sister and family info merge

codescripts/reformVCF.py

@@ -0,0 +1,139 @@
+# import modules
+import sys, argparse, os
+import fileinput
+import re
+
+parser = argparse.ArgumentParser(description="This script is to split samples in VCF files and rewrite to the right style")
+
+parser.add_argument('-vcf', '--familyVCF', type=str, help='VCF with sister and mendelian infomation',  required=True)
+parser.add_argument('-name', '--familyName', type=str, help='Family name of the VCF file',  required=True)
+
+args = parser.parse_args()
+
+# Rename input:
+inputFile = args.familyVCF
+family_name = args.familyName
+
+# output filename
+LCL5_name = family_name + '.LCL5.vcf'
+LCL5file = open(LCL5_name,'w')
+LCL6_name = family_name + '.LCL6.vcf'
+LCL6file = open(LCL6_name,'w')
+LCL7_name = family_name + '.LCL7.vcf'
+LCL7file = open(LCL7_name,'w')
+LCL8_name = family_name + '.LCL8.vcf'
+LCL8file = open(LCL8_name,'w')
+family_filename = family_name + '.vcf'
+familyfile = open(family_filename,'w')
+
+# default columns, which will be included in the included in the calssifier
+vcfheader = '''##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="Voted by at least two replicates, six callers and two sequencing sites">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##INFO=<ID=sister,Number=0,Type=Flag,Description="0 for sister consistent, 1 for sister inconsistent">
+##INFO=<ID=trioLCL5,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##INFO=<ID=trioLCL6,Number=0,Type=Flag,Description="0 for trio consistent, 1 for trio inconsistent">
+##contig=<ID=chr1,length=248956422>
+##contig=<ID=chr2,length=242193529>
+##contig=<ID=chr3,length=198295559>
+##contig=<ID=chr4,length=190214555>
+##contig=<ID=chr5,length=181538259>
+##contig=<ID=chr6,length=170805979>
+##contig=<ID=chr7,length=159345973>
+##contig=<ID=chr8,length=145138636>
+##contig=<ID=chr9,length=138394717>
+##contig=<ID=chr10,length=133797422>
+##contig=<ID=chr11,length=135086622>
+##contig=<ID=chr12,length=133275309>
+##contig=<ID=chr13,length=114364328>
+##contig=<ID=chr14,length=107043718>
+##contig=<ID=chr15,length=101991189>
+##contig=<ID=chr16,length=90338345>
+##contig=<ID=chr17,length=83257441>
+##contig=<ID=chr18,length=80373285>
+##contig=<ID=chr19,length=58617616>
+##contig=<ID=chr20,length=64444167>
+##contig=<ID=chr21,length=46709983>
+##contig=<ID=chr22,length=50818468>
+##contig=<ID=chrX,length=156040895>
+'''
+# write VCF
+LCL5colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL5'+'\n'
+LCL5file.write(vcfheader)
+LCL5file.write(LCL5colname)
+
+LCL6colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL6'+'\n'
+LCL6file.write(vcfheader)
+LCL6file.write(LCL6colname)
+
+LCL7colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL7'+'\n'
+LCL7file.write(vcfheader)
+LCL7file.write(LCL7colname)
+
+LCL8colname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+family_name+'_LCL8'+'\n'
+LCL8file.write(vcfheader)
+LCL8file.write(LCL8colname)
+
+familycolname = '#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t'+'LCL5\t'+'LCL6\t'+'LCL7\t'+'_LCL8'+'\n'
+familyfile.write(vcfheader)
+familyfile.write(familycolname)
+
+# reform VCF
+def process(oneLine):
+	line = oneLine.rstrip()
+	strings = line.strip().split('\t')
+	# replace .
+	# LCL5 uniq
+	if strings[11] == '.':
+		strings[11] = '0/0'
+		strings[9] = strings[12]
+		strings[10] = strings[13]
+	else:
+		pass
+	# LCL6 uniq
+	if strings[14] == '.':
+		strings[14] = '0/0'
+		strings[12] = strings[9]
+		strings[13] = strings[10]
+	else:
+		pass
+	# sister
+	if strings[11] == strings[14]:
+		info = "sister=1"
+	else:
+		info = "sister=0"
+	# trioLCL5
+	if strings[15] == 'MD=1':
+		info = info + ";trioLCL5=1"
+	else:
+		info = info + ";trioLCL5=0"
+	# trioLCL6
+	if strings[7] == 'MD=1':
+		info = info + ";trioLCL6=1"
+	else:
+		info = info + ";trioLCL6=0"
+	# output LCL5
+	LCL5outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+strings[5]+'\t'+strings[6]+'\t'+ info +'\t'+ strings[8] + '\t' + strings[14] + '\n'
+	LCL5file.write(LCL5outLine)
+	# output LCL6
+	LCL6outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+strings[5]+'\t'+strings[6]+'\t'+ info +'\t'+ strings[8] + '\t' + strings[11] + '\n'
+	LCL6file.write(LCL6outLine)
+	# output LCL7
+	LCL7outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+strings[5]+'\t'+strings[6]+'\t'+ info +'\t'+ strings[8] + '\t' + strings[10] + '\n'
+	LCL7file.write(LCL7outLine)
+	# output LCL8
+	LCL8outLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+strings[5]+'\t'+strings[6]+'\t'+ info +'\t'+ strings[8] + '\t' + strings[9] + '\n'
+	LCL8file.write(LCL8outLine)
+	# output family
+	familyoutLine = strings[0]+'\t'+strings[1]+'\t'+strings[2]+'\t'+strings[3]+'\t'+strings[4]+'\t'+strings[5]+'\t'+strings[6]+'\t'+ info +'\t'+ strings[8] + '\t' + strings[14] + '\t' + strings[11] + '\t' + strings[10] + '\t' + strings[9] + '\n'
+	familyfile.write(familyoutLine)
+
+
+for line in fileinput.input(inputFile):
+	m = re.match('^\#',line)
+	if m is not None:
+		pass
+	else:
+		process(line)
+		
+

