse 22, D-04103 Leipzig, Germany.},
	Aid = {10.1038/nature01025 {$[$}doi{$]$}, nature01025 {$[$}pii{$]$}},
	Au = {Enard W and Przeworski M and Fisher SE and Lai CS and Wiebe V and Kitano T and Monaco AP and Paabo S},
	Author = {Enard, Wolfgang and Przeworski, Molly and Fisher, Simon E and Lai, Cecilia S L and Wiebe, Victor and Kitano, Takashi and Monaco, Anthony P and Paabo, Svante},
	Da = {20020822},
	Date-Added = {2006-11-21 08:38:48 -0800},
	Date-Modified = {2006-11-21 08:38:48 -0800},
	Dcom = {20020923},
	Dep = {20020814},
	Edat = {2002/08/23 10:00},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Alleles, Amino Acid Sequence, Amino Acid Substitution/genetics, Animals, Cloning, Molecular, Comparative Study, Conserved Sequence/genetics, *Evolution, Molecular, Forkhead Transcription Factors, Humans, *Language, Mice, Molecular Sequence Data, Mutation/genetics, Phylogeny, Primates/genetics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Selection (Genetics), *Speech, Speech Disorders/*genetics, Transcription Factors/chemistry/*genetics/*metabolism, Variation (Genetics)/genetics},
	Language = {eng},
	Lr = {20051117},
	Mhda = {2002/09/24 06:00},
	Number = {6900},
	Own = {NLM},
	Pages = {869-72},
	Phst = {2002/08/14 {$[$}aheadofprint{$]$}},
	Pl = {England},
	Pmid = {12192408},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (FOXP2 protein, human), 0 (Forkhead Transcription Factors), 0 (Transcription Factors)},
	Sb = {IM},
	So = {Nature. 2002 Aug 22;418(6900):869-72. Epub 2002 Aug 14.},
	Stat = {MEDLINE},
	Title = {Molecular evolution of FOXP2, a gene involved in speech and language.},
	Volume = {418},
	Year = {2002}}

@article{Przeworski2003,
	Abstract = {The fixation of a beneficial allele in a population leaves a well-characterized signature in patterns of nucleotide variation at linked sites. This signature can be used to estimate the time since fixation from patterns of polymorphism in extant individuals. I introduce a method to assess the support in polymorphism data for a recent episode of directional positive selection and to estimate the time since fixation. I summarize the polymorphism data by three statistics that carry information about levels of diversity, the allele frequency spectrum, and the extent of allelic associations. Simulations are then used to obtain a sample from the posterior distribution of the time since fixation, conditional on the observed summaries. I test the performance of the approach on simulated data and apply it to the gene tb1 in maize. The data support the recent fixation of a favored allele, consistent with what is known about the importance of tb1 in the domestication process of maize.},
	Address = {Max Planck Institute for Evolutionary Anthropology, Deutscher Platz 6, 04103 Leipzig, Germany. przewors@eva.mpg.de},
	Au = {Przeworski M},
	Author = {Przeworski, Molly},
	Da = {20030821},
	Date-Added = {2006-11-21 08:38:48 -0800},
	Date-Modified = {2006-11-21 08:38:48 -0800},
	Dcom = {20040511},
	Edat = {2003/08/22 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Algorithms, *Alleles, Base Sequence, Computer Simulation, Crossing Over, Genetic, Diploidy, Gene Frequency, Genes, Plant, Genetics, Population, Kinetics, Linkage (Genetics), Models, Genetic, Mutation, Polymorphism, Genetic, Recombination, Genetic, Selection (Genetics), Time Factors, Variation (Genetics), Zea mays/genetics},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/05/12 05:00},
	Number = {4},
	Own = {NLM},
	Pages = {1667-76},
	Pl = {United States},
	Pmid = {12930770},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2003 Aug;164(4):1667-76.},
	Stat = {MEDLINE},
	Title = {Estimating the time since the fixation of a beneficial allele.},
	Volume = {164},
	Year = {2003}}

@article{Przeworski2002,
	Abstract = {In Drosophila and humans, there are accumulating examples of loci with a significant excess of high-frequency-derived alleles or high levels of linkage disequilibrium, relative to a neutral model of a random-mating population of constant size. These are features expected after a recent selective sweep. Their prevalence suggests that positive directional selection may be widespread in both species. However, as I show here, these features do not persist long after the sweep ends: The high-frequency alleles drift to fixation and no longer contribute to polymorphism, while linkage disequilibrium is broken down by recombination. As a result, loci chosen without independent evidence of recent selection are not expected to exhibit either of these features, even if they have been affected by numerous sweeps in their genealogical history. How then can we explain the patterns in the data? One possibility is population structure, with unequal sampling from different subpopulations. Alternatively, positive selection may not operate as is commonly modeled. In particular, the rate of fixation of advantageous mutations may have increased in the recent past.},
	Address = {Department of Statistics, University of Oxford, Oxford OX1 3TG, United Kingdom. przewors@eva.mpg.de},
	Au = {Przeworski M},
	Author = {Przeworski, Molly},
	Da = {20020319},
	Date-Added = {2006-11-21 08:38:48 -0800},
	Date-Modified = {2006-11-21 08:38:48 -0800},
	Dcom = {20020906},
	Edat = {2002/03/20 10:00},
	Ein = {Genetics. 2002 Dec;162(4):2053., Genetics. 2002 Jul;161(3):1355.},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Adaptation, Biological/*genetics, Animals, Drosophila/genetics, Humans, *Linkage Disequilibrium, *Models, Genetic, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2002/09/07 10:01},
	Number = {3},
	Own = {NLM},
	Pages = {1179-89},
	Pl = {United States},
	Pmid = {11901132},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2002 Mar;160(3):1179-89.},
	Stat = {MEDLINE},
	Title = {The signature of positive selection at randomly chosen loci.},
	Volume = {160},
	Year = {2002}}

@article{Walletal2002,
	Abstract = {We analyze patterns of nucleotide variability at 15 X-linked loci and 14 autosomal loci from a North American population of Drosophila simulans. We show that there is significantly more linkage disequilibrium on the X chromosome than on chromosome arm 3R and much more linkage disequilibrium on both chromosomes than expected from estimates of recombination rates, mutation rates, and levels of diversity. To explore what types of evolutionary models might explain this observation, we examine a model of recurrent, nonoverlapping selective sweeps and a model of a recent drastic bottleneck (e.g., founder event) in the demographic history of North American populations of D. simulans. The simple sweep model is not consistent with the observed patterns of linkage disequilibrium nor with the observed frequencies of segregating mutations. Under a restricted range of parameter values, a simple bottleneck model is consistent with multiple facets of the data. While our results do not exclude some influence of selection on X vs. autosome variability levels, they suggest that demography alone may account for patterns of linkage disequilibrium and the frequency spectrum of segregating mutations in this population of D. simulans.},
	Address = {Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, Massachusetts 02138, USA. jwall@fas.harvard.edu},
	Au = {Wall JD and Andolfatto P and Przeworski M},
	Author = {Wall, Jeffrey D and Andolfatto, Peter and Przeworski, Molly},
	Da = {20020920},
	Date-Added = {2006-11-21 08:38:48 -0800},
	Date-Modified = {2006-11-21 08:38:48 -0800},
	Dcom = {20030327},
	Edat = {2002/09/21 10:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Drosophila/*genetics, Linkage (Genetics), *Models, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics), X Chromosome},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2003/03/28 05:00},
	Number = {1},
	Own = {NLM},
	Pages = {203-16},
	Pl = {United States},
	Pmid = {12242234},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2002 Sep;162(1):203-16.},
	Stat = {MEDLINE},
	Title = {Testing models of selection and demography in Drosophila simulans.},
	Volume = {162},
	Year = {2002}}

@article{Pennacchioetal2006,
	Abstract = {Identifying the sequences that direct the spatial and temporal expression of genes and defining their function in vivo remains a significant challenge in the annotation of vertebrate genomes. One major obstacle is the lack of experimentally validated training sets. In this study, we made use of extreme evolutionary sequence conservation as a filter to identify putative gene regulatory elements, and characterized the in vivo enhancer activity of a large group of non-coding elements in the human genome that are conserved in human-pufferfish, Takifugu (Fugu) rubripes, or ultraconserved in human-mouse-rat. We tested 167 of these extremely conserved sequences in a transgenic mouse enhancer assay. Here we report that 45% of these sequences functioned reproducibly as tissue-specific enhancers of gene expression at embryonic day 11.5. While directing expression in a broad range of anatomical structures in the embryo, the majority of the 75 enhancers directed expression to various regions of the developing nervous system. We identified sequence signatures enriched in a subset of these elements that targeted forebrain expression, and used these features to rank all approximately 3,100 non-coding elements in the human genome that are conserved between human and Fugu. The testing of the top predictions in transgenic mice resulted in a threefold enrichment for sequences with forebrain enhancer activity. These data dramatically expand the catalogue of human gene enhancers that have been characterized in vivo, and illustrate the utility of such training sets for a variety of biological applications, including decoding the regulatory vocabulary of the human genome.},
	Address = {{$[$}1{$]$} US Department of Energy Joint Genome Institute, Walnut Creek, California 94598, USA [2] Genomics Division, MS 84-171, Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA.},
	Aid = {nature05295 {$[$}pii{$]$}, 10.1038/nature05295 {$[$}doi{$]$}},
	Author = {Pennacchio, LA and Ahituv, N and Moses, AM and Prabhakar, S and Nobrega, MA and Shoukry, M and Minovitsky, S and Dubchak, I and Holt, A and Lewis, KD and Plajzer-Frick, I and Akiyama, J and De Val, S and Afzal, V and Black, BL and Couronne, O and Eisen, MB and Visel, A and Rubin, EM},
	Da = {20061106},
	Date-Added = {2006-11-13 12:07:53 -0800},
	Date-Modified = {2006-12-04 13:12:15 -0800},
	Dep = {20061105},
	Edat = {2006/11/07 09:00},
	Jid = {0410462},
	Journal = {Nature},
	Language = {ENG},
	Mhda = {2006/11/07 09:00},
	Number = {1476-4687 (Electronic)},
	Own = {NLM},
	Phst = {2006/06/14 {$[$}received{$]$}, 2006/09/22 {$[$}accepted{$]$}, 2006/11/05 {$[$}aheadofprint{$]$}},
	Pmid = {17086198},
	Pst = {aheadofprint},
	Pt = {JOURNAL ARTICLE},
	Pubm = {Print-Electronic},
	So = {Nature. 2006 Nov 5;.},
	Stat = {Publisher},
	Title = {In vivo enhancer analysis of human conserved non-coding sequences.},
	Volume = {444},
	Year = {2006}}

@article{Risch2000,
	Abstract = {Human genetics is now at a critical juncture. The molecular methods used successfully to identify the genes underlying rare mendelian syndromes are failing to find the numerous genes causing more common, familial, non-mendelian diseases. With the human genome sequence nearing completion, new opportunities are being presented for unravelling the complex genetic basis of non-mendelian disorders based on large-scale genome-wide studies. Considerable debate has arisen regarding the best approach to take. In this review I discuss these issues, together with suggestions for optimal post-genome strategies.},
	Address = {Department of Genetics, Stanford University School of Medicine, California 94305-5120, USA.},
	Aid = {10.1038/35015718 {$[$}doi{$]$}},
	Au = {Risch NJ},
	Author = {Risch, N J},
	Da = {20000707},
	Date-Added = {2006-11-13 11:49:11 -0800},
	Date-Modified = {2006-11-13 11:49:11 -0800},
	Dcom = {20000707},
	Edat = {2000/06/24 11:00},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Biotechnology, Computational Biology, Genetic Diseases, Inborn/genetics, Genetic Predisposition to Disease, Genetics, Medical/*trends, *Genome, Human, Humans},
	Language = {eng},
	Lr = {20051116},
	Mhda = {2000/07/15 11:00},
	Number = {6788},
	Own = {NLM},
	Pages = {847-56},
	Pl = {ENGLAND},
	Pmid = {10866211},
	Pst = {ppublish},
	Pt = {Journal Article, Review},
	Pubm = {Print},
	Rf = {47},
	Sb = {IM},
	So = {Nature. 2000 Jun 15;405(6788):847-56.},
	Stat = {MEDLINE},
	Title = {Searching for genetic determinants in the new millennium.},
	Volume = {405},
	Year = {2000}}

@article{Olsonetal2004,
	Abstract = {We define 'genetic individuality' as intraspecies variation that has substantial heritability and involves traits that are sufficiently common that they can be observed in any modest-sized sampling of individuals. We propose that genetic individuality is largely shaped by the combinatory shuffling of a modest number of genes, each of which exists as a family of functionally and structurally diverged alleles. Unequivocal examples of such allele families are found at the O-antigen-biosynthetic locus in Pseudomonas aeruginosa and the human leucocyte antigen locus in humans. We examine characteristic features of these allele families and explore the possibility that genetic loci with similar characteristics can be recognized in a whole-genome scan of human genetic variation.},
	Address = {University of Washington Genome Center, Department of Medicine, University of Washington, Seattle, WA 98195, USA. mvo@u.washington.edu},
	Au = {Olson MV and Kas A and Bubb K and Qui R and Smith EE and Raymond CK and Kaul R},
	Author = {Olson, M V and Kas, A and Bubb, K and Qui, R and Smith, E E and Raymond, C K and Kaul, R},
	Da = {20040406},
	Date-Added = {2006-11-13 11:48:23 -0800},
	Date-Modified = {2006-11-13 11:48:23 -0800},
	Dcom = {20040505},
	Edat = {2004/04/07 05:00},
	Gr = {P50 HG02351/HG/NHGRI},
	Issn = {0962-8436 (Print)},
	Jid = {7503623},
	Journal = {Philos Trans R Soc Lond B Biol Sci},
	Jt = {Philosophical transactions of the Royal Society of London. Series B, Biological sciences.},
	Keywords = {*Alleles, Base Sequence, Comparative Study, *Evolution, Genome, Human, HLA Antigens/genetics, Humans, *Models, Genetic, Molecular Sequence Data, O Antigens/genetics, Pseudomonas aeruginosa, Recombination, Genetic/*genetics, Research Support, U.S. Gov't, P.H.S., Selection (Genetics), *Variation (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/05/07 05:00},
	Number = {1441},
	Own = {NLM},
	Pages = {129-40},
	Pl = {England},
	Pmid = {15065665},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (HLA Antigens), 0 (O Antigens), 0 (O antigen, Pseudomonas)},
	Sb = {IM},
	So = {Philos Trans R Soc Lond B Biol Sci. 2004 Jan 29;359(1441):129-40.},
	Stat = {MEDLINE},
	Title = {Hypervariability, suppressed recombination and the genetics of individuality.},
	Volume = {359},
	Year = {2004}}

@article{Chakravarti2001,
	Aid = {10.1038/35057281 {$[$}doi{$]$}},
	Au = {Chakravarti A},
	Author = {Chakravarti, A},
	Con = {Nature. 2001 Feb 15;409(6822):860-921. PMID: 11237011, Nature. 2001 Feb 15;409(6822):928-33. PMID: 11237013},
	Da = {20010309},
	Date-Added = {2006-11-13 11:45:34 -0800},
	Date-Modified = {2006-11-13 11:45:34 -0800},
	Dcom = {20010322},
	Edat = {2001/03/10 10:00},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Chromosome Mapping, Forecasting, *Genetics, Medical, *Genome, Human, Human Genome Project, Humans, *Polymorphism, Single Nucleotide, Variation (Genetics), X Chromosome, Y Chromosome},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2001/03/27 10:01},
	Number = {6822},
	Own = {NLM},
	Pages = {822-3},
	Pl = {England},
	Pmid = {11236997},
	Pst = {ppublish},
	Pt = {Comment, News},
	Pubm = {Print},
	Sb = {IM},
	So = {Nature. 2001 Feb 15;409(6822):822-3.},
	Stat = {MEDLINE},
	Title = {To a future of genetic medicine.},
	Volume = {409},
	Year = {2001}}

@article{Chakravarti1999,
	Abstract = {The complete human genome nucleotide sequence and technologies for assessing sequence variation on a genome-scale will prompt comprehensive studies of comparative genomic diversity in human populations across the globe. These studies, besides rejuvenating population genetics and our interest in how genetic variation is created and maintained, will provide the intellectual basis for understanding the genetic basis for complex diseases and traits.},
	Address = {Department of Genetics and Center for Human Genetics, Case Western Reserve University School of Medicine and University Hospitals of Cleveland, Ohio 44106, USA. axc39@po.cwru.edu},
	Aid = {10.1038/4482 {$[$}doi{$]$}},
	Au = {Chakravarti A},
	Author = {Chakravarti, A},
	Da = {19990127},
	Date-Added = {2006-11-13 11:45:34 -0800},
	Date-Modified = {2006-11-13 11:45:34 -0800},
	Dcom = {19990127},
	Edat = {1999/01/23},
	Issn = {1061-4036 (Print)},
	Jid = {9216904},
	Journal = {Nat Genet},
	Jt = {Nature genetics.},
	Keywords = {*Base Sequence, *Genome, Human, Geography, Humans, Phenotype, Polymorphism, Genetic/genetics, Variation (Genetics)/*genetics},
	Language = {eng},
	Lr = {20051116},
	Mhda = {1999/01/23 00:01},
	Number = {1 Suppl},
	Own = {NLM},
	Pages = {56-60},
	Pl = {UNITED STATES},
	Pmid = {9915503},
	Pst = {ppublish},
	Pt = {Journal Article, Review},
	Pubm = {Print},
	Rf = {52},
	Sb = {IM},
	So = {Nat Genet. 1999 Jan;21(1 Suppl):56-60.},
	Stat = {MEDLINE},
	Title = {Population genetics--making sense out of sequence.},
	Volume = {21},
	Year = {1999}}

@article{KatzmanKernetal2007,
	Author = {Katzman, Sol and Kern, Andrew D and Bejerano, Gill and Fewell, Ginger and Fulton, Lucinda and Wilson, Richard K and Salama, Sofie R and Haussler, David},
	Date-Added = {2006-11-11 14:15:27 -0800},
	Date-Modified = {2007-09-02 10:50:14 -0700},
	Journal = {Science},
	Pages = {915},
	Title = {Human ultraconserved elements are ultraselected},
	Volume = {317},
	Year = {2007}}

@article{Hahnetal2005,
	Abstract = {The idea that natural selection on genes might be detected using only a single genome has been put forward by Plotkin and colleagues, who present a method that they claim can detect selection without the need for comparative data and which, if correct, would confer greater power of analysis with less information. Here we argue that their method depends on assumptions that confound their conclusions and that, even if these assumptions were valid, the authors' inferences about adaptive natural selection are unjustified.},
	Address = {Center for Population Biology and Section of Evolution and Ecology, University of California, Davis, California 95616, USA. mwhahn@ucdavis.edu},
	Aid = {nature03221 {$[$}pii{$]$}, 10.1038/nature03221 {$[$}doi{$]$}},
	Au = {Hahn MW and Mezey JG and Begun DJ and Gillespie JH and Kern AD and Langley CH and Moyle LC},
	Author = {Hahn, Matthew W and Mezey, Jason G and Begun, David J and Gillespie, John H and Kern, Andrew D and Langley, Charles H and Moyle, Leonie C},
	Con = {Nature. 2004 Apr 29;428(6986):942-5. PMID: 15118727},
	Da = {20050121},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:28:48 -0800},
	Dcom = {20050204},
	Edat = {2005/01/22 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Bias (Epidemiology), Codon/*genetics, *Evolution, *Genome, Bacterial, Genomics/*methods, Models, Genetic, Mutation, Missense/genetics, Mycobacterium tuberculosis/genetics, Reproducibility of Results, *Selection (Genetics)},
	Language = {eng},
	Mhda = {2005/02/05 09:00},
	Number = {7023},
	Own = {NLM},
	Pages = {E5-6; discussion E7-8},
	Pl = {England},
	Pmid = {15662370},
	Pst = {ppublish},
	Pt = {Comment, Journal Article},
	Pubm = {Print},
	Rn = {0 (Codon)},
	Sb = {IM},
	So = {Nature. 2005 Jan 20;433(7023):E5-6; discussion E7-8.},
	Stat = {MEDLINE},
	Title = {Evolutionary genomics: codon bias and selection on single genomes.},
	Volume = {433},
	Year = {2005}}

