first commit

inputs

+{
+  "{{ project_name }}.satellite": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/Satellite.3.bed",
+  "{{ project_name }}.mhc": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/mhc.hg38.bed",
+  "{{ project_name }}.disk_size": "100",
+  "{{ project_name }}.vcf_idx": "{{ vcf_idx }}",
+  "{{ project_name }}.SINE": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/SINE.3.bed",
+  "{{ project_name }}.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-tools:latest",
+  "{{ project_name }}.sample_name": "{{ sample_name }}",
+  "{{ project_name }}.del_breakpoint": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/Tier1.del.breakpoint",
+  "{{ project_name }}.ins_breakpoint": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/Tier1.ins.breakpoint",
+  "{{ project_name }}.LINE": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/LINE.3.bed",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.large img-ubuntu-vpc",
+  "{{ project_name }}.LTR": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/LTR.3.bed",
+  "{{ project_name }}.simple_repeat": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/simple_repeat.3.bed",
+  "{{ project_name }}.vcf": "{{ vcf }}",
+  "{{ project_name }}.confidence_bed": "oss://pgx-result/renluyao/manuscript_v3.0/reference_dataset_v202011/Quartet.callable.voted.collapse.bed",
+  "{{ project_name }}.low_complexity": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/Low_complexity.3.bed",
+  "{{ project_name }}.SD": "oss://pgx-result/renluyao/manuscript_v3.0/difficult_region/hg38_SD_merge.chr1-22X.bed"
+}

tasks/in_out.wdl

+task in_out {
+	File vcf
+	File vcf_idx
+
+	File confidence_bed
+
+	String sample_name
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		rtg vcffilter -i ${vcf} -o ${sample_name}.insideBed.vcf.gz --include-bed=${confidence_bed}
+
+		rtg vcffilter -i ${vcf} -o ${sample_name}.outsideBed.vcf.gz --exclude-bed=${confidence_bed}
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File in_vcf = "${sample_name}.insideBed.vcf.gz"
+		File in_vcf_idx = "${sample_name}.insideBed.vcf.gz.tbi"
+		File out_vcf = "${sample_name}.outsideBed.vcf.gz"
+		File out_vcf_idx = "${sample_name}.outsideBed.vcf.gz.tbi"
+	}
+}

