merge results

inputs

@@ -1,13 +1,26 @@
 {
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.LCL6familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL5VCFrename.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL6mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.mergeSister.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL5mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.test_name": "{{ test_name }}",
   "{{ project_name }}.disk_size": "150",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
   "{{ project_name }}.LCL6variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
+  "{{ project_name }}.LCL6zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL7familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL5familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL6VCFrename.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL5merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.reformVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call:v1.1",
+  "{{ project_name }}.LCL5zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc",
+  "{{ project_name }}.LCL8familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL7variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
   "{{ project_name }}.LCL5variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
   "{{ project_name }}.LCL8variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
-}
+}
+

tasks/merge.wdl

@@ -1,6 +1,7 @@
 task merge {
 	Array[File] family_vcf_gz
 	Array[File] family_vcf_idx
+	String test_name
 	String sample
 	String docker
 	String cluster_config
@@ -8,9 +9,34 @@ task merge {
 	
 	command <<<
 
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample}.merged.vcf ${sep=" " family_vcf_gz}
+		rtg vcfmerge --force-merge-all -o ${sample}.merged.vcf.gz ${sep=" " family_vcf_gz}
+		rtg vcffilter -i ${sample}.merged.vcf.gz -o ${sample}.snv.merged.vcf.gz --snps-only --all-samples
+		rtg vcffilter -i ${sample}.merged.vcf.gz -o ${sample}.indel.merged.vcf.gz --non-snps-only --all-samples
+
+		zcat ${sample}.indel.merged.vcf.gz | grep '#CHROM' | cut -f10-12 > name
+
+		for i in {10..12}; do zcat ${sample}.snv.merged.vcf.gz | grep -v '#' | cut -f$i | cut -d ':' -f2-4 | grep -v '\.'| sort | uniq -c | awk '{print $1, substr($1,0,7)}' | sed 's/\s\+/\t/g' | cut -f1 > $i.snv.txt; done
+
+		paste *.snv.txt | cat name - > snv.txt
+
+		for i in {10..12}; do zcat ${sample}.indel.merged.vcf.gz | grep -v '#' | cut -f$i | cut -d ':' -f2-4 | grep -v '\.'| sort | uniq -c | awk '{print $1, substr($1,0,7)}' | sed 's/\s\+/\t/g' | cut -f1 > $i.indel.txt; done
+
+		paste *.indel.txt | cat name - > index.txt
+
+		echo 'type' > column
+		echo '0,0,0' >> column
+		echo '0,0,1' >> column
+		echo '0,1,0' >> column
+		echo '0,1,1' >> column
+		echo '1,0,0' >> column
+		echo '1,0,1' >> column
+		echo '1,1,0' >> column
+		echo '1,1,1' >> column
+
+		paste column snv.txt > ${test_name}.snv.txt
+
+		paste column indel.txt > ${test_name}.indel.txt
 
-		cat ${sample}.merged.vcf | grep -v '#' | cut -f1-2 | sed s'/\t/_/g' | sort | uniq -c | sed 's/\s\+/\t/g' | awk '{ if ($1 != 1) { print } }' | cut -f3 > ${sample}.vcf_dup.txt
 
 	>>>
 
@@ -21,7 +47,13 @@ task merge {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File merged_vcf = "${sample}.merged.vcf"
-		File vcf_dup = "${sample}.vcf_dup.txt"
+		File merged_vcf = "${sample}.merged.vcf.gz"
+		File merged_vcf_idx = "${sample}.merged.vcf.gz.tbi"
+		File merged_snv = "${sample}.snv.merged.vcf.gz"
+		File merged_snv_idx = "${sample}.snv.merged.vcf.gz.tbi"
+		File merged_indel = "${sample}.indel.merged.vcf.gz"
+		File merged_indel_idx = "${sample}.indel.merged.vcf.gz.tbi"
+		File snv = "${test_name}.snv.txt"
+		File indel = "${test_name}.indel.txt"
 	}
 }

workflow.wdl

@@ -1,11 +1,18 @@
 import "./tasks/variantsNorm.wdl" as variantsNorm
 import "./tasks/mendelian.wdl" as mendelian
+import "./tasks/zipIndex.wdl" as zipIndex
+import "./tasks/VCFrename.wdl" as VCFrename
+import "./tasks/mergeSister.wdl" as mergeSister
+import "./tasks/reformVCF.wdl" as reformVCF
+import "./tasks/merge.wdl" as merge
+import "./tasks/votes.wdl" as votes
 
 workflow {{ project_name }} {
 	File inputSamplesFile
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
 	File ref_dir
 	String fasta
+	String test_name
 	String cluster_config
 	String disk_size
 
@@ -72,5 +79,104 @@ workflow {{ project_name }} {
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
+		call zipIndex.zipIndex as LCL5zipIndex {
+			input:
+			vcf=LCL5mendelian.trio_vcf,
+			sample="LCL5",
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call zipIndex.zipIndex as LCL6zipIndex {
+			input:
+			vcf=LCL6mendelian.trio_vcf,
+			sample="LCL6",
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}		
+		call VCFrename.VCFrename as LCL5VCFrename {
+			input:
+			trio_vcf_gz=LCL5zipIndex.vcf_gz,
+			trio_vcf_idx=LCL5zipIndex.vcf_idx,
+			mother_name=quartet[7],
+			father_name=quartet[6],
+			child_name=quartet[4],
+			family_name=quartet[8],
+			child="LCL5",
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call VCFrename.VCFrename as LCL6VCFrename {
+			input:
+			trio_vcf_gz=LCL6zipIndex.vcf_gz,
+			trio_vcf_idx=LCL6zipIndex.vcf_idx,
+			mother_name=quartet[7],
+			father_name=quartet[6],
+			child_name=quartet[5],
+			family_name=quartet[8],
+			child="LCL6",
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call mergeSister.mergeSister as mergeSister {
+			input:
+			LCL5_trio_vcf_gz=LCL5VCFrename.rename_trio_vcf_gz,
+			LCL5_trio_vcf_idx=LCL5VCFrename.rename_trio_vcf_idx,
+			LCL6_trio_vcf_gz=LCL6VCFrename.rename_trio_vcf_gz,
+			LCL6_trio_vcf_idx=LCL6VCFrename.rename_trio_vcf_idx,
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call reformVCF.reformVCF as reformVCF {
+			input:
+			family_mendelian_info=mergeSister.family_mendelian_info,
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size			
+		}
+		call zipIndex.zipIndex as LCL5familyzipIndex {
+			input:
+			vcf=reformVCF.LCL5_family_info,
+			sample='LCL5',
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call zipIndex.zipIndex as LCL6familyzipIndex {
+			input:
+			vcf=reformVCF.LCL6_family_info,
+			sample='LCL6',
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call zipIndex.zipIndex as LCL7familyzipIndex {
+			input:
+			vcf=reformVCF.LCL7_family_info,
+			sample='LCL7',
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call zipIndex.zipIndex as LCL8familyzipIndex {
+			input:
+			vcf=reformVCF.LCL8_family_info,
+			sample='LCL8',
+			family_name=quartet[8],
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}		
 	}
+	call merge.merge as LCL5merge {
+		input:
+		family_vcf_gz=LCL5familyzipIndex.vcf_gz,
+		family_vcf_idx=LCL5familyzipIndex.vcf_idx,
+		sample="LCL5",
+		test_name=test_name,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+
 }