@article{HahnKern2005,
	Abstract = {Most proteins do not evolve in isolation, but as components of complex genetic networks. Therefore, a protein's position in a network may indicate how central it is to cellular function and, hence, how constrained it is evolutionarily. To look for an effect of position on evolutionary rate, we examined the protein-protein interaction networks in three eukaryotes: yeast, worm, and fly. We find that the three networks have remarkably similar structure, such that the number of interactors per protein and the centrality of proteins in the networks have similar distributions. Proteins that have a more central position in all three networks, regardless of the number of direct interactors, evolve more slowly and are more likely to be essential for survival. Our results are thus consistent with a classic proposal of Fisher's that pleiotropy constrains evolution.},
	Aid = {msi072 {$[$}pii{$]$}, 10.1093/molbev/msi072 {$[$}doi{$]$}},
	Au = {Hahn MW and Kern AD},
	Author = {Hahn, Matthew W and Kern, Andrew D},
	Da = {20050329},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:28:48 -0800},
	Dcom = {20050926},
	Dep = {20041222},
	Edat = {2004/12/24 09:00},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {Eukaryotic Cells/metabolism, Evolution, *Genomics, Proteins/*metabolism, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Mhda = {2005/09/27 09:00},
	Number = {4},
	Own = {NLM},
	Pages = {803-6},
	Phst = {2004/12/22 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15616139},
	Pst = {ppublish},
	Pt = {Letter},
	Pubm = {Print-Electronic},
	Rn = {0 (Proteins)},
	Sb = {IM},
	So = {Mol Biol Evol. 2005 Apr;22(4):803-6. Epub 2004 Dec 22.},
	Stat = {MEDLINE},
	Title = {Comparative genomics of centrality and essentiality in three eukaryotic protein-interaction networks.},
	Volume = {22},
	Year = {2005}}

@article{KernKondrashov2004,
	Abstract = {The function of protein and RNA molecules depends on complex epistatic interactions between sites. Therefore, the deleterious effect of a mutation can be suppressed by a compensatory second-site substitution. In relating a list of 86 pathogenic mutations in human tRNAs encoded by mitochondrial genes to the sequences of their mammalian orthologs, we noted that 52 pathogenic mutations were present in normal tRNAs of one or several nonhuman mammals. We found at least five mechanisms of compensation for 32 pathogenic mutations that destroyed a Watson-Crick pair in one of the four tRNA stems: restoration of the affected Watson-Crick interaction (25 cases), strengthening of another pair (4 cases), creation of a new pair (8 cases), changes of multiple interactions in the affected stem (11 cases) and changes involving the interaction between the loop and stem structures (3 cases). A pathogenic mutation and its compensating substitution are fixed in a lineage in rapid succession, and often a compensatory interaction evolves convergently in different clades. At least 10%, and perhaps as many as 50%, of all nucleotide substitutions in evolving mammalian tRNAs participate in such interactions, indicating that the evolution of tRNAs proceeds along highly epistatic fitness ridges.},
	Address = {Center for Population Biology, Section of Evolution and Ecology, University of California at Davis, Davis, California 95616, USA.},
	Aid = {ng1451 {$[$}pii{$]$}, 10.1038/ng1451 {$[$}doi{$]$}},
	Au = {Kern AD and Kondrashov FA},
	Author = {Kern, Andrew D and Kondrashov, Fyodor A},
	Da = {20041029},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:28:48 -0800},
	Dcom = {20041207},
	Dep = {20041024},
	Edat = {2004/10/27 09:00},
	Issn = {1061-4036 (Print)},
	Jid = {9216904},
	Journal = {Nat Genet},
	Jt = {Nature genetics.},
	Keywords = {Animals, DNA, Mitochondrial, Epistasis, Genetic, Evolution, Molecular, Humans, Mammals, Molecular Sequence Data, *Mutation, Nucleic Acid Conformation, Phylogeny, RNA/*genetics, RNA, Transfer/*genetics, Research Support, U.S. Gov't, P.H.S.},
	Language = {eng},
	Mhda = {2004/12/16 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {1207-12},
	Phst = {2004/06/14 {$[$}received{$]$}, 2004/09/20 {$[$}accepted{$]$}, 2004/10/24 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15502829},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (DNA, Mitochondrial), 0 (RNA, mitochondrial), 63231-63-0 (RNA), 9014-25-9 (RNA, Transfer)},
	Sb = {IM},
	So = {Nat Genet. 2004 Nov;36(11):1207-12. Epub 2004 Oct 24.},
	Stat = {MEDLINE},
	Title = {Mechanisms and convergence of compensatory evolution in mammalian mitochondrial tRNAs.},
	Volume = {36},
	Year = {2004}}

@article{KernBegun2005,
	Abstract = {Despite the fact that D. melanogaster and D. simulans have been the central model system for molecular population genetics, few data are available for noncoding regions. Here, we present an analysis of population genetic data from intergenic regions and comparisons of these data to previously collected data from introns and exons. Polymorphisms and fixations were categorized as A/T to G/C or G/C to A/T changes and were polarized by inferring the ancestral state using both parsimony and maximum likelihood. Noncoding fixations in both D. melanogaster and D. simulans were consistent with equilibrium base-composition evolution. However, polarized noncoding polymorphisms, revealed a different pattern. Although A/T to G/C and G/C to A/T polymorphisms in D. simulans were consistent with equilibrium, we observed a highly significant dearth of A/T to G/C polymorphisms in D. melanogaster introns but not in intergenic sequences. Such data could be explained by recent evolution of mutational biases associated with transcription or by lineage-specific selection on base composition. These data reveal the complexity of evolutionary processes acting even on noncoding DNA in Drosophila.},
	Address = {Center for Population Biology, University of California, Davis, USA. adkern@ucdavis.edu},
	Aid = {10.1093/molbev/msh269 {$[$}doi{$]$}, msh269 {$[$}pii{$]$}},
	Au = {Kern AD and Begun DJ},
	Author = {Kern, Andrew D and Begun, David J},
	Da = {20041130},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:28:48 -0800},
	Dcom = {20050519},
	Dep = {20040929},
	Edat = {2004/10/01 05:00},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {Animals, Cell Lineage, Comparative Study, DNA/genetics, Drosophila/genetics, Drosophila melanogaster/*genetics, Evolution, Molecular, Female, Genes, Insect, Genetics, Population, Introns/genetics, Likelihood Functions, Models, Genetic, Mutation, *Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics), Variation (Genetics)},
	Language = {eng},
	Lr = {20051116},
	Mhda = {2005/05/20 09:00},
	Number = {1},
	Own = {NLM},
	Pages = {51-62},
	Phst = {2004/09/29 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15456897},
	Pst = {ppublish},
	Pt = {Journal Article, Review},
	Pubm = {Print-Electronic},
	Rf = {75},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Mol Biol Evol. 2005 Jan;22(1):51-62. Epub 2004 Sep 29.},
	Stat = {MEDLINE},
	Title = {Patterns of polymorphism and divergence from noncoding sequences of Drosophila melanogaster and D. simulans: evidence for nonequilibrium processes.},
	Volume = {22},
	Year = {2005}}

@article{Kernetal2004,
	Abstract = {Accessory gland proteins are a major component of Drosophila seminal fluid. These proteins have a variety of functions and may be subject to sexual selection and/or antagonistic evolution between the sexes. Most population genetic data from these proteins are from D. melanogaster and D. simulans. Here, we extend the population genetic analysis of Acp genes to the other simulans complex species, D. mauritiana and D. sechellia. We sequenced population samples of seven Acp's from D. mauritiana, D. sechellia, and D. simulans. We investigated the population genetics of these genes on individual simulans complex lineages and compared Acp polymorphism and divergence to polymorphism and divergence from a set of non-Acp loci in the same species. Polymorphism and divergence data from the simulans complex revealed little evidence for adaptive protein evolution at individual loci. However, we observed a dramatically inflated index of dispersion for amino acid substitutions in the simulans complex at Acp genes, but not at non-Acp genes. This pattern of episodic bursts of protein evolution in Acp's provides the strongest evidence to date that the population genetic mechanisms driving Acp divergence are different from the mechanisms driving evolution at most Drosophila genes.},
	Address = {Center for Population Biology, University of California, Davis, 95616, USA. adkern@ucdavis.ed},
	Aid = {10.1534/genetics.103.020883 {$[$}doi{$]$}, 167/2/725 {$[$}pii{$]$}},
	Au = {Kern AD and Jones CD and Begun DJ},
	Author = {Kern, Andrew D and Jones, Corbin D and Begun, David J},
	Da = {20040707},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:28:48 -0800},
	Dcom = {20050426},
	Edat = {2004/07/09 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Drosophila/*genetics/physiology, Drosophila Proteins/*genetics, Genetics, Population, Genitalia, Male/*physiology, Male, Models, Genetic, Models, Theoretical, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Variation (Genetics)},
	Language = {eng},
	Mhda = {2005/04/27 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {725-35},
	Pl = {United States},
	Pmid = {15238524},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Drosophila Proteins)},
	Sb = {IM},
	So = {Genetics. 2004 Jun;167(2):725-35.},
	Stat = {MEDLINE},
	Title = {Molecular population genetics of male accessory gland proteins in the Drosophila simulans complex.},
	Volume = {167},
	Year = {2004}}

@article{PollardSalamaetal2006,
	Abstract = {The developmental and evolutionary mechanisms behind the emergence of human-specific brain features remain largely unknown. However, the recent ability to compare our genome to that of our closest relative, the chimpanzee, provides new avenues to link genetic and phenotypic changes in the evolution of the human brain. We devised a ranking of regions in the human genome that show significant evolutionary acceleration. Here we report that the most dramatic of these 'human accelerated regions', HAR1, is part of a novel RNA gene (HAR1F) that is expressed specifically in Cajal-Retzius neurons in the developing human neocortex from 7 to 19 gestational weeks, a crucial period for cortical neuron specification and migration. HAR1F is co-expressed with reelin, a product of Cajal-Retzius neurons that is of fundamental importance in specifying the six-layer structure of the human cortex. HAR1 and the other human accelerated regions provide new candidates in the search for uniquely human biology.},
	Address = {Center for Biomolecular Science \& Engineering, Department of Molecular, Cell & Developmental Biology, University of California, Santa Cruz, California 95064, USA.},
	Aid = {nature05113 {$[$}pii{$]$}, 10.1038/nature05113 {$[$}doi{$]$}},
	Au = {Pollard KS and Salama SR and Lambert N and Lambot MA and Coppens S and Pedersen JS and Katzman S and King B and Onodera C and Siepel A and Kern AD and Dehay C and Igel H and Ares M Jr and Vanderhaeghen P and Haussler D},
	Author = {Pollard, Katherine S and Salama, Sofie R and Lambert, Nelle and Lambot, Marie-Alexandra and Coppens, Sandra and Pedersen, Jakob S and Katzman, Sol and King, Bryan and Onodera, Courtney and Siepel, Adam and Kern, Andrew D and Dehay, Colette and Igel, Haller and Ares, Manuel Jr and Vanderhaeghen, Pierre and Haussler, David},
	Cin = {Nature. 2006 Sep 14;443(7108):149-50. PMID: 16915234},
	Da = {20060914},
	Date-Added = {2006-11-09 11:28:48 -0800},
	Date-Modified = {2006-11-09 11:29:19 -0800},
	Dcom = {20061013},
	Dep = {20060816},
	Edat = {2006/08/18 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Aging/genetics, Animals, Base Sequence, Cell Adhesion Molecules, Neuronal/genetics, Cerebral Cortex/anatomy \& histology/*embryology/*metabolism, *Evolution, Molecular, Extracellular Matrix Proteins/genetics, Gene Expression Profiling, *Gene Expression Regulation, Developmental, Humans, Macaca/genetics, Molecular Sequence Data, Mutation/genetics, Neocortex/anatomy \& histology/embryology/metabolism, Nerve Tissue Proteins/genetics, Nucleic Acid Conformation, Organ Specificity, RNA Stability, RNA, Untranslated/chemistry/*genetics/metabolism, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Serine Endopeptidases/genetics, Time Factors},
	Language = {eng},
	Mhda = {2006/10/14 09:00},
	Number = {7108},
	Own = {NLM},
	Pages = {167-72},
	Phst = {2006/06/27 {$[$}received{$]$}, 2006/07/25 {$[$}accepted{$]$}, 2006/08/16 {$[$}aheadofprint{$]$}},
	Pl = {England},
	Pmid = {16915236},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (Cell Adhesion Molecules, Neuronal), 0 (Extracellular Matrix Proteins), 0 (Nerve Tissue Proteins), 0 (RNA, Untranslated), EC 3.4.21 (Serine Endopeptidases), EC 3.4.21.- (reelin protein)},
	Sb = {IM},
	Si = {GENBANK/DQ860409, GENBANK/DQ860410, GENBANK/DQ860411, GENBANK/DQ860412, GENBANK/DQ860413, GENBANK/DQ860414, GENBANK/DQ860415},
	So = {Nature. 2006 Sep 14;443(7108):167-72. Epub 2006 Aug 16.},
	Stat = {MEDLINE},
	Title = {An RNA gene expressed during cortical development evolved rapidly in humans.},
	Volume = {443},
	Year = {2006}}

@article{brooksGelman1997,
	Author = {Brooks, S.P. and Gelman, A.},
	Date-Added = {2006-10-09 16:24:26 -0700},
	Date-Modified = {2006-10-09 16:25:54 -0700},
	Journal = {Journal of Computational and Graphical Statistics},
	Pages = {434-455},
	Title = {General methods for monitoring convergence of iterative simulations},
	Volume = {7},
	Year = {1997}}

@article{Bustamante2002,
	Abstract = {Population geneticists have long sought to estimate the distribution of selection intensities among genes of diverse function across the genome. Only recently have DNA sequencing and analytical techniques converged to make this possible. Important advances have come from comparing genetic variation within species (polymorphism) with fixed differences between species (divergence). These approaches have been used to examine individual genes for evidence of selection. Here we use the fact that the time since species divergence allows combination of data across genes. In a comparison of amino-acid replacements among species of the mustard weed Arabidopsis with those among species of the fruitfly Drosophila, we find evidence for predominantly beneficial gene substitutions in Drosophila but predominantly detrimental substitutions in Arabidopsis. We attribute this difference to the Arabidopsis mating system of partial self-fertilization, which corroborates a prediction of population genetics theory that species with a high frequency of inbreeding are less efficient in eliminating deleterious mutations owing to their reduced effective population size.},
	Address = {Department of Organismic and Evolutionary Biology, Harvard University, 16 Divinity Avenue, Cambridge, Massachusetts 02138, USA.},
	Aid = {10.1038/416531a {$[$}doi{$]$}, 416531a {$[$}pii{$]$}},
	Au = {Bustamante CD and Nielsen R and Sawyer SA and Olsen KM and Purugganan MD and Hartl DL},
	Author = {Bustamante, Carlos D and Nielsen, Rasmus and Sawyer, Stanley A and Olsen, Kenneth M and Purugganan, Michael D and Hartl, Daniel L},
	Da = {20020404},
	Date-Added = {2006-10-06 15:57:18 -0700},
	Date-Modified = {2006-10-06 15:57:18 -0700},
	Dcom = {20020522},
	Edat = {2002/04/05 10:00},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Amino Acid Substitution, Animals, Arabidopsis/*genetics/physiology, Drosophila/genetics, Evolution, Genes, Plant, *Inbreeding, Models, Genetic, Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2002/05/25 10:01},
	Number = {6880},
	Own = {NLM},
	Pages = {531-4},
	Pl = {England},
	Pmid = {11932744},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Nature. 2002 Apr 4;416(6880):531-4.},
	Stat = {MEDLINE},
	Title = {The cost of inbreeding in Arabidopsis.},
	Volume = {416},
	Year = {2002}}

@article{Sawyer2003,
	Abstract = {One of the principal goals of population genetics is to understand the processes by which genetic variation within species (polymorphism) becomes converted into genetic differences between species (divergence). In this transformation, selective neutrality, near neutrality, and positive selection may each play a role, differing from one gene to the next. Synonymous nucleotide sites are often used as a uniform standard of comparison across genes on the grounds that synonymous sites are subject to relatively weak selective constraints and so may, to a first approximation, be regarded as neutral. Synonymous sites are also interdigitated with nonsynonymous sites and so are affected equally by genomic context and demographic factors. Hence a comparison of levels of polymorphism and divergence between synonymous sites and amino acid replacement sites in a gene is potentially informative about the magnitude of selective forces associated with amino acid replacements. We have analyzed 56 genes in which polymorphism data from D. simulans are compared with divergence from a reference strain of D. melanogaster. The framework of the analysis is Bayesian and assumes that the distribution of selective effects (Malthusian fitnesses) is Gaussian with a mean that differs for each gene. In such a model, the average scaled selection intensity (gamma = N(e)s) of amino acid replacements eligible to become polymorphic or fixed is -7.31, and the standard deviation of selective effects within each locus is 6.79 (assuming homoscedasticity across loci). For newly arising mutations of this type that occur in autosomal or X-linked genes, the average proportion of beneficial mutations is 19.7%. Among the amino acid polymorphisms in the sample, the expected average proportion of beneficial mutations is 47.7%, and among amino acid replacements that become fixed the average proportion of beneficial mutations is 94.3%. The average scaled selection intensity of fixed mutations is +5.1. The presence of positive selection is pervasive with the single exception of kl-5, a Y-linked fertility gene. We find no evidence that a significant fraction of fixed amino acid replacements is neutral or nearly neutral or that positive selection drives amino acid replacements at only a subset of the loci. These results are model dependent and we discuss possible modifications of the model that might allow more neutral and nearly neutral amino acid replacements to be fixed.},
	Address = {Department of Mathematics, Washington University, St. Louis, MO 63130, USA.},
	Aid = {10.1007/s00239-003-0022-3 {$[$}doi{$]$}},
	Au = {Sawyer SA and Kulathinal RJ and Bustamante CD and Hartl DL},
	Author = {Sawyer, Stanley A and Kulathinal, Rob J and Bustamante, Carlos D and Hartl, Daniel L},
	Da = {20040310},
	Date-Added = {2006-10-06 15:57:18 -0700},
	Date-Modified = {2006-10-06 15:57:18 -0700},
	Dcom = {20040805},
	Edat = {2004/03/11 05:00},
	Gr = {GM60035/GM/NIGMS, GM65169/GM/NIGMS},
	Jid = {0360051},
	Journal = {J Mol Evol},
	Jt = {Journal of molecular evolution.},
	Keywords = {Amino Acid Substitution, Animals, *Bayes Theorem, Comparative Study, Drosophila/*genetics, Models, Genetic, Mutation, *Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., *Selection (Genetics), X Chromosome, Y Chromosome},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/08/06 05:00},
	Number = {0022-2844 (Print)},
	Own = {NLM},
	Pages = {S154-64},
	Pl = {United States},
	Pmid = {15008412},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {J Mol Evol. 2003;57 Suppl 1:S154-64.},
	Stat = {MEDLINE},
	Title = {Bayesian analysis suggests that most amino acid replacements in Drosophila are driven by positive selection.},
	Volume = {57 Suppl 1},
	Year = {2003}}

@article{Akeyetal2004,
	Abstract = {Identifying regions of the human genome that have been targets of natural selection will provide important insights into human evolutionary history and may facilitate the identification of complex disease genes. Although the signature that natural selection imparts on DNA sequence variation is difficult to disentangle from the effects of neutral processes such as population demographic history, selective and demographic forces can be distinguished by analyzing multiple loci dispersed throughout the genome. We studied the molecular evolution of 132 genes by comprehensively resequencing them in 24 African-Americans and 23 European-Americans. We developed a rigorous computational approach for taking into account multiple hypothesis tests and demographic history and found that while many apparent selective events can instead be explained by demography, there is also strong evidence for positive or balancing selection at eight genes in the European-American population, but none in the African-American population. Our results suggest that the migration of modern humans out of Africa into new environments was accompanied by genetic adaptations to emergent selective forces. In addition, a region containing four contiguous genes on Chromosome 7 showed striking evidence of a recent selective sweep in European-Americans. More generally, our results have important implications for mapping genes underlying complex human diseases.},
	Address = {Division of Human Biology, Fred Hutchinson Cancer Research Center, Seattle, Washington, USA. jakey@fhcrc.org <jakey@fhcrc.org>},
	Aid = {10.1371/journal.pbio.0020286 {$[$}doi{$]$}},
	Au = {Akey JM and Eberle MA and Rieder MJ and Carlson CS and Shriver MD and Nickerson DA and Kruglyak L},
	Author = {Akey, Joshua M and Eberle, Michael A and Rieder, Mark J and Carlson, Christopher S and Shriver, Mark D and Nickerson, Deborah A and Kruglyak, Leonid},
	Da = {20041020},
	Date-Added = {2006-10-06 15:26:21 -0700},
	Date-Modified = {2006-11-21 10:08:21 -0800},
	Dcom = {20060523},
	Dep = {20040907},
	Edat = {2004/09/14 05:00},
	Gr = {HL66642/HL/NHLBI, HL66682/HL/NHLBI, MH59520/MH/NIMH, U01 HL69757/HL/NHLBI},
	Issn = {1545-7885 (Electronic)},
	Jid = {101183755},
	Journal = {PLoS Biol},
	Jt = {PLoS biology.},
	Keywords = {African Continental Ancestry Group, Chromosomes, Human, Pair 7, Computational Biology, European Continental Ancestry Group, Evolution, Molecular, *Genetics, Population, *Genome, Human, Humans, Models, Genetic, Models, Statistical, Polymorphism, Genetic, Polymorphism, Single Nucleotide, Population Groups, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., Selection (Genetics), Sequence Analysis, DNA, *Variation (Genetics)},
	Language = {eng},
	Mhda = {2006/05/24 09:00},
	Number = {10},
	Own = {NLM},
	Pages = {e286},
	Phst = {2004/04/23 {$[$}received{$]$}, 2004/06/25 {$[$}accepted{$]$}, 2004/09/07 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15361935},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {PLoS Biol. 2004 Oct;2(10):e286. Epub 2004 Sep 7.},
	Stat = {MEDLINE},
	Title = {Population history and natural selection shape patterns of genetic variation in 132 genes.},
	Volume = {2},
	Year = {2004}}

