Renamed filter into cohort and some other small things.

* Singularised `masks` into `mask`.
* The directories for masks are available on the command line.
* Removed all mentions of swegen.

Author: viklund

README.md

@@ -66,7 +66,7 @@ Options:
                 Callers: manta, fermikit
                 Annotation: vep, snpeff
                 Extra: normalize (with vt),
-                       filter (with bed files in masks_filters/, by default swegen is used)
+                       filter (with bed files in mask_cohort/)
     --sg_mask_ovlp  Fractional overlap for use with the filter option
     --no_sg_reciprocal  Don't use a reciprocal overlap for the filter option
     --outdir        Directory where resultfiles are stored (default: results)
@@ -114,10 +114,10 @@ file. That file also specifies how to deal with errors and the interaction
 with the Slurm scheduler, you probably don't want to change those unless you
 know what you are doing.
 
-The two folders `masks_artifacts` and `masks_filters` contain bed files to
+The two folders `mask_artifacts` and `mask_cohort` contain bed files to
 filter the vcf-files from the callers. The artifact directory contains files
-that should mask out problematic regions, it removes everything that has an
-overlaps at least 25% with a region in the artifact mask. The filter one is
+that should remove problematic regions, it removes everything that has an
+overlap of at least 25% with a region in the artifact mask. The cohort one is
 for more stringent filtering of already known variants, and here the default
 filter threshold is instead a reciprocal overlap of 95%. It can be customized
 with the two options `sg_mask_ovlp` (default 0.95) and `no_sg_reciprocal`.

main.nf

@@ -170,7 +170,7 @@ process artifact_mask_vcfs {
 
     """
     BNAME=\$( echo $svfile | cut -d. -f1 )
-    MASK_DIR=$params.mask_dirs.masks_artifacts
+    MASK_DIR=$params.mask_dir_artifacts
 
     # We don't want to change the filename in this process so we copy the
     # infile and remove the symbolic link. And then recreate the file at the
@@ -191,14 +191,14 @@ process artifact_mask_vcfs {
 }
 
 
-ch_noswegen_mask = ch_artifact_masked_vcfs.tap { ch_swegen_mask_in }
+ch_nocohort_mask = ch_artifact_masked_vcfs.tap { ch_cohort_mask_in }
 reciprocal = params.no_sg_reciprocal ? '': '-r'
 
-process swegen_mask_vcfs {
+process cohort_mask_vcfs {
     input:
-        set file(svfile), val(uuid), val(dir) from ch_swegen_mask_in
+        set file(svfile), val(uuid), val(dir) from ch_cohort_mask_in
     output:
-        set file('*_swegen_masked.vcf'), val(uuid), val(dir) into ch_swegen_masked_vcfs
+        set file('*_cohort_masked.vcf'), val(uuid), val(dir) into ch_cohort_masked_vcfs
 
     tag "$uuid $svfile"
 
@@ -207,8 +207,8 @@ process swegen_mask_vcfs {
 
     """
     BNAME=\$( echo $svfile | cut -d. -f1 )
-    MASK_FILE=\${BNAME}_swegen_masked.vcf
-    MASK_DIR=$params.mask_dirs.masks_filters
+    MASK_FILE=\${BNAME}_cohort_masked.vcf
+    MASK_DIR=$params.mask_dir_cohort
 
     cp $svfile workfile
     for mask in \$MASK_DIR/*; do
@@ -224,7 +224,7 @@ process swegen_mask_vcfs {
     """
 }
 
-ch_masked_vcfs = ch_noswegen_mask.mix(ch_swegen_masked_vcfs)
+ch_masked_vcfs = ch_nocohort_mask.mix(ch_cohort_masked_vcfs)
 
 // To make intersect files we need to combine them into one channel with
 // toList() and then sort in the map so that fermi is before manta in the
@@ -439,7 +439,7 @@ def usage_message() {
     log.info '                Callers: manta, fermikit'
     log.info '                Annotation: vep, snpeff'
     log.info '                Extra: normalize (with vt),'
-    log.info '                       filter (with bed files in masks_filters/, by default swegen is used)'
+    log.info '                       filter (with bed files in mask_cohort/)'
     log.info '    --sg_mask_ovlp  Fractional overlap for use with the filter option'
     log.info '    --no_sg_reciprocal  Don\'t use a reciprocal overlap for the filter option'
     log.info '    --outdir        Directory where resultfiles are stored (default: results)'

masks_artifacts/LCR-hs37d5.bed.gz mask_artifacts/LCR-hs37d5.bed.gzmasks_artifacts/LCR-hs37d5.bed.gz renamed to mask_artifacts/LCR-hs37d5.bed.gz

@@ -8,9 +8,9 @@ params {
     prefix = ''
     help = False
 
-    //optional swegen masking
-    sg_mask_ovlp = 0.95 // --sg_mask_ovlp in case other overlap value than default 0.95 for swegen
-    no_sg_reciprocal = False // --no_sg_reciprocal in case swegen masking should not include reciprocal overlap option
+    //optional cohort masking
+    sg_mask_ovlp = 0.95 // --sg_mask_ovlp in case other overlap value than default 0.95 for cohort
+    no_sg_reciprocal = False // --no_sg_reciprocal in case cohort masking should not include reciprocal overlap option
 
     // Reference assemblies
     ref_fasta = "/sw/data/uppnex/ToolBox/ReferenceAssemblies/hg38make/bundle/2.8/b37/human_g1k_v37.fasta"
@@ -24,10 +24,8 @@ params {
     }
 
     // Dirs that contain BED files for masking
-    mask_dirs {
-        masks_artifacts = "$baseDir/masks_artifacts"
-        masks_filters = "$baseDir/masks_filters"
-    }
+    mask_dir_artifacts = "$baseDir/mask_artifacts"
+    mask_dir_cohort = "$baseDir/mask_cohort"
 }
 
 profiles {