astrocyte-review-bibliography.bib

@article{liberzon_molecular_2011,
	title = {Molecular signatures database ({MSigDB}) 3.0},
	volume = {27},
	issn = {1367-4803},
	url = {https://academic.oup.com/bioinformatics/article/27/12/1739/257711},
	doi = {10.1093/bioinformatics/btr260},
	abstract = {Abstract.  Motivation: Well-annotated gene sets representing the universe of the biological processes are critical for meaningful and insightful interpretation},
	language = {en},
	number = {12},
	urldate = {2020-10-12},
	journal = {Bioinformatics},
	author = {Liberzon, Arthur and Subramanian, Aravind and Pinchback, Reid and Thorvaldsdóttir, Helga and Tamayo, Pablo and Mesirov, Jill P.},
	month = jun,
	year = {2011},
	note = {Publisher: Oxford Academic},
	pages = {1739--1740},
}

@article{the_gene_ontology_consortium_gene_2019,
	title = {The {Gene} {Ontology} {Resource}: 20 years and still {GOing} strong},
	volume = {47},
	issn = {0305-1048},
	shorttitle = {The {Gene} {Ontology} {Resource}},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6323945/},
	doi = {10.1093/nar/gky1055},
	abstract = {The Gene Ontology resource (GO; http://geneontology.org) provides structured, computable knowledge regarding the functions of genes and gene products. Founded in 1998, GO has become widely adopted in the life sciences, and its contents are under continual improvement, both in quantity and in quality. Here, we report the major developments of the GO resource during the past two years. Each monthly release of the GO resource is now packaged and given a unique identifier (DOI), enabling GO-based analyses on a specific release to be reproduced in the future. The molecular function ontology has been refactored to better represent the overall activities of gene products, with a focus on transcription regulator activities. Quality assurance efforts have been ramped up to address potentially out-of-date or inaccurate annotations. New evidence codes for high-throughput experiments now enable users to filter out annotations obtained from these sources. GO-CAM, a new framework for representing gene function that is more expressive than standard GO annotations, has been released, and users can now explore the growing repository of these models. We also provide the ‘GO ribbon’ widget for visualizing GO annotations to a gene; the widget can be easily embedded in any web page.},
	urldate = {2019-10-06},
	journal = {Nucleic Acids Research},
	author = {{The Gene Ontology Consortium}},
	month = jan,
	year = {2019},
	pmid = {30395331},
	pmcid = {PMC6323945},
	pages = {D330--D338},
}

@article{ashburner_gene_2000,
	title = {Gene {Ontology}: tool for the unification of biology},
	volume = {25},
	issn = {1061-4036},
	shorttitle = {Gene {Ontology}},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3037419/},
	doi = {10.1038/75556},
	abstract = {Genomic sequencing has made it clear that a large fraction of the genes specifying the core biological functions are shared by all eukaryotes. Knowledge of the biological role of such shared proteins in one organism can often be transferred to other organisms. The goal of the Gene Ontology Consortium is to produce a dynamic, controlled vocabulary that can be applied to all eukaryotes even as knowledge of gene and protein roles in cells is accumulating and changing. To this end, three independent ontologies accessible on the World-Wide Web (http://www.geneontology.org) are being constructed: biological process, molecular function and cellular component.},
	number = {1},
	urldate = {2019-10-06},
	journal = {Nature genetics},
	author = {Ashburner, Michael and Ball, Catherine A. and Blake, Judith A. and Botstein, David and Butler, Heather and Cherry, J. Michael and Davis, Allan P. and Dolinski, Kara and Dwight, Selina S. and Eppig, Janan T. and Harris, Midori A. and Hill, David P. and Issel-Tarver, Laurie and Kasarskis, Andrew and Lewis, Suzanna and Matese, John C. and Richardson, Joel E. and Ringwald, Martin and Rubin, Gerald M. and Sherlock, Gavin},
	month = may,
	year = {2000},
	pmid = {10802651},
	pmcid = {PMC3037419},
	pages = {25--29},
}

