info intergration

codescripts/extract_vcf_information.py

@@ -56,10 +56,6 @@ def parse_INFO(info):
 			values.append('1')
 		elif kv[0] == 'AF':
 			pass
-		elif kv[0] == 'POSITIVE_TRAIN_SITE':
-			pass
-		elif kv[0] == 'NEGATIVE_TRAIN_SITE':
-			pass
 		else:
 			keys.append(kv[0])
 			values.append(kv[1])

codescripts/high_confidence_call_vote.py

@@ -5,7 +5,8 @@ import re
 import pandas as pd
 from operator import itemgetter
 from collections import Counter
-from itertools import islice  
+from itertools import islice
+from __future__ import division  
 
 # input arguments
 parser = argparse.ArgumentParser(description="this script is to count voting number")

inputs

@@ -1,4 +1,5 @@
 {
+  "{{ project_name }}.LCL6normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ 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 }}.LCL6familyzipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
@@ -7,15 +8,21 @@
   "{{ 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 }}.LCL7normZip.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 }}.inputSamplesFile": "{{ inputSamplesFile }}",
+  "{{ project_name }}.LCL6bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.repeat_bed": "oss://pgx-result/renluyao/manuscript/all.repeat.bed",
   "{{ 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 }}.LCL5mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL6zipIndex.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL8mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL5votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
   "{{ 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 }}.LCL5normZip.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 }}.LCL8votes.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.1",
@@ -23,10 +30,16 @@
   "{{ 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 }}.LCL5bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL6mergeVCF.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 }}.LCL7mergeVCF.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ 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 }}.LCL7bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.LCL8variantsNorm.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/bcftools:v1.9",
+  "{{ project_name }}.LCL8bedAnnotation.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.LCL8normZip.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
 }
 

tasks/bed_annotation.wdl

@@ -0,0 +1,25 @@
+task bed_annotation {
+	File merged_vcf
+	File merged_vcf_idx
+	File repeat_bed
+	String sample
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		rtg vcfannotate --bed-info=${repeat_bed} -i ${merged_vcf} -o ${sample}.normed.repeatAnno.vcf.gz
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File repeat_annotated_vcf = "${sample}.normed.repeatAnno.vcf.gz"
+	}
+}

tasks/extract_info.wdl

@@ -0,0 +1,25 @@
+task extract_info {
+	File vcf
+	String vcf_name = basename(vcf,".vcf")
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+
+		python /opt/extract_vcf_information.py -i ${vcf} -o ${vcf_name}.txt
+		cat ${vcf_name}.txt | cut -f23,25,27,22,12,21,3,18,4,8,11,15 > ${vcf_name}.essential.txt
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File vcf_info = "${vcf_name}.txt"
+		File vcf_needed_info = "${vcf_name}.essential.txt"
+	}
+}

tasks/indelNorm.wdl

@@ -1,30 +0,0 @@
-task indelNorm {
-	File vcf
-	File ref_dir
-	String fasta
-	String sampleName
-	String docker
-	String cluster_config
-	String disk_size
-	
-	command <<<
-
-		cat ${vcf} | grep '#' > header
-		cat ${vcf} | grep -v '#' > body
-		cat body | grep -w '^chr1\|^chr2\|^chr3\|^chr4\|^chr5\|^chr6\|^chr7\|^chr8\|^chr9\|^chr10\|^chr11\|^chr12\|^chr13\|^chr14\|^chr15\|^chr16\|^chr17\|^chr18\|^chr19\|^chr20\|^chr21\|^chr22\|^chrX' > body.filtered
-		cat header body.filtered > ${sampleName}.filtered.vcf
-
-		/opt/hall-lab/bcftools-1.9/bin/bcftools norm -f ${ref_dir}/${fasta} ${sampleName}.filtered.vcf > ${sampleName}.normed.vcf
-
-	>>>
-
-	runtime {
-		docker:docker
-		cluster: cluster_config
-		systemDisk: "cloud_ssd 40"
-		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File normed_vcf = "${sampleName}.normed.vcf"
-	}
-}

tasks/mergeVCFInfo.wdl

@@ -8,7 +8,7 @@ task mergeVCFInfo {
 	
 	command <<<
 
-		rtg vcfmerge --force-merge-all --no-gzip -o ${sample}.merged.info.vcf ${sep=" " vcf_gz}
+		rtg vcfmerge --force-merge-all -o ${sample}.merged.info.vcf.gz ${sep=" " vcf_gz}
  
 	>>>
 
@@ -19,6 +19,7 @@ task mergeVCFInfo {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File merged_info = "${sample}.merged.info.vcf"
+		File merged_vcf = "${sample}.merged.info.vcf.gz"
+		File merged_vcf_idx = "${sample}.merged.info.vcf.gz.tbi"
 	}
 }

tasks/reformVCF.wdl

@@ -8,7 +8,6 @@ task reformVCF {
 	command <<<
 
 	python /opt/reformVCF.py -vcf ${family_mendelian_info} -name ${family_name}
-	
 
 	>>>
 

tasks/votes.wdl

@@ -9,7 +9,6 @@ task votes {
 	
 	command <<<
 		python /opt/high_confidence_call_vote.py -vcf ${merged_vcf} -dup ${vcf_dup} -sample ${sample} -prefix ${prefix}
-		cat ${prefix}_annotated.vcf | cut -f1-9,45 | grep -v 'filtered' | grep -v 'confirm for parents' | grep -v 'pcr-free-speicifc' | grep -v 'pcr-speicifc' | grep -v 'dupVar' > ${prefix}_bechmarking_calls.vcf
 	>>>
 
 	runtime {
@@ -20,6 +19,5 @@ task votes {
 	}
 	output {
 		File annotated_vcf = "${prefix}_annotated.vcf"
-		File benchmark_call = "${prefix}_bechmarking_calls.vcf"
 	}
 }

tasks/zipIndex.wdl

@@ -1,14 +1,13 @@
 task zipIndex {
 	File vcf
-	String sample
-	String family_name
+	String vcf_name = basename(vcf,".vcf")
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
-		rtg bgzip ${vcf} -c > ${family_name}.${sample}.vcf.gz
-		rtg index -f vcf ${family_name}.${sample}.vcf.gz
+		rtg bgzip ${vcf} -c > ${vcf_name}.vcf.gz
+		rtg index -f vcf ${vcf_name}.vcf.gz
 
