test

tasks/VEP.wdl

@@ -0,0 +1,82 @@
+task VEP {
+
+  File vcf
+  String sample_id
+  String basename = basename(vcf,".vcf")
+  String tumor_id
+  String normal_id
+  File ref_dir
+  String fasta
+  String vep_path
+  File cache
+  String ncbi_build
+  String species
+  Boolean only_pass
+  String vcf2maf_path
+  String docker
+  String cluster_config
+  String disk_size
+
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+
+    if [ only_pass ]; then
+      awk -F'\t' '{if(($1~"^#")||($1!~"^#" && $7=="PASS")){print $0}}' ${vcf} > ${sample_id}.INPUT.vcf
+    else
+      cp ${vcf} ${sample_id}.INPUT.vcf
+    fi
+
+    # 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} \
+    # --vep-data ${cache} \
+    # --ncbi-build ${ncbi_build} \
+    # --species ${species} \
+    # --vep-fork $nt
+
+    # vep
+    perl ${vep_path}/vep \
+    --input_file ${sample_id}.INPUT.vcf --output_file ${basename}.vep.vcf \
+    --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
+
+    # vcf2maf
+    perl ${vcf2maf_path}/vcf2maf.pl \
+    --inhibit-vep
+    --input-vcf ${basename}.vep.vcf --output-maf ${basename}.maf \
+    --tumor-id ${tumor_id} --normal-id ${normal_id} \
+    --ref-fasta ${ref_dir}/${fasta} \
+    --vep-path ${vep_path} \
+    --vep-data ${cache} \
+    --ncbi-build ${ncbi_build} \
+    --species ${species} \
+    --vep-fork $nt
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+
+  output {
+    File input_vcf = "${sample_id}.INPUT.vcf"
+    File vep_vcf = "${basename}.vep.vcf"
+    File maf = "${basename}.maf"
+  }
+}

workflow.wdl

@@ -1,4 +1,4 @@
-import "./tasks/vcf2maf.wdl" as vcf2maf
+import "./tasks/VEP.wdl" as VEP
 
 workflow {{ project_name }} {
   
@@ -18,7 +18,7 @@ workflow {{ project_name }} {
   String cluster_config
   String disk_size
 
-  call vcf2maf.vcf2maf as vcf2maf {
+  call VEP.VEP as VEP {
     input: 
     vcf=vcf,
     sample_id=sample_id,