Alter: Annotate BND

README.md

@@ -22,5 +22,6 @@ $ choppy batch YaqingLiu/VEP-latest samples.csv -p Project [-l project:Label]
 $ choppy query -L project:Label | grep "status"
 ```
 ### Output
-
-.maf
+1. maf
+2. INPUT.vcf
+3. BND.VEP.txt

defaults

@@ -7,6 +7,7 @@
   "species": "homo_sapiens_merged",
   "ncbi_build": "GRCh38",
   "only_pass": true,
+  "vcf2maf_path": "/opt/mskcc-vcf2maf", 
   "disk_size": "200",
   "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc"
 }

inputs

@@ -10,6 +10,7 @@
   "{{ project_name }}.ncbi_build": "{{ ncbi_build }}",
   "{{ project_name }}.species": "{{ species }}",
   "{{ project_name }}.only_pass": {{ only_pass | tojson }},
+  "{{ project_name }}.vcf2maf_path": "{{ vcf2maf_path }}",
   "{{ project_name }}.vep_docker": "{{ vep_docker }}",
   "{{ project_name }}.disk_size": "{{ disk_size }}",
   "{{ project_name }}.cluster_config": "{{ cluster_config }}"

tasks/vcf2maf.wdl

@@ -12,6 +12,7 @@ task vcf2maf {
   String ncbi_build
   String species
   Boolean only_pass
+  String vcf2maf_path
   String docker
   String cluster_config
   String disk_size
@@ -28,8 +29,13 @@ task vcf2maf {
       cp ${vcf} ${sample_id}.INPUT.vcf
     fi
 
-    perl /opt/mskcc-vcf2maf/vcf2maf.pl \
-    --input-vcf ${sample_id}.INPUT.vcf --output-maf ${basename}.maf \
+    # Extract the BND variants from VCF
+    awk -F'\t' '{if(($1~"^#")||($8!~".*SVTYPE=BND.*")){print $0}}' ${sample_id}.INPUT.vcf > ${sample_id}.INPUT.vcf2maf.vcf
+    awk -F'\t' '{if(($1~"^#")||($8~".*SVTYPE=BND.*")){print $0}}' ${sample_id}.INPUT.vcf > ${sample_id}.INPUT.VEP.vcf
+
+    # vcf2maf
+    perl ${vcf2maf_path}/vcf2maf.pl \
+    --input-vcf ${sample_id}.INPUT.vcf2maf.vcf --output-maf ${basename}.maf \
     --tumor-id ${tumor_id} --normal-id ${normal_id} \
     --ref-fasta ${ref_dir}/${fasta} \
     --vep-path ${vep_path} \
@@ -37,6 +43,16 @@ task vcf2maf {
     --ncbi-build ${ncbi_build} \
     --species ${species} \
     --vep-fork $nt
+
+    # vep: only annotate the BND
+    perl ${vep_path}/vep \
+    --input_file ${sample_id}.INPUT.VEP.vcf --output_file ${basename}.BND.VEP.txt \
+    --fasta ${ref_dir}/${fasta} \
+    --dir ${cache} \
+    --assembly ${ncbi_build} \
+    --species ${species} \
+    --fork $nt \
+    --no_progress --no_stats --buffer_size 5000 --sift b --ccds --uniprot --hgvs --symbol --numbers --domains --gene_phenotype --canonical --protein --biotype --uniprot --tsl --variant_class --shift_hgvs 1 --check_existing --total_length --allele_number --no_escape --xref_refseq --failed 1 --tab --flag_pick_allele --pick_order canonical,tsl,biotype,rank,ccds,length --format vcf --force_overwrite --offline --pubmed --regulatory
   >>>
   
   runtime {
@@ -49,5 +65,6 @@ task vcf2maf {
   output {
     File input_vcf = "${sample_id}.INPUT.vcf"
     File maf = "${basename}.maf"
+    File bnd_vep = "${basename}.BND.VEP.txt"
   }
 }

workflow.wdl

@@ -13,6 +13,7 @@ workflow {{ project_name }} {
   String ncbi_build
   String species
   Boolean only_pass
+  String vcf2maf_path
   String vep_docker
   String cluster_config
   String disk_size
@@ -30,6 +31,7 @@ workflow {{ project_name }} {
     ncbi_build=ncbi_build,
     species=species,
     only_pass=only_pass,
+    vcf2maf_path=vcf2maf_path,
     docker=vep_docker,
     cluster_config=cluster_config,
     disk_size=disk_size