@article{Drake2005,
	Abstract = {Noncoding genetic variants are likely to influence human biology and disease, but recognizing functional noncoding variants is difficult. Approximately 3% of noncoding sequence is conserved among distantly related mammals, suggesting that these evolutionarily conserved noncoding regions (CNCs) are selectively constrained and contain functional variation. However, CNCs could also merely represent regions with lower local mutation rates. Here we address this issue and show that CNCs are selectively constrained in humans by analyzing HapMap genotype data. Specifically, new (derived) alleles of SNPs within CNCs are rarer than new alleles in nonconserved regions (P = 3 x 10(-18)), indicating that evolutionary pressure has suppressed CNC-derived allele frequencies. Intronic CNCs and CNCs near genes show greater allele frequency shifts, with magnitudes comparable to those for missense variants. Thus, conserved noncoding variants are more likely to be functional. Allele frequency distributions highlight selectively constrained genomic regions that should be intensively surveyed for functionally important variation.},
	Address = {Program in Genomics and Division of Endocrinology, Children's Hospital, Boston, Massachusetts 02115, USA.},
	Aid = {ng1710 {$[$}pii{$]$}, 10.1038/ng1710 {$[$}doi{$]$}},
	Au = {Drake JA and Bird C and Nemesh J and Thomas DJ and Newton-Cheh C and Reymond A and Excoffier L and Attar H and Antonarakis SE and Dermitzakis ET and Hirschhorn JN},
	Author = {Drake, Jared A and Bird, Christine and Nemesh, James and Thomas, Daryl J and Newton-Cheh, Christopher and Reymond, Alexandre and Excoffier, Laurent and Attar, Homa and Antonarakis, Stylianos E and Dermitzakis, Emmanouil T and Hirschhorn, Joel N},
	Da = {20060130},
	Date-Added = {2006-10-06 12:33:02 -0700},
	Date-Modified = {2009-02-27 14:13:22 -0500},
	Dcom = {20060404},
	Dep = {20051225},
	Edat = {2005/12/29 09:00},
	Gr = {Wellcome Trust},
	Issn = {1061-4036 (Print)},
	Jid = {9216904},
	Journal = {Nat Genet},
	Jt = {Nature genetics.},
	Keywords = {Conserved Sequence/*genetics, Gene Frequency/genetics, Humans, Mutation/*genetics, Polymorphism, Single Nucleotide/genetics, Population Groups/genetics, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, *Selection (Genetics)},
	Language = {eng},
	Mhda = {2006/04/06 09:00},
	Number = {2},
	Own = {NLM},
	Pages = {223-7},
	Phst = {2005/10/14 {$[$}received{$]$}, 2005/11/04 {$[$}accepted{$]$}, 2005/12/25 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16380714},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Nat Genet. 2006 Feb;38(2):223-7. Epub 2005 Dec 25.},
	Stat = {MEDLINE},
	Title = {Conserved noncoding sequences are selectively constrained and not mutation cold spots.},
	Volume = {38},
	Year = {2005}}

@article{Feng:2006qy,
	Abstract = {The identification of ultraconserved noncoding sequences in vertebrates has been associated with developmental regulators and DNA-binding proteins. One of the first of these was identified in the intergenic region between the Dlx-5 and Dlx-6 genes, members of the Dlx/dll homeodomain-containing protein family. In previous experiments, we showed that Sonic hedgehog treatment of forebrain neural explants results in the activation of Dlx-2 and the novel noncoding RNA (ncRNA), Evf-1. In this report, we show that the Dlx-5/6 ultraconserved region is transcribed to generate an alternatively spliced form of Evf-1, the ncRNA Evf-2. Evf-2 specifically cooperates with Dlx-2 to increase the transcriptional activity of the Dlx-5/6 enhancer in a target and homeodomain-specific manner. A stable complex containing the Evf-2 ncRNA and the Dlx-2 protein forms in vivo, suggesting that the Evf-2 ncRNA activates transcriptional activity by directly influencing Dlx-2 activity. These experiments identify a novel mechanism whereby transcription is controlled by the cooperative actions of an ncRNA and a homeodomain protein. The possibility that a subset of vertebrate ultraconserved regions may function at both the DNA and RNA level to control key developmental regulators may explain why ultraconserved sequences exhibit 90% or more conservation even after 450 million years of vertebrate evolution.},
	Address = {Program in Neurobiology and Department of Pediatrics, Children's Memorial Hospital and Feinberg School of Medicine, Northwestern University, Chicago, Illinois 60614, USA.},
	Aid = {gad.1416106 {$[$}pii{$]$}, 10.1101/gad.1416106 {$[$}doi{$]$}},
	Au = {Feng J and Bi C and Clark BS and Mady R and Shah P and Kohtz JD},
	Author = {Feng, Jianchi and Bi, Chunming and Clark, Brian S and Mady, Rina and Shah, Palak and Kohtz, Jhumku D},
	Da = {20060605},
	Date-Added = {2006-10-06 12:24:09 -0700},
	Date-Modified = {2006-10-06 12:24:09 -0700},
	Dcom = {20060628},
	Dep = {20060516},
	Edat = {2006/05/18 09:00},
	Gr = {HD044745/HD/NICHD, R21HD049875/HD/NICHD},
	Issn = {0890-9369 (Print)},
	Jid = {8711660},
	Journal = {Genes Dev},
	Jt = {Genes \& development.},
	Keywords = {Alternative Splicing, Animals, Base Sequence, Cell Line, DNA Primers, Homeodomain Proteins/*genetics, Immunoprecipitation, In Situ Hybridization, Mice, RNA/*genetics, Rats, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Transcription Factors/*genetics, *Transcription, Genetic},
	Language = {eng},
	Mhda = {2006/06/29 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {1470-84},
	Phst = {2006/05/16 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16705037},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (DNA Primers), 0 (Distal-less homeobox proteins), 0 (Homeodomain Proteins), 0 (Transcription Factors), 63231-63-0 (RNA)},
	Sb = {IM},
	So = {Genes Dev. 2006 Jun 1;20(11):1470-84. Epub 2006 May 16.},
	Stat = {MEDLINE},
	Title = {The Evf-2 noncoding RNA is transcribed from the Dlx-5/6 ultraconserved region and functions as a Dlx-2 transcriptional coactivator.},
	Volume = {20},
	Year = {2006}}

@article{Poulin:2005fj,
	Abstract = {Genomic sequence comparisons among human, mouse, and pufferfish (Takifugu rubripes (Fugu)) have revealed a set of extremely conserved noncoding sequences. While this high degree of sequence conservation suggests severe evolutionary constraint and predicts a lack of tolerance to change to retain in vivo functionality, such elements have been minimally explored experimentally. In this study, we describe the in-depth characterization of an ancient conserved enhancer, Dc2, located near the dachshund gene, which displays a human-Fugu identity of 84% over 424 basepairs (bp). In addition to this large overall conservation, we find that Dc2 is characterized by the presence of a large block of sequence (144 bp) that is completely identical among human, mouse, chicken, zebrafish, and Fugu. Through the testing of reporter vector constructs in transgenic mice, we observed that the 424-bp Dc2-conserved element is necessary and sufficient for brain tissue enhancer activity. In vivo analyses also revealed that the 144-bp 100% conserved sequence is necessary, but not sufficient, to replicate Dc2 enhancer function. However, the introduction of two separate 16-bp insertions into the highly conserved enhancer core did not cause any detectable modification of its in vivo activity. Our observations indicate that the 144-bp 100% conserved element is tolerant of change at least at the resolution of this transgenic mouse assay and suggest that purifying selection on the Dc2 sequence might not be as strong as we predicted or that some unknown property also constrains this highly conserved enhancer sequence.},
	Address = {Department of Energy Joint Genome Institute, Walnut Creek, CA 94598, USA.},
	Aid = {S0888-7543(05)00064-9 {$[$}pii{$]$}, 10.1016/j.ygeno.2005.03.003 {$[$}doi{$]$}},
	Au = {Poulin F and Nobrega MA and Plajzer-Frick I and Holt A and Afzal V and Rubin EM and Pennacchio LA},
	Author = {Poulin, Francis and Nobrega, Marcelo A and Plajzer-Frick, Ingrid and Holt, Amy and Afzal, Veena and Rubin, Edward M and Pennacchio, Len A},
	Da = {20050511},
	Date-Added = {2006-10-06 12:24:09 -0700},
	Date-Modified = {2006-10-06 12:24:09 -0700},
	Dcom = {20051006},
	Dep = {20050415},
	Edat = {2005/05/12 09:00},
	Gr = {HL 88728/HL/NHLBI},
	Issn = {0888-7543 (Print)},
	Jid = {8800135},
	Journal = {Genomics},
	Jt = {Genomics.},
	Keywords = {Animals, Conserved Sequence/*genetics, Enhancer Elements (Genetics)/*genetics, *Gene Expression Regulation, Developmental, Humans, Mice, Mice, Transgenic, Nuclear Proteins/*genetics, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., Takifugu/*genetics},
	Language = {eng},
	Mhda = {2005/10/07 09:00},
	Number = {6},
	Own = {NLM},
	Pages = {774-81},
	Phst = {2005/01/19 {$[$}received{$]$}, 2005/03/04 {$[$}revised{$]$}, 2005/03/07 {$[$}accepted{$]$}, 2005/04/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15885503},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (DACH2 protein, human), 0 (Dach2 protein, mouse), 0 (Nuclear Proteins)},
	Sb = {IM},
	So = {Genomics. 2005 Jun;85(6):774-81. Epub 2005 Apr 15.},
	Stat = {MEDLINE},
	Title = {In vivo characterization of a vertebrate ultraconserved enhancer.},
	Volume = {85},
	Year = {2005}}

@article{Tran:2006uq,
	Abstract = {MicroRNAs are short (approximately 22 nt) regulatory RNA molecules that play key roles in metazoan development and have been implicated in human disease. First discovered in Caenorhabditis elegans, over 2500 microRNAs have been isolated in metazoans and plants; it has been estimated that there may be more than a thousand microRNA genes in the human genome alone. Motivated by the experimental observation of strong conservation of the microRNA let-7 among nearly all metazoans, we developed a novel methodology to characterize the class of such strongly conserved sequences: we identified a non-redundant set of all sequences 20 to 29 bases in length that are shared among three insects: fly, bee and mosquito. Among the few hundred sequences greater than 20 bases in length are close to 40% of the 78 confirmed fly microRNAs, along with other non-coding RNAs and coding sequence.},
	Address = {Department of Biochemistry, Baylor College of Medicine, TX, USA.},
	Aid = {34/9/e65 {$[$}pii{$]$}, 10.1093/nar/gkl173 {$[$}doi{$]$}},
	Au = {Tran T and Havlak P and Miller J},
	Author = {Tran, T and Havlak, P and Miller, J},
	Da = {20060515},
	Date-Added = {2006-10-06 12:24:09 -0700},
	Date-Modified = {2006-10-06 12:24:09 -0700},
	Dcom = {20060530},
	Dep = {20060512},
	Edat = {2006/05/16 09:00},
	Gr = {1 U01 HG003273/HG/NHGRI},
	Issn = {1362-4962 (Electronic)},
	Jid = {0411011},
	Journal = {Nucleic Acids Res},
	Jt = {Nucleic acids research.},
	Keywords = {Animals, Anopheles gambiae/*genetics, Base Sequence, Bees/*genetics, Conserved Sequence, Drosophila melanogaster/*genetics, Genome, Insect, Genomics, MicroRNAs/*chemistry, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't},
	Language = {eng},
	Mhda = {2006/05/31 09:00},
	Number = {9},
	Own = {NLM},
	Pages = {e65},
	Pl = {England},
	Pmid = {16698958},
	Pst = {epublish},
	Pt = {Journal Article},
	Pubm = {Electronic},
	Rn = {0 (MicroRNAs)},
	Sb = {IM},
	So = {Nucleic Acids Res. 2006 May 12;34(9):e65.},
	Stat = {MEDLINE},
	Title = {MicroRNA enrichment among short 'ultraconserved' sequences in insects.},
	Volume = {34},
	Year = {2006}}

@article{Bejerano2006,
	Abstract = {Hundreds of highly conserved distal cis-regulatory elements have been characterized so far in vertebrate genomes. Many thousands more are predicted on the basis of comparative genomics. However, in stark contrast to the genes that they regulate, in invertebrates virtually none of these regions can be traced by using sequence similarity, leaving their evolutionary origins obscure. Here we show that a class of conserved, primarily non-coding regions in tetrapods originated from a previously unknown short interspersed repetitive element (SINE) retroposon family that was active in the Sarcopterygii (lobe-finned fishes and terrestrial vertebrates) in the Silurian period at least 410 million years ago (ref. 4), and seems to be recently active in the 'living fossil' Indonesian coelacanth, Latimeria menadoensis. Using a mouse enhancer assay we show that one copy, 0.5 million bases from the neuro-developmental gene ISL1, is an enhancer that recapitulates multiple aspects of Isl1 expression patterns. Several other copies represent new, possibly regulatory, alternatively spliced exons in the middle of pre-existing Sarcopterygian genes. One of these, a more than 200-base-pair ultraconserved region, 100% identical in mammals, and 80% identical to the coelacanth SINE, contains a 31-amino-acid-residue alternatively spliced exon of the messenger RNA processing gene PCBP2 (ref. 6). These add to a growing list of examples in which relics of transposable elements have acquired a function that serves their host, a process termed 'exaptation', and provide an origin for at least some of the many highly conserved vertebrate-specific genomic sequences.},
	Address = {Center for Biomolecular Science and Engineering, University of California Santa Cruz, Santa Cruz, California 95064, USA. jill@soe.ucsc.edu},
	Aid = {nature04696 {$[$}pii{$]$}, 10.1038/nature04696 {$[$}doi{$]$}},
	Au = {Bejerano G and Lowe CB and Ahituv N and King B and Siepel A and Salama SR and Rubin EM and Kent WJ and Haussler D},
	Author = {Bejerano, Gill and Lowe, Craig B and Ahituv, Nadav and King, Bryan and Siepel, Adam and Salama, Sofie R and Rubin, Edward M and Kent, W James and Haussler, David},
	Da = {20060504},
	Date-Added = {2006-10-06 12:06:03 -0700},
	Date-Modified = {2006-10-06 12:06:16 -0700},
	Dcom = {20060531},
	Dep = {20060416},
	Edat = {2006/04/21 09:00},
	Issn = {1476-4687 (Electronic)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {Animals, Base Sequence, Conserved Sequence/*genetics, Enhancer Elements (Genetics)/*genetics, Exons/*genetics, Fossils, Gene Expression Regulation, Developmental, Humans, Organ Specificity, Phylogeny, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Retroelements/*genetics, Short Interspersed Nucleotide Elements/genetics, Vertebrates/genetics},
	Language = {eng},
	Mhda = {2006/06/01 09:00},
	Number = {7089},
	Own = {NLM},
	Pages = {87-90},
	Phst = {2005/11/27 {$[$}received{$]$}, 2006/03/02 {$[$}accepted{$]$}, 2006/04/16 {$[$}aheadofprint{$]$}},
	Pl = {England},
	Pmid = {16625209},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (Retroelements)},
	Sb = {IM},
	So = {Nature. 2006 May 4;441(7089):87-90. Epub 2006 Apr 16.},
	Stat = {MEDLINE},
	Title = {A distal enhancer and an ultraconserved exon are derived from a novel retroposon.},
	Volume = {441},
	Year = {2006}}

@article{Bejerano2004,
	Abstract = {There are 481 segments longer than 200 base pairs (bp) that are absolutely conserved (100% identity with no insertions or deletions) between orthologous regions of the human, rat, and mouse genomes. Nearly all of these segments are also conserved in the chicken and dog genomes, with an average of 95 and 99% identity, respectively. Many are also significantly conserved in fish. These ultraconserved elements of the human genome are most often located either overlapping exons in genes involved in RNA processing or in introns or nearby genes involved in the regulation of transcription and development. Along with more than 5000 sequences of over 100 bp that are absolutely conserved among the three sequenced mammals, these represent a class of genetic elements whose functions and evolutionary origins are yet to be determined, but which are more highly conserved between these species than are proteins and appear to be essential for the ontogeny of mammals and other vertebrates.},
	Address = {Department of Biomolecular Engineering, University of California Santa Cruz, Santa Cruz, CA 95064, USA. jill@soe.ucsc.edu},
	Aid = {10.1126/science.1098119 {$[$}doi{$]$}, 1098119 {$[$}pii{$]$}},
	Au = {Bejerano G and Pheasant M and Makunin I and Stephen S and Kent WJ and Mattick JS and Haussler D},
	Author = {Bejerano, Gill and Pheasant, Michael and Makunin, Igor and Stephen, Stuart and Kent, W James and Mattick, John S and Haussler, David},
	Da = {20040528},
	Date-Added = {2006-10-06 12:06:03 -0700},
	Date-Modified = {2006-10-06 12:06:29 -0700},
	Dcom = {20040615},
	Dep = {20040506},
	Edat = {2004/05/08 05:00},
	Gr = {1P41HG02371/HG/NHGRI},
	Issn = {1095-9203 (Electronic)},
	Jid = {0404511},
	Journal = {Science},
	Jt = {Science.},
	Keywords = {Alternative Splicing, Animals, Base Sequence, Chickens/genetics, Computational Biology, *Conserved Sequence, DNA, Intergenic, Dogs/genetics, Evolution, Molecular, Exons, Gene Expression Regulation, Genes, Genome, *Genome, Human, Humans, Introns, Mice/genetics, Molecular Sequence Data, Mutation, Nucleic Acid Conformation, RNA/chemistry/genetics/metabolism, Rats/genetics, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Takifugu/genetics},
	Language = {eng},
	Lr = {20051117},
	Mhda = {2004/06/16 05:00},
	Number = {5675},
	Own = {NLM},
	Pages = {1321-5},
	Phst = {2004/05/06 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15131266},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (DNA, Intergenic), 63231-63-0 (RNA)},
	Sb = {IM},
	So = {Science. 2004 May 28;304(5675):1321-5. Epub 2004 May 6.},
	Stat = {MEDLINE},
	Title = {Ultraconserved elements in the human genome.},
	Volume = {304},
	Year = {2004}}

@book{fisher1930,
	Address = {Oxford},
	Author = {R. A. Fisher},
	Date-Added = {2006-08-28 18:25:40 -0700},
	Date-Modified = {2006-08-28 18:26:45 -0700},
	Publisher = {Clarendon Press},
	Title = {The Genetical Theory of Natural Selection},
	Year = {1930}}

@article{viterbi1967,
	Author = {Viterbi, A. J.},
	Date-Added = {2006-08-24 15:53:34 -0700},
	Date-Modified = {2006-08-24 15:54:36 -0700},
	Journal = {IEEE Trans. Inf. Theory},
	Pages = {260-269},
	Title = {Error bounds for convolutional codes and an asymptotically optimum decoding algorithm},
	Volume = {IT-13},
	Year = {1967}}