@article{jassal_reactome_2020,
	title = {The {Reactome} {Pathway} {Knowledgebase}},
	volume = {48},
	issn = {1362-4962},
	doi = {10.1093/nar/gkz1031},
	abstract = {The Reactome Knowledgebase (https://reactome.org) provides molecular details of signal transduction, transport, DNA replication, metabolism and other cellular processes as an ordered network of molecular transformations in a single consistent data model, an extended version of a classic metabolic map. Reactome functions both as an archive of biological processes and as a tool for discovering functional relationships in data such as gene expression profiles or somatic mutation catalogs from tumor cells. To extend our ability to annotate human disease processes, we have implemented a new drug class and have used it initially to annotate drugs relevant to cardiovascular disease. Our annotation model depends on external domain experts to identify new areas for annotation and to review new content. New web pages facilitate recruitment of community experts and allow those who have contributed to Reactome to identify their contributions and link them to their ORCID records. To improve visualization of our content, we have implemented a new tool to automatically lay out the components of individual reactions with multiple options for downloading the reaction diagrams and associated data, and a new display of our event hierarchy that will facilitate visual interpretation of pathway analysis results.},
	language = {eng},
	number = {D1},
	journal = {Nucleic Acids Research},
	author = {Jassal, Bijay and Matthews, Lisa and Viteri, Guilherme and Gong, Chuqiao and Lorente, Pascual and Fabregat, Antonio and Sidiropoulos, Konstantinos and Cook, Justin and Gillespie, Marc and Haw, Robin and Loney, Fred and May, Bruce and Milacic, Marija and Rothfels, Karen and Sevilla, Cristoffer and Shamovsky, Veronica and Shorser, Solomon and Varusai, Thawfeek and Weiser, Joel and Wu, Guanming and Stein, Lincoln and Hermjakob, Henning and D'Eustachio, Peter},
	year = {2020},
	pmid = {31691815},
	pmcid = {PMC7145712},
	keywords = {Databases, Chemical, Databases, Pharmaceutical, Genome, Human, Humans, Knowledge Bases, Metabolic Networks and Pathways, Protein Interaction Maps, Signal Transduction, Software},
	pages = {D498--D503},
}

@article{szklarczyk_string_2019,
	title = {{STRING} v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets},
	volume = {47},
	issn = {1362-4962},
	shorttitle = {{STRING} v11},
	doi = {10.1093/nar/gky1131},
	abstract = {Proteins and their functional interactions form the backbone of the cellular machinery. Their connectivity network needs to be considered for the full understanding of biological phenomena, but the available information on protein-protein associations is incomplete and exhibits varying levels of annotation granularity and reliability. The STRING database aims to collect, score and integrate all publicly available sources of protein-protein interaction information, and to complement these with computational predictions. Its goal is to achieve a comprehensive and objective global network, including direct (physical) as well as indirect (functional) interactions. The latest version of STRING (11.0) more than doubles the number of organisms it covers, to 5090. The most important new feature is an option to upload entire, genome-wide datasets as input, allowing users to visualize subsets as interaction networks and to perform gene-set enrichment analysis on the entire input. For the enrichment analysis, STRING implements well-known classification systems such as Gene Ontology and KEGG, but also offers additional, new classification systems based on high-throughput text-mining as well as on a hierarchical clustering of the association network itself. The STRING resource is available online at https://string-db.org/.},
	language = {eng},
	number = {D1},
	journal = {Nucleic Acids Research},
	author = {Szklarczyk, Damian and Gable, Annika L. and Lyon, David and Junge, Alexander and Wyder, Stefan and Huerta-Cepas, Jaime and Simonovic, Milan and Doncheva, Nadezhda T. and Morris, John H. and Bork, Peer and Jensen, Lars J. and Mering, Christian von},
	year = {2019},
	pmid = {30476243},
	pmcid = {PMC6323986},
	note = {Number: D1},
	keywords = {Animals, Databases, Genetic, Gene Ontology, Genomics, Humans, Protein Interaction Mapping, Software},
	pages = {D607--D613},
}

@article{kuleshov_enrichr_2016,
	title = {Enrichr: a comprehensive gene set enrichment analysis web server 2016 update},
	volume = {44},
	issn = {1362-4962},
	shorttitle = {Enrichr},
	doi = {10.1093/nar/gkw377},
	abstract = {Enrichment analysis is a popular method for analyzing gene sets generated by genome-wide experiments. Here we present a significant update to one of the tools in this domain called Enrichr. Enrichr currently contains a large collection of diverse gene set libraries available for analysis and download. In total, Enrichr currently contains 180 184 annotated gene sets from 102 gene set libraries. New features have been added to Enrichr including the ability to submit fuzzy sets, upload BED files, improved application programming interface and visualization of the results as clustergrams. Overall, Enrichr is a comprehensive resource for curated gene sets and a search engine that accumulates biological knowledge for further biological discoveries. Enrichr is freely available at: http://amp.pharm.mssm.edu/Enrichr.},
	language = {eng},
	number = {W1},
	journal = {Nucleic Acids Research},
	author = {Kuleshov, Maxim V. and Jones, Matthew R. and Rouillard, Andrew D. and Fernandez, Nicolas F. and Duan, Qiaonan and Wang, Zichen and Koplev, Simon and Jenkins, Sherry L. and Jagodnik, Kathleen M. and Lachmann, Alexander and McDermott, Michael G. and Monteiro, Caroline D. and Gundersen, Gregory W. and Ma'ayan, Avi},
	year = {2016},
	pmid = {27141961},
	pmcid = {PMC4987924},
	note = {Number: W1},
	keywords = {Benchmarking, computational biology, Databases, Genetic, Gene Expression Profiling, Gene Library, Gene Ontology, Genome, Human, Humans, Internet, Molecular Sequence Annotation, User-Computer Interface},
	pages = {W90--97},
}

