now computing stats on subwindows within focal (#92)

* now computing stats on subwindows within focal * state of things for probgen poster * outputting vcf for shic * updating env.yml * flatten samples * fixed environment.yml --------- Co-authored-by: andrewkern <[email protected]>
popsim-consortium · Jun 23, 2023 · 2d0b547 · 2d0b547
1 parent f6f94fd
commit 2d0b547
Show file tree

Hide file tree

Showing 5 changed files with 1,015 additions and 60 deletions.
diff --git a/environment.yml b/environment.yml
@@ -2,6 +2,7 @@ name: analysis2
 channels:
   - conda-forge
   - bioconda
+  - r
 dependencies:
   - gcc
   - gmp
@@ -28,6 +29,13 @@ dependencies:
   - mamba
   - openjdk
   - sweepfinder2
+  - scikit-learn
+  - r-base
+  - r-essentials
+  - r-irkernel
+  - r-ggplot2
+  - r-dplyr
+  - libprotobuf=3.21.12
   - pip:
     - git+https://github.com/popsim-consortium/stdpopsim.git
     - scikit-allel

diff --git a/power_analysis.ipynb b/power_analysis.ipynb
diff --git a/workflows/config/snakemake/small_sweep.yaml b/workflows/config/snakemake/small_sweep.yaml
@@ -1,6 +1,6 @@
 # General configs
 seed: 12345
-replicates: 2
+replicates: 3
 output_dir: results
 
 # Contig configs
@@ -27,11 +27,13 @@ annotation_list:
 num_windows: 2 # number of sweep locations in chromosome
 focal_size: 5_000_000 # size of the focal sweep window in bp
 buffer_cM: 2.5
+num_subwins: 10 # number of subwindows within focal to compute statistic
 # Sweep configs
 coeffs: 
   bounds: [0.03, 0.1]
   grid_size: 1 # This will yield just one s=0.03 or 2Ns~600
 sweep_min_freq: 0.8
+time_multipliers: [1, 2, 4]
 
 # slim settings
 slim_scaling_factor: 2

diff --git a/workflows/config/snakemake/sweep_config.yaml b/workflows/config/snakemake/sweep_config.yaml
@@ -12,8 +12,8 @@ genetic_map: HapMapII_GRCh38
 demo_model:
   id: OutOfAfrica_3G09
   samples: 
-    YRI: 1000
-    CEU: 1000
+    YRI: 10
+    CEU: 10
     CHB: 0
 
 # BGS configs
@@ -27,11 +27,14 @@ annotation_list:
 num_windows: 100 # number of sweep locations in chromosome
 focal_size: 5_000_000 # size of the focal sweep window in bp
 buffer_cM: 2.5
+num_subwins: 10 # number of subwindows within focal to compute statistic
+
 # Sweep configs
 coeffs: 
   bounds: [0.03, 0.1]
   grid_size: 1 # This will yield just one s=0.03 or 2Ns~600
 sweep_min_freq: 0.8
+time_multipliers: [1]
 
 # slim settings
 slim_scaling_factor: 2