@book{wright1969,
	Address = {Chicago},
	Author = {Wright, S},
	Date-Added = {2006-08-24 15:36:54 -0700},
	Date-Modified = {2006-08-24 15:39:56 -0700},
	Publisher = {University of Chicago Press},
	Title = {Evolution and the Genetics of Populations},
	Volume = {Vol. 2: The Theory of Gene Frequencies},
	Year = {1969}}

@article{baldietal1994,
	Abstract = {Hidden Markov model (HMM) techniques are used to model families of biological sequences. A smooth and convergent algorithm is introduced to iteratively adapt the transition and emission parameters of the models from the examples in a given family. The HMM approach is applied to three protein families: globins, immunoglobulins, and kinases. In all cases, the models derived capture the important statistical characteristics of the family and can be used for a number of tasks, including multiple alignments, motif detection, and classification. For K sequences of average length N, this approach yields an effective multiple-alignment algorithm which requires O(KN2) operations, linear in the number of sequences.},
	Affiliation = {Division of Biology, California Institute of Technology, Pasadena 91125.},
	Au = {Baldi P and Chauvin Y and Hunkapiller T and McClure MA},
	Author = {Baldi, P and Chauvin, Y and Hunkapiller, T and McClure, M A},
	Da = {19940308},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {19940308},
	Edat = {1994/02/01},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Algorithms, Amino Acid Sequence, Animals, Comparative Study, Globins/genetics, Humans, Immunoglobulins/genetics, *Markov Chains, *Models, Genetic, Molecular Sequence Data, Protein Kinases/genetics, Proteins/*genetics, Sequence Alignment/*methods/statistics \& numerical data, Sequence Homology, Amino Acid},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1994/02/01 00:01},
	Number = {3},
	Own = {NLM},
	Pages = {1059-63},
	Pl = {UNITED STATES},
	Pmid = {8302831},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Immunoglobulins)},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 1994 Feb 1;91(3):1059-63.},
	Stat = {MEDLINE},
	Title = {Hidden Markov models of biological primary sequence information.},
	Volume = {91},
	Year = {1994}}

@article{churchill1989,
	Abstract = {The composition of naturally occurring DNA sequences is often strikingly heterogeneous. In this paper, the DNA sequence is viewed as a stochastic process with local compositional properties determined by the states of a hidden Markov chain. The model used is a discrete-state, discrete-outcome version of a general model for non-stationary time series proposed by Kitagawa (1987). A smoothing algorithm is described which can be used to reconstruct the hidden process and produce graphic displays of the compositional structure of a sequence. The problem of parameter estimation is approached using likelihood methods and an EM algorithm for approximating the maximum likelihood estimate is derived. The methods are applied to sequences from yeast mitochondrial DNA, human and mouse mitochondrial DNAs, a human X chromosomal fragment and the complete genome of bacteriophage lambda.},
	Aid = {S0092-8240(89)80049-7 {$[$}pii{$]$}},
	Au = {Churchill GA},
	Author = {Churchill, G A},
	Da = {19890602},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {19890602},
	Edat = {1989/01/01},
	Issn = {0092-8240 (Print)},
	Jid = {0401404},
	Journal = {Bull Math Biol},
	Jt = {Bulletin of mathematical biology.},
	Keywords = {*Base Sequence, DNA/*genetics, *Models, Genetic, Models, Theoretical, *Probability, *Stochastic Processes},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1989/01/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {79-94},
	Pl = {UNITED STATES},
	Pmid = {2706403},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Bull Math Biol. 1989;51(1):79-94.},
	Stat = {MEDLINE},
	Title = {Stochastic models for heterogeneous DNA sequences.},
	Volume = {51},
	Year = {1989}}

@article{felsensteinChurchill1996,
	Abstract = {The method of Hidden Markov Models is used to allow for unequal and unknown evolutionary rates at different sites in molecular sequences. Rates of evolution at different sites are assumed to be drawn from a set of possible rates, with a finite number of possibilities. The overall likelihood of phylogeny is calculated as a sum of terms, each term being the probability of the data given a particular assignment of rates to sites, times the prior probability of that particular combination of rates. The probabilities of different rate combinations are specified by a stationary Markov chain that assigns rate categories to sites. While there will be a very large number of possible ways of assigning rates to sites, a simple recursive algorithm allows the contributions to the likelihood from all possible combinations of rates to be summed, in a time proportional to the number of different rates at a single site. Thus with three rates, the effort involved is no greater than three times that for a single rate. This "Hidden Markov Model" method allows for rates to differ between sites and for correlations between the rates of neighboring sites. By summing over all possibilities it does not require us to know the rates at individual sites. However, it does not allow for correlation of rates at nonadjacent sites, nor does it allow for a continuous distribution of rates over sites. It is shown how to use the Newton-Raphson method to estimate branch lengths of a phylogeny and to infer from a phylogeny what assignment of rates to sites has the largest posterior probability. An example is given using beta-hemoglobin DNA sequences in eight mammal species; the regions of high and low evolutionary rates are inferred and also the average length of patches of similar rates.},
	Affiliation = {Department of Genetics, University of Washington, Seattle 98195, USA.},
	Au = {Felsenstein J and Churchill GA},
	Author = {Felsenstein, J and Churchill, G A},
	Da = {19960320},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {19960320},
	Edat = {1996/01/01},
	Gr = {2 R55 GM41716-04/GM/NIGMS},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {Animals, Base Sequence, *Computer Simulation, *Evolution, Molecular, Humans, Markov Chains, Molecular Sequence Data, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1996/01/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {93-104},
	Pl = {UNITED STATES},
	Pmid = {8583911},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	Si = {GENBANK/J03643},
	So = {Mol Biol Evol. 1996 Jan;13(1):93-104.},
	Stat = {MEDLINE},
	Title = {A Hidden Markov Model approach to variation among sites in rate of evolution.},
	Volume = {13},
	Year = {1996}}

@article{siepeletal2005,
	Abstract = {We have conducted a comprehensive search for conserved elements in vertebrate genomes, using genome-wide multiple alignments of five vertebrate species (human, mouse, rat, chicken, and Fugu rubripes). Parallel searches have been performed with multiple alignments of four insect species (three species of Drosophila and Anopheles gambiae), two species of Caenorhabditis, and seven species of Saccharomyces. Conserved elements were identified with a computer program called phastCons, which is based on a two-state phylogenetic hidden Markov model (phylo-HMM). PhastCons works by fitting a phylo-HMM to the data by maximum likelihood, subject to constraints designed to calibrate the model across species groups, and then predicting conserved elements based on this model. The predicted elements cover roughly 3%-8% of the human genome (depending on the details of the calibration procedure) and substantially higher fractions of the more compact Drosophila melanogaster (37%-53%), Caenorhabditis elegans (18%-37%), and Saccharaomyces cerevisiae (47%-68%) genomes. From yeasts to vertebrates, in order of increasing genome size and general biological complexity, increasing fractions of conserved bases are found to lie outside of the exons of known protein-coding genes. In all groups, the most highly conserved elements (HCEs), by log-odds score, are hundreds or thousands of bases long. These elements share certain properties with ultraconserved elements, but they tend to be longer and less perfectly conserved, and they overlap genes of somewhat different functional categories. In vertebrates, HCEs are associated with the 3' UTRs of regulatory genes, stable gene deserts, and megabase-sized regions rich in moderately conserved noncoding sequences. Noncoding HCEs also show strong statistical evidence of an enrichment for RNA secondary structure.},
	Affiliation = {Center for Biomolecular Science and Engineering, University of California, Santa Cruz, Santa Cruz, California 95064, USA. acs@soe.ucsc.edu},
	Aid = {10.1101/gr.3715005 {$[$}doi{$]$}},
	Au = {Siepel A and Bejerano G and Pedersen JS and Hinrichs AS and Hou M and Rosenbloom K and Clawson H and Spieth J and Hillier LW and Richards S and Weinstock GM and Wilson RK and Gibbs RA and Kent WJ and Miller W and Haussler D},
	Author = {Siepel, Adam and Bejerano, Gill and Pedersen, Jakob S and Hinrichs, Angie S and Hou, Minmei and Rosenbloom, Kate and Clawson, Hiram and Spieth, John and Hillier, Ladeana W and Richards, Stephen and Weinstock, George M and Wilson, Richard K and Gibbs, Richard A and Kent, W James and Miller, Webb and Haussler, David},
	Da = {20050803},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {20051114},
	Dep = {20050715},
	Edat = {2005/07/19 09:00},
	Gr = {IP41HG02371/HG/NHGRI},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research.},
	Keywords = {3' Untranslated Regions, Animals, Base Pairing/genetics, Base Sequence, Caenorhabditis elegans/genetics, *Conserved Sequence, DNA, Intergenic, *Evolution, Molecular, Genome, Humans, Insects/*genetics, Molecular Sequence Data, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Saccharomyces/genetics, Vertebrates/*genetics, Yeasts/*genetics},
	Language = {eng},
	Mhda = {2005/11/15 09:00},
	Number = {8},
	Own = {NLM},
	Pages = {1034-50},
	Phst = {2005/07/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16024819},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Rn = {0 (DNA, Intergenic)},
	Sb = {IM},
	So = {Genome Res. 2005 Aug;15(8):1034-50. Epub 2005 Jul 15.},
	Stat = {MEDLINE},
	Title = {Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes.},
	Volume = {15},
	Year = {2005}}

@article{siepelHaussler2004,
	Abstract = {A few models have appeared in recent years that consider not only the way substitutions occur through evolutionary history at each site of a genome, but also the way the process changes from one site to the next. These models combine phylogenetic models of molecular evolution, which apply to individual sites, and hidden Markov models, which allow for changes from site to site. Besides improving the realism of ordinary phylogenetic models, they are potentially very powerful tools for inference and prediction--for example, for gene finding or prediction of secondary structure. In this paper, we review progress on combined phylogenetic and hidden Markov models and present some extensions to previous work. Our main result is a simple and efficient method for accommodating higher-order states in the HMM, which allows for context-dependent models of substitution--that is, models that consider the effects of neighboring bases on the pattern of substitution. We present experimental results indicating that higher-order states, autocorrelated rates, and multiple functional categories all lead to significant improvements in the fit of a combined phylogenetic and hidden Markov model, with the effect of higher-order states being particularly pronounced.},
	Affiliation = {Center for Biomolecular Science and Engineering, University of California, 1156 High Street, Santa Cruz, CA 95064, USA. acs@soe.ucsc.edu},
	Aid = {10.1089/1066527041410472 {$[$}doi{$]$}},
	Au = {Siepel A and Haussler D},
	Author = {Siepel, Adam and Haussler, David},
	Da = {20040802},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {20040826},
	Edat = {2004/08/03 05:00},
	Gr = {1P41 HG 02371/HG/NHGRI},
	Issn = {1066-5277 (Print)},
	Jid = {9433358},
	Journal = {J Comput Biol},
	Jt = {Journal of computational biology : a journal of computational molecular cell biology.},
	Keywords = {Computational Biology/*methods/statistics \& numerical data, Genomics/methods/statistics \& numerical data, Likelihood Functions, *Markov Chains, Phylogeny, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., Sequence Analysis, DNA/*statistics \& numerical data, Sequence Analysis, Protein/*statistics \& numerical data},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/08/27 05:00},
	Number = {2-3},
	Own = {NLM},
	Pages = {413-28},
	Pl = {United States},
	Pmid = {15285899},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {J Comput Biol. 2004;11(2-3):413-28.},
	Stat = {MEDLINE},
	Title = {Combining phylogenetic and hidden Markov models in biosequence analysis.},
	Volume = {11},
	Year = {2004}}

@article{yang1995,
	Abstract = {We describe a model for the evolution of DNA sequences by nucleotide substitution, whereby nucleotide sites in the sequence evolve over time, whereas the rates of substitution are variable and correlated over sites. The temporal process used to describe substitutions between nucleotides is a continuous-time Markov process, with the four nucleotides as the states. The spatial process used to describe variation and dependence of substitution rates over sites is based on a serially correlated gamma distribution, i.e., an auto-gamma model assuming Markov-dependence of rates at adjacent sites. To achieve computational efficiency, we use several equal-probability categories to approximate the gamma distribution, and the result is an auto-discrete-gamma model for rates over sites. Correlation of rates at sites then is modeled by the Markov chain transition of rates at adjacent sites from one rate category to another, the states of the chain being the rate categories. Two versions of nonparametric models, which place no restrictions on the distributional forms of rates for sites, also are considered, assuming either independence or Markov dependence. The models are applied to data of a segment of mitochondrial genome from nine primate species. Model parameters are estimated by the maximum likelihood method, and models are compared by the likelihood ratio test. Tremendous variation of rates among sites in the sequence is revealed by the analyses, and when rate differences for different codon positions are appropriately accounted for in the models, substitution rates at adjacent sites are found to be strongly (positively) correlated. Robustness of the results to uncertainty of the phylogenetic tree linking the species is examined.},
	Affiliation = {Department of Zoology, Natural History Museum, London, United Kingdom.},
	Au = {Yang Z},
	Author = {Yang, Z},
	Da = {19950518},
	Date-Added = {2006-08-24 15:19:57 -0700},
	Date-Modified = {2006-08-24 15:19:57 -0700},
	Dcom = {19950518},
	Edat = {1995/02/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Codon/genetics, DNA, Mitochondrial/*genetics, *Evolution, Likelihood Functions, Markov Chains, *Models, Genetic, Primates/genetics, Research Support, Non-U.S. Gov't, Variation (Genetics)/*physiology},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1995/02/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {993-1005},
	Pl = {UNITED STATES},
	Pmid = {7713447},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Codon)},
	Sb = {IM},
	So = {Genetics. 1995 Feb;139(2):993-1005.},
	Stat = {MEDLINE},
	Title = {A space-time process model for the evolution of DNA sequences.},
	Volume = {139},
	Year = {1995}}

@conference{haussleretal1993,
	Author = {Haussler, D. and Krogh, A. and Mian, I. S. and Sjolander, K},
	Booktitle = {Proceeding of the Twenty-Sixth Hawaii International Conference on System Sciences. IEEE, Los Alamitos, Calif.},
	Date-Added = {2006-08-24 15:14:25 -0700},
	Date-Modified = {2006-08-24 15:16:38 -0700},
	Editor = {T. N. Mudge and V. Milutinovic and L. Hunter},
	Title = {Protein modeling using hidden Markov models: analysis of globins},
	Year = {1993}}

@article{baumetal1970,
	Author = {Baum, L.E. and Petrie, T. and Soules, G. and Weiss, N.},
	Date-Added = {2006-08-24 15:05:19 -0700},
	Date-Modified = {2006-08-24 15:06:37 -0700},
	Journal = {Ann. Math. Stat.},
	Pages = {164-171},
	Title = {A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains},
	Volume = {41},
	Year = {1970}}

@article{baumPetrie1966,
	Author = {Baum, L. E. and Petrie, T.},
	Date-Added = {2006-08-24 15:04:00 -0700},
	Date-Modified = {2006-08-24 15:05:12 -0700},
	Journal = {Ann. Math. Stat.},
	Pages = {1554-1563},
	Title = {Statistical inference for probabilistic functions of finite state Markov chains},
	Volume = {37},
	Year = {1966}}

@article{innanKim2004,
	Abstract = {The process of strong artificial selection during a domestication event is modeled, and its effect on the pattern of DNA polymorphism is investigated. The model also considers population bottleneck during domestication. Artificial selection during domestication is different from a regular selective sweep because artificial selection acts on alleles that may have been neutral variants before domestication. Therefore, the fixation of such a beneficial allele does not always wipe out DNA variation in the surrounding region. The amount by which variation is reduced largely depends on the initial frequency of the beneficial allele, p. As a consequence, p has a strong effect on the likelihood of detecting the signature of selection during domestication from patterns of polymorphism. These theoretical results are discussed in light of data collected from maize. Although the main focus of this article is on domestication, this model can also be generalized to describe selective sweeps from standing genetic variation.},
	Affiliation = {Human Genetics Center, School of Public Health, University of Texas Health Science Center, Houston, TX 77030, USA. hideki.innan@uth.tmc.edu},
	Aid = {0401720101 {$[$}pii{$]$}},
	Au = {Innan H and Kim Y},
	Author = {Innan, Hideki and Kim, Yuseob},
	Da = {20040721},
	Date-Added = {2006-08-24 11:03:29 -0700},
	Date-Modified = {2006-08-24 11:03:29 -0700},
	Dcom = {20040826},
	Dep = {20040712},
	Edat = {2004/07/14 05:00},
	Gr = {2R01 GM51932-06A1/GM/NIGMS},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Alleles, Crops, Agricultural/genetics, Genetics, Population, Models, Genetic, *Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, P.H.S., *Selection (Genetics), Zea mays/*genetics},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/08/27 05:00},
	Number = {29},
	Own = {NLM},
	Pages = {10667-72},
	Phst = {2004/07/12 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15249682},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 2004 Jul 20;101(29):10667-72. Epub 2004 Jul 12.},
	Stat = {MEDLINE},
	Title = {Pattern of polymorphism after strong artificial selection in a domestication event.},
	Volume = {101},
	Year = {2004}}

@article{kim2006,
	Abstract = {The allele frequency of a neutral variant in a population is pushed either upward or downward by directional selection on a linked beneficial mutation ("selective sweeps"). DNA sequences sampled after the fixation of the beneficial allele thus contain an excess of rare neutral alleles. This study investigates the allele frequency distribution under selective sweep models using analytic approximation and simulation. First, given a single selective sweep at a fixed time, I derive an expression for the sampling probabilities of neutral mutants. This solution can be used to estimate the time of the fixation of a beneficial allele from sequence data. Next, I obtain an approximation to mean allele frequencies under recurrent selective sweeps. Under recurrent sweeps, the frequency spectrum is skewed toward rare alleles. However, the excess of high-frequency derived alleles, previously shown to be a signature of single selective sweeps, disappears with recurrent sweeps. It is shown that, using this approximation and multilocus polymorphism data, genomewide parameters of directional selection can be estimated.},
	Affiliation = {Department of Biology, University of Rochester, Rochester, New York 14620, USA. yuseob.kim@asu.edu},
	Aid = {10.1534/genetics.105.048447 {$[$}doi{$]$}},
	Au = {Kim Y},
	Author = {Kim, Yuseob},
	Da = {20060323},
	Date-Added = {2006-08-24 11:03:29 -0700},
	Date-Modified = {2006-08-24 11:03:30 -0700},
	Dep = {20051215},
	Edat = {2005/12/20 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Language = {eng},
	Mhda = {2005/12/20 09:00},
	Number = {3},
	Own = {NLM},
	Pages = {1967-78},
	Phst = {2005/12/15 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {16361239},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genetics. 2006 Mar;172(3):1967-78. Epub 2005 Dec 15.},
	Stat = {In-Process},
	Title = {Allele frequency distribution under recurrent selective sweeps.},
	Volume = {172},
	Year = {2006}}

@article{kimNielsen2004,
	Abstract = {The hitchhiking effect of a beneficial mutation, or a selective sweep, generates a unique distribution of allele frequencies and spatial distribution of polymorphic sites. A composite-likelihood test was previously designed to detect these signatures of a selective sweep, solely on the basis of the spatial distribution and marginal allele frequencies of polymorphisms. As an excess of linkage disequilibrium (LD) is also known to be a strong signature of a selective sweep, we investigate how much statistical power is increased by the inclusion of information regarding LD. The expected pattern of LD is predicted by a genealogical approach. Both theory and simulation suggest that strong LD is generated in narrow regions at both sides of the location of beneficial mutation. However, a lack of LD is expected across the two sides. We explore various ways to detect this signature of selective sweeps by statistical tests. A new composite-likelihood method is proposed to incorporate information regarding LD. This method enables us to detect selective sweeps and estimate the parameters of the selection model better than the previous composite-likelihood method that does not take LD into account. However, the improvement made by including LD is rather small, suggesting that most of the relevant information regarding selective sweeps is captured by the spatial distribution and marginal allele frequencies of polymorphisms.},
	Affiliation = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA. ykim@mail.rochester.edu},
	Aid = {167/3/1513 {$[$}pii{$]$}},
	Au = {Kim Y and Nielsen R},
	Author = {Kim, Yuseob and Nielsen, Rasmus},
	Da = {20040728},
	Date-Added = {2006-08-24 11:03:29 -0700},
	Date-Modified = {2006-08-24 11:03:30 -0700},
	Dcom = {20050224},
	Edat = {2004/07/29 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Comparative Study, Computer Simulation, Gene Frequency, *Genetics, Population, Haplotypes/genetics, Likelihood Functions, *Linkage Disequilibrium, *Models, Genetic, Mutation/genetics, Polymorphism, Genetic, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2005/02/25 09:00},
	Number = {3},
	Own = {NLM},
	Pages = {1513-24},
	Pl = {United States},
	Pmid = {15280259},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2004 Jul;167(3):1513-24.},
	Stat = {MEDLINE},
	Title = {Linkage disequilibrium as a signature of selective sweeps.},
	Volume = {167},
	Year = {2004}}