@article{puente-santamaria_tfeachip_2019,
	title = {{TFEA}.{ChIP}: a tool kit for transcription factor binding site enrichment analysis capitalizing on {ChIP}-seq datasets},
	volume = {35},
	issn = {1367-4811},
	shorttitle = {{TFEA}.{ChIP}},
	doi = {10.1093/bioinformatics/btz573},
	abstract = {SUMMARY: The computational identification of the transcription factors (TFs) [more generally, transcription regulators, (TR)] responsible for the co-regulation of a specific set of genes is a common problem found in genomic analysis. Herein, we describe TFEA.ChIP, a tool that makes use of ChIP-seq datasets to estimate and visualize TR enrichment in gene lists representing transcriptional profiles. We validated TFEA.ChIP using a wide variety of gene sets representing signatures of genetic and chemical perturbations as input and found that the relevant TR was correctly identified in 126 of a total of 174 analyzed. Comparison with other TR enrichment tools demonstrates that TFEA.ChIP is an highly customizable package with an outstanding performance.
AVAILABILITY AND IMPLEMENTATION: TFEA.ChIP is implemented as an R package available at Bioconductor https://www.bioconductor.org/packages/devel/bioc/html/TFEA.ChIP.html and github https://github.com/LauraPS1/TFEA.ChIP\_downloads. A web-based GUI to the package is also available at https://www.iib.uam.es/TFEA.ChIP/.
SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
	language = {eng},
	number = {24},
	journal = {Bioinformatics (Oxford, England)},
	author = {Puente-Santamaria, Laura and Wasserman, Wyeth W. and Del Peso, Luis},
	year = {2019},
	pmid = {31347689},
	note = {Number: 24},
	keywords = {Binding Sites, Chromatin Immunoprecipitation Sequencing, Genomics, Software, Transcription Factors},
	pages = {5339--5340},
}

@article{johnson_large-scale_2020,
	title = {Large-scale proteomic analysis of {Alzheimer}'s disease brain and cerebrospinal fluid reveals early changes in energy metabolism associated with microglia and astrocyte activation},
	volume = {26},
	issn = {1546-170X},
	doi = {10.1038/s41591-020-0815-6},
	abstract = {Our understanding of Alzheimer's disease (AD) pathophysiology remains incomplete. Here we used quantitative mass spectrometry and coexpression network analysis to conduct the largest proteomic study thus far on AD. A protein network module linked to sugar metabolism emerged as one of the modules most significantly associated with AD pathology and cognitive impairment. This module was enriched in AD genetic risk factors and in microglia and astrocyte protein markers associated with an anti-inflammatory state, suggesting that the biological functions it represents serve a protective role in AD. Proteins from this module were elevated in cerebrospinal fluid in early stages of the disease. In this study of {\textgreater}2,000 brains and nearly 400 cerebrospinal fluid samples by quantitative proteomics, we identify proteins and biological processes in AD brains that may serve as therapeutic targets and fluid biomarkers for the disease.},
	language = {eng},
	number = {5},
	journal = {Nature Medicine},
	author = {Johnson, Erik C. B. and Dammer, Eric B. and Duong, Duc M. and Ping, Lingyan and Zhou, Maotian and Yin, Luming and Higginbotham, Lenora A. and Guajardo, Andrew and White, Bartholomew and Troncoso, Juan C. and Thambisetty, Madhav and Montine, Thomas J. and Lee, Edward B. and Trojanowski, John Q. and Beach, Thomas G. and Reiman, Eric M. and Haroutunian, Vahram and Wang, Minghui and Schadt, Eric and Zhang, Bin and Dickson, Dennis W. and Ertekin-Taner, Nilüfer and Golde, Todd E. and Petyuk, Vladislav A. and De Jager, Philip L. and Bennett, David A. and Wingo, Thomas S. and Rangaraju, Srikant and Hajjar, Ihab and Shulman, Joshua M. and Lah, James J. and Levey, Allan I. and Seyfried, Nicholas T.},
	year = {2020},
	pmid = {32284590},
	pmcid = {PMC7405761},
	note = {Number: 5},
	keywords = {Alzheimer Disease, Animals, Astrocytes, Biomarkers, Brain, Case-Control Studies, cerebrospinal fluid, Cohort Studies, Disease Progression, Energy Metabolism, Female, Gene Regulatory Networks, Humans, Male, Mass Spectrometry, Metabolic Networks and Pathways, Mice, Microglia, Nerve Tissue Proteins, Neurogenesis, Proteomics, Sample Size, Time Factors},
	pages = {769--780},
}