inputs

@@ -1,17 +1,28 @@
 {
+  "{{ project_name }}.LCL7merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
-  "{{ project_name }}.VCFrename.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.sister.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
-  "{{ project_name }}.mendelian.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ 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 }}.disk_size": "150",
-  "{{ project_name }}.merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
-  "{{ project_name }}.zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
+  "{{ project_name }}.LCL6merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL6variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
-  "{{ project_name }}.mapper_caller": "{{ mapper_caller }}",
+  "{{ 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 }}.LCL8merge.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ 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/ExtractVCFinfo.wdl

@@ -1,34 +0,0 @@
-task ExtractVCFinfo {
-	File snv_train
-	File snv_test
-	File indel_train
-	File indel_test
-	String snv_train_sampleName = basename(snv_train,".vcf")
-	String snv_test_sampleName = basename(snv_test,".vcf")
-	String indel_train_sampleName = basename(indel_train,".vcf")
-	String indel_test_sampleName = basename(indel_test,".vcf")	
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		python /opt/extract_vcf_information.py -i ${snv_train} -o ${snv_train_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${snv_test} -o ${snv_test_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${indel_train} -o ${indel_train_sampleName}.txt
-		python /opt/extract_vcf_information.py -i ${indel_test} -o ${indel_test_sampleName}.txt
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File snv_train_vcf = "${snv_train_sampleName}.txt"
-		File snv_test_vcf = "${snv_test_sampleName}.txt"
-		File indel_train_vcf = "${indel_train_sampleName}.txt"
-		File indel_test_vcf = "${indel_test_sampleName}.txt"
-	}
-}

tasks/KeepVar.wdl

@@ -1,27 +0,0 @@
-task KeepVar {
-	File violation_merged_vcf
-	File consistent_merged_vcf
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		python /opt/select_small_variants_supported_by_all_callsets.py -i ${violation_merged_vcf} -o violation.all.selected
-
-		python /opt/select_small_variants_supported_by_all_callsets.py -i ${consistent_merged_vcf} -o consistent.all.selected
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File violation_keeped_vcf = "violation.all.selected.vcf"
-		File violation_outlier_vcf = "violation.all.selected_outlier.vcf"
-		File consistent_keeped_vcf = "consistent.all.selected.vcf"
-		File consistent_outlier_vcf = "consistent.all.selected_outlier.vcf"
-	}
-}
-