@article{nielsenetal2005,
	Abstract = {Detecting selective sweeps from genomic SNP data is complicated by the intricate ascertainment schemes used to discover SNPs, and by the confounding influence of the underlying complex demographics and varying mutation and recombination rates. Current methods for detecting selective sweeps have little or no robustness to the demographic assumptions and varying recombination rates, and provide no method for correcting for ascertainment biases. Here, we present several new tests aimed at detecting selective sweeps from genomic SNP data. Using extensive simulations, we show that a new parametric test, based on composite likelihood, has a high power to detect selective sweeps and is surprisingly robust to assumptions regarding recombination rates and demography (i.e., has low Type I error). Our new test also provides estimates of the location of the selective sweep(s) and the magnitude of the selection coefficient. To illustrate the method, we apply our approach to data from the Seattle SNP project and to Chromosome 2 data from the HapMap project. In Chromosome 2, the most extreme signal is found in the lactase gene, which previously has been shown to be undergoing positive selection. Evidence for selective sweeps is also found in many other regions, including genes known to be associated with disease risk such as DPP10 and COL4A3.},
	Affiliation = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA. rasmus@binf.ku.dk},
	Aid = {10.1101/gr.4252305 {$[$}doi{$]$}},
	Au = {Nielsen R and Williamson S and Kim Y and Hubisz MJ and Clark AG and Bustamante C},
	Author = {Nielsen, Rasmus and Williamson, Scott and Kim, Yuseob and Hubisz, Melissa J and Clark, Andrew G and Bustamante, Carlos},
	Da = {20051027},
	Date-Added = {2006-08-24 11:03:29 -0700},
	Date-Modified = {2006-08-24 11:03:30 -0700},
	Dcom = {20060502},
	Edat = {2005/10/28 09:00},
	Gr = {HG003229/HG/NHGRI},
	Issn = {1088-9051 (Print)},
	Jid = {9518021},
	Journal = {Genome Res},
	Jt = {Genome research.},
	Keywords = {African Americans/genetics, Comparative Study, Computer Simulation, European Continental Ancestry Group/genetics, Genome, Human/*genetics, Genomics/methods, Haplotypes/genetics, Humans, *Models, Genetic, Polymorphism, Single Nucleotide/*genetics, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2006/05/04 09:00},
	Number = {11},
	Own = {NLM},
	Pages = {1566-75},
	Pl = {United States},
	Pmid = {16251466},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genome Res. 2005 Nov;15(11):1566-75.},
	Stat = {MEDLINE},
	Title = {Genomic scans for selective sweeps using SNP data.},
	Volume = {15},
	Year = {2005}}

@article{crumpGillespie1977,
	Au = {Crump KS and Gillespie JH},
	Author = {Crump, K S and Gillespie, J H},
	Da = {19771229},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19771229},
	Edat = {1977/08/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {*Alleles, Animals, Gene Frequency, *Genetics, Population, Humans, Models, Biological, Mutation},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1977/08/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {10-20},
	Pl = {UNITED STATES},
	Pmid = {918870},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1977 Aug;12(1):10-20.},
	Stat = {MEDLINE},
	Title = {Geographical distribution of a neutral allele considered as a branching process.},
	Volume = {12},
	Year = {1977}}

@article{ewensGillespie1974,
	Aid = {0040-5809(74)90030-6 {$[$}pii{$]$}},
	Au = {Ewens WJ and Gillespie JH},
	Author = {Ewens, W J and Gillespie, J H},
	Da = {19750113},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19750113},
	Edat = {1974/08/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {*Alleles, Gene Frequency, *Genetics, Population, Mathematics, *Models, Theoretical, Mutation, Probability},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1974/08/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {35-57},
	Pl = {UNITED STATES},
	Pmid = {4417325},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1974 Aug;6(1):35-57.},
	Stat = {MEDLINE},
	Title = {Some simulation results for the neutral allele model, with interpretations.},
	Volume = {6},
	Year = {1974}}

@article{gillespie1972,
	Aid = {0040-5809(72)90001-9 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19731114},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19731114},
	Edat = {1972/09/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {*Alleles, Environment, *Gene Frequency, Genotype, Haploidy, Models, Biological, Probability, Selection (Genetics)},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1972/09/01 00:01},
	Number = {3},
	Own = {NLM},
	Pages = {241-8},
	Pl = {UNITED STATES},
	Pmid = {4667084},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1972 Sep;3(3):241-8.},
	Stat = {MEDLINE},
	Title = {The effects of stochastic environments on allele frequencies in natural populations.},
	Volume = {3},
	Year = {1972}}

@article{gillespie1974,
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19740731},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19740731},
	Edat = {1974/03/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Alleles, Animals, Gene Frequency, Genotype, Haploidy, Humans, Models, Biological, Population Density, Probability, *Selection (Genetics), *Variation (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1974/03/01 00:01},
	Number = {3},
	Own = {NLM},
	Pages = {601-6},
	Pl = {UNITED STATES},
	Pmid = {4833578},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 1974 Mar;76(3):601-6.},
	Stat = {MEDLINE},
	Title = {Nautural selection for within-generation variance in offspring number.},
	Volume = {76},
	Year = {1974}}

@article{gillespie1975,
	Abstract = {In the classical model of genetic drift in population genetics theory, use is made of a hypothetical "infinite-gametic pool". If, instead, the gametic pool is determined by the random number of offspring per individual, a new form of natural selection acting on the variance in offspring number occurs. A diffusion model of this selection process is derived and some of its properties are explored. It is shown that, independent of the sampling scheme used, the diffusion equation has the drift coefficient M(p) = p(1-p) (mul--mu2 + sigma2e2--sigma2el) and the diffusion coefficient v(p) equals p(1-p) [psigma2e2 + (l--p)sigma2el]. It is also pointed out that the Direct Product Branching process model of genetic drift introduces a non-biological interaction between individuals and is thus inappropriate for modeling natural selection.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19760320},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19760320},
	Edat = {1975/10/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Alleles, *Evolution, Genetics, Population, *Haploidy, *Models, Biological, *Population Density, *Variation (Genetics)},
	Language = {eng},
	Lr = {20011114},
	Mhda = {1975/10/01 00:01},
	Number = {2},
	Oid = {NASA: 76093069},
	Own = {NLM},
	Pages = {403-13},
	Pl = {UNITED STATES},
	Pmid = {1205132},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 1975 Oct;81(2):403-13.},
	Stat = {MEDLINE},
	Title = {Natural selection for within-generation variance in offspring number II. Discrite haploid models.},
	Volume = {81},
	Year = {1975}}

@article{gillespie1976,
	Aid = {0040-5809(76)90017-4 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19761230},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19761230},
	Edat = {1976/10/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Environment, *Genetics, Population, Humans, *Models, Biological, *Population Dynamics, *Residential Mobility},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1976/10/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {227-38},
	Pl = {UNITED STATES},
	Pmid = {982331},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1976 Oct;10(2):227-38.},
	Stat = {MEDLINE},
	Title = {The role of migration in the genetic structure of populations in temporally and spatially varying environments. II. Island models.},
	Volume = {10},
	Year = {1976}}

@article{gillespie1977,
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19770630},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19770630},
	Edat = {1977/03/31},
	Issn = {0028-0836 (Print)},
	Jid = {0410462},
	Journal = {Nature},
	Jt = {Nature.},
	Keywords = {*Alleles, Environment, *Genetics, Population, Models, Biological, Selection (Genetics)},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1977/03/31 00:01},
	Number = {5601},
	Own = {NLM},
	Pages = {443-5},
	Pl = {ENGLAND},
	Pmid = {859613},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Nature. 1977 Mar 31;266(5601):443-5.},
	Stat = {MEDLINE},
	Title = {Sampling theory for alleles in a random environment.},
	Volume = {266},
	Year = {1977}}

@article{gillespie1978,
	Aid = {0040-5809(78)90002-3 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19790425},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19790425},
	Edat = {1978/08/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Enzymes/*genetics, Mathematics, *Models, Biological, *Variation (Genetics)},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1978/08/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {1-45},
	Pl = {UNITED STATES},
	Pmid = {741392},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Enzymes)},
	Sb = {IM},
	So = {Theor Popul Biol. 1978 Aug;14(1):1-45.},
	Stat = {MEDLINE},
	Title = {A general model to account for enzyme variation in natural populations. V. The SAS--CFF model.},
	Volume = {14},
	Year = {1978}}

@article{gillespie1980,
	Aid = {0040-5809(80)90002-7 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19801021},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19801021},
	Edat = {1980/04/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Alleles, Gene Frequency, Homozygote, *Models, Genetic, *Selection (Genetics)},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1980/04/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {129-40},
	Pl = {UNITED STATES},
	Pmid = {7404437},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1980 Apr;17(2):129-40.},
	Stat = {MEDLINE},
	Title = {The stationary distribution of an asymmetrical model of selection in a random environment.},
	Volume = {17},
	Year = {1980}}

@article{gillespie1981,
	Abstract = {A diffusion model of the modification of mutation rates at a heterotic locus in a finite population is examined. An asymptotic analysis assuming strong selection and weak linkage shows that selection can operate on mutation rates in this setting. There exists a favored mutation rate which is a function only of the equilibrium allele frequency of the heterotic locus and the population size. It is independent of the strength of selection at the heterotoxic locus. Computer simulations are also provided to show that this form of natural selection can occur.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19810820},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19810820},
	Edat = {1981/04/01},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Computers, *Evolution, *Models, Biological, *Mutation, Selection (Genetics)},
	Language = {eng},
	Lr = {20011114},
	Mhda = {1981/04/01 00:01},
	Number = {4},
	Oid = {NASA: 81223896},
	Own = {NLM},
	Pages = {2452-4},
	Pl = {UNITED STATES},
	Pmid = {6941302},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 1981 Apr;78(4):2452-4.},
	Stat = {MEDLINE},
	Title = {Evolution of the mutation rate at a heterotic locus.},
	Volume = {78},
	Year = {1981}}

@article{gillespie1983,
	Abstract = {If the fitnesses of n haploid alleles in a finite population are assigned at random and if the alleles can mutate to one another, and if the population is initially fixed for the kth most fit allele, then the mean number of substitutions that will occur before the most fit allele is fixed is shown to be (formula; see text) when selection is strong and mutation is weak. This result is independent of the parameters that went into the model. The result is used to provide a partial explanation for the large variance observed in the rates of molecular evolution.},
	Aid = {0040-5809(83)90014-X {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19831021},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19831021},
	Edat = {1983/04/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Diploidy, Gene Frequency, *Genes, Haploidy, Mutation, *Probability, Selection (Genetics), *Stochastic Processes},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1983/04/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {202-15},
	Pl = {UNITED STATES},
	Pmid = {6612632},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1983 Apr;23(2):202-15.},
	Stat = {MEDLINE},
	Title = {A simple stochastic gene substitution model.},
	Volume = {23},
	Year = {1983}}

@article{gillespie1984,
	Abstract = {It is argued that the apparent constancy of the rate of molecular evolution may be an artifact due to the very slow rate of evolution of individual amino acids. A statistical analysis of protein evolution using a stationary point process as the null hypothesis leads to the conclusion that molecular evolution is episodic, with short bursts of rapid evolution followed by long periods of slow evolution. Such dynamics are incompatible with the neutral allele theory and require a revision of the standard interpretation of the molecular clock.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19850221},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19850221},
	Edat = {1984/12/01},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Alleles, Amino Acid Sequence, Animals, *Evolution, Humans, *Models, Genetic, *Periodicity, *Phylogeny, Proteins/*genetics},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1984/12/01 00:01},
	Number = {24},
	Oid = {NASA: 85088538},
	Own = {NLM},
	Pages = {8009-13},
	Pl = {UNITED STATES},
	Pmid = {6595674},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Proteins)},
	Sb = {S},
	So = {Proc Natl Acad Sci U S A. 1984 Dec;81(24):8009-13.},
	Stat = {MEDLINE},
	Title = {The molecular clock may be an episodic clock.},
	Volume = {81},
	Year = {1984}}

@article{gillespie1984b,
	Abstract = {A model of selection is described in which optimizing phenotypic selection is combined with pleiotropic overdominance. Thus, the role that mutation commonly plays in models of phenotypic evolution is replaced by balancing selection. Expressions are provided for the equilibrium genetic variance in phenotype and for the heterozygosity. An approximate analysis of the transient properties of the model shows that, in certain circumstances, the behavior is quite similar to that of models based on the interaction of mutation and selection.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19840815},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19840815},
	Edat = {1984/06/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Genes, Dominant, Mathematics, *Models, Genetic, Phenotype, *Selection (Genetics), *Variation (Genetics)},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1984/06/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {321-30},
	Pl = {UNITED STATES},
	Pmid = {6735172},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 1984 Jun;107(2):321-30.},
	Stat = {MEDLINE},
	Title = {Pleiotropic overdominance and the maintenance of genetic variation in polygenic characters.},
	Volume = {107},
	Year = {1984}}

@article{gillespie1985,
	Abstract = {The interaction of genetic drift, mutation, and selection in a random environment is investigated using an asymptotic analysis based on assumptions of weak mutation and strong selection. It is shown that genetic drift can be a potent force for removing variation from the population when the random environment tends to occasionally push alleles down to low frequencies.},
	Aid = {0040-5809(85)90011-5 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19850919},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19850919},
	Edat = {1985/04/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Animals, *Environment, *Gene Frequency, Mathematics, Models, Genetic, *Mutation, *Selection (Genetics)},
	Language = {eng},
	Lr = {20031114},
	Mhda = {1985/04/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {222-37},
	Pl = {UNITED STATES},
	Pmid = {4023954},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1985 Apr;27(2):222-37.},
	Stat = {MEDLINE},
	Title = {The interaction of genetic drift and mutation with selection in a fluctuating environment.},
	Volume = {27},
	Year = {1985}}

@article{gillespie1986,
	Abstract = {A statistical analysis of DNA sequences from four nuclear loci and five mitochondrial loci from different orders of mammals is described. A major aim of the study is to describe the variation in the rate of molecular evolution of proteins and DNA. A measure of rate variability is the statistic R, the ratio of the variance in the number of substitutions to the mean number. For proteins, R is found to be in the range 0.16 less than R less than 35.55, thus extending in both directions the values seen in previous studies. An analysis of codons shows that there is a highly significant excess of double substitutions in the first and second positions, but not in the second and third or first and third positions. The analysis of the dynamics of nucleotide evolution showed that the ergodic Markov chain models that are the basis of most published formulas for correcting for multiple substitutions are incompatible with the data. A bootstrap procedure was used to show that the evolution of the individual nucleotides, even the third positions, show the same variation in rates as seen in the proteins. It is argued that protein and silent DNA evolution are uncoupled, with the evolution at both levels showing patterns that are better explained by the action of natural selection than by neutrality. This conclusion is based primarily on a comparison of the nuclear and mitochondrial results.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19861015},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19861015},
	Edat = {1986/08/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Base Sequence, Codon, DNA/*genetics, *Evolution, Genes, Humans, Mitochondria/metabolism, *Models, Genetic, Phylogeny, Species Specificity, Statistics, *Variation (Genetics)},
	Language = {eng},
	Lr = {20051117},
	Mhda = {1986/08/01 00:01},
	Number = {4},
	Own = {NLM},
	Pages = {1077-91},
	Pl = {UNITED STATES},
	Pmid = {3744027},
	Pst = {ppublish},
	Pt = {Case Reports},
	Pubm = {Print},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Genetics. 1986 Aug;113(4):1077-91.},
	Stat = {MEDLINE},
	Title = {Variability of evolutionary rates of DNA.},
	Volume = {113},
	Year = {1986}}

@article{gillespie1986b,
	Abstract = {This paper concludes that the statistical properties of protein evolution are compatible with a particular model of evolution by natural selection. The argument begins with a statistical description of the molecular clock based on a Poisson process with a randomly varying tick rate. If the time scale of the change of the tick rate of the molecular clock is assumed to be much less than the average time between substitutions, then it is shown that the substitution process must be episodic, with bursts of substitutions being separated by long periods of time with no substitutions. This analysis generalizes the recent work of Gillespie (1984a). The second part of the argument shows that a simple model of evolution by natural selection--one that incorporates a changing environment, the molecular landscape, and a simple form of epistasis--exhibits dynamics that are identical to those inferred from the statistical analysis. This leads to the conclusion that natural selection is a viable explanation for protein evolution. In addition, a correction formula for multiple substitutions is given that does not require that the substitution process be a Poisson process, and some comments on the inability of the neutral allele theory to account for the dynamics of the substitution process are presented.},
	Affiliation = {Department of Genetics, University of California, Davis 95616.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19880504},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19880504},
	Edat = {1986/03/01},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {Animals, Crystallins, Cytochrome c Group, *Evolution, Hemoglobins, Humans, Models, Theoretical, Myoglobin, Probability, *Proteins, Ribonucleases, *Selection (Genetics), Time Factors},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1986/03/01 00:01},
	Number = {2},
	Oid = {NASA: 88174338},
	Own = {NLM},
	Pages = {138-55},
	Pl = {UNITED STATES},
	Pmid = {2832690},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Crystallins)},
	Sb = {S},
	So = {Mol Biol Evol. 1986 Mar;3(2):138-55.},
	Stat = {MEDLINE},
	Title = {Natural selection and the molecular clock.},
	Volume = {3},
	Year = {1986}}

@article{gillespie1988,
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19880609},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19880609},
	Edat = {1988/02/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {*Alleles, *Evolution, *Models, Genetic, Time Factors},
	Language = {eng},
	Lr = {20011114},
	Mhda = {1988/02/01 00:01},
	Number = {2},
	Oid = {NASA: 88196854},
	Own = {NLM},
	Pages = {385-8},
	Pl = {UNITED STATES},
	Pmid = {3360308},
	Pst = {ppublish},
	Pt = {Letter},
	Pubm = {Print},
	Sb = {S},
	So = {Genetics. 1988 Feb;118(2):385-8.},
	Stat = {MEDLINE},
	Title = {More on the overdispersed molecular clock.},
	Volume = {118},
	Year = {1988}}

@article{gillespie1989,
	Abstract = {Recent efforts to estimate the index of dispersion {$[$}R(t){$]$} of molecular evolution-i.e., the ratio of the variance in the number of substitutions on a lineage to the mean number-have suffered from an inability to adjust the data for lineage effects. These effects may include the generation-time dependency of the rate of evolution or improper assumptions about the branching pattern of a phylogenetic tree. In the present paper a method for correcting for lineage effects in the estimation of R(t) is presented for trees made up of three species. The recent data published by Li et al. for 20 loci in three orders of mammals is examined, and the average R(t), corrected for lineage effects, is shown to be 7.75 for replacement substitutions and 3.3 for silent substitutions. Thus the high values reported earlier may not be dismissed as due to generation-time effects or improper assumptions about phylogenies. Computer simulations are presented to give confidence in the estimate for replacement substitutions but also to demonstrate that the estimate for silent substitutions is sensitive to corrections for multiple substitutions and is not as reliable. This work's implications for our understanding of the mechanism of molecular evolution are discussed, and the arguments in favor of the hypothesis that replacement substitutions are mostly selected while silent substitutions are mostly neutral is presented.},
	Affiliation = {Department of Genetics, University of California, Davis 95616.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19910501},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19910501},
	Edat = {1989/11/01},
	Issn = {0737-4038 (Print)},
	Jid = {8501455},
	Journal = {Mol Biol Evol},
	Jt = {Molecular biology and evolution.},
	Keywords = {*Algorithms, Computer Simulation, *Evolution, *Models, Genetic, Mutation, Phylogeny},
	Language = {eng},
	Lr = {20011114},
	Mhda = {1989/11/01 00:01},
	Number = {6},
	Oid = {NASA: 91179351},
	Own = {NLM},
	Pages = {636-47},
	Pl = {UNITED STATES},
	Pmid = {2488476},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Mol Biol Evol. 1989 Nov;6(6):636-47.},
	Stat = {MEDLINE},
	Title = {Lineage effects and the index of dispersion of molecular evolution.},
	Volume = {6},
	Year = {1989}}

