Fixbug: vcf2vcf parameter

tasks/VEP.wdl

@@ -3,8 +3,6 @@ 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
@@ -26,14 +24,18 @@ task VEP {
 
     awk -F'\t' '{if(($1~"^#")||($1!~"^#" && $7=="PASS")){print $0}}' ${vcf} > ${sample_id}.vcf
     
+
+
     # Judge the SAMPLE info of vcf file
-    ncol=`awk -F'\t' '{if($1!~"^#"){print NF}}' ${sample_id}.vcf | uniq`
-    if [ $ncol -lt 11 ]; then
-      SAMPLE_vcf2maf="--tumor-id ${tumor_id} --normal-id ${normal_id}"
-      SAMPLE_vcf2vcf="--vcf-tumor-id ${tumor_id} --vcf-normal-id ${normal_id}"
+    tumor_id=`awk -F'\t' '{if($1~"^#CHROM"){print $10}}' ${vcf}`
+    normal_id=`awk -F'\t' '{if($1~"^#CHROM"){print $11}}' ${vcf}`
+
+    if [ $normal_id ]; then
+      SAMPLE_vcf2maf="--tumor-id $tumor_id --normal-id $normal_id"
+      SAMPLE_vcf2vcf="--vcf-tumor-id $tumor_id --vcf-normal-id $normal_id"
     else
-      SAMPLE_vcf2maf="--tumor-id ${sample_id}"
-      SAMPLE_vcf2vcf="--vcf-tumor-id ${sample_id}"
+      SAMPLE_vcf2maf="--tumor-id $tumor_id"
+      SAMPLE_vcf2vcf="--vcf-tumor-id $tumor_id"
     fi
 
     # Set the buffer_size based on the data size
@@ -44,36 +46,6 @@ task VEP {
       buffer_size="--buffer_size 1000"
     fi
 
-    # Extract the BND variants from VCF
-    # awk -F'\t' '{if(($1~"^#")||($8!~".*SVTYPE=BND.*")){print $0}}' ${sample_id}.PASS.vcf > ${sample_id}.PASS.vcf2maf.vcf
-    # awk -F'\t' '{if(($1~"^#")||($8~".*SVTYPE=BND.*")){print $0}}' ${sample_id}.PASS.vcf > ${sample_id}.INPUT.VEP.vcf
-
-    # vcf2maf
-    # perl ${vcf2maf_path}/vcf2maf.pl \
-    # --input-vcf ${sample_id}.PASS.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}.vcf --output_file ${basename}.PASS.vep.vcf \
-    # --fasta ${ref_dir}/${fasta} \
-    # --dir ${cache} \
-    # --assembly ${ncbi_build} \
-    # --species ${species} \
-    # --fork $nt \
-    # --format vcf --vcf \
-    # --no_progress \
-    # --no_stats \
-    # $buffer_size \
-    # --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 --flag_pick_allele --pick_order canonical,tsl,biotype,rank,ccds,length --force_overwrite --offline --pubmed --regulatory
-    
     # vcf2vcf: transfer into a standardized format
     perl ${vcf2maf_path}/vcf2vcf.pl \
     --input-vcf ${sample_id}.vcf --output-vcf ${basename}.norm.vcf \
@@ -110,6 +82,7 @@ task VEP {
   }
 
   output {
+    File norm_vcf = "${basename}.norm.vcf"
     File vep_vcf = "${basename}.vep.vcf"
     File maf = "${basename}.maf"
   }

workflow.wdl

@@ -19,8 +19,6 @@ workflow {{ project_name }} {
     input: 
     vcf=vcf,
     sample_id=sample_id,
-    tumor_id=sample_id + ".T",
-    normal_id=sample_id + ".N",
     ref_dir=ref_dir,
     fasta=fasta,
     vep_path=vep_path,