tasks/SepSnvIndel.wdl

@@ -1,69 +0,0 @@
-task SepSnvIndel {
-	File vcf
-	String sampleName = basename(vcf,".normed.vcf")
-	File keeped_vcf
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-		cat ${vcf} | grep '#' > header
-		cat ${vcf} | sed '/^#/d' | awk '$5!~/,/' > removed.body
-		cat ${vcf} | sed '/^#/d' | awk '$5~/,/' > MNP.body
-		cat header removed.body > ${sampleName}.MNPremoved.vcf
-		cat header MNP.body > ${sampleName}.MNP.vcf
-
-		rtg bgzip ${sampleName}.MNPremoved.vcf
-		rtg index -f vcf ${sampleName}.MNPremoved.vcf.gz
-
-
-		rtg bgzip ${keeped_vcf} -c > all.selected.vcf.gz
-		rtg index -f vcf all.selected.vcf.gz
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.train.vcf.gz --include-vcf=all.selected.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.test.vcf.gz --exclude-vcf=all.selected.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.train.vcf.gz --include-vcf=all.selected.vcf.gz --non-snps-only
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.test.vcf.gz --exclude-vcf=all.selected.vcf.gz --non-snps-only
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.snv.vcf.gz --snps-only 
-
-		rtg vcffilter -i ${sampleName}.MNPremoved.vcf.gz -o ${sampleName}.normed.indel.vcf.gz --non-snps-only
-	
-
-		gzip -d ${sampleName}.normed.snv.train.vcf.gz -c > ${sampleName}.normed.snv.train.vcf
-		gzip -d ${sampleName}.normed.snv.test.vcf.gz -c > ${sampleName}.normed.snv.test.vcf
-		gzip -d ${sampleName}.normed.indel.train.vcf.gz -c > ${sampleName}.normed.indel.train.vcf
-		gzip -d ${sampleName}.normed.indel.test.vcf.gz -c > ${sampleName}.normed.indel.test.vcf
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File MNP="${sampleName}.MNP.vcf"
-		File snv_gz = "${sampleName}.normed.snv.vcf.gz"
-		File snv_idx = "${sampleName}.normed.snv.vcf.gz.tbi"
-		File indel_gz = "${sampleName}.normed.indel.vcf.gz"
-		File indel_idx = "${sampleName}.normed.indel.vcf.gz.tbi"
-		File snv_train = "${sampleName}.normed.snv.train.vcf"
-		File snv_test = "${sampleName}.normed.snv.test.vcf"
-		File indel_train = "${sampleName}.normed.indel.train.vcf"
-		File indel_test = "${sampleName}.normed.indel.test.vcf"
-		File snv_train_gz = "${sampleName}.normed.snv.train.vcf.gz"
-		File snv_test_gz = "${sampleName}.normed.snv.test.vcf.gz"
-		File indel_train_gz = "${sampleName}.normed.indel.train.vcf.gz"
-		File indel_test_gz = "${sampleName}.normed.indel.test.vcf.gz"
-		File snv_train_idx = "${sampleName}.normed.snv.train.vcf.gz.tbi"
-		File snv_test_idx = "${sampleName}.normed.snv.test.vcf.gz.tbi"
-		File indel_train_idx = "${sampleName}.normed.indel.train.vcf.gz.tbi"
-		File indel_test_idx = "${sampleName}.normed.indel.test.vcf.gz.tbi"		
-	}
-}