@article{gillespie1989b,
	Abstract = {A model of molecular evolution is presented that is based on the combined action of natural selection, genetic drift, and mutation. The mathematical description of the model uses strong-selection, weak-mutation limits to approximate the dynamics of multidimensional diffusion processes with one dimensional Markov chains. This approach leads to a great simplification of the dynamics and provides a unified method for describing many different mechanisms of natural selection. In this paper two models are examined, one based on selection in a randomly fluctuating environment, the other on overdominance. Both models exhibit similar dynamics, with a rapid buildup phase that introduces new alleles into the population, followed by a relatively quiescent phase where new alleles may enter and leave the population at a low rate. If occasional extreme environmental changes occur that favor particular alleles, the resulting dynamics turn out to be in remarkable agreement with many of the observations on molecular evolution and polymorphism. Thus the model is at least as successful as the neutral theory in accounting for evolutionary events at the molecular level.},
	Affiliation = {Department of Genetics, University of California, Davis 95616.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19900112},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19900112},
	Edat = {1989/01/01},
	Issn = {0831-2796 (Print)},
	Jid = {8704544},
	Journal = {Genome},
	Jt = {Genome / National Research Council Canada = Genome / Conseil national de recherches Canada.},
	Keywords = {*Evolution, Gene Frequency, Models, Genetic, Mutation, Polymorphism, Genetic/*genetics, *Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1989/01/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {311-5},
	Pl = {CANADA},
	Pmid = {2591738},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genome. 1989;31(1):311-5.},
	Stat = {MEDLINE},
	Title = {Could natural selection account for molecular evolution and polymorphism?},
	Volume = {31},
	Year = {1989}}

@article{gillespie1990,
	Abstract = {This paper provides a theoretical description of the distribution of the number of mutations that separate alleles that are held in a population by balancing selection. Two models of nucleotide site epistasis are described: parity models and additive site models. Parity models are shown to result in a more uniform distribution of mutations across alleles than the neutral model, while additive sites models show a more extreme distribution. The analytic approach uses strong-selection, weak-mutation approximations to constant-fitness and random-environment diffusion models.},
	Affiliation = {Department of Genetics, University of California, Davis 95616.},
	Aid = {0040-5809(90)90028-T {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19900514},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19900514},
	Edat = {1990/02/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Base Sequence, DNA/*genetics, Epistasis, Genetic, Female, Gene Frequency, *Genetics, Population, Humans, *Models, Genetic, Mutation, Parity, Polymorphism, Genetic/genetics, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics), Variation (Genetics)/*genetics},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1990/02/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {91-109},
	Pl = {UNITED STATES},
	Pmid = {2326769},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {9007-49-2 (DNA)},
	Sb = {IM},
	So = {Theor Popul Biol. 1990 Feb;37(1):91-109.},
	Stat = {MEDLINE},
	Title = {The molecular nature of allelic diversity for two models of balancing selection.},
	Volume = {37},
	Year = {1990}}

@article{gillespie1993,
	Affiliation = {Section of Evolution and Ecology, University of California, Davis 95916.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Con = {Proc Natl Acad Sci U S A. 1993 Nov 15;90(22):10424-8. PMID: 8248125},
	Da = {19931229},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19931229},
	Edat = {1993/11/15},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Evolution, Mutation, RNA Viruses/*genetics, Vesicular stomatitis-Indiana virus/genetics},
	Language = {eng},
	Lr = {20011126},
	Mhda = {1993/11/15 00:01},
	Number = {22},
	Own = {NLM},
	Pages = {10411-2},
	Pl = {UNITED STATES},
	Pmid = {8248122},
	Pst = {ppublish},
	Pt = {Comment},
	Pubm = {Print},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 1993 Nov 15;90(22):10411-2.},
	Stat = {MEDLINE},
	Title = {Episodic evolution of RNA viruses.},
	Volume = {90},
	Year = {1993}}

@article{gillespie1993b,
	Abstract = {A computer simulation of the process of nucleotide substitutions in a finite haploid population subject to selection in a randomly fluctuating environment provides a number of unexpected results. For rapidly fluctuating environments, substitutions are more regular than random. A small mutation-rate approximation is used to explain the regularity. The explanation does not depend heavily on the particulars of the haploid model, leading to the conjecture that many symmetrical models of molecular evolution with rapidly changing parameters may exhibit substitutions that are more regular than random. When fitnesses change very slowly, the simulation shows that substitutions are more clumped than random. Here a small-mutation approximation shows that the clustering is due to the increase in fitness that accompanies each successive substitution with a consequent lowering of the effective mutation rate. The two observations taken together suggest that the common observation that amino acid substitutions are clustered in time is due to the presence of parameters that change very slowly.},
	Affiliation = {Center for Population Biology, University of California, Davis 95616.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19930916},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19930916},
	Edat = {1993/07/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Computer Simulation, Environment, *Evolution, *Haploidy, *Models, Genetic, Mutation},
	Language = {eng},
	Lr = {20011114},
	Mhda = {1993/07/01 00:01},
	Number = {3},
	Own = {NLM},
	Pages = {971-81},
	Pl = {UNITED STATES},
	Pmid = {8349119},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {S},
	So = {Genetics. 1993 Jul;134(3):971-81.},
	Stat = {MEDLINE},
	Title = {Substitution processes in molecular evolution. I. Uniform and clustered substitutions in a haploid model.},
	Volume = {134},
	Year = {1993}}

@article{gillespie1994,
	Abstract = {The substitution processes for various models of deleterious alleles are examined using computer simulations and mathematical analyses. Most of the work focuses on the house-of-cards model, which is a popular model of deleterious allele evolution. The rate of substitution is shown to be a concave function of the strength of selection as measured by alpha = 2N sigma, where N is the population size and sigma is the standard deviation of fitness. For alpha < 1, the house-of-cards model is essentially a neutral model; for alpha > 4, the model ceases to evolve. The stagnation for large alpha may be understood by appealing to the theory of records. The house-of-cards model evolves to a state where the vast majority of all mutations are deleterious, but precisely one-half of those mutations that fix are deleterious (the other half are advantageous). Thus, the model is not a model of exclusively deleterious evolution as is frequently claimed. It is argued that there are no biologically reasonable models of molecular evolution where the vast majority of all substitutions are deleterious. Other models examined include the exponential and gamma shift models, the Hartl-Dykhuizen-Dean (HDD) model, and the optimum model. Of all those examined, only the optimum and HDD models appear to be reasonable candidates for silent evolution. None of the models are viewed as good candidates for protein evolution, as none are both biologically reasonable and exhibit the variability in substitutions commonly observed in protein sequence data.},
	Affiliation = {Section of Evolution and Ecology, University of California, Davis 95616.},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19950314},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19950314},
	Edat = {1994/11/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {*Alleles, Computer Simulation, *Evolution, Models, Genetic, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1994/11/01 00:01},
	Number = {3},
	Own = {NLM},
	Pages = {943-52},
	Pl = {UNITED STATES},
	Pmid = {7851786},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 1994 Nov;138(3):943-52.},
	Stat = {MEDLINE},
	Title = {Substitution processes in molecular evolution. III. Deleterious alleles.},
	Volume = {138},
	Year = {1994}}

@article{gillespie1997,
	Abstract = {A simulation study of the effects of linked selection on a neutral locus is described. Of six models of selection examined, four could be called variation-reducing as they lower the level of molecular variation at the neutral locus. Unfortunately, all four distort the neutral frequency spectrum in similar ways, making the problem of inferring the appropriate model quite difficult. Similarly, an examination of the effects of linked selection on the non-random association of mutations at two linked neutral loci did not suggest that this property would be useful for inferring the nature of linked selection either. Linked selection may have a profound effect on the 'effective population size' of the neutral locus. For two of the variation-reducing models, the effective size at the neutral locus is almost independent of the actual population size.},
	Affiliation = {Section of Evolution and Ecology, University of California, Davis 95616, USA. jhgillespie@ucdavis.edu},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {19980218},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19980218},
	Edat = {1998/02/14},
	Issn = {0378-1119 (Print)},
	Jid = {7706761},
	Journal = {Gene},
	Jt = {Gene.},
	Keywords = {*Alleles, Computer Simulation, Models, Genetic, Recombination, Genetic, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1998/02/14 00:01},
	Number = {1-2},
	Own = {NLM},
	Pages = {291-9},
	Pl = {NETHERLANDS},
	Pmid = {9461403},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Gene. 1997 Dec 31;205(1-2):291-9.},
	Stat = {MEDLINE},
	Title = {Junk ain't what junk does: neutral alleles in a selected context.},
	Volume = {205},
	Year = {1997}}

@article{gillespie1999,
	Abstract = {The results of a computer simulation study of the role of population size in population genetical models of molecular evolution are presented. If the mutation rate and strength of selection are held fixed and the population size increased, the eight models examined fall into three domains based on their rates of substitution. In the Ohta domain, the rate of substitution decreases with increasing population size; in the Kimura domain, the rate of substitution remains close to the mutation rate; in the Darwin domain, the rate of substitution increases without bound. In the Kimura and Darwin domains, the rate of substitution is much less sensitive to the population size than suggested by two-allele theories. Remarkably, the overdominance model converges to the neutral model with increasing N. The variation at a neutral locus linked to a selected locus is found to be insensitive to the population size for certain models of selection. A selected locus can actually cause the rate of substitution of deleterious alleles at a linked locus to increase with increasing population size. These unexpected results illustrate that intuition based on two-allele theory is often misleading.},
	Affiliation = {Section of Evolution and Ecology, University of California, One Shields Avenue, Davis, California 95616, USA.},
	Aid = {10.1006/tpbi.1998.1391 {$[$}doi{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Ci = {Copyright 1999 Academic Press.},
	Da = {19990608},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19990608},
	Edat = {1999/05/18},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Animals, Computer Simulation, *Evolution, Molecular, *Genetics, Population, Linkage (Genetics), Models, Genetic, Mutation/genetics, Population Density, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1999/05/18 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {145-56},
	Pl = {UNITED STATES},
	Pmid = {10329514},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1999 Apr;55(2):145-56.},
	Stat = {MEDLINE},
	Title = {The role of population size in molecular evolution.},
	Volume = {55},
	Year = {1999}}

@article{gillespie2000,
	Abstract = {Selected substitutions at one locus can induce stochastic dynamics that resemble genetic drift at a closely linked neutral locus. The pseudohitchhiking model is a one-locus model that approximates these effects and can be used to describe the major consequences of linked selection. As the changes in neutral allele frequencies when hitchhiking are rapid, diffusion theory is not appropriate for studying neutral dynamics. A stationary distribution and some results on substitution processes are presented that use the theory of continuous-time Markov processes with discontinuous sample paths. The coalescent of the pseudohitchhiking model is shown to have a random number of branches at each node, which leads to a frequency spectrum that is different from that of the equilibrium neutral model. If genetic draft, the name given to these induced stochastic effects, is a more important stochastic force than genetic drift, then a number of paradoxes that have plagued population genetics disappear.},
	Affiliation = {Section of Evolution and Ecology, University of California, Davis 95616, USA. jhgillespie@ucdavis.edu},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {20000908},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {20000908},
	Edat = {2000/06/03 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Crossing Over, Genetic, *Gene Frequency, *Models, Genetic, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2000/09/19 11:01},
	Number = {2},
	Own = {NLM},
	Pages = {909-19},
	Pl = {UNITED STATES},
	Pmid = {10835409},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2000 Jun;155(2):909-19.},
	Stat = {MEDLINE},
	Title = {Genetic drift in an infinite population. The pseudohitchhiking model.},
	Volume = {155},
	Year = {2000}}

@article{gillespie2000b,
	Abstract = {Selective substitutions at one locus induce stochastic dynamics at a linked neutral locus that resemble genetic drift even when the population size is infinite. This new stochastic force, which is called genetic draft, causes genetic variation at the neutral locus to decrease with population size and the rate of deleterious substitution to increase with population size. The fact that heterozygosities in natural populations are only weakly dependent on population size suggests that genetic draft may be a much more important stochastic force than genetic drift in natural populations. Some of the mathematical properties of genetic draft are explored.},
	Affiliation = {Section of Evolution and Ecology, University of California, CA 95616, Davis, USA. jhgillespie@ucdavis.edu},
	Aid = {S0378-1119(00)00485-6 {$[$}pii{$]$}},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {20010222},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {20010315},
	Edat = {2001/02/13 11:00},
	Issn = {0378-1119 (Print)},
	Jid = {7706761},
	Journal = {Gene},
	Jt = {Gene.},
	Keywords = {Alleles, Animals, *Evolution, Molecular, Gene Frequency, *Genetics, Population, Heterozygote, Humans, Models, Genetic, Mutation/*genetics, Research Support, U.S. Gov't, Non-P.H.S., Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2001/03/17 10:01},
	Number = {1},
	Own = {NLM},
	Pages = {11-8},
	Pl = {Netherlands},
	Pmid = {11164032},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Gene. 2000 Dec 30;261(1):11-8.},
	Stat = {MEDLINE},
	Title = {The neutral theory in an infinite population.},
	Volume = {261},
	Year = {2000}}

@article{gillespie2001,
	Abstract = {This paper examines aspects of genetic draft, the stochastic force induced by substitutions at one locus on the dynamics of a closely linked locus. Of particular interest is the role of population size on genetic draft. Remarkably, the rate of substitution of weakly selected advantageous mutations decreases with increasing population size, whereas that for deleterious mutations increases with population size. This dependency on population size is the opposite of that for genetic drift. Moreover, these rates are only weakly dependent on population size, again contrary to the strong dependency of drift-based dynamics. Four models of the strongly selected loci responsible for genetic draft are examined. Three of these exhibit a very weak dependency on population size, which implies that their induced effects will also be weakly dependent on population size. Together, these results suggest that population size and binomial sampling may not be relevant to a species' evolution. If this is the case, then a number of evolutionary conundrums are resolved.},
	Affiliation = {Section of Evolution and Ecology, University of California, Davis 95616, USA. jhgillespie@ucdavis.edu},
	Au = {Gillespie JH},
	Author = {Gillespie, J H},
	Da = {20020116},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {20021010},
	Edat = {2002/01/17 10:00},
	Issn = {0014-3820 (Print)},
	Jid = {0373224},
	Journal = {Evolution Int J Org Evolution},
	Jt = {Evolution; international journal of organic evolution.},
	Keywords = {Alleles, Animals, *Evolution, *Genetics, Population, Genotype, Mathematics, Mutation, Phenotype, *Population Density, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2002/10/11 04:00},
	Number = {11},
	Own = {NLM},
	Pages = {2161-9},
	Pl = {United States},
	Pmid = {11794777},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Evolution Int J Org Evolution. 2001 Nov 11;55(11):2161-9.},
	Stat = {MEDLINE},
	Title = {Is the population size of a species relevant to its evolution?},
	Volume = {55},
	Year = {2001}}

@article{gillespieKojima1968,
	Au = {Gillespie JH and Kojima K},
	Author = {Gillespie, J H and Kojima, K},
	Da = {19681209},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19681209},
	Edat = {1968/10/01},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Animals, Drosophila/*enzymology, Esterases/analysis, Fructose-Bisphosphate Aldolase/analysis, Glucosephosphate Dehydrogenase/analysis, Glycolysis, Heterozygote, Hexokinase/analysis, Malate Dehydrogenase/analysis, Melanesia, *Polymorphism, Genetic, Polynesia},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1968/10/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {582-5},
	Pl = {UNITED STATES},
	Pmid = {5245992},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {EC 1.1.1.37 (Malate Dehydrogenase)},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 1968 Oct;61(2):582-5.},
	Stat = {MEDLINE},
	Title = {The degree of polymorphisms in enzymes involved in energy production compared to that in nonspecific enzymes in two Drosophila ananassae populations.},
	Volume = {61},
	Year = {1968}}

@article{gillespieLangley1974,
	Au = {Gillespie JH and Langley CH},
	Author = {Gillespie, J H and Langley, C H},
	Da = {19740820},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19740820},
	Edat = {1974/04/01},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Animals, Chromosome Mapping, Environment, *Enzymes, Gene Frequency, Heterozygote, Homeostasis, Humans, Hybrid Vigor, *Models, Biological, *Polymorphism, Genetic, Selection (Genetics), *Variation (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1974/04/01 00:01},
	Number = {4},
	Own = {NLM},
	Pages = {837-48},
	Pl = {UNITED STATES},
	Pmid = {4838763},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Enzymes)},
	Sb = {IM},
	So = {Genetics. 1974 Apr;76(4):837-48.},
	Stat = {MEDLINE},
	Title = {A general model to account for enzyme variation in natural populations.},
	Volume = {76},
	Year = {1974}}

@article{gillespieLangley1979,
	Abstract = {Langley and Fitch (1974, 1976) have shown that the pattern of nucleotide substitutions in proteins is inconsistent with a Poisson process with constant rate. From this they conclude that the rate is temporally heterogeneous. It is pointed out in this note that a process which is temporally homogeneous but not a Poisson process is compatible with the data if the coefficient of variation of the time between substitutions is around 1.63. Furthermore, theoretical analysis of samples from neutral phylogenies shows that these samples should not appear to be samples from a Poisson process, but should deviate from a Poisson process in the same direction, though perhaps not to the same extent, as do the data.},
	Au = {Gillespie JH and Langley CH},
	Author = {Gillespie, J H and Langley, C H},
	Da = {19790925},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19790925},
	Edat = {1979/06/08},
	Issn = {0022-2844 (Print)},
	Jid = {0360051},
	Journal = {J Mol Evol},
	Jt = {Journal of molecular evolution.},
	Keywords = {Animals, *Evolution, Genetics, Population, Homozygote, Mathematics, Models, Biological, Phylogeny},
	Language = {eng},
	Lr = {20031114},
	Mhda = {1979/06/08 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {27-34},
	Pl = {GERMANY, WEST},
	Pmid = {458870},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {J Mol Evol. 1979 Jun 8;13(1):27-34.},
	Stat = {MEDLINE},
	Title = {Are evolutionary rates really variable?},
	Volume = {13},
	Year = {1979}}

@article{longGillespie1991,
	Abstract = {This paper is concerned with the divergence of synonymous codon usage and its bias in three homologous genes within vertebrate species. Genetic distances among species are described in terms of synonymous codon usage divergence and the correlation is found between the genetic distances and taxonomic distances among species under study. A codon usage clock is reported in alpha-globin and beta-globin. A method is developed to define the synonymous codon preference bias and it is observed that the bias changes considerably among species.},
	Affiliation = {Department of Genetics, University of California, Davis 95616.},
	Au = {Long M and Gillespie JH},
	Author = {Long, M and Gillespie, J H},
	Da = {19910506},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19910506},
	Edat = {1991/01/01},
	Issn = {0022-2844 (Print)},
	Jid = {0360051},
	Journal = {J Mol Evol},
	Jt = {Journal of molecular evolution.},
	Keywords = {Animals, Base Composition, *Codon, *Evolution, Gene Frequency, Humans, *Sequence Homology, Nucleic Acid, Vertebrates/*genetics},
	Language = {eng},
	Lr = {20041117},
	Mhda = {1991/01/01 00:01},
	Number = {1},
	Own = {NLM},
	Pages = {6-15},
	Pl = {UNITED STATES},
	Pmid = {1901369},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Rn = {0 (Codon)},
	Sb = {IM},
	So = {J Mol Evol. 1991 Jan;32(1):6-15.},
	Stat = {MEDLINE},
	Title = {Codon usage divergence of homologous vertebrate genes and codon usage clock.},
	Volume = {32},
	Year = {1991}}

@article{ohtaGillespie1996,
	Abstract = {A short history of the major features of neutral theories of molecular evolution is presented. Emphasis is placed on the nearly neutral theory, as this version of the neutral theory has explained the widest range of phenomena. The shift of interest from protein to DNA evolution is chronicled, leading to the modern view that silent and replacement substitutions are responding to different evolutionary forces. However, the exact nature and magnitude of these forces remains controversial, as all current theoretical models suffer either from assumptions that are not quite realistic or from an inability to account readily for all phenomena. Although the gathering of sequence data has been the main effort of contemporary population genetics, further exploration of theoretical models of molecular evolution would provide a more coherent framework for data analysis.},
	Affiliation = {National Institute of Genetics, , Mishima, , 411, Japan},
	Aid = {S0040580996900076 {$[$}pii{$]$}},
	Author = {Ohta T and Gillespie JH},
	Da = {19961010},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Edat = {1996/04/01},
	Issn = {0040-5809 (Print)},
	Journal = {Theor Popul Biol},
	Language = {ENG},
	Mhda = {1996/04/01},
	Number = {2},
	Own = {NLM},
	Pages = {128-42},
	Pmid = {8813019},
	Pst = {ppublish},
	Pt = {JOURNAL ARTICLE},
	Pubm = {Print},
	So = {Theor Popul Biol. 1996 Apr;49(2):128-42.},
	Stat = {Publisher},
	Title = {Development of Neutral and Nearly Neutral Theories},
	Volume = {49},
	Year = {1996}}