tasks/region.wdl

+task region {
+	File sub_vcf
+	File sub_vcf_idx
+
+	File satellite
+	File simple_repeat
+	File SINE
+	File LINE
+	File LTR
+	File low_complexity
+	File SD
+	File ins_breakpoint
+	File del_breakpoint
+	File mhc
+
+	String sample_name
+	String tag
+	String docker
+	String cluster_config
+	String disk_size
+	
+	command <<<
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.satellite.vcf.gz --include-bed=${satellite}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.simple_repeat.vcf.gz --include-bed=${simple_repeat}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.SINE.vcf.gz --include-bed=${SINE}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.LINE.vcf.gz --include-bed=${LINE}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.LTR.vcf.gz --include-bed=${LTR}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.low_complexity.vcf.gz --include-bed=${low_complexity}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.SD.vcf.gz --include-bed=${SD}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.ins_breakpoint.vcf.gz --include-bed=${ins_breakpoint}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.del_breakpoint.vcf.gz --include-bed=${del_breakpoint}
+
+		rtg vcffilter -i ${sub_vcf} -o ${sample_name}.${tag}.mhc.vcf.gz --include-bed=${mhc}
+
+
+		rtg vcfstat ${sample_name}.${tag}.satellite.vcf.gz > ${sample_name}.${tag}.satellite.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.simple_repeat.vcf.gz > ${sample_name}.${tag}.simple_repeat.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.SINE.vcf.gz > ${sample_name}.${tag}.SINE.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.LINE.vcf.gz > ${sample_name}.${tag}.LINE.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.LTR.vcf.gz > ${sample_name}.${tag}.LTR.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.low_complexity.vcf.gz > ${sample_name}.${tag}.low_complexity.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.SD.vcf.gz > ${sample_name}.${tag}.SD.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.ins_breakpoint.vcf.gz > ${sample_name}.${tag}.ins_breakpoint.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.del_breakpoint.vcf.gz > ${sample_name}.${tag}.del_breakpoint.vcfstat.txt
+		rtg vcfstat ${sample_name}.${tag}.mhc.vcf.gz > ${sample_name}.${tag}.mhc.vcfstat.txt
+
+
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File satellite_vcf = "${sample_name}.${tag}.satellite.vcf.gz"
+		File simple_repeat_vcf = "${sample_name}.${tag}.simple_repeat.vcf.gz"
+		File SINE_vcf = "${sample_name}.${tag}.SINE.vcf.gz"
+		File LINE_vcf = "${sample_name}.${tag}.LINE.vcf.gz"
+		File LTR_vcf = "${sample_name}.${tag}.LTR.vcf.gz"
+		File low_complexity_vcf = "${sample_name}.${tag}.low_complexity.vcf.gz"
+		File SD_vcf = "${sample_name}.${tag}.SD.vcf.gz"
+		File ins_breakpoint_vcf = "${sample_name}.${tag}.ins_breakpoint.vcf.gz"
+		File del_breakpoint_vcf = "${sample_name}.${tag}.del_breakpoint.vcf.gz"
+		File mhc_vcf = "${sample_name}.${tag}.mhc.vcf.gz"
+		File satellite_stat = "${sample_name}.${tag}.satellite.vcfstat.txt"
+		File simple_repeat_stat = "${sample_name}.${tag}.simple_repeat.vcfstat.txt"
+		File SINE_stat = "${sample_name}.${tag}.SINE.vcfstat.txt"
+		File LINE_stat = "${sample_name}.${tag}.LINE.vcfstat.txt"
+		File LTR_stat = "${sample_name}.${tag}.LTR.vcfstat.txt"
+		File low_complexity_stat = "${sample_name}.${tag}.low_complexity.vcfstat.txt"
+		File SD_stat = "${sample_name}.${tag}.SD.vcfstat.txt"
+		File ins_breakpoint_stat = "${sample_name}.${tag}.ins_breakpoint.vcfstat.txt"
+		File del_breakpoint_stat = "${sample_name}.${tag}.del_breakpoint.vcfstat.txt"
+		File mhc_stat = "${sample_name}.${tag}.mhc.vcfstat.txt"
+	}
+}

workflow.wdl

+import "./tasks/in_out.wdl" as in_out
+import "./tasks/region.wdl" as region
+
+
+workflow {{ project_name }} {
+
+	File vcf
+	File vcf_idx
+
+	File confidence_bed
+
+	File satellite
+	File simple_repeat
+	File SINE
+	File LINE
+	File LTR
+	File low_complexity
+	File SD
+	File ins_breakpoint
+	File del_breakpoint
+	File mhc
+
+	String sample_name
+
+	String docker
+	String cluster_config
+	String disk_size
+
+	call in_out.in_out as in_out {
+		input:
+		vcf=vcf,
+		vcf_idx=vcf_idx,
+		confidence_bed=confidence_bed,
+		sample_name=sample_name,
+		docker=docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+
+	call region.region as region {
+		input:
+		sub_vcf=in_out.in_vcf,
+		sub_vcf_idx=in_out.in_vcf_idx,
+		satellite=satellite,
+		simple_repeat=simple_repeat,
+		SINE=SINE,
+		LINE=LINE,
+		LTR=LTR,
+		low_complexity=low_complexity,
+		SD=SD,
+		ins_breakpoint=ins_breakpoint,
+		del_breakpoint=del_breakpoint,
+		mhc=mhc,
+		sample_name=sample_name,
+		tag="inside",
+		docker=docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+
+	call region.region as region {
+		input:
+		sub_vcf=in_out.out_vcf,
+		sub_vcf_idx=in_out.out_vcf_idx,
+		satellite=satellite,
+		simple_repeat=simple_repeat,
+		SINE=SINE,
+		LINE=LINE,
+		LTR=LTR,
+		low_complexity=low_complexity,
+		SD=SD,
+		ins_breakpoint=ins_breakpoint,
+		del_breakpoint=del_breakpoint,
+		mhc=mhc,
+		sample_name=sample_name,
+		tag="outside",
+		docker=docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+
+}
+