high_confidence_calls_manuscript/workflow.wdl

import "./tasks/variantsNorm.wdl" as variantsNorm
import "./tasks/extract_info.wdl" as extract_info
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
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

	scatter (quartet in inputSamples){
		call variantsNorm.variantsNorm as LCL5variantsNorm{
			input:
			vcf=quartet[0],
			ref_dir=ref_dir,
			fasta=fasta,
			sampleName=quartet[4],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call variantsNorm.variantsNorm as LCL6variantsNorm{
			input:
			vcf=quartet[1],
			ref_dir=ref_dir,
			fasta=fasta,
			sampleName=quartet[5],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call variantsNorm.variantsNorm as LCL7variantsNorm{
			input:
			vcf=quartet[2],
			ref_dir=ref_dir,
			fasta=fasta,
			sampleName=quartet[6],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call variantsNorm.variantsNorm as LCL8variantsNorm{
			input:
			vcf=quartet[3],
			ref_dir=ref_dir,
			fasta=fasta,
			sampleName=quartet[7],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call extract_info.extract_info as LCL5extract_info {
			input:
			normed_vcf=LCL5variantsNorm.normed_vcf,
			sampleName=quartet[4],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call extract_info.extract_info as LCL6extract_info {
			input:
			normed_vcf=LCL6variantsNorm.normed_vcf,
			sampleName=quartet[5],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call extract_info.extract_info as LCL7extract_info {
			input:
			normed_vcf=LCL7variantsNorm.normed_vcf,
			sampleName=quartet[6],
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call extract_info.extract_info as LCL8extract_info {
			input:
			normed_vcf=LCL8variantsNorm.normed_vcf,
			sampleName=quartet[8],
			cluster_config=cluster_config,
			disk_size=disk_size
		}		
		call zipIndex.zipIndex as LCL5normZip{
			input:
			vcf=LCL5extract_info.vcf_info,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call zipIndex.zipIndex as LCL6normZip{
			input:
			vcf=LCL6extract_info.vcf_info,
			cluster_config=cluster_config,
			disk_size=disk_size		
		}
		call zipIndex.zipIndex as LCL7normZip{
			input:
			vcf=LCL7extract_info.vcf_info,
			cluster_config=cluster_config,
			disk_size=disk_size		
		}
		call zipIndex.zipIndex as LCL8normZip{
			input:
			vcf=LCL8extract_info.vcf_info,
			cluster_config=cluster_config,
			disk_size=disk_size		
		}
		call mendelian.mendelian as LCL5mendelian {
			input:
			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,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call mendelian.mendelian as LCL6mendelian {
			input:
			child_vcf=LCL6variantsNorm.normed_vcf,
			LCL7_vcf=LCL7variantsNorm.normed_vcf,
			LCL8_vcf=LCL8variantsNorm.normed_vcf,
			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 LCL5zipIndex {
			input:
			vcf=LCL5mendelian.trio_vcf,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call zipIndex.zipIndex as LCL6zipIndex {
			input:
			vcf=LCL6mendelian.trio_vcf,
			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,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call zipIndex.zipIndex as LCL6familyzipIndex {
			input:
			vcf=reformVCF.LCL6_family_info,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call zipIndex.zipIndex as LCL7familyzipIndex {
			input:
			vcf=reformVCF.LCL7_family_info,
			cluster_config=cluster_config,
			disk_size=disk_size
		}
		call zipIndex.zipIndex as LCL8familyzipIndex {
			input:
			vcf=reformVCF.LCL8_family_info,
			cluster_config=cluster_config,
			disk_size=disk_size
		}		
	}
	### family info 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 votes.votes as LCL5votes{
		input:
		merged_vcf=LCL5merge.merged_vcf,
		vcf_dup=LCL5merge.vcf_dup,
		sample='LCL5',
		prefix='LCL5_consensus',
		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 votes.votes as LCL6votes {
		input:
		merged_vcf=LCL6merge.merged_vcf,
		vcf_dup=LCL6merge.vcf_dup,
		sample='LCL6',
		prefix='LCL6_consensus',
		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 votes.votes as LCL7votes {
		input:
		merged_vcf=LCL7merge.merged_vcf,
		vcf_dup=LCL7merge.vcf_dup,
		sample='LCL7',
		prefix='LCL7_consensus',
		cluster_config=cluster_config,
		disk_size=disk_size
	}	
	call merge.merge as LCL8merge {
		input:
		family_vcf_gz=LCL8familyzipIndex.vcf_gz,
		family_vcf_idx=LCL8familyzipIndex.vcf_idx,
		sample="LCL8",
		cluster_config=cluster_config,
		disk_size=disk_size
	}
	call votes.votes as LCL8votes {
		input:
		merged_vcf=LCL8merge.merged_vcf,
		vcf_dup=LCL8merge.vcf_dup,
		sample='LCL8',
		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
	}
}