@article{grubman_single-cell_2019,
	title = {A single-cell atlas of entorhinal cortex from individuals with {Alzheimer}'s disease reveals cell-type-specific gene expression regulation},
	volume = {22},
	issn = {1546-1726},
	doi = {10.1038/s41593-019-0539-4},
	abstract = {There is currently little information available about how individual cell types contribute to Alzheimer's disease. Here we applied single-nucleus RNA sequencing to entorhinal cortex samples from control and Alzheimer's disease brains (n = 6 per group), yielding a total of 13,214 high-quality nuclei. We detail cell-type-specific gene expression patterns, unveiling how transcriptional changes in specific cell subpopulations are associated with Alzheimer's disease. We report that the Alzheimer's disease risk gene APOE is specifically repressed in Alzheimer's disease oligodendrocyte progenitor cells and astrocyte subpopulations and upregulated in an Alzheimer's disease-specific microglial subopulation. Integrating transcription factor regulatory modules with Alzheimer's disease risk loci revealed drivers of cell-type-specific state transitions towards Alzheimer's disease. For example, transcription factor EB, a master regulator of lysosomal function, regulates multiple disease genes in a specific Alzheimer's disease astrocyte subpopulation. These results provide insights into the coordinated control of Alzheimer's disease risk genes and their cell-type-specific contribution to disease susceptibility. These results are available at http://adsn.ddnetbio.com.},
	language = {eng},
	number = {12},
	journal = {Nature Neuroscience},
	author = {Grubman, Alexandra and Chew, Gabriel and Ouyang, John F. and Sun, Guizhi and Choo, Xin Yi and McLean, Catriona and Simmons, Rebecca K. and Buckberry, Sam and Vargas-Landin, Dulce B. and Poppe, Daniel and Pflueger, Jahnvi and Lister, Ryan and Rackham, Owen J. L. and Petretto, Enrico and Polo, Jose M.},
	year = {2019},
	pmid = {31768052},
	note = {Number: 12},
	keywords = {Humans, Female, Male, Apolipoproteins E, Alzheimer Disease, Case-Control Studies, Microglia, Astrocytes, Gene Expression Regulation, Up-Regulation, Genetic Predisposition to Disease, Sequence Analysis, RNA, Atlases as Topic, Down-Regulation, Entorhinal Cortex, Oligodendrocyte Precursor Cells},
	pages = {2087--2097},
}

@article{cheneby_remap_2018,
	title = {{ReMap} 2018: an updated atlas of regulatory regions from an integrative analysis of {DNA}-binding {ChIP}-seq experiments},
	volume = {46},
	issn = {0305-1048},
	shorttitle = {{ReMap} 2018},
	url = {https://doi.org/10.1093/nar/gkx1092},
	doi = {10.1093/nar/gkx1092},
	abstract = {With this latest release of ReMap (http://remap.cisreg.eu), we present a unique collection of regulatory regions in human, as a result of a large-scale integrative analysis of ChIP-seq experiments for hundreds of transcriptional regulators (TRs) such as transcription factors, transcriptional co-activators and chromatin regulators. In 2015, we introduced the ReMap database to capture the genome regulatory space by integrating public ChIP-seq datasets, covering 237 TRs across 13 million (M) peaks. In this release, we have extended this catalog to constitute a unique collection of regulatory regions. Specifically, we have collected, analyzed and retained after quality control a total of 2829 ChIP-seq datasets available from public sources, covering a total of 485 TRs with a catalog of 80M peaks. Additionally, the updated database includes new search features for TR names as well as aliases, including cell line names and the ability to navigate the data directly within genome browsers via public track hubs. Finally, full access to this catalog is available online together with a TR binding enrichment analysis tool. ReMap 2018 provides a significant update of the ReMap database, providing an in depth view of the complexity of the regulatory landscape in human.},
	number = {D1},
	urldate = {2021-02-28},
	journal = {Nucleic Acids Research},
	author = {Chèneby, Jeanne and Gheorghe, Marius and Artufel, Marie and Mathelier, Anthony and Ballester, Benoit},
	month = jan,
	year = {2018},
	pages = {D267--D275},
}