@article{turelliGillespie1980,
	Aid = {0040-5809(80)90004-0 {$[$}pii{$]$}},
	Au = {Turelli M and Gillespie JH},
	Author = {Turelli, M and Gillespie, J H},
	Da = {19801021},
	Date-Added = {2006-08-24 10:25:12 -0700},
	Date-Modified = {2006-08-24 10:25:12 -0700},
	Dcom = {19801021},
	Edat = {1980/04/01},
	Issn = {0040-5809 (Print)},
	Jid = {0256422},
	Journal = {Theor Popul Biol},
	Jt = {Theoretical population biology.},
	Keywords = {Genetics, Population, *Models, Biological, *Population Density},
	Language = {eng},
	Lr = {20001218},
	Mhda = {1980/04/01 00:01},
	Number = {2},
	Own = {NLM},
	Pages = {167-89},
	Pl = {UNITED STATES},
	Pmid = {7404438},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Theor Popul Biol. 1980 Apr;17(2):167-89.},
	Stat = {MEDLINE},
	Title = {Conditions for the existence of stationary densities for some two-dimensional diffusion processes with applications in population biology.},
	Volume = {17},
	Year = {1980}}

@article{bustamanteetal2001,
	Abstract = {In this article we explore statistical properties of the maximum-likelihood estimates (MLEs) of the selection and mutation parameters in a Poisson random field population genetics model of directional selection at DNA sites. We derive the asymptotic variances and covariance of the MLEs and explore the power of the likelihood ratio tests (LRT) of neutrality for varying levels of mutation and selection as well as the robustness of the LRT to deviations from the assumption of free recombination among sites. We also discuss the coverage of confidence intervals on the basis of two standard-likelihood methods. We find that the LRT has high power to detect deviations from neutrality and that the maximum-likelihood estimation performs very well when the ancestral states of all mutations in the sample are known. When the ancestral states are not known, the test has high power to detect deviations from neutrality for negative selection but not for positive selection. We also find that the LRT is not robust to deviations from the assumption of independence among sites.},
	Affiliation = {Department of Organismic and Evolutionary Biology, Harvard University, Cambridge, Massachusetts 02138, USA.},
	Au = {Bustamante CD and Wakeley J and Sawyer S and Hartl DL},
	Author = {Bustamante, C D and Wakeley, J and Sawyer, S and Hartl, D L},
	Da = {20020107},
	Date-Added = {2006-08-23 16:02:19 -0700},
	Date-Modified = {2006-08-23 16:02:19 -0700},
	Dcom = {20020315},
	Edat = {2002/01/10 10:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Alleles, Likelihood Functions, *Models, Genetic, Models, Statistical, Poisson Distribution, *Recombination, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S.},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2002/03/16 10:01},
	Number = {4},
	Own = {NLM},
	Pages = {1779-88},
	Pl = {United States},
	Pmid = {11779814},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2001 Dec;159(4):1779-88.},
	Stat = {MEDLINE},
	Title = {Directional selection and the site-frequency spectrum.},
	Volume = {159},
	Year = {2001}}

@article{williamsonetal2004,
	Abstract = {We develop a Poisson random-field model of polymorphism and divergence that allows arbitrary dominance relations in a diploid context. This model provides a maximum-likelihood framework for estimating both selection and dominance parameters of new mutations using information on the frequency spectrum of sequence polymorphisms. This is the first DNA sequence-based estimator of the dominance parameter. Our model also leads to a likelihood-ratio test for distinguishing nongenic from genic selection; simulations indicate that this test is quite powerful when a large number of segregating sites are available. We also use simulations to explore the bias in selection parameter estimates caused by unacknowledged dominance relations. When inference is based on the frequency spectrum of polymorphisms, genic selection estimates of the selection parameter can be very strongly biased even for minor deviations from the genic selection model. Surprisingly, however, when inference is based on polymorphism and divergence (McDonald-Kreitman) data, genic selection estimates of the selection parameter are nearly unbiased, even for completely dominant or recessive mutations. Further, we find that weak overdominant selection can increase, rather than decrease, the substitution rate relative to levels of polymorphism. This nonintuitive result has major implications for the interpretation of several popular tests of neutrality.},
	Affiliation = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA. sw292@cornell.edu},
	Aid = {168/1/463 {$[$}pii{$]$}},
	Au = {Williamson S and Fledel-Alon A and Bustamante CD},
	Author = {Williamson, Scott and Fledel-Alon, Adi and Bustamante, Carlos D},
	Da = {20040929},
	Date-Added = {2006-08-23 16:02:19 -0700},
	Date-Modified = {2006-08-23 16:02:19 -0700},
	Dcom = {20050412},
	Edat = {2004/09/30 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Computer Simulation, *Evolution, Molecular, *Genetics, Population, Inheritance Patterns/genetics, Likelihood Functions, *Models, Genetic, Mutation/genetics, *Polymorphism, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2005/04/13 09:00},
	Number = {1},
	Own = {NLM},
	Pages = {463-75},
	Pl = {United States},
	Pmid = {15454557},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2004 Sep;168(1):463-75.},
	Stat = {MEDLINE},
	Title = {Population genetics of polymorphism and divergence for diploid selection models with arbitrary dominance.},
	Volume = {168},
	Year = {2004}}

@article{williamsonetal2005,
	Abstract = {Natural selection and demographic forces can have similar effects on patterns of DNA polymorphism. Therefore, to infer selection from samples of DNA sequences, one must simultaneously account for demographic effects. Here we take a model-based approach to this problem by developing predictions for patterns of polymorphism in the presence of both population size change and natural selection. If data are available from different functional classes of variation, and a priori information suggests that mutations in one of those classes are selectively neutral, then the putatively neutral class can be used to infer demographic parameters, and inferences regarding selection on other classes can be performed given demographic parameter estimates. This procedure is more robust to assumptions regarding the true underlying demography than previous approaches to detecting and analyzing selection. We apply this method to a large polymorphism data set from 301 human genes and find (i) widespread negative selection acting on standing nonsynonymous variation, (ii) that the fitness effects of nonsynonymous mutations are well predicted by several measures of amino acid exchangeability, especially site-specific methods, and (iii) strong evidence for very recent population growth.},
	Affiliation = {Department of Biological Statistics and Computational Biology, 101 Biotechnology Building, Cornell University, Ithaca, NY 14853, USA.},
	Aid = {10.1073/pnas.0502300102 {$[$}doi{$]$}},
	Au = {Williamson SH and Hernandez R and Fledel-Alon A and Zhu L and Nielsen R and Bustamante CD},
	Author = {Williamson, Scott H and Hernandez, Ryan and Fledel-Alon, Adi and Zhu, Lan and Nielsen, Rasmus and Bustamante, Carlos D},
	Da = {20050602},
	Date-Added = {2006-08-23 16:02:19 -0700},
	Date-Modified = {2006-08-23 16:02:19 -0700},
	Dcom = {20050816},
	Dep = {20050519},
	Edat = {2005/05/21 09:00},
	Gr = {1R01HG03229-01/HG/NHGRI},
	Issn = {0027-8424 (Print)},
	Jid = {7505876},
	Journal = {Proc Natl Acad Sci U S A},
	Jt = {Proceedings of the National Academy of Sciences of the United States of America.},
	Keywords = {Comparative Study, Computational Biology/methods, Genes/genetics, *Genome, Human, Genomics/methods, Humans, Likelihood Functions, *Models, Genetic, Mutation/genetics, *Polymorphism, Genetic, *Population Growth, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2005/08/17 09:00},
	Number = {22},
	Own = {NLM},
	Pages = {7882-7},
	Phst = {2005/05/19 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15905331},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Proc Natl Acad Sci U S A. 2005 May 31;102(22):7882-7. Epub 2005 May 19.},
	Stat = {MEDLINE},
	Title = {Simultaneous inference of selection and population growth from patterns of variation in the human genome.},
	Volume = {102},
	Year = {2005}}

@article{zhuBustamante2005,
	Abstract = {We present a novel composite-likelihood-ratio test (CLRT) for detecting genes and genomic regions that are subject to recurrent natural selection (either positive or negative). The method uses the likelihood functions of Hartl et al. (1994) for inference in a Wright-Fisher genic selection model and corrects for nonindependence among sites by application of coalescent simulations with recombination. Here, we (1) characterize the distribution of the CLRT statistic (Lambda) as a function of the population recombination rate (R=4Ner); (2) explore the effects of bias in estimation of R on the size (type I error) of the CLRT; (3) explore the robustness of the model to population growth, bottlenecks, and migration; (4) explore the power of the CLRT under varying levels of mutation, selection, and recombination; (5) explore the discriminatory power of the test in distinguishing negative selection from population growth; and (6) evaluate the performance of maximum composite-likelihood estimation (MCLE) of the selection coefficient. We find that the test has excellent power to detect weak negative selection and moderate power to detect positive selection. Moreover, the test is quite robust to bias in the estimate of local recombination rate, but not to certain demographic scenarios such as population growth or a recent bottleneck. Last, we demonstrate that the MCLE of the selection parameter has little bias for weak negative selection and has downward bias for positively selected mutations.},
	Affiliation = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA.},
	Aid = {10.1534/genetics.104.035097 {$[$}doi{$]$}},
	Au = {Zhu L and Bustamante CD},
	Author = {Zhu, Lan and Bustamante, Carlos D},
	Da = {20050803},
	Date-Added = {2006-08-23 16:02:19 -0700},
	Date-Modified = {2006-08-23 16:02:19 -0700},
	Dcom = {20060210},
	Dep = {20050506},
	Edat = {2005/05/10 09:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Base Sequence/*genetics, Computer Simulation, *Genetics, Population, Likelihood Functions, *Models, Genetic, Mutation/genetics, Recombination, Genetic/genetics, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2006/02/14 09:00},
	Number = {3},
	Own = {NLM},
	Pages = {1411-21},
	Phst = {2005/05/06 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15879513},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genetics. 2005 Jul;170(3):1411-21. Epub 2005 May 6.},
	Stat = {MEDLINE},
	Title = {A composite-likelihood approach for detecting directional selection from DNA sequence data.},
	Volume = {170},
	Year = {2005}}

@article{jensenetal2005,
	Abstract = {In 2002 Kim and Stephan proposed a promising composite-likelihood method for localizing and estimating the fitness advantage of a recently fixed beneficial mutation. Here, we demonstrate that their composite-likelihood-ratio (CLR) test comparing selective and neutral hypotheses is not robust to undetected population structure or a recent bottleneck, with some parameter combinations resulting in a false positive rate of nearly 90%. We also propose a goodness-of-fit test for discriminating rejections due to directional selection (true positive) from those due to population and demographic forces (false positives) and demonstrate that the new method has high sensitivity to differentiate the two classes of rejections.},
	Affiliation = {Department of Molecular Biology and Genetics, Cornell University, Ithaca, New York 14853, USA.},
	Aid = {10.1534/genetics.104.038224 {$[$}doi{$]$}},
	Au = {Jensen JD and Kim Y and DuMont VB and Aquadro CF and Bustamante CD},
	Author = {Jensen, Jeffrey D and Kim, Yuseob and DuMont, Vanessa Bauer and Aquadro, Charles F and Bustamante, Carlos D},
	Da = {20050803},
	Date-Added = {2006-08-23 15:57:41 -0700},
	Date-Modified = {2006-08-23 15:58:14 -0700},
	Dcom = {20060210},
	Dep = {20050523},
	Edat = {2005/05/25 09:00},
	Gr = {GM36431/GM/NIGMS},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Computer Simulation, *Demography, *Genetics, Population, Likelihood Functions, *Models, Genetic, Mutation/genetics, *Polymorphism, Genetic, Reproducibility of Results, Research Support, N.I.H., Extramural, Research Support, U.S. Gov't, Non-P.H.S., Research Support, U.S. Gov't, P.H.S., *Selection (Genetics)},
	Language = {eng},
	Mhda = {2006/02/14 09:00},
	Number = {3},
	Own = {NLM},
	Pages = {1401-10},
	Phst = {2005/05/23 {$[$}aheadofprint{$]$}},
	Pl = {United States},
	Pmid = {15911584},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print-Electronic},
	Sb = {IM},
	So = {Genetics. 2005 Jul;170(3):1401-10. Epub 2005 May 23.},
	Stat = {MEDLINE},
	Title = {Distinguishing between selective sweeps and demography using DNA polymorphism data.},
	Volume = {170},
	Year = {2005}}

@article{KimStephan2003,
	Abstract = {Recurrent directional selection on a partially recombining chromosome may cause a substantial reduction of standing genetic variation in natural populations. Previous studies of this effect, commonly called selective sweeps, assumed that at most one beneficial allele is on the way to fixation at a given time. However, for a high rate of selected substitutions and a low recombination rate, this assumption can easily be violated. We investigated this problem using full-forward simulations and analytical approximations. We found that interference between linked beneficial alleles causes a reduction of their fixation probabilities. The hitchhiking effect on linked neutral variation for a given substitution also slightly decreases due to interference. As a result, the strength of recurrent selective sweeps is weakened. However, this effect is significant only in chromosomal regions of relatively low recombination rates where the level of variation is greatly reduced. Therefore, previous results on recurrent selective sweeps although derived for a restricted parameter range are still valid. Analytical approximations are obtained for the case of complete linkage for which interference between competing beneficial alleles is maximal.},
	Affiliation = {Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, New York 14853, USA. yk249@cornell.edu},
	Au = {Kim Y and Stephan W},
	Author = {Kim, Yuseob and Stephan, Wolfgang},
	Da = {20030516},
	Date-Added = {2006-08-23 15:57:41 -0700},
	Date-Modified = {2006-08-23 15:58:02 -0700},
	Dcom = {20040130},
	Edat = {2003/05/17 05:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {*Computer Simulation, *Linkage (Genetics), Recombination, Genetic, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., *Selection (Genetics)},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2004/01/31 05:00},
	Number = {1},
	Own = {NLM},
	Pages = {389-98},
	Pl = {United States},
	Pmid = {12750349},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2003 May;164(1):389-98.},
	Stat = {MEDLINE},
	Title = {Selective sweeps in the presence of interference among partially linked loci.},
	Volume = {164},
	Year = {2003}}

@article{kimStephan2002,
	Abstract = {The theory of genetic hitchhiking predicts that the level of genetic variation is greatly reduced at the site of strong directional selection and increases as the recombinational distance from the site of selection increases. This characteristic pattern can be used to detect recent directional selection on the basis of DNA polymorphism data. However, the large variance of nucleotide diversity in samples of moderate size imposes difficulties in detecting such patterns. We investigated the patterns of genetic variation along a recombining chromosome by constructing ancestral recombination graphs that are modified to incorporate the effect of genetic hitchhiking. A statistical method is proposed to test the significance of a local reduction of variation and a skew of the frequency spectrum caused by a hitchhiking event. This method also allows us to estimate the strength and the location of directional selection from DNA sequence data.},
	Affiliation = {Department of Evolutionary Biology, University of Munich, 80333 Munich, Germany.},
	Au = {Kim Y and Stephan W},
	Author = {Kim, Yuseob and Stephan, Wolfgang},
	Da = {20020225},
	Date-Added = {2006-08-23 15:57:41 -0700},
	Date-Modified = {2006-08-23 15:57:53 -0700},
	Dcom = {20020524},
	Edat = {2002/02/28 10:00},
	Issn = {0016-6731 (Print)},
	Jid = {0374636},
	Journal = {Genetics},
	Jt = {Genetics.},
	Keywords = {Chromosomes/*genetics, Evolution, Molecular, Heterozygote, Likelihood Functions, *Linkage (Genetics), *Models, Theoretical, Mutation/genetics, Polymorphism, Genetic/genetics, *Recombination, Genetic, Research Support, Non-U.S. Gov't},
	Language = {eng},
	Lr = {20041117},
	Mhda = {2002/05/25 10:01},
	Number = {2},
	Own = {NLM},
	Pages = {765-77},
	Pl = {United States},
	Pmid = {11861577},
	Pst = {ppublish},
	Pt = {Journal Article},
	Pubm = {Print},
	Sb = {IM},
	So = {Genetics. 2002 Feb;160(2):765-77.},
	Stat = {MEDLINE},
	Title = {Detecting a local signature of genetic hitchhiking along a recombining chromosome.},
	Volume = {160},
	Year = {2002}}

@article{sawyerHartl1992,
	Author = {S. A. Sawyer and D. L. Hartl},
	Date-Added = {2006-08-23 14:45:30 -0700},
	Date-Modified = {2006-08-23 14:46:25 -0700},
	Journal = {Genetics},
	Pages = {1161-1176},
	Title = {Population Genetics of Polymorphism and Divergence},
	Volume = {132},
	Year = {1992}}

@article{wright1938,
	Author = {Wright, S},
	Date-Added = {2006-08-23 14:41:06 -0700},
	Date-Modified = {2006-08-23 14:44:46 -0700},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Number = {7},
	Pages = {253-259},
	Title = {The distribution of gene frequencies under irreversible mutation},
	Volume = {24},
	Year = {1938}}

@article{clarketal2003,
	Author = {Clark, AG and Glanowski, S and Nielsen, R and Thomas, PD and Kejariwal, A and Todd, MA and Tanenbaum, DM and Civello, D and Lu, F and Murphy ,B and Ferriera,S and Wang,G and Zheng, X and White ,TJ and Sninsky, JJ and Adams ,MD and Cargill,M},
	Date-Added = {2006-08-22 16:04:59 -0700},
	Date-Modified = {2006-08-23 14:15:46 -0700},
	Journal = {Science},
	Pages = {1960-3},
	Title = {Inferring nonneutral evolution from human-chimp-mouse orthologous gene trios.},
	Volume = {302},
	Year = {2003}}

@article{StajHahn2005,
	Author = {Stajich, JE and Hahn, MW.},
	Date-Added = {2006-08-22 15:05:22 -0700},
	Date-Modified = {2006-08-22 15:53:07 -0700},
	Journal = {Mol Biol Evol.},
	Month = {Jan},
	Number = {1},
	Pages = {63-73},
	Title = {Disentangling the effects of demography and selection in human history.},
	Volume = {22},
	Year = {2005}}

@article{kre2000,
	Abstract = {The development of statistical tests of natural selection at the DNA level in population samples has been ongoing for the past 13 years. The current state of the field is reviewed, and the available tests of selection are described. All tests use predictions from the theory of neutrally evolving sites as a null hypothesis. Departures from equilibrium-neutral expectations can indicate the presence of natural selection acting either at one or more of the sites under investigation or at a sufficiently tightly linked site. Complications can arise in the interpretation of departures from neutrality if populations are not at equilibrium for mutation and genetic drift or if populations are subdivided, both of which are likely scenarios for humans. Attempts to understand the nonequilibrium configuration of silent polymorphism in human mitochondrial DNA illustrate the difficulty of distinguishing between selection and alternative demographic hypotheses. The range of plausible alternatives to selection will become better defined, however, as additional population genetic data sets become available, allowing better null models to be constructed.},
	Author = {Kreitman, M.},
	Date-Added = {2006-08-22 12:13:31 -0700},
	Date-Modified = {2006-08-22 12:45:31 -0700},
	Journal = {Annu Rev Genomics Hum Genet.},
	Pages = {539-59},
	Title = {Methods to detect selection in populations with applications to the human.},
	Volume = {1},
	Year = {2000}}

@book{lew1974,
	Address = {New York},
	Author = {Richard C. Lewontin},
	Publisher = {Columbia University Press},
	Title = {The Genetic Basis of Evolutionary Change},
	Year = {1974}}

@article{may1974,
	Author = {John Maynard Smith and John Haigh},
	Journal = {Genetical Research},
	Pages = {23-35},
	Title = {The hitchhiking effect of a favorable gene},
	Volume = {23},
	Year = {1974}}

@article{gil2000,
	Author = {John H. Gillespie},
	Journal = {Genetics},
	Pages = {909-919},
	Title = {Genetic Drift in an Infinite Population: The Pseudohitchhiking Model},
	Volume = {155},
	Year = {2000}}

@article{gil1997,
	Author = {John H. Gillespie},
	Journal = {Gene},
	Pages = {291-299},
	Title = {Junk ain't what junk does: neutral alleles in a selected context},
	Volume = {205},
	Year = {1997}}