tasks/SepTrueFalse.wdl

@@ -1,71 +0,0 @@
-task SepTrueFalse {
-	File snv_true_bed
-	File snv_false_bed
-	File indel_true_bed
-	File indel_false_bed
-	File snv_padding
-	File indel_padding
-
-	File snv_gz
-	File indel_gz
-	File snv_idx
-	File indel_idx
-	File snv_test_gz
-	File indel_test_gz
-	File snv_test_idx
-	File indel_test_idx	
-
-	String sampleName = basename(snv_gz,".normed.snv.vcf.gz")
-	String docker
-	String cluster_config
-	String disk_size
-
-	command <<<
-
-	rtg vcffilter -i ${snv_test_gz} -o ${sampleName}.true.snv.vcf.gz --include-bed=${snv_true_bed}
-
-	rtg vcffilter -i ${snv_test_gz} -o ${sampleName}.false.snv.vcf.gz --include-bed=${snv_false_bed}
-
-	rtg vcffilter -i ${snv_gz} -o ${sampleName}.remain.snv.vcf.gz --exclude-bed=${snv_false_bed}
-
-	rtg vcffilter -i ${snv_gz} -o ${sampleName}.padding.snv.vcf.gz --include-bed=${snv_padding}
-
-	
-	rtg vcffilter -i ${indel_test_gz} -o ${sampleName}.true.indel.vcf.gz --include-bed=${indel_true_bed}
-
-	rtg vcffilter -i ${indel_test_gz} -o ${sampleName}.false.indel.vcf.gz --include-bed=${indel_false_bed}
-
-	rtg vcffilter -i ${indel_gz} -o ${sampleName}.remain.indel.vcf.gz --exclude-bed=${indel_false_bed}
-
-	rtg vcffilter -i ${indel_gz} -o ${sampleName}.padding.indel.vcf.gz --include-bed=${indel_padding}
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File snv_true_vcf = "${sampleName}.true.snv.vcf.gz"
-		File snv_true_vcf_index = "${sampleName}.true.snv.vcf.gz.tbi"
-		File snv_false_vcf = "${sampleName}.false.snv.vcf.gz"
-		File snv_false_vcf_index = "${sampleName}.false.snv.vcf.gz.tbi"
-		File snv_remain_vcf = "${sampleName}.remain.snv.vcf.gz"
-		File snv_remain_vcf_index = "${sampleName}.remain.snv.vcf.gz.tbi"
-		File snv_padding_vcf = "${sampleName}.padding.snv.vcf.gz"
-		File snv_padding_vcf_index = "${sampleName}.padding.snv.vcf.gz.tbi"
-
-		File indel_true_vcf = "${sampleName}.true.indel.vcf.gz"
-		File indel_true_vcf_index = "${sampleName}.true.indel.vcf.gz.tbi"
-		File indel_false_vcf = "${sampleName}.false.indel.vcf.gz"
-		File indel_false_vcf_index = "${sampleName}.false.indel.vcf.gz.tbi"
-		File indel_remain_vcf = "${sampleName}.remain.indel.vcf.gz"
-		File indel_remain_vcf_index = "${sampleName}.remain.indel.vcf.gz.tbi"
-		File indel_padding_vcf = "${sampleName}.padding.indel.vcf.gz"
-		File indel_padding_vcf_index = "${sampleName}.padding.indel.vcf.gz.tbi"
-	}
-}
-

tasks/VCFrename.wdl

@@ -1,26 +1,21 @@
 task VCFrename {
-	File mother_vcf_gz
-	File father_vcf_gz
-	File twins_vcf_gz
-	File mother_vcf_idx
-	File father_vcf_idx
-	File twins_vcf_idx
+	File trio_vcf_gz
+	File trio_vcf_idx
 	String mother_name
 	String father_name
+	String child_name
 	String family_name
+	String child
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		echo "MOTHER ${mother_name}" > mother_rename.txt
-		rtg vcfannotate -i ${mother_vcf_gz} -o ${mother_name}.rename.vcf.gz --relabel=mother_rename.txt
+		echo "MOTHER ${mother_name}.${child}
+		FATHER ${father_name}.${child}
+		CHILD ${child_name}" > rename.txt
 
-		echo "FATHER ${father_name}" > father_rename.txt
-		rtg vcfannotate -i ${father_vcf_gz} -o ${father_name}.rename.vcf.gz --relabel=father_rename.txt
-
-		echo "CHILD ${family_name}" > child_rename.txt
-		rtg vcfannotate -i ${twins_vcf_gz} -o ${family_name}.twins.rename.vcf.gz --relabel=child_rename.txt
+		rtg vcfannotate -i ${trio_vcf_gz} -o ${family_name}.${child}.rename.vcf.gz --relabel=rename.txt
 	>>>
 
