use splited gvcf as mendelian analysis input

codescripts/get_family.sh

@@ -0,0 +1,35 @@
+cat chr*gt | cut -f1-9,10,41,74,107 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_SEQ2000_BGI_1_20180518.vcf
+cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$11"\t"$52"\t"$85"\t"$12}'  | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_SEQ2000_BGI_2_20180518.vcf
+cat chr*gt | cut -f1-9,21,30,63,96 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_SEQ2000_BGI_3_20180518.vcf
+
+cat chr*gt | cut -f1-9,88,91,94,98 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_T7_WGE_1_20191105.vcf
+cat chr*gt | cut -f1-9,89,92,95,99 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_T7_WGE_2_20191105.vcf
+cat chr*gt | cut -f1-9,90,93,97,100 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_BGI_T7_WGE_3_20191105.vcf
+
+cat chr*gt | cut -f1-9,61,68,75,81 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_1_20181108.vcf
+cat chr*gt | cut -f1-9,62,69,76,82 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_2_20181108.vcf
+cat chr*gt | cut -f1-9,64,70,77,83 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_3_20181108.vcf
+
+cat chr*gt | cut -f1-9,65,71,78,84 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_4_20181108.vcf
+cat chr*gt | cut -f1-9,66,72,79,86 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_5_20181108.vcf
+cat chr*gt | cut -f1-9,67,73,80,87 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_ARD_6_20181108.vcf
+
+cat chr*gt | cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$114"\t"$117"\t"$15"\t"$18}' | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_BRG_1_20180930.vcf
+cat chr*gt | cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$115"\t"$13"\t"$16"\t"$19}' | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_BRG_2_20180930.vcf
+cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$116"\t"$14"\t"$17"\t"$20}' | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_BRG_3_20180930.vcf
+
+cat chr*gt | cut -f1-9,101,102,103,104 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_WUX_1_20190917.vcf
+cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$109"\t"$106"\t"$108"\t"$105}' | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_WUX_2_20190917.vcf
+cat chr*gt | awk '{print $1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$113"\t"$112"\t"$111"\t"$110}' | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_Nova_WUX_3_20190917.vcf
+
+cat chr*gt | cut -f1-9,22,25,28,32 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_ARD_1_20170403.vcf
+cat chr*gt | cut -f1-9,23,26,29,33 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_ARD_2_20170403.vcf
+cat chr*gt | cut -f1-9,24,27,31,34 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_ARD_3_20170403.vcf
+
+cat chr*gt | cut -f1-9,35,38,42,45 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_NVG_1_20170329.vcf
+cat chr*gt | cut -f1-9,36,39,43,46 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_NVG_2_20170329.vcf
+cat chr*gt | cut -f1-9,37,40,44,47 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_NVG_3_20170329.vcf
+
+cat chr*gt | cut -f1-9,48,51,55,58 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_WUX_1_20170216.vcf
+cat chr*gt | cut -f1-9,49,53,56,59 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_WUX_2_20170216.vcf
+cat chr*gt | cut -f1-9,50,54,57,60 | grep -v '#CHROM' | sort -k1,1 -k2,2n | cat header - > Quartet_DNA_ILM_XTen_WUX_3_20170216.vcf

codescripts/merge_mendelian_vot.py

@@ -1,11 +1,12 @@
 import pandas as pd
 import sys, argparse, os
 
-men = pd.read_table(sys.argv[1],header=None)
+men = pd.read_table(sys.argv[1],header=None,low_memory=False)
 vote = pd.read_table(sys.argv[2],low_memory=False)
-mut = pd.read_table(sys.argv[3],header=None)
-
+men[1]=men[1].astype(str)
 merged_df = pd.merge(vote, men,  how='inner', left_on=['CHROM','POS'], right_on = [0,1])
+lcl5_dat = merged_df[(merged_df[5]!='./.') & (merged_df[5]!='0/0')]
+
 merged_df['mendelian_check'] = 'MIE'
 merged_df.loc[merged_df[2]=='1:1:1','mendelian_check'] = 'MP'
 sub = merged_df[['CHROM','POS','LCL5_detected_num','mendelian_check',2]]