@article{fishilevich_genehancer_2017,
	title = {{GeneHancer}: genome-wide integration of enhancers and target genes in {GeneCards}},
	volume = {2017},
	issn = {1758-0463},
	shorttitle = {{GeneHancer}},
	url = {https://doi.org/10.1093/database/bax028},
	doi = {10.1093/database/bax028},
	abstract = {A major challenge in understanding gene regulation is the unequivocal identification of enhancer elements and uncovering their connections to genes. We present GeneHancer, a novel database of human enhancers and their inferred target genes, in the framework of GeneCards. First, we integrated a total of 434 000 reported enhancers from four different genome-wide databases: the Encyclopedia of DNA Elements (ENCODE), the Ensembl regulatory build, the functional annotation of the mammalian genome (FANTOM) project and the VISTA Enhancer Browser. Employing an integration algorithm that aims to remove redundancy, GeneHancer portrays 285 000 integrated candidate enhancers (covering 12.4\% of the genome), 94 000 of which are derived from more than one source, and each assigned an annotation-derived confidence score. GeneHancer subsequently links enhancers to genes, using: tissue co-expression correlation between genes and enhancer RNAs, as well as enhancer-targeted transcription factor genes; expression quantitative trait loci for variants within enhancers; and capture Hi-C, a promoter-specific genome conformation assay. The individual scores based on each of these four methods, along with gene–enhancer genomic distances, form the basis for GeneHancer’s combinatorial likelihood-based scores for enhancer–gene pairing. Finally, we define ‘elite’ enhancer–gene relations reflecting both a high-likelihood enhancer definition and a strong enhancer–gene association.GeneHancer predictions are fully integrated in the widely used GeneCards Suite, whereby candidate enhancers and their annotations are displayed on every relevant GeneCard. This assists in the mapping of non-coding variants to enhancers, and via the linked genes, forms a basis for variant–phenotype interpretation of whole-genome sequences in health and disease.Database URL:http://www.genecards.org/},
	number = {bax028},
	urldate = {2021-02-28},
	journal = {Database},
	author = {Fishilevich, Simon and Nudel, Ron and Rappaport, Noa and Hadar, Rotem and Plaschkes, Inbar and Iny Stein, Tsippi and Rosen, Naomi and Kohn, Asher and Twik, Michal and Safran, Marilyn and Lancet, Doron and Cohen, Dana},
	month = jan,
	year = {2017},
}