 	runtime {
@@ -30,11 +25,7 @@ task VCFrename {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File rename_mother_vcf_gz = "${mother_name}.rename.vcf.gz"
-		File rename_father_vcf_gz = "${father_name}.rename.vcf.gz"
-		File rename_twins_vcf_gz = "${family_name}.twins.rename.vcf.gz"
-		File rename_mother_vcf_idx = "${mother_name}.rename.vcf.gz.tbi"
-		File rename_father_vcf_idx = "${father_name}.rename.vcf.gz.tbi"
-		File rename_twins_vcf_idx = "${family_name}.twins.rename.vcf.gz.tbi"
+		File rename_trio_vcf_gz = "${family_name}.${child}.rename.vcf.gz"
+		File rename_trio_vcf_idx = "${family_name}.${child}.rename.vcf.gz.tbi"
 	}
 }

tasks/mendelian.wdl

@@ -1,10 +1,10 @@
 task mendelian {
-	File sister_vcf
+	File child_vcf
 	File LCL7_vcf
 	File LCL8_vcf
 	String LCL7_name
 	String LCL8_name
-	String family_name
+	String child_name
 	File ref_dir
 	String fasta
 	String docker
@@ -13,20 +13,12 @@ task mendelian {
 	
 	command <<<
 		export LD_LIBRARY_PATH=/opt/htslib-1.9
-
+		nt=$(nproc)
 		mkdir VBT
 
-		/opt/VBT-TrioAnalysis/vbt mendelian -ref ${ref_dir}/${fasta} -mother ${LCL8_vcf} -father ${LCL7_vcf} -child ${sister_vcf} -outDir VBT -out-prefix ${family_name} --output-violation-regions
-
-		cat VBT/${family_name}_trio.vcf | grep '#' | cut -f1-9,10 > mother_header
-		cat VBT/${family_name}_trio.vcf | grep -v '#' | cut -f1-9,10 | grep 'MD=1' | grep -v '0/0' | cat mother_header - > ${LCL8_name}.sister.mendelian.gt.vcf
-
-		cat VBT/${family_name}_trio.vcf | grep '#' | cut -f1-9,11 > father_header
-		cat VBT/${family_name}_trio.vcf | grep -v '#' | cut -f1-9,11 | grep 'MD=1' | grep -v '0/0' | cat father_header - > ${LCL7_name}.sister.mendelian.gt.vcf
-
-		cat VBT/${family_name}_trio.vcf | grep '#' | cut -f1-9,12 > twin_header
-		cat VBT/${family_name}_trio.vcf | grep -v '#' | cut -f1-9,12 | grep 'MD=1' | grep -v '0/0' | cat twin_header - > ${family_name}.twins.sister.mendelian.gt.vcf
+		/opt/VBT-TrioAnalysis/vbt mendelian -ref ${ref_dir}/${fasta} -mother ${LCL8_vcf} -father ${LCL7_vcf} -child ${child_vcf} -outDir VBT -out-prefix ${child_name}.family --output-violation-regions -thread-count $nt
 
+		cat VBT/${child_name}.family_trio.vcf > ${child_name}.family.vcf
 	>>>
 
 	runtime {
@@ -37,8 +29,6 @@ task mendelian {
 	}
 	output {
 		Array[File] vbt_mendelian = glob("VBT/*")
-		File mother_vcf = "${LCL8_name}.sister.mendelian.gt.vcf"
-		File father_vcf = "${LCL7_name}.sister.mendelian.gt.vcf"
-		File twins_vcf = "${family_name}.twins.sister.mendelian.gt.vcf"
+		File trio_vcf = "${child_name}.family.vcf"
 	}
 }

tasks/merge.wdl

@@ -1,21 +1,15 @@
 task merge {
-	Array[File] rename_mother_vcf_gz
-	Array[File] rename_mother_vcf_idx
-	Array[File] rename_father_vcf_gz
-	Array[File] rename_father_vcf_idx
-	Array[File] rename_twins_vcf_gz
-	Array[File] rename_twins_vcf_idx
-	String mapper_caller
+	Array[File] family_vcf_gz
+	Array[File] family_vcf_idx
+	String sample
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg vcfmerge --force-merge-all --no-gzip -o LCL8.${mapper_caller}.sister.consistent.merged.vcf ${sep=" " rename_mother_vcf_gz}
 
-		rtg vcfmerge --force-merge-all --no-gzip -o LCL7.${mapper_caller}.sister.consistent.merged.vcf ${sep=" " rename_father_vcf_gz}
+		rtg vcfmerge --force-merge-all --no-gzip -o ${sample}.merged.vcf ${sep=" " family_vcf_gz}
 
