Better sorting of freebayes outputs

marine-omics · Apr 2, 2024 · 60bfac6 · 60bfac6
1 parent b097472
commit 60bfac6
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 2 deletions.
diff --git a/main.nf b/main.nf
@@ -91,7 +91,7 @@ workflow {
   ch_baicollection = ch_mapped_marked_bais.map{m,b -> b} | collect
   ch_chunk_vcfs = freebayes(ch_bamcollection,ch_baicollection,genome_fasta,genome_fai,ch_regions,file(params.populations)) | collect
 
-  freebayes_collect(ch_chunk_vcfs)
+  freebayes_collect(ch_chunk_vcfs,"${projectDir}/bash/sort_vcf_files.sh")
 
 // bcftools
   mpileup_call(ch_bamcollection,ch_baicollection,genome_fasta,genome_fai)  

diff --git a/modules/freebayes.nf b/modules/freebayes.nf
@@ -90,6 +90,7 @@ process freebayes_collect {
 
     input:
     path(vcf)
+    path('sort_vcf_files.sh')
 
     output:
     path("*.vcf.gz"), emit: vcf
@@ -100,7 +101,7 @@ process freebayes_collect {
     def prefix="freebayes"
 
     """
-    cat *.vcf | vcffirstheader | vcfstreamsort -w 1000 > ${prefix}.vcf
+    sort_vcf_files.sh | xargs cat | vcffirstheader | vcfstreamsort -w 1000 > ${prefix}.vcf
 
     bgzip ${prefix}.vcf
     tabix ${prefix}.vcf.gz

diff --git a/shell/sort_vcf_files.sh b/shell/sort_vcf_files.sh
@@ -0,0 +1 @@
+ls *.vcf | awk -F "[:.-]" '{print $1,$2,$3,$4,$5}' | sort -k2,2 -k4,4n | awk '{printf("%s.%s.%s:%s-%s.vcf\n",$1,$2,$3,$4,$5)}'