@article{dunham_integrated_2012,
	title = {An integrated encyclopedia of {DNA} elements in the human genome},
	volume = {489},
	copyright = {2012 The Author(s)},
	issn = {1476-4687},
	url = {https://www.nature.com/articles/nature11247},
	doi = {10.1038/nature11247},
	abstract = {The human genome encodes the blueprint of life, but the function of the vast majority of its nearly three billion bases is unknown. The Encyclopedia of DNA Elements (ENCODE) project has systematically mapped regions of transcription, transcription factor association, chromatin structure and histone modification. These data enabled us to assign biochemical functions for 80\% of the genome, in particular outside of the well-studied protein-coding regions. Many discovered candidate regulatory elements are physically associated with one another and with expressed genes, providing new insights into the mechanisms of gene regulation. The newly identified elements also show a statistical correspondence to sequence variants linked to human disease, and can thereby guide interpretation of this variation. Overall, the project provides new insights into the organization and regulation of our genes and genome, and is an expansive resource of functional annotations for biomedical research.},
	language = {en},
	number = {7414},
	urldate = {2021-02-28},
	journal = {Nature},
	author = {Dunham, Ian and Kundaje, Anshul and Aldred, Shelley F. and Collins, Patrick J. and Davis, Carrie A. and Doyle, Francis and Epstein, Charles B. and Frietze, Seth and Harrow, Jennifer and Kaul, Rajinder and Khatun, Jainab and Lajoie, Bryan R. and Landt, Stephen G. and Lee, Bum-Kyu and Pauli, Florencia and Rosenbloom, Kate R. and Sabo, Peter and Safi, Alexias and Sanyal, Amartya and Shoresh, Noam and Simon, Jeremy M. and Song, Lingyun and Trinklein, Nathan D. and Altshuler, Robert C. and Birney, Ewan and Brown, James B. and Cheng, Chao and Djebali, Sarah and Dong, Xianjun and Dunham, Ian and Ernst, Jason and Furey, Terrence S. and Gerstein, Mark and Giardine, Belinda and Greven, Melissa and Hardison, Ross C. and Harris, Robert S. and Herrero, Javier and Hoffman, Michael M. and Iyer, Sowmya and Kellis, Manolis and Khatun, Jainab and Kheradpour, Pouya and Kundaje, Anshul and Lassmann, Timo and Li, Qunhua and Lin, Xinying and Marinov, Georgi K. and Merkel, Angelika and Mortazavi, Ali and Parker, Stephen C. J. and Reddy, Timothy E. and Rozowsky, Joel and Schlesinger, Felix and Thurman, Robert E. and Wang, Jie and Ward, Lucas D. and Whitfield, Troy W. and Wilder, Steven P. and Wu, Weisheng and Xi, Hualin S. and Yip, Kevin Y. and Zhuang, Jiali and Bernstein, Bradley E. and Birney, Ewan and Dunham, Ian and Green, Eric D. and Gunter, Chris and Snyder, Michael and Pazin, Michael J. and Lowdon, Rebecca F. and Dillon, Laura A. L. and Adams, Leslie B. and Kelly, Caroline J. and Zhang, Julia and Wexler, Judith R. and Green, Eric D. and Good, Peter J. and Feingold, Elise A. and Bernstein, Bradley E. and Birney, Ewan and Crawford, Gregory E. and Dekker, Job and Elnitski, Laura and Farnham, Peggy J. and Gerstein, Mark and Giddings, Morgan C. and Gingeras, Thomas R. and Green, Eric D. and Guigó, Roderic and Hardison, Ross C. and Hubbard, Timothy J. and Kellis, Manolis and Kent, W. James and Lieb, Jason D. and Margulies, Elliott H. and Myers, Richard M. and Snyder, Michael and Stamatoyannopoulos, John A. and Tenenbaum, Scott A. and Weng, Zhiping and White, Kevin P. and Wold, Barbara and Khatun, Jainab and Yu, Yanbao and Wrobel, John and Risk, Brian A. and Gunawardena, Harsha P. and Kuiper, Heather C. and Maier, Christopher W. and Xie, Ling and Chen, Xian and Giddings, Morgan C. and Bernstein, Bradley E. and Epstein, Charles B. and Shoresh, Noam and Ernst, Jason and Kheradpour, Pouya and Mikkelsen, Tarjei S. and Gillespie, Shawn and Goren, Alon and Ram, Oren and Zhang, Xiaolan and Wang, Li and Issner, Robbyn and Coyne, Michael J. and Durham, Timothy and Ku, Manching and Truong, Thanh and Ward, Lucas D. and Altshuler, Robert C. and Eaton, Matthew L. and Kellis, Manolis and Djebali, Sarah and Davis, Carrie A. and Merkel, Angelika and Dobin, Alex and Lassmann, Timo and Mortazavi, Ali and Tanzer, Andrea and Lagarde, Julien and Lin, Wei and Schlesinger, Felix and Xue, Chenghai and Marinov, Georgi K. and Khatun, Jainab and Williams, Brian A. and Zaleski, Chris and Rozowsky, Joel and Röder, Maik and Kokocinski, Felix and Abdelhamid, Rehab F. and Alioto, Tyler and Antoshechkin, Igor and Baer, Michael T. and Batut, Philippe and Bell, Ian and Bell, Kimberly and Chakrabortty, Sudipto and Chen, Xian and Chrast, Jacqueline and Curado, Joao and Derrien, Thomas and Drenkow, Jorg and Dumais, Erica and Dumais, Jackie and Duttagupta, Radha and Fastuca, Megan and Fejes-Toth, Kata and Ferreira, Pedro and Foissac, Sylvain and Fullwood, Melissa J. and Gao, Hui and Gonzalez, David and Gordon, Assaf and Gunawardena, Harsha P. and Howald, Cédric and Jha, Sonali and Johnson, Rory and Kapranov, Philipp and King, Brandon and Kingswood, Colin and Li, Guoliang and Luo, Oscar J. and Park, Eddie and Preall, Jonathan B. and Presaud, Kimberly and Ribeca, Paolo and Risk, Brian A. and Robyr, Daniel and Ruan, Xiaoan and Sammeth, Michael and Sandhu, Kuljeet Singh and Schaeffer, Lorain and See, Lei-Hoon and Shahab, Atif and Skancke, Jorgen and Suzuki, Ana Maria and Takahashi, Hazuki and Tilgner, Hagen and Trout, Diane and Walters, Nathalie and Wang, Huaien and Wrobel, John and Yu, Yanbao and Hayashizaki, Yoshihide and Harrow, Jennifer and Gerstein, Mark and Hubbard, Timothy J. and Reymond, Alexandre and Antonarakis, Stylianos E. and Hannon, Gregory J. and Giddings, Morgan C. and Ruan, Yijun and Wold, Barbara and Carninci, Piero and Guigó, Roderic and Gingeras, Thomas R. and Rosenbloom, Kate R. and Sloan, Cricket A. and Learned, Katrina and Malladi, Venkat S. and Wong, Matthew C. and Barber, Galt P. and Cline, Melissa S. and Dreszer, Timothy R. and Heitner, Steven G. and Karolchik, Donna and Kent, W. James and Kirkup, Vanessa M. and Meyer, Laurence R. and Long, Jeffrey C. and Maddren, Morgan and Raney, Brian J. and Furey, Terrence S. and Song, Lingyun and Grasfeder, Linda L. and Giresi, Paul G. and Lee, Bum-Kyu and Battenhouse, Anna and Sheffield, Nathan C. and Simon, Jeremy M. and Showers, Kimberly A. and Safi, Alexias and London, Darin and Bhinge, Akshay A. and Shestak, Christopher and Schaner, Matthew R. and Ki Kim, Seul and Zhang, Zhuzhu Z. and Mieczkowski, Piotr A. and Mieczkowska, Joanna O. and Liu, Zheng and McDaniell, Ryan M. and Ni, Yunyun and Rashid, Naim U. and Kim, Min Jae and Adar, Sheera and Zhang, Zhancheng and Wang, Tianyuan and Winter, Deborah and Keefe, Damian and Birney, Ewan and Iyer, Vishwanath R. and Lieb, Jason D. and Crawford, Gregory E. and Li, Guoliang and Sandhu, Kuljeet Singh and Zheng, Meizhen and Wang, Ping and Luo, Oscar J. and Shahab, Atif and Fullwood, Melissa J. and Ruan, Xiaoan and Ruan, Yijun and Myers, Richard M. and Pauli, Florencia and Williams, Brian A. and Gertz, Jason and Marinov, Georgi K. and Reddy, Timothy E. and Vielmetter, Jost and Partridge, E. and Trout, Diane and Varley, Katherine E. and Gasper, Clarke and {The ENCODE Project Consortium} and {Overall coordination (data analysis coordination)} and {Data production leads (data production)} and {Lead analysts (data analysis)} and {Writing group} and {NHGRI project management (scientific management)} and {Principal investigators (steering committee)} and {Boise State University and University of North Carolina at Chapel Hill Proteomics groups (data production and analysis)} and {Broad Institute Group (data production and analysis)} and Cold Spring Harbor, Center for Genomic Regulation, Barcelona, RIKEN, Sanger Institute, University of Lausanne, Genome Institute of Singapore group (data production {and} analysis), University of Geneva and {Data coordination center at UC Santa Cruz (production data coordination)} and Duke University, University of Texas, Austin, University of North Carolina-Chapel Hill group (data production {and} analysis), EBI and {Genome Institute of Singapore group (data production and analysis)} and HudsonAlpha Institute, UC Irvine, Stanford group (data production {and} analysis), Caltech},
	month = sep,
	year = {2012},
	note = {Number: 7414
Publisher: Nature Publishing Group},
	pages = {57--74},
}