-		rtg vcfmerge --force-merge-all --no-gzip -o Twins.${mapper_caller}.sister.consistent.merged.vcf ${sep=" " rename_twins_vcf_gz}
 	>>>
 
 	runtime {
@@ -25,8 +19,6 @@ task merge {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File mother_merged_vcf = "LCL8.${mapper_caller}.sister.consistent.merged.vcf"
-		File father_merged_vcf = "LCL7.${mapper_caller}.sister.consistent.merged.vcf"
-		File twins_merged_vcf = "Twins.${mapper_caller}.sister.consistent.merged.vcf"
+		File merged_vcf = "${sample}.merged.vcf"
 	}
 }

tasks/mergeBed.wdl

@@ -1,35 +0,0 @@
-task mergeBed {
-	Array[File] snv_true_bed
-	Array[File] snv_false_bed
-	Array[File] indel_true_bed
-	Array[File] indel_false_bed
-	Array[File]	indel_padding
-	Array[File] snv_padding
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_true_bed} ${sep=" " indel_true_bed}  > merged.true.bed
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_false_bed} ${sep=" " indel_false_bed}  > merged.false.bed
-
-	/opt/ccdg/bedtools-2.27.1/bin/bedtools multiinter -i ${sep=" " snv_padding} ${sep=" " indel_padding}  > merged.padding.bed	
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File true_bed = "merged.true.bed"
-		File false_bed = "merged.false.bed"
-		File padding = "merged.padding.bed"
-	}
-}
-

tasks/mergeSister.wdl

@@ -0,0 +1,34 @@
+task mergeSister {
+	File LCL5_trio_vcf_gz
+	File LCL5_trio_vcf_idx
+	File LCL6_trio_vcf_gz
+	File LCL6_trio_vcf_idx
+	String family_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		rtg vcfmerge -o LCL5.LCL6.merged.vcf.gz ${LCL5_trio_vcf_gz} ${LCL6_trio_vcf_gz}
+
+		rtg vcfmerge -o LCL6.LCL5.merged.vcf.gz ${LCL6_trio_vcf_gz} ${LCL5_trio_vcf_gz}
+
+		zcat LCL5.LCL6.merged.vcf.gz | grep '##' > header
+		zcat LCL5.LCL6.merged.vcf.gz | grep -v '##' | cut -f8 > LCL5.mendelian
+		zcat LCL6.LCL5.merged.vcf.gz | grep -v '##' | paste - LCL5.mendelian > body
+
+		cat header body > ${family_name}.trio.info.vcf
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File family_mendelian_info = "${family_name}.trio.info.vcf"
+	}
+
+}

tasks/mergeVCF.wdl

@@ -1,61 +0,0 @@
-task mergeVCF {
-	Array[File] snv_true_vcf
-	Array[File] snv_true_vcf_index
-	Array[File] snv_false_vcf
-	Array[File] snv_false_vcf_index
-	Array[File] snv_remain_vcf
-	Array[File] snv_remain_vcf_index
-	Array[File] snv_padding_vcf
-	Array[File] snv_padding_vcf_index
-
-	Array[File] indel_true_vcf
-	Array[File] indel_true_vcf_index
-	Array[File] indel_false_vcf
-	Array[File] indel_false_vcf_index
-	Array[File] indel_remain_vcf
-	Array[File] indel_remain_vcf_index 
-	Array[File] indel_padding_vcf
-	Array[File] indel_padding_vcf_index
-
-	String quartet_sample
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.true.vcf.gz ${sep=" " snv_true_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.false.vcf.gz ${sep=" " snv_false_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.remain.vcf.gz ${sep=" " snv_remain_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.snv.padding.vcf.gz ${sep=" " snv_padding_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.true.vcf.gz ${sep=" " indel_true_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.false.vcf.gz ${sep=" " indel_false_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.remain.vcf.gz ${sep=" " indel_remain_vcf}
-
-		rtg vcfmerge --force-merge-all --no-gzip -o ${quartet_sample}.indel.padding.vcf.gz ${sep=" " indel_padding_vcf}
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File merged_snv_true = "${quartet_sample}.snv.true.vcf.gz"
-		File merged_snv_false = "${quartet_sample}.snv.false.vcf.gz"
-		File merged_snv_remain = "${quartet_sample}.snv.remain.vcf.gz"
-		File merged_snv_padding = "${quartet_sample}.snv.padding.vcf.gz"
-		File merged_indel_true = "${quartet_sample}.indel.true.vcf.gz"
-		File merged_indel_false = "${quartet_sample}.indel.false.vcf.gz"
-		File merged_indel_remain = "${quartet_sample}.indel.remain.vcf.gz"
-		File merged_indel_padding = "${quartet_sample}.indel.padding.vcf.gz"
-	}
-
-}

