first commit

inputs

@@ -0,0 +1,18 @@
+{
+  "{{ project_name }}.benchmarking_dir": "oss://chinese-quartet/quartet-result-data/NCTR_benchmarking_20181215/",
+  "{{ project_name }}.vcfstat.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-hap:latest",
+  "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
+  "{{ project_name }}.benchmark.cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+  "{{ project_name }}.benchmark.disk_size": "150",
+  "{{ project_name }}.vcfstat.disk_size": "100",
+  "{{ project_name }}.benchmark.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-hap:latest",
+  "{{ project_name }}.inputSamplesFile": "{{ inputSamplesFile }}",
+  "{{ project_name }}.mergeNum.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/gatk:v2019.01",
+  "{{ project_name }}.mergeNum.disk_size": "100",
+  "{{ project_name }}.multiqc.cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+  "{{ project_name }}.multiqc.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/multiqc:v1.8",
+  "{{ project_name }}.mergeNum.cluster_config": "OnDemand bcs.a2.large img-ubuntu-vpc",
+  "{{ project_name }}.vcfstat.cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+  "{{ project_name }}.multiqc.disk_size": "100",
+  "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
+}

tasks/benchmark.wdl

@@ -0,0 +1,64 @@
+task benchmark {
+	File vcf
+	File benchmarking_dir
+	File ref_dir
+	String sample = basename(vcf,".vcf")
+	String sample_mark
+	String fasta
+	String docker
+	String cluster_config
+	String disk_size
+
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		mkdir -p /cromwell_root/tmp
+		cp -r ${ref_dir} /cromwell_root/tmp/
+
+		export HGREF=/cromwell_root/tmp/reference_data/GRCh38.d1.vd1.fa
+
+		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 > ${sample}.filtered.vcf
+
+		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip ${sample}.filtered.vcf -c > ${sample}.filtered.rtg.vcf.gz
+		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.filtered.rtg.vcf.gz
+
+		if [ ${sample_mark} == "LCL5" ];then
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL5.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL5.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+	    elif [ ${sample_mark} == "LCL6" ]; then
+	    	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL6.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL6.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+        elif [ ${sample_mark} == "LCL7" ]; then
+        	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL7.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL7.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+	    elif [ ${sample_mark} == "LCL8" ]; then
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL8.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL8.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+        else
+        	echo "only for quartet samples"
+        fi		
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File rtg_vcf = "${sample}.rtg.vcf.gz"
+		File rtg_vcf_index = "${sample}.rtg.vcf.gz.tbi"
+		File gzip_vcf = "${sample}.vcf.gz"
+		File gzip_vcf_index = "${sample}.vcf.gz.tbi"
+		File roc_all_csv = "${sample}.roc.all.csv.gz"
+		File roc_indel = "${sample}.roc.Locations.INDEL.csv.gz"
+		File roc_indel_pass = "${sample}.roc.Locations.INDEL.PASS.csv.gz"
+		File roc_snp = "${sample}.roc.Locations.SNP.csv.gz"
+		File roc_snp_pass = "${sample}.roc.Locations.SNP.PASS.csv.gz"
+		File summary = "${sample}.summary.csv"
+		File extended = "${sample}.extended.csv"
+		File metrics = "${sample}.metrics.json.gz"
+	}
+}

tasks/mergeNum.wdl

@@ -0,0 +1,26 @@
+task mergeNum {
+	Array[File] vcfnumber
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		for i in ${sep=" " vcfnumber}
+		do
+		  cat $i | cut -d':' -f2 | tr '\n' '\t' | sed s'/\t$/\n/g' >> vcfstats
+		done
+		sed '1i\File\tFailed Filters\tPassed Filters\tSNPs\tMNPs\tInsertions\tDeletions\tIndels\tSame as reference\tSNP Transitions/Transversions\tTotal Het/Hom ratio\tSNP Het/Hom ratio\tMNP Het/Hom ratio\tInsertion Het/Hom ratio\tDeletion Het/Hom ratio\tIndel Het/Hom ratio\tInsertion/Deletion ratio\tIndel/SNP+MNP ratio' vcfstats > vcfstats.txt
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk:"cloud_ssd 40"
+    	dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File vcfstat="vcfstats.txt"
+	}
+}

tasks/multiqc.wdl

@@ -0,0 +1,31 @@
+task multiqc {
+
+	Array[File] summary
+
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		mkdir -p /cromwell_root/tmp/benchmark
+
+		cp ${sep=" " summary} /cromwell_root/tmp/benchmark
+
+		multiqc /cromwell_root/tmp/
+	
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File multiqc_html = "multiqc_report.html"
+		Array[File] multiqc_txt = glob("multiqc_data/*")
+	}
+}

tasks/vcfstat.wdl

@@ -0,0 +1,24 @@
+task vcfstat {
+	File rtg_vcf
+	File rtg_vcf_index
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+
+		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfstats ${rtg_vcf} > onestats.txt
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster:cluster_config
+    	systemDisk:"cloud_ssd 40"
+    	dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File vcfnumber="onestats.txt"
+	}
+}

workflow.wdl

@@ -0,0 +1,44 @@
+import "./tasks/benchmark.wdl" as benchmark
+import "./tasks/multiqc.wdl" as multiqc
+import "./tasks/vcfstat.wdl" as vcfstat
+import "./tasks/mergeNum.wdl" as mergeNum
+
+workflow {{ project_name }} {
+
+	File inputSamplesFile
+	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)
+	File benchmarking_dir
+	File ref_dir
+	String fasta
+
+	scatter (sample in inputSamples) {
+
+		call benchmark.benchmark as benchmark {
+			input:
+			vcf=sample[0],
+			benchmarking_dir=benchmarking_dir,
+			ref_dir=ref_dir,
+			sample_mark=sample[1],
+			fasta=fasta
+		}
+
+		call vcfstat.vcfstat as vcfstat {
+			input:
+			rtg_vcf=benchmark.rtg_vcf,
+			rtg_vcf_index=benchmark.rtg_vcf_index
+		}	
+
+	}
+
+	call multiqc.multiqc as multiqc {
+		input:
+		summary=benchmark.summary
+	}
+
+	call mergeNum.mergeNum as mergeNum {
+		input:
+		vcfnumber=vcfstat.vcfnumber	
+	}
+
+}
+