@article{gil1993,
	Author = {John H. Gillespie},
	Journal = {Genetics},
	Pages = {971-981},
	Title = {Substitution processes in molecular evolution. I. Uniform and clustered substitutions in a haploid model.},
	Volume = {134},
	Year = {1993}}

@article{taj1989,
	Author = {Fumio Tajima},
	Journal = {Genetics},
	Pages = {585-595},
	Title = {Statistical method for testing the neutral mutation hypothesis by DNA polymorphism},
	Volume = {123},
	Year = {1989}}

@article{bra1995,
	Author = {John M. Braverman and Richard R. Hudson and Norman L. Kaplan and Charles H. Langley and Wolfgang Stephan},
	Journal = {Genetics},
	Pages = {783-796},
	Title = {The hitchhiking effect on the site frequency spectrum of DNA polymorphisms.},
	Volume = {140},
	Year = {1995}}

@article{hud1988,
	Author = {Richard R. Hudson and Normal L. Kaplan},
	Journal = {Genetics},
	Pages = {831-840},
	Title = {The Coalescent Process in Models With Selection and Recombination},
	Volume = {120},
	Year = {1988}}

@article{hud2001,
	Author = {Richard R. Hudson},
	Journal = {Genetics},
	Pages = {1805-1817},
	Title = {Two-Locus Sampling Distributions and Their Applications},
	Volume = {159},
	Year = {2001}}

@article{kap1988,
	Author = {Normal L. Kaplan and Thomas Darden and Richard R. Hudson},
	Journal = {Genetics},
	Pages = {819-829},
	Title = {The Coalescent Process in Models With Selection},
	Volume = {120},
	Year = {1988}}

@article{hud1987,
	Author = {Richard R. Hudson},
	Journal = {Genetical Research},
	Pages = {245-250},
	Title = {Estimation the recombination parameter of a finite population model without selection},
	Volume = {50},
	Year = {1987}}

@article{gil1994a,
	Author = {John H. Gillespie},
	Journal = {Evolution},
	Pages = {1101-1113},
	Title = {Substitution Processes in Molecular Evolution. II. Exchangeable Models from Population Genetics},
	Volume = {48},
	Year = {1994}}

@article{gil1984,
	Author = {John H. Gillespie},
	Journal = {Evolution},
	Pages = {1116-1129},
	Title = {Molecular Evolution Over the Mutational Landscape},
	Volume = {38},
	Year = {1984}}

@article{gil1978,
	Author = {John H. Gillespie and Harry A. Guess},
	Journal = {American Naturalist},
	Pages = {897-909},
	Title = {The Effects of Environmental Autocorrelations on the Progress of Selection in a Random Environment},
	Volume = {112},
	Year = {1978}}

@article{gil1977,
	Author = {John H. Gillespie},
	Journal = {Genetics},
	Pages = {569-579},
	Title = {Multilocus Behavior in Random Environments},
	Volume = {87},
	Year = {1977}}

@article{gil1994b,
	Author = {John H. Gillespie},
	Journal = {Genetics},
	Pages = {943-952},
	Title = {Substitution Processes in Molecular Evolution. III. Deleterious Alleles},
	Volume = {138},
	Year = {1994}}

@article{gil2001,
	Author = {John H. Gillespie},
	Journal = {Evolution},
	Pages = {2161-2169},
	Title = {Is the Population Size of a Species Relevent to its Evolution?},
	Volume = {55},
	Year = {2001}}

@article{gil1999,
	Author = {John H. Gillespie},
	Journal = {Theoretical Population Biology},
	Pages = {145-156},
	Title = {The Role of Population Size in Molecular Evolution},
	Volume = {55},
	Year = {1999}}

@article{bar2000,
	Author = {N. H. Barton},
	Journal = {Philosophical Transactions of the Royal Society of London. B.},
	Pages = {1553-1562},
	Title = {Genetic Hitchhiking},
	Volume = {355},
	Year = {2000}}

@article{koj1967,
	Author = {Ken-Ichi Kojima and Henry E. Schaffer},
	Journal = {Evolution},
	Pages = {518-531},
	Title = {Survival Process of Linked Mutant Genes},
	Volume = {21},
	Year = {1967}}

@article{kim1969,
	Author = {Motoo Kimura},
	Journal = {Genetics},
	Pages = {893},
	Title = {The number of heterozygous nucleotide sites maintained in a finite population due to a steady flux of mutations},
	Volume = {61},
	Year = {1969}}

@article{sha1979,
	Author = {D. M. Shaw and C. H. Langley},
	Journal = {Nature},
	Pages = {695-699},
	Title = {Inter- and intraspecific variation in restriction maps of Drosophila mitochondrial DNAs},
	Volume = {281},
	Year = {1979}}

@article{kre1983,
	Author = {M. Kreitman},
	Journal = {Nature},
	Pages = {412-417},
	Title = {Nucleotide polymorphism at the alcohol dehydrogenase locus of Drosophila melanogaster},
	Volume = {304},
	Year = {1983}}

@article{gil1986,
	Author = {John H. Gillespie},
	Journal = {Genetics},
	Pages = {1077-1091},
	Title = {Variability of evolutionary rates of DNA},
	Volume = {113},
	Year = {1986}}

@article{hud1987b,
	Author = {Richard R. Hudson and M. Kreitman and M. Aguade},
	Journal = {Genetics},
	Pages = {153-159},
	Title = {A test of the neutral molecular evolution based on nucleotide data},
	Volume = {116},
	Year = {1987}}

@article{agu1989,
	Author = {M. Aguad{\'e} and N. Miyashita and C. H. Langley},
	Journal = {Genetics},
	Pages = {607-615},
	Title = {Reduced variation in the yellow-achaete-scute region in natural populations of Drosophila melanogaster},
	Volume = {122},
	Year = {1989}}

@article{agu1994,
	Author = {M. Aguad{\'e} and W. Meyers and A. D. Long and C. H. Langley},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Pages = {4658-4662},
	Title = {Reduced DNA sequence polymorphism in the su(s) and su(wa) regions of Drosophila melanogaster as revealed by SSCP and stratified DNA sequencing},
	Volume = {91},
	Year = {1994}}

@article{miy1990,
	Author = {N. T. Miyashita},
	Journal = {Genetics},
	Pages = {407-419},
	Title = {Molecular and phenotypic variation of the Zw locus region in Drosphila melanogaster},
	Volume = {125},
	Year = {1990}}

@article{beg1991,
	Author = {D. J. Begun and C. F. Aquadro},
	Journal = {Genetics},
	Number = {1147-1158},
	Title = {Molecular population genetics of the distal portion of the X chromosome in Drosophila: evidence for genetic hitchhiking of the yellow-achaete region},
	Volume = {129},
	Year = {1991}}

@article{ber1991,
	Author = {A. J. Berry and J. W. Ajioki and M. Kreitman},
	Journal = {Genetics},
	Pages = {1111-1117},
	Title = {Lack of polymorphism on the Drosophila fourth chromosome resulting from selection},
	Volume = {129},
	Year = {1991}}

@article{mar1992,
	Author = {J. M. Mart{\'\i}n-Campos and J. M. Comeron and N. Miyashita and M. Aguad{\'e}},
	Journal = {Genetics},
	Pages = {805-816},
	Title = {Intraspecific and interspecific variation at the y-ac-sc region of Drosophila simulans and Drosophila melanogaster},
	Volume = {130},
	Year = {1992}}

@article{lan1993,
	Author = {C. H. Langley and J. McDonald and N. Miyashita and M. Aguad{\'e}},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Pages = {1800-1803},
	Title = {Lack of correlation between interspecific divergence and intraspecific polymorphism at the suppressor of forked region in Drosophila melanogaster and Drosophila simulans},
	Volume = {90},
	Year = {1993}}

@article{ste1989,
	Author = {W. Stephan and C. H. Langley},
	Journal = {Genetics},
	Pages = {88-99},
	Title = {Molecular genetic variation in the centromeric region of the X chromosome in three Drosophila ananassae populations. I. Contrasts between the vermilion and forked loci},
	Volume = {121},
	Year = {1989}}

@inbook{aqu1994,
	Author = {C. F. Aquadro and D. J. Begun and E. C. Kindahl},
	Chapter = {Selection, recombination, and DNA polymorphism in Drosophila},
	Pages = {46-56},
	Publisher = {Chapman & Hall},
	Title = {Non-neutral Evolution: Theories and Molecular Data},
	Year = {1994}}

@article{nac1997,
	Author = {M. Nachman},
	Journal = {Genetics},
	Pages = {1303-1316},
	Title = {Patterns of DNA variability at X-linked loci in Mus domesticus},
	Volume = {147},
	Year = {1997}}

@article{nac1998,
	Author = {M. Nachman and V. L. Bauer and S. L. Crowell and C. F. Aquadro},
	Journal = {Genetics},
	Pages = {1133-1141},
	Title = {DNA variability and recombination rates at X-linked loci in humans},
	Volume = {150},
	Year = {1998}}

@book{kim1983,
	Address = {New York},
	Author = {Motoo Kimura},
	Publisher = {Cambridge University Press},
	Title = {The neutral theory of molecular evolution},
	Year = {1983}}

@article{kap1989,
	Author = {N. L. Kaplan and R. R. Hudson and C. H. Langley},
	Journal = {Genetics},
	Pages = {887-899},
	Title = {The hitchhiking effect revisited.},
	Volume = {123},
	Year = {1989}}

@article{ste1992,
	Author = {W. Stephan and T. H. E. Wiehe and M. W. Lenz},
	Journal = {Theoretical Population Biology},
	Pages = {237-254},
	Title = {The effect of strongly selected substitutions on neutral polymorphism: analytical results based on diffusion theory},
	Volume = {41},
	Year = {1992}}

@article{wie1993,
	Author = {T. H. E. Wiehe and W. Stephan},
	Journal = {Molecular Biology and Evolution},
	Pages = {842-854},
	Title = {Analysis of a genetic hitchhiking model, and its application to DNA polymorphism data from Drosophila melanogaster},
	Volume = {10},
	Year = {1993}}

@article{cha1994,
	Author = {B. Charlesworth},
	Journal = {Genetical Research},
	Pages = {213-228},
	Title = {The effect of Background selection against deleterious alleles on weakly selected, linked variants},
	Volume = {63},
	Year = {1994}}

@article{cha1995,
	Author = {D. Charlesworth and B. Charlesworth and M. T. Morgan},
	Journal = {Genetics},
	Pages = {1619-1632},
	Title = {The pattern of neutral molecular variation under the background selection model},
	Volume = {141},
	Year = {1995}}

@article{hud1995,
	Author = {R. R. Hudson and N. L. Kaplan},
	Journal = {Genetics},
	Pages = {1605-1617},
	Title = {Deleterious Background Selection with recombination},
	Volume = {141},
	Year = {1995}}

@article{hud1994,
	Author = {R. R. Hudson},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Pages = {6815-6818},
	Title = {How can low levels of DNA sequence variation in regions of the Drosophila genome with low recombination rates be explained?},
	Volume = {91},
	Year = {1994}}

@article{nor1996,
	Author = {M. Nordborg and B. Charlesworth and D. Charlesworth},
	Journal = {Genetical Research},
	Pages = {159-174},
	Title = {The effect of recombination on background selection},
	Volume = {67},
	Year = {1996}}

@article{ste1999,
	Author = {W. Stephan and B. Charlesworth and G. McVean},
	Journal = {Genetical Research},
	Pages = {133-146},
	Title = {The effect of background selection at a single locus on weakly selected, partially linked variants},
	Volume = {73},
	Year = {1999}}

@incollection{gil1994c,
	Address = {London},
	Author = {John H. Gillespie},
	Booktitle = {Non-neutral Evolution: Theories and Molecular Data},
	Editor = {B. Golding},
	Pages = {1-17},
	Publisher = {Chapman and Hall},
	Title = {Alternatives to the Neutral Theory},
	Year = {1994}}

@article{kim2000,
	Author = {Y. Kim and W. Stephan},
	Journal = {Genetics},
	Pages = {1415-1427},
	Title = {Joint Effects of genetic hitchhiking and background selection on neutral variation},
	Volume = {155},
	Year = {2000}}

@article{bar1998,
	Author = {N. H. Barton},
	Journal = {Genetical Reseach Cambridge},
	Pages = {123-133},
	Title = {The effect of hitch-hiking on neutral genealogies},
	Volume = {72},
	Year = {1998}}

@article{bar1995,
	Author = {N. H Barton},
	Journal = {Genetics},
	Pages = {821-841},
	Title = {Linkage and the Limits to Natural Selection},
	Volume = {140},
	Year = {1995}}

@article{tho1977,
	Author = {Glenys Thomson},
	Journal = {Genetics},
	Pages = {753-77},
	Title = {The Effect of a Selected Locus on LInked Neutral Loci},
	Volume = {85},
	Year = {1977}}

@article{gro1998,
	Author = {Mark N. Grote and William Klitz and Glenys Thomson},
	Journal = {Genetics},
	Pages = {1295-1307},
	Title = {Constrained Disequilibrium Values and Hitchhiking in a Three-Locus System},
	Volume = {150},
	Year = {1998}}

@article{wat1975,
	Author = {G. A. Watterson},
	Journal = {Theoretical Population Biology},
	Pages = {256-276},
	Title = {On the number of segregating sites in genetical models without recombination},
	Volume = {7},
	Year = {1975}}

@article{taj1983,
	Author = {Fumio Tajima},
	Journal = {Genetics},
	Pages = {437-460},
	Title = {Evolutionary relationship of DNA sequences in finite populations},
	Volume = {105},
	Year = {1983}}

@article{sim1995,
	Author = {Katy L. Simonsen and Gary A. Churchill and Charles F. Aquadro},
	Journal = {Genetics},
	Pages = {413-429},
	Title = {Properties of Statistical Tests of Neutrality for DNA Polymorphism Data},
	Volume = {141},
	Year = {1995}}

@article{fuLi1993,
	Author = {Y. -X. Fu and W. -H. Li},
	Date-Modified = {2006-08-23 15:43:41 -0700},
	Journal = {Genetics},
	Pages = {693-709},
	Title = {Statistical tests of neutrality of mutations},
	Volume = {133},
	Year = {1993}}

@article{fu1995,
	Author = {Y. -X. Fu},
	Journal = {Theoretical Population Biology},
	Pages = {172-197},
	Title = {Statistical Properties of Segregating Sites},
	Volume = {48},
	Year = {1995}}

@article{fayWu2000,
	Author = {J. C. Fay and C. -I. Wu},
	Date-Modified = {2006-08-23 15:44:13 -0700},
	Journal = {Genetics},
	Pages = {1405-1413},
	Title = {Hitchhiking under positive Darwinian selection},
	Volume = {155},
	Year = {2000}}

@article{prz2002,
	Author = {M. Przeworksi},
	Journal = {Genetics},
	Pages = {1179-1189},
	Title = {The signature of positive selection at randomly chosen loci},
	Volume = {160},
	Year = {2002}}

@article{cha1993,
	Author = {B. Charlesworth and M. T. Morgan and D. Charlesworth},
	Journal = {Genetics},
	Pages = {1289-1303},
	Title = {The effect of deleterious mutations on neutral molecular variation},
	Volume = {134},
	Year = {1993}}

@article{gil1978b,
	Author = {J. H. Gillespie},
	Journal = {Theoretical Population Biology},
	Pages = {1-45},
	Title = {A general model to account for enzyme variation in natural poulations. V. The SAS-CFF model.},
	Volume = {14},
	Year = {1978}}

@article{tak1975,
	Author = {N. Takahata and K. Ishii and H. Matsuda},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Pages = {4541-4545},
	Title = {Effect of temporal fluctation of selection coefficient on gene frequency in a population},
	Volume = {72},
	Year = {1975}}

@book{gil1991,
	Address = {New York},
	Author = {J. H. Gillespie},
	Publisher = {Oxford University Press},
	Title = {The causes of molecular evolution},
	Year = {1991}}

@article{lan2000,
	Author = {C. H. Langley and B. P. Lazzaro and W. Philips and E. Heikkinen and J. M. Braverman},
	Journal = {Genetics},
	Pages = {1837-1852},
	Title = {Linkage disequilibria and the site frequency spectra in the su(s) and su(wa) regions of the Drosophila melanogaster X chromosome},
	Volume = {156},
	Year = {2000}}

@article{tak1990,
	Author = {N. Takahata},
	Journal = {Proceedings of the National Academy of Sciences USA},
	Pages = {2419-2423},
	Title = {A simple genealogical structure of strongly balanced allelic lines and trans-species evolution of polymorphism},
	Volume = {72},
	Year = {1990}}

@incollection{oht1977,
	Author = {T. Ohta},
	Booktitle = {Molecular Evolution and Polymorphism},
	Editor = {M. Kimura},
	Publisher = {National Institute of Genetics},
	Title = {Extension of the neutral mutation},
	Year = {1977}}

@article{hil1966,
	Author = {W. G. Hill and A. Robertson},
	Journal = {Genetical Research},
	Pages = {269-294},
	Title = {The effect of linkage on the limits to artificial selection},
	Volume = {8},
	Year = {1966}}

@article{li1987,
	Author = {W. -H. Li},
	Journal = {Journal of Molecular Evolution},
	Pages = {337-345},
	Title = {Models of nearly neutral mutations with particular implications for nonrandom usage of synonymous codons},
	Volume = {24},
	Year = {1987}}

@article{mcv2000,
	Author = {G. McVean and B. Charlesworth},
	Journal = {Genetics},
	Pages = {929-944},
	Title = {The effects of Hill-Robertson interference betweeen selected mutations on patterns of molecular evolution},
	Volume = {155},
	Year = {2000}}

@article{com1999,
	Author = {J. M. Comeron and M. Kreitman and M. Aguade},
	Journal = {Genetics},
	Pages = {239-249},
	Title = {Natural selection on synonymous sites is correlated with gene length and recombination in Drosophila},
	Volume = {151},
	Year = {1999}}

@article{com2002,
	Author = {J. M. Comeron and M. Kreitman},
	Journal = {Genetics},
	Pages = {389-410},
	Title = {Population, evolutionary and genomic consequences of interference selection},
	Volume = {161},
	Year = {2002}}

@article{fel1974,
	Author = {J. Felsenstein},
	Journal = {Genetics},
	Pages = {737-756},
	Title = {The evolutionary advatage of recombination},
	Volume = {78},
	Year = {1974}}

@article{aka1994,
	Author = {H. Akashi},
	Journal = {Genetics},
	Pages = {927-935},
	Title = {Synonymous codon usage in Drosophila melanogaster: Natural selection and translational accuracy},
	Volume = {136},
	Year = {1994}}

@article{med1979,
	Author = {J. R. Medina and C. Petit},
	Journal = {Journal of Theoretical Biology},
	Pages = {235-246},
	Title = {The hitch-hiking effect as a dispersive process},
	Volume = {81},
	Year = {1979}}

@article{hil1994,
	Author = {H. Hilton and R. M. Kliman and J. Hey},
	Journal = {Evolution},
	Pages = {1900-1913},
	Title = {Using hitchhiking genes to study adaptation and divergence during speciation within the Drosophila melanogaster species clade},
	Volume = {48},
	Year = {1994}}

@article{wan2002,
	Author = {W. Wang and K. Thornton and A. Berry and M. Long},
	Journal = {Science},
	Pages = {134-137},
	Title = {Nucleotide variation along the Drosophila melanogaster fourth chromosome},
	Volume = {295},
	Year = {2002}}

@article{jen2002,
	Author = {M. A. Jensen and B. Charlesworth and M. Kreitman},
	Journal = {Genetics},
	Pages = {493-507},
	Title = {Patterns of genetic variation at a chromosome 4 locus of Drosophila melanogaster and D. simulans},
	Volume = {160},
	Year = {2002}}

@book{ash1989,
	Address = {Cold Spring Harbor, New York},
	Author = {M. Ashburner},
	Publisher = {Cold Spring Harbor Laboratory Press},
	Title = {Drosophila: A Laboratory Handbook},
	Year = {1989}}

@article{seg1996,
	Author = {C. Segarra and G. Ribo and M. Aguade},
	Journal = {Genetics},
	Pages = {139-146},
	Title = {Differentiation of Muller's chromosomal elements D and R in the obscura group},
	Volume = {144},
	Year = {1996}}

@article{ran1997,
	Author = {J. M. Ranz and C. Segarra and A. Ruiz},
	Journal = {Genetics},
	Pages = {281-295},
	Title = {Chromosomal Homology and MOlecular Organization of Muller's Elements D and E in the Drosophila repleta species group},
	Volume = {145},
	Year = {1997}}