inputs

@@ -1,8 +1,10 @@
 {
-  "{{ project_name }}.disk_size": "100",
-  "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
-  "{{ project_name }}.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
-  "{{ project_name }}.sample_name": "{{ sample_name }}",
-  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.xlarge img-ubuntu-vpc",
-  "{{ project_name }}.mut_file": "oss://pgx-result/renluyao/manuscript/mutation_type"
-}
+  "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.family_vcf": "{{ family_vcf }}",
+  "{{ project_name }}.disk_size": "500",
+  "{{ project_name }}.SMALLcluster_config": "OnDemand bcs.ps.g.xlarge img-ubuntu-vpc",
+  "{{ project_name }}.BIGcluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
+  "{{ project_name }}.MENDELIANdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.DIYdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
+  "{{ project_name }}.ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
+}

tasks/mendelian.wdl

@@ -0,0 +1,46 @@
+task mendelian {
+	File family_vcf
+	File ref_dir
+	String family_name = basename(family_vcf,".vcf")
+	String fasta
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		export LD_LIBRARY_PATH=/opt/htslib-1.9
+		nt=$(nproc)
+
+		echo -e "${family_name}\tLCL8\t0\t0\t2\t-9\n${family_name}\tLCL7\t0\t0\t1\t-9\n${family_name}\tLCL5\tLCL7\tLCL8\t2\t-9" > ${family_name}.D5.ped
+
+		mkdir VBT_D5
+		/opt/VBT-TrioAnalysis/vbt mendelian -ref ${ref_dir}/${fasta} -mother ${family_vcf} -father ${family_vcf} -child ${family_vcf} -pedigree ${family_name}.D5.ped -outDir VBT_D5 -out-prefix ${family_name}.D5 --output-violation-regions -thread-count $nt
+
+		cat VBT_D5/${family_name}.D5_trio.vcf > ${family_name}.D5.vcf
+
+		echo -e "${family_name}\tLCL8\t0\t0\t2\t-9\n${family_name}\tLCL7\t0\t0\t1\t-9\n${family_name}\tLCL6\tLCL7\tLCL8\t2\t-9" > ${family_name}.D6.ped
+
+		mkdir VBT_D6
+		/opt/VBT-TrioAnalysis/vbt mendelian -ref ${ref_dir}/${fasta} -mother ${family_vcf} -father ${family_vcf} -child ${family_vcf} -pedigree ${family_name}.D6.ped -outDir VBT_D6 -out-prefix ${family_name}.D6 --output-violation-regions -thread-count $nt
+
+		cat VBT_D6/${family_name}.D6_trio.vcf > ${family_name}.D6.vcf
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File D5_ped = "${family_name}.D5.ped"
+		File D6_ped = "${family_name}.D6.ped"
+		Array[File] D5_mendelian = glob("VBT_D5/*")
+		Array[File] D6_mendelian = glob("VBT_D6/*")
+		File D5_trio_vcf = "${family_name}.D5.vcf"
+		File D6_trio_vcf = "${family_name}.D6.vcf"
+	}
+}
+
+
+

tasks/merge_chromo.wdl

@@ -1,33 +0,0 @@
-task merge_chromo {
-	Array[File] mendelian_vote_snv
-	Array[File] mendelian_vote_indel
-	String sample_name
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-		cat ${sep=" " mendelian_vote_snv} > ${sample_name}.snv.txt
-
-		cat ${sep=" " mendelian_vote_indel} > ${sample_name}.indel.txt
-
-		cat ${sample_name}.snv.txt |  cut -f3,4 | sort | uniq -c > ${sample_name}.snv.summary.txt
-
-		cat ${sample_name}.indel.txt |  cut -f3,4 | sort | uniq -c > ${sample_name}.indel.summary.txt
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File mendelian_vote_summary_snv = "${sample_name}.snv.summary.txt"
-		File mendelian_vote_summary_indel = "${sample_name}.indel.summary.txt"
-		File mendelian_vote_summary_snv_detail = "${sample_name}.snv.txt"
-		File mendelian_vote_summary_indel_detail = "${sample_name}.indel.txt"
-	}
-}