tasks/reformVCF.wdl

@@ -0,0 +1,30 @@
+task reformVCF {
+	File family_mendelian_info
+	File family_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+	python /opt/reformVCF.py -vcf ${family_mendelian_info} -name ${family_name}
+	
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File LCL5_family_info = "${family_name}.LCL5.vcf"
+		File LCL6_family_info = "${family_name}.LCL6.vcf"
+		File LCL7_family_info = "${family_name}.LCL7.vcf"
+		File LCL8_family_info = "${family_name}.LCL8.vcf"
+		File family_info = "${family_name}.vcf"
+	}
+}
+

tasks/zipIndex.wdl

@@ -1,21 +1,14 @@
 task zipIndex {
-	File mother_vcf
-	File father_vcf
-	File twins_vcf
+	File vcf
+	String sample
 	String family_name
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg bgzip ${mother_vcf} -c > ${family_name}.LCL8.vcf.gz
-		rtg index -f vcf ${family_name}.LCL8.vcf.gz
-
-		rtg bgzip ${father_vcf} -c > ${family_name}.LCL7.vcf.gz
-		rtg index -f vcf ${family_name}.LCL7.vcf.gz
-
-		rtg bgzip ${twins_vcf} -c > ${family_name}.twins.vcf.gz
-		rtg index -f vcf ${family_name}.twins.vcf.gz
+		rtg bgzip ${vcf} -c > ${family_name}.${sample}.vcf.gz
+		rtg index -f vcf ${family_name}.${sample}.vcf.gz
 
 	>>>
 
@@ -26,11 +19,7 @@ task zipIndex {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File mother_vcf_gz = "${family_name}.LCL8.vcf.gz"
-		File father_vcf_gz = "${family_name}.LCL7.vcf.gz"
-		File twins_vcf_gz = "${family_name}.twins.vcf.gz"
-		File mother_vcf_idx = "${family_name}.LCL8.vcf.gz.tbi"
-		File father_vcf_idx = "${family_name}.LCL7.vcf.gz.tbi"
-		File twins_vcf_idx = "${family_name}.twins.vcf.gz.tbi"
+		File vcf_gz = "${family_name}.${sample}.vcf.gz"
+		File vcf_idx = "${family_name}.${sample}.vcf.gz.tbi"
 	}
 }

workflow.wdl

@@ -1,10 +1,11 @@
 import "./tasks/variantsNorm.wdl" as variantsNorm
-import "./tasks/sister.wdl" as sister
 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
- 
+
 workflow {{ project_name }} {
 	File inputSamplesFile
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
@@ -12,102 +13,189 @@ workflow {{ project_name }} {
 	String fasta
 	String cluster_config
 	String disk_size
-	String mapper_caller
 