@article{lachmann_chea_2010,
	title = {{ChEA}: transcription factor regulation inferred from integrating genome-wide {ChIP}-{X} experiments},
	volume = {26},
	issn = {1367-4811},
	shorttitle = {{ChEA}},
	doi = {10.1093/bioinformatics/btq466},
	abstract = {MOTIVATION: Experiments such as ChIP-chip, ChIP-seq, ChIP-PET and DamID (the four methods referred herein as ChIP-X) are used to profile the binding of transcription factors to DNA at a genome-wide scale. Such experiments provide hundreds to thousands of potential binding sites for a given transcription factor in proximity to gene coding regions.
RESULTS: In order to integrate data from such studies and utilize it for further biological discovery, we collected interactions from such experiments to construct a mammalian ChIP-X database. The database contains 189,933 interactions, manually extracted from 87 publications, describing the binding of 92 transcription factors to 31,932 target genes. We used the database to analyze mRNA expression data where we perform gene-list enrichment analysis using the ChIP-X database as the prior biological knowledge gene-list library. The system is delivered as a web-based interactive application called ChIP Enrichment Analysis (ChEA). With ChEA, users can input lists of mammalian gene symbols for which the program computes over-representation of transcription factor targets from the ChIP-X database. The ChEA database allowed us to reconstruct an initial network of transcription factors connected based on shared overlapping targets and binding site proximity. To demonstrate the utility of ChEA we present three case studies. We show how by combining the Connectivity Map (CMAP) with ChEA, we can rank pairs of compounds to be used to target specific transcription factor activity in cancer cells.
AVAILABILITY: The ChEA software and ChIP-X database is freely available online at: http://amp.pharm.mssm.edu/lib/chea.jsp.},
	language = {eng},
	number = {19},
	journal = {Bioinformatics (Oxford, England)},
	author = {Lachmann, Alexander and Xu, Huilei and Krishnan, Jayanth and Berger, Seth I. and Mazloom, Amin R. and Ma'ayan, Avi},
	month = oct,
	year = {2010},
	pmid = {20709693},
	pmcid = {PMC2944209},
	keywords = {Chromatin Immunoprecipitation, Databases, Genetic, Gene Expression Regulation, Genome, Software, Transcription Factors},
	pages = {2438--2444},
}

