Update: varscan

defaults

@@ -9,6 +9,7 @@
   "SENTIEON_LICENSE": "192.168.0.55:8990",
   "dbmills_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
   "db_mills": "Mills_and_1000G_gold_standard.indels.hg38.vcf",
+  "hg": "hg38",
   "database": "oss://pgx-reference-data/annovar_hg38/",
   "germline_resource": "oss://pgx-reference-data/gnomAD/af-only-gnomad.v3.1.1.vcf.gz",
   "germline_resource_tbi": "oss://pgx-reference-data/gnomAD/af-only-gnomad.v3.1.1.vcf.gz.tbi",

inputs

@@ -19,6 +19,7 @@
   "{{ project_name }}.germline_resource_tbi": "{{ germline_resource_tbi }}",
   "{{ project_name }}.regions": "{{ regions }}",
   "{{ project_name }}.interval_padding": "{{ interval_padding }}",
+  "{{ project_name }}.hg": "{{ hg }}",
   "{{ project_name }}.database": "{{ database }}",
   "{{ project_name }}.tnseq_pon": "{{ tnseq_pon }}",
   "{{ project_name }}.tnscope_pon": "{{ tnscope_pon }}",

tasks/annovar.wdl

@@ -3,6 +3,7 @@ task annovar {
   String sample
   File vcf
   String annotated_vcf = basename(vcf,".vcf")
+  String hg
   File database
   String docker
   String cluster_config
@@ -13,7 +14,7 @@ task annovar {
     set -o pipefail
     set -e
     nt=$(nproc)
-    /installations/annovar/table_annovar.pl ${vcf} ${database} -buildver hg38 -out ${annotated_vcf} -remove -protocol refGene,cytoBand,genomicSuperDups,ljb26_all,dbnsfp35c,intervar_20180118,cosmic70,exac03,gnomad211_exome,clinvar_20200316 -operation g,r,r,f,f,f,f,f,f,f -nastring . -vcfinput -thread $nt
+    /installations/annovar/table_annovar.pl ${vcf} ${database} -buildver ${hg} -hgvs -out ${annotated_vcf} -remove -protocol refGene,cytoBand,genomicSuperDups,ljb26_all,dbnsfp35c,intervar_20180118,cosmic70,exac03,gnomad211_exome,clinvar_20200316 -operation g,r,r,f,f,f,f,f,f,f -nastring . -vcfinput -thread $nt
   >>>
   
   runtime {
@@ -25,7 +26,7 @@ task annovar {
 
   output {
     File avinput = "${annotated_vcf}.avinput"
-    File multianno_txt = "${annotated_vcf}.hg38_multianno.txt"
-    File multianno = "${annotated_vcf}.hg38_multianno.vcf"
+    File multianno_txt = "${annotated_vcf}.multianno.txt"
+    File multianno = "${annotated_vcf}.multianno.vcf"
   }
 }

tasks/somaticFilter.wdl

@@ -25,6 +25,11 @@ task somaticFilter {
     java -Xmx12g -jar /opt/VarScan.v2.4.3.jar somaticFilter ${varscan_indel_germline_hc} --min-coverage 10 --min-reads2 2 --min-strands2 1 --min-avg-qual 20 --p-value 0.1 --output-file ${sample}.VarScan.TN.INDEL.Germline.filter.vcf
 
     java -Xmx12g -jar /opt/VarScan.v2.4.3.jar somaticFilter ${varscan_indel_loh_hc} --min-coverage 10 --min-reads2 2 --min-strands2 1 --min-avg-qual 20 --p-value 0.1 --output-file ${sample}.VarScan.TN.INDEL.LOH.filter.vcf
+
+    # Merge SNP and INDEL
+    awk '{if ($1!~/^#/) print}' ${sample}.VarScan.TN.SNP.Somatic.filter.vcf | cat - ${sample}.VarScan.TN.INDEL.Somatic.filter.vcf > ${sample}.VarScan.TN.Somatic.filter.vcf
+    awk '{if ($1!~/^#/) print}' ${sample}.VarScan.TN.SNP.Germline.filter.vcf | cat - ${sample}.VarScan.TN.INDEL.Germline.filter.vcf > ${sample}.VarScan.TN.Germline.filter.vcf
+    awk '{if ($1!~/^#/) print}' ${sample}.VarScan.TN.SNP.LOH.filter.vcf | cat - ${sample}.VarScan.TN.INDEL.LOH.filter.vcf > ${sample}.VarScan.TN.LOH.filter.vcf
   >>>
 
   runtime {
@@ -35,11 +40,8 @@ task somaticFilter {
   }
 
   output {
-		File varscan_snp_somatic_filter = "${sample}.VarScan.TN.SNP.Somatic.filter.vcf"
-    File varscan_snp_germline_filter = "${sample}.VarScan.TN.SNP.Germline.filter.vcf"
-		File varscan_snp_loh_filter = "${sample}.VarScan.TN.SNP.LOH.filter.vcf"
-		File varscan_indel_somatic_filter = "${sample}.VarScan.TN.INDEL.Somatic.filter.vcf"
-    File varscan_indel_germline_filter = "${sample}.VarScan.TN.INDEL.Germline.filter.vcf"
-		File varscan_indel_loh_filter = "${sample}.VarScan.TN.INDEL.LOH.filter.vcf"
+		File varscan_snp_somatic_filter = "${sample}.VarScan.TN.Somatic.filter.vcf"
+    File varscan_snp_germline_filter = "${sample}.VarScan.TN.Germline.filter.vcf"
+		File varscan_snp_loh_filter = "${sample}.VarScan.TN.LOH.filter.vcf"
   }
 }

workflow.wdl

@@ -35,6 +35,7 @@ workflow {{ project_name }} {
   String dbsnp
   File germline_resource
   File germline_resource_tbi
+  String hg
   File database
   
   File? regions
@@ -284,6 +285,7 @@ workflow {{ project_name }} {
       input:
       sample=sample_id,
       vcf=TNseq.TNseq_vcf,
+      hg=hg,
       database=database,
       docker=annovar_docker,
       cluster_config=cluster_config,
@@ -321,6 +323,7 @@ workflow {{ project_name }} {
       input:
       sample=sample_id,
       vcf=TNscope.TNscope_vcf,
+      hg=hg,
       database=database,
       docker=annovar_docker,
       cluster_config=cluster_config,
@@ -338,7 +341,7 @@ workflow {{ project_name }} {
       normal_bam_index=normal_BQSR.recaled_bam_index,
       ref_dir=ref_dir,
       fasta=fasta,    
-      docker=varscan_docker,	
+      docker=varscan_docker,
       disk_size=disk_size,
       cluster_config=cluster_config
     }