Merge pull request #26 from zjnolen/subsample

Enable subsampling to lower depth

.test/config/config.yaml

@@ -24,10 +24,6 @@ exclude_ind: []
 
 excl_pca-admix: []
 
-#==================== Downsampling Configuration ======================#
-
-downsample_cov:
-
 #====================== Analysis Selection ============================#
 
 populations: []
@@ -68,6 +64,29 @@ analyses:
   inbreeding_ngsf-hmm: true
   ibs_matrix: true
 
+#==================== Downsampling Configuration ======================#
+
+subsample_dp: 2
+
+subsample_redo_filts: true
+
+subsample_analyses:
+  estimate_ld: true
+  ld_decay: true
+  pca_pcangsd: true
+  admix_ngsadmix: true
+  relatedness:
+    ngsrelate: true
+    ibsrelate_ibs: true
+    ibsrelate_sfs: true
+  thetas_angsd: true
+  heterozygosity_angsd: true
+  fst_angsd:
+    populations: true
+    individuals: true
+  inbreeding_ngsf-hmm: true
+  ibs_matrix: true
+
 #=========================== Filter Sets ==============================#
 
 filter_beds:
@@ -109,6 +128,7 @@ params:
     extra_beagle: ""
     snp_pval: "1e-6"
     min_maf: 0.05
+    mindepthind_heterozygosity: 3
   ngsld:
     max_kb_dist_est-ld: 200
     max_kb_dist_decay: 100

README.md

@@ -69,6 +69,12 @@ Additionally, several data filtering options are available:
 - Removal of regions with low mappability for fragments of a specified size
 - Removal of regions with extreme high or low depth
 - Removal of regions with a certain amount of missing data
+- Multiple filter sets from user provided BED files that can be intersected
+  with other enabled filters (for instance, performing analyses on neutral
+  sites and genic regions separately)
+
+All the above analyses can also be performed with sample depth subsampled to
+a uniform level to account for differences in depth between samples.
 
 ## Getting Started
 

config/README.md

@@ -282,6 +282,30 @@ settings for each analysis are set in the next section.
   - `ibs_matrix:` Estimate pairwise identity by state distance between all
     samples using ANGSD. (`true`/`false`)
 
+#### Downsampling Section
+
+As this workflow is aimed at low coverage samples, its likely there might be
+considerable variance in sample depth. For this reason, it may be good to
+subsample all your samples to a similar depth to examine if variation in depth
+is influencing results. To do this, set an integer value here to subsample all
+your samples down to and run specific analyses.
+
+- `subsample_dp:` A mean depth to subsample your reads to. This will be done
+  per sample, and subsample from all the reads. If a sample already has the
+  same, or lower, depth than this number, it will just be used as is in the
+  analysis. (INT)
+
+- `subsample_redo_filts:` Make a separate filtered sites file using the
+  subsampled bams to calculate depth based filters. If left disabled, the
+  depth filters will be determined from the full coverage files.
+  (`true`/`false`)
+
+- `subsample_analyses:` Individually enable analyses to be performed with the
+  subsampled data. These are the same as the ones above in the analyses
+  section. Enabling here will only run the analysis for the subsampled data,
+  if you want to run it for the full data as well, you need to enable it in the
+  analyses section as well. (`true`/`false`)
+
 #### Filter Sets
 
 By default, this workflow will perform all analyses requested in the above

config/config.yaml

@@ -24,12 +24,6 @@ exclude_ind: []
 
 excl_pca-admix: []
 
-#==================== Downsampling Configuration ======================#
-
-# untested, not recommended for now
-
-downsample_cov:
-
 #====================== Analysis Selection ============================#
 
 populations: []
@@ -70,6 +64,29 @@ analyses:
   inbreeding_ngsf-hmm: false
   ibs_matrix: false
 
+#==================== Downsampling Configuration ======================#
+
+subsample_dp:
+
+subsample_redo_filts:
+
+subsample_analyses:
+  estimate_ld: false
+  ld_decay: false
+  pca_pcangsd: false
+  admix_ngsadmix: false
+  relatedness:
+    ngsrelate: false
+    ibsrelate_ibs: false
+    ibsrelate_sfs: false
+  thetas_angsd: false
+  heterozygosity_angsd: false
+  fst_angsd:
+    populations: false
+    individuals: false
+  inbreeding_ngsf-hmm: false
+  ibs_matrix: false
+
 #=========================== Filter Sets ==============================#
 
 filter_beds:
@@ -109,6 +126,7 @@ params:
     extra_beagle: ""
     snp_pval: "1e-6"
     min_maf: 0.05
+    mindepthind_heterozygosity: 3
   ngsld:
     max_kb_dist_est-ld: 4000
     max_kb_dist_decay: 100