-	scatter (sample in inputSamples){
+	scatter (quartet in inputSamples){
 		call variantsNorm.variantsNorm as LCL5variantsNorm{
 			input:
-			vcf=sample[0],
+			vcf=quartet[0],
 			ref_dir=ref_dir,
 			fasta=fasta,
-			sampleName=sample[4],
+			sampleName=quartet[4],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
 		call variantsNorm.variantsNorm as LCL6variantsNorm{
 			input:
-			vcf=sample[1],
+			vcf=quartet[1],
 			ref_dir=ref_dir,
 			fasta=fasta,
-			sampleName=sample[5],
+			sampleName=quartet[5],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
 		call variantsNorm.variantsNorm as LCL7variantsNorm{
 			input:
-			vcf=sample[2],
+			vcf=quartet[2],
 			ref_dir=ref_dir,
 			fasta=fasta,
-			sampleName=sample[6],
+			sampleName=quartet[6],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
 		call variantsNorm.variantsNorm as LCL8variantsNorm{
 			input:
-			vcf=sample[3],
+			vcf=quartet[3],
 			ref_dir=ref_dir,
 			fasta=fasta,
-			sampleName=sample[7],
+			sampleName=quartet[7],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call sister.sister as sister{
+		call mendelian.mendelian as LCL5mendelian {
 			input:
-			LCL5_vcf=LCL5variantsNorm.normed_vcf,
-			LCL6_vcf=LCL6variantsNorm.normed_vcf,
+			child_vcf=LCL5variantsNorm.normed_vcf,
+			LCL7_vcf=LCL7variantsNorm.normed_vcf,
+			LCL8_vcf=LCL8variantsNorm.normed_vcf,
+			LCL7_name=quartet[6],
+			LCL8_name=quartet[7],
+			child_name=quartet[4],
 			ref_dir=ref_dir,
 			fasta=fasta,
-			family_name=sample[8],
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call mendelian.mendelian as mendelian {
-			input: 
-			sister_vcf=sister.sister_consistent_vcf,
+		call mendelian.mendelian as LCL6mendelian {
+			input:
+			child_vcf=LCL6variantsNorm.normed_vcf,
 			LCL7_vcf=LCL7variantsNorm.normed_vcf,
 			LCL8_vcf=LCL8variantsNorm.normed_vcf,
-			LCL7_name=sample[6],
-			LCL8_name=sample[7],
-			family_name=sample[8],
+			LCL7_name=quartet[6],
+			LCL8_name=quartet[7],
+			child_name=quartet[5],
 			ref_dir=ref_dir,
 			fasta=fasta,
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
-		call zipIndex.zipIndex as zipIndex{
+		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:
-			mother_vcf=mendelian.mother_vcf,
-			father_vcf=mendelian.father_vcf,
-			twins_vcf=mendelian.twins_vcf,
-			family_name=sample[8],
+			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 VCFrename.VCFrename as VCFrename{
-			input:
-			mother_vcf_gz=zipIndex.mother_vcf_gz,
-			father_vcf_gz=zipIndex.father_vcf_gz,
-			twins_vcf_gz=zipIndex.twins_vcf_gz,
-			mother_vcf_idx=zipIndex.mother_vcf_idx,
-			father_vcf_idx=zipIndex.father_vcf_idx,
-			twins_vcf_idx=zipIndex.twins_vcf_idx,
-			mother_name=sample[7],
-			father_name=sample[6],
-			family_name=sample[8],
+		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 merge {
+	call merge.merge as LCL5merge {
+		input:
+		family_vcf_gz=LCL5familyzipIndex.vcf_gz,
+		family_vcf_idx=LCL5familyzipIndex.vcf_idx,
+		sample="LCL5",
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call merge.merge as LCL6merge {
+		input:
+		family_vcf_gz=LCL6familyzipIndex.vcf_gz,
+		family_vcf_idx=LCL6familyzipIndex.vcf_idx,
+		sample="LCL6",
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call merge.merge as LCL7merge {
+		input:
+		family_vcf_gz=LCL7familyzipIndex.vcf_gz,
+		family_vcf_idx=LCL7familyzipIndex.vcf_idx,
+		sample="LCL7",
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call merge.merge as LCL8merge {
 		input:
-		rename_mother_vcf_gz=VCFrename.rename_mother_vcf_gz,
-		rename_mother_vcf_idx=VCFrename.rename_mother_vcf_idx,
-		rename_father_vcf_gz=VCFrename.rename_father_vcf_gz,
-		rename_father_vcf_idx=VCFrename.rename_father_vcf_idx,
-		rename_twins_vcf_gz=VCFrename.rename_twins_vcf_gz,
-		rename_twins_vcf_idx=VCFrename.rename_twins_vcf_idx,
-		mapper_caller=mapper_caller,
+		family_vcf_gz=LCL8familyzipIndex.vcf_gz,
+		family_vcf_idx=LCL8familyzipIndex.vcf_idx,
+		sample="LCL8",
 		cluster_config=cluster_config,
 		disk_size=disk_size
 	}