tasks/merge_mendelian.wdl

@@ -0,0 +1,35 @@
+task merge_mendelian {
+	File D5_trio_vcf
+	File D6_trio_vcf
+	File family_vcf
+	String family_name = basename(family_vcf,".family.vcf")
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		cat ${D5_trio_vcf} | grep -v '##' > ${family_name}.D5.txt
+		cat ${D6_trio_vcf} | grep -v '##' > ${family_name}.D6.txt
+		cat ${family_vcf} | grep -v '##' | awk '
+		    BEGIN { OFS = "\t" }
+		    NF > 2 && FNR > 1 { 
+		        for ( i=9; i<=NF; i++ ) { 
+		            split($i,a,":") ;$i = a[1];
+		        } 
+		    } 
+		    { print }
+		' > ${family_name}.consensus.txt
+		python /opt/merge_two_family_with_genotype.py -LCL5 ${family_name}.D5.txt -LCL6 ${family_name}.D6.txt -genotype ${family_name}.consensus.txt -family ${family_name}
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File project_mendelian = "${family_name}.txt"
+		File project_mendelian_summary = "${family_name}.summary.txt"
+	}
+}

tasks/merge_mendelian_vote.wdl

@@ -1,31 +0,0 @@
-task merge_mendelian_vote {
-	File vote_file
-	File mendelian_file
-	File mut_file
-	String output_prefix
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-		python /opt/merge_mendelian_vote.py ${mendelian_file} ${vote_file} ${mut_file} ${output_prefix}.mendelian.vote.txt
-
-		cat ${output_prefix}.mendelian.vote.txt | awk '{ if ((length($6) == 1) && (length($7) == 1)) { print } }' > ${output_prefix}.snv
-
-		cat ${output_prefix}.mendelian.vote.txt | awk '{ if ((length($6) > 1) || (length($7) > 1)) { print } }' > ${output_prefix}.indel		
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File mendelian_vote = "${output_prefix}.mendelian.vote.txt"
-		File mendelian_vote_snv = "${output_prefix}.snv"
-		File mendelian_vote_indel = "${output_prefix}.indel"
-	}
-}

workflow.wdl

@@ -1,34 +1,34 @@
-import "./tasks/merge_mendelian_vote.wdl" as merge_mendelian_vote
-import "./tasks/merge_chromo.wdl" as merge_chromo
+import "./tasks/mendelian.wdl" as mendelian
+import "./tasks/merge_mendelian.wdl" as merge_mendelian
 
 workflow {{ project_name }} {
-	File inputSamplesFile
-	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
-	File mut_file
-	String docker
-	String sample_name
-	String cluster_config
+	File family_vcf
+	File ref_dir
+	String fasta
+	String MENDELIANdocker
+	String DIYdocker
+	String BIGcluster_config
+	String SMALLcluster_config
 	String disk_size
 
-	scatter (sample in inputSamples){
-		call merge_mendelian_vote.merge_mendelian_vote as merge_mendelian_vote {
-			input:
-			vote_file=sample[0],
-			mendelian_file=sample[1],
-			output_prefix=sample[2],
-			mut_file=mut_file,
-			docker=docker,
-			cluster_config=cluster_config,
-			disk_size=disk_size
-		}
+	call mendelian.mendelian as mendelian {
+		input:
+		family_vcf=family_vcf,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=MENDELIANdocker,
+		cluster_config=BIGcluster_config,
+		disk_size=disk_size		
 	}
-	call merge_chromo.merge_chromo as merge_chromo {
+
+	call merge_mendelian.merge_mendelian as merge_mendelian {
 		input:
-		mendelian_vote_snv=merge_mendelian_vote.mendelian_vote_snv,
-		mendelian_vote_indel=merge_mendelian_vote.mendelian_vote_indel,
-		sample_name=sample_name,
-		docker=docker,
-		cluster_config=cluster_config,
+		D5_trio_vcf=mendelian.D5_trio_vcf,
+		D6_trio_vcf=mendelian.D6_trio_vcf,
+		family_vcf=family_vcf,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
 		disk_size=disk_size
 	}
+
 }