 	>>>
 
@@ -19,7 +18,7 @@ task zipIndex {
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		File vcf_gz = "${family_name}.${sample}.vcf.gz"
-		File vcf_idx = "${family_name}.${sample}.vcf.gz.tbi"
+		File vcf_gz = "${vcf_name}.vcf.gz"
+		File vcf_idx = "${vcf_name}.vcf.gz.tbi"
 	}
 }

workflow.wdl

@@ -6,11 +6,14 @@ import "./tasks/mergeSister.wdl" as mergeSister
 import "./tasks/reformVCF.wdl" as reformVCF
 import "./tasks/merge.wdl" as merge
 import "./tasks/votes.wdl" as votes
+import "./tasks/bed_annotation.wdl" as bed_annotation
+import "./tasks/mergeVCFInfo.wdl" as mergeVCFInfo
 
 workflow {{ project_name }} {
 	File inputSamplesFile
 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
 	File ref_dir
+	File repeat_bed
 	String fasta
 	String cluster_config
 	String disk_size
@@ -52,6 +55,30 @@ workflow {{ project_name }} {
 			cluster_config=cluster_config,
 			disk_size=disk_size
 		}
+		call zipIndex.zipIndex as LCL5normZip{
+			input:
+			vcf=LCL5variantsNorm.normed_vcf,
+			cluster_config=cluster_config,
+			disk_size=disk_size
+		}
+		call zipIndex.zipIndex as LCL6normZip{
+			input:
+			vcf=LCL6variantsNorm.normed_vcf,
+			cluster_config=cluster_config,
+			disk_size=disk_size		
+		}
+		call zipIndex.zipIndex as LCL7normZip{
+			input:
+			vcf=LCL7variantsNorm.normed_vcf,
+			cluster_config=cluster_config,
+			disk_size=disk_size		
+		}
+		call zipIndex.zipIndex as LCL8normZip{
+			input:
+			vcf=LCL8variantsNorm.normed_vcf,
+			cluster_config=cluster_config,
+			disk_size=disk_size		
+		}
 		call mendelian.mendelian as LCL5mendelian {
 			input:
 			child_vcf=LCL5variantsNorm.normed_vcf,
@@ -81,16 +108,12 @@ workflow {{ project_name }} {
 		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
 		}		
@@ -138,36 +161,29 @@ workflow {{ project_name }} {
 		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
 		}		
 	}
+	### family info merge
 	call merge.merge as LCL5merge {
 		input:
 		family_vcf_gz=LCL5familyzipIndex.vcf_gz,
@@ -235,6 +251,75 @@ workflow {{ project_name }} {
 		prefix='LCL8_consensus',
 		cluster_config=cluster_config,
 		disk_size=disk_size
-	}	
+	}
+	### vcf original information
+	call mergeVCFInfo.mergeVCFInfo as LCL5mergeVCF {
+		input:
+		vcf_gz=LCL5normZip.vcf_gz,
+		vcf_idx=LCL5normZip.vcf_idx,
+		sample='LCL5',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call bed_annotation.bed_annotation as LCL5bedAnnotation {
+		input:
+		merged_vcf=LCL5mergeVCF.merged_vcf,
+		merged_vcf_idx=LCL5mergeVCF.merged_vcf_idx,
+		repeat_bed=repeat_bed,
+		sample='LCL5',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call mergeVCFInfo.mergeVCFInfo as LCL6mergeVCF {
+		input:
+		vcf_gz=LCL6normZip.vcf_gz,
+		vcf_idx=LCL6normZip.vcf_idx,
+		sample='LCL6',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call bed_annotation.bed_annotation as LCL6bedAnnotation {
+		input:
+		merged_vcf=LCL6mergeVCF.merged_vcf,
+		merged_vcf_idx=LCL6mergeVCF.merged_vcf_idx,
+		repeat_bed=repeat_bed,
+		sample='LCL6',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call mergeVCFInfo.mergeVCFInfo as LCL7mergeVCF {
+		input:
+		vcf_gz=LCL7normZip.vcf_gz,
+		vcf_idx=LCL7normZip.vcf_idx,
+		sample='LCL7',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call bed_annotation.bed_annotation as LCL7bedAnnotation {
+		input:
+		merged_vcf=LCL7mergeVCF.merged_vcf,
+		merged_vcf_idx=LCL7mergeVCF.merged_vcf_idx,
+		repeat_bed=repeat_bed,
+		sample='LCL7',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call mergeVCFInfo.mergeVCFInfo as LCL8mergeVCF {
+		input:
+		vcf_gz=LCL8normZip.vcf_gz,
+		vcf_idx=LCL8normZip.vcf_idx,
+		sample='LCL8',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	call bed_annotation.bed_annotation as LCL8bedAnnotation {
+		input:
+		merged_vcf=LCL8mergeVCF.merged_vcf,
+		merged_vcf_idx=LCL8mergeVCF.merged_vcf_idx,
+		repeat_bed=repeat_bed,
+		sample='LCL8',
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
 }