@article{simpson_microarray_2011,
	title = {Microarray analysis of the astrocyte transcriptome in the aging brain: relationship to {Alzheimer}'s pathology and {APOE} genotype},
	volume = {32},
	issn = {1558-1497},
	shorttitle = {Microarray analysis of the astrocyte transcriptome in the aging brain},
	doi = {10.1016/j.neurobiolaging.2011.04.013},
	abstract = {Astrocytes contribute to a variety of functions in the brain, including homeostasis, synapse formation, plasticity, and metabolism. Astrocyte dysfunction may disrupt their normal role, including neuronal support, thereby contributing to neurodegenerative pathologies, including Alzheimer's disease (AD). To understand the role of astrocytes in the pathogenesis of age-related disorders, we isolated astrocytes by laser capture microdissection, using glial fibrillary acidic protein (GFAP) as a marker, and characterized the astrocyte transcriptome at different Braak neurofibrillary tangle stages in postmortem temporal cortex samples derived from the Medical Research Council Cognitive Function and Ageing Study (MRC CFAS) cohort, using microarray analysis. The largest number of significant, differentially expressed genes were identified when the expression profile of astrocytes from isocortical stages of neurofibrillary tangle pathology (Braak stages V-VI) were compared with entorhinal stages (Braak stages I-II). Dysregulation of genes associated with the actin cytoskeleton, proliferation, apoptosis, and ubiquitin-mediated proteolysis occurred at low Braak stages, while altered regulation of intracellular signaling pathways, including insulin, phosphatidylinositol 3-kinase (PI3K)/Akt, and mitogen-activated protein kinase (MAPK) pathways were primarily associated with high levels of Alzheimer-type pathology, and occurred at lower Braak stages in individuals with the APOEε4 allele. Our findings implicate astrocyte dysfunction in the pathogenesis of neurodegenerative pathology in the aging brain, and provide a basis for future candidate studies based on specific pathways.},
	language = {eng},
	number = {10},
	journal = {Neurobiology of Aging},
	author = {Simpson, Julie E. and Ince, Paul G. and Shaw, Pamela J. and Heath, Paul R. and Raman, Rohini and Garwood, Claire J. and Gelsthorpe, Catherine and Baxter, Lynne and Forster, Gillian and Matthews, Fiona E. and Brayne, Carol and Wharton, Stephen B. and {MRC Cognitive Function and Ageing Neuropathology Study Group}},
	month = oct,
	year = {2011},
	pmid = {21705112},
	keywords = {Actins, Aged, Aged, 80 and over, Aging, Apolipoproteins E, Astrocytes, Female, Gene Expression Regulation, Genotype, Glial Fibrillary Acidic Protein, Humans, Male, Microarray Analysis, Microdissection, Postmortem Changes, Reproducibility of Results, Signal Transduction, Temporal Lobe, Transcriptome},
	pages = {1795--1807},
}

@article{the_uniprot_consortium_uniprot_2021,
	title = {{UniProt}: the universal protein knowledgebase in 2021},
	volume = {49},
	issn = {0305-1048},
	shorttitle = {{UniProt}},
	url = {https://doi.org/10.1093/nar/gkaa1100},
	doi = {10.1093/nar/gkaa1100},
	abstract = {The aim of the UniProt Knowledgebase is to provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functional information. In this article, we describe significant updates that we have made over the last two years to the resource. The number of sequences in UniProtKB has risen to approximately 190 million, despite continued work to reduce sequence redundancy at the proteome level. We have adopted new methods of assessing proteome completeness and quality. We continue to extract detailed annotations from the literature to add to reviewed entries and supplement these in unreviewed entries with annotations provided by automated systems such as the newly implemented Association-Rule-Based Annotator (ARBA). We have developed a credit-based publication submission interface to allow the community to contribute publications and annotations to UniProt entries. We describe how UniProtKB responded to the COVID-19 pandemic through expert curation of relevant entries that were rapidly made available to the research community through a dedicated portal. UniProt resources are available under a CC-BY (4.0) license via the web at https://www.uniprot.org/.},
	number = {D1},
	urldate = {2021-04-01},
	journal = {Nucleic Acids Research},
	author = {{The UniProt Consortium}},
	month = jan,
	year = {2021},
	pages = {D480--D489},
}

@article{tweedie_genenamesorg_2021,
	title = {Genenames.org: the {HGNC} and {VGNC} resources in 2021},
	volume = {49},
	issn = {0305-1048},
	shorttitle = {Genenames.org},
	url = {https://doi.org/10.1093/nar/gkaa980},
	doi = {10.1093/nar/gkaa980},
	abstract = {The HUGO Gene Nomenclature Committee (HGNC) based at EMBL’s European Bioinformatics Institute (EMBL-EBI) assigns unique symbols and names to human genes. There are over 42,000 approved gene symbols in our current database of which over 19 000 are for protein-coding genes. While we still update placeholder and problematic symbols, we are working towards stabilizing symbols where possible; over 2000 symbols for disease associated genes are now marked as stable in our symbol reports. All of our data is available at the HGNC website https://www.genenames.org. The Vertebrate Gene Nomenclature Committee (VGNC) was established to assign standardized nomenclature in line with human for vertebrate species lacking their own nomenclature committee. In addition to the previous VGNC core species of chimpanzee, cow, horse and dog, we now name genes in cat, macaque and pig. Gene groups have been added to VGNC and currently include two complex families: olfactory receptors (ORs) and cytochrome P450s (CYPs). In collaboration with specialists we have also named CYPs in species beyond our core set. All VGNC data is available at https://vertebrate.genenames.org/. This article provides an overview of our online data and resources, focusing on updates over the last two years.},
	number = {D1},
	urldate = {2021-04-01},
	journal = {Nucleic Acids Research},
	author = {Tweedie, Susan and Braschi, Bryony and Gray, Kristian and Jones, Tamsin E M and Seal, Ruth L and Yates, Bethan and Bruford, Elspeth A},
	month = jan,
	year = {2021},
	pages = {D939--D946},
}