only benchmark

big_workflow

@@ -0,0 +1,42 @@
+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	
+	}
+
+}
+

inputs

@@ -1,18 +1,10 @@
 {
   "{{ project_name }}.benchmarking_dir": "oss://pgx-result/renluyao/manuscript/benchmark_calls_v3.0/",
-  "{{ 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.a2.7xlarge img-ubuntu-vpc",
-  "{{ project_name }}.benchmark.disk_size": "500",
-  "{{ 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 }}.disk_size": "500",
+  "{{ project_name }}.vcf_idx": "{{ vcf_idx }}",
+  "{{ project_name }}.docker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-hap:latest",
+  "{{ project_name }}.cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
+  "{{ project_name }}.vcf": "{{ vcf }}",
   "{{ project_name }}.ref_dir": "oss://chinese-quartet/quartet-storage-data/reference_data/"
 }

tasks/benchmark.wdl

@@ -1,9 +1,9 @@
 task benchmark {
 	File vcf
+	File vcf_idx
 	File benchmarking_dir
 	File ref_dir
-	String sample = basename(vcf,".vcf")
-	String sample_mark
+	String sample = basename(vcf,".vcf.gz")
 	String fasta
 	String docker
 	String cluster_config
@@ -19,22 +19,14 @@ task benchmark {
 
 		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.afterfilterdiffbed.vcf.gz ${sample}.filtered.rtg.vcf.gz -f ${benchmarking_dir}/LCL5.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-	    elif [ ${sample_mark} == "LCL6" ]; then
-	    	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL6.afterfilterdiffbed.vcf.gz ${sample}.filtered.rtg.vcf.gz -f ${benchmarking_dir}/LCL6.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-        elif [ ${sample_mark} == "LCL7" ]; then
-        	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL7.afterfilterdiffbed.vcf.gz ${sample}.filtered.rtg.vcf.gz -f ${benchmarking_dir}/LCL7.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-	    elif [ ${sample_mark} == "LCL8" ]; then
-			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL8.afterfilterdiffbed.vcf.gz ${sample}.filtered.rtg.vcf.gz -f ${benchmarking_dir}/LCL8.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+		if [[ ${sample} =~ "LCL5" ]];then
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL5.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL5.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+	    elif [[ ${sample} =~ "LCL6" ]]; then
+	    	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL6.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL6.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+        elif [[ ${sample} =~ "LCL7" ]]; then
+        	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL7.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL7.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+	    elif [[ ${sample} =~ "LCL8" ]]; then
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL8.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL8.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
         else
         	echo "only for quartet samples"
         fi		
@@ -48,8 +40,8 @@ task benchmark {
 	}
 
 	output {
-		File rtg_vcf = "${sample}.filtered.rtg.vcf.gz"
-		File rtg_vcf_index = "${sample}.filtered.rtg.vcf.gz.tbi"
+		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"

workflow.wdl

@@ -1,42 +1,25 @@
 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 vcf
+	File vcf_idx
 	File benchmarking_dir
 	File ref_dir
 	String fasta
+	String docker
+	String cluster_config
+	String disk_size
 
-	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 {
+	call benchmark.benchmark as benchmark {
 		input:
-		summary=benchmark.summary
+		vcf=vcf,
+		vcf_idx=vcf_idx,
+		benchmarking_dir=benchmarking_dir,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
 	}
-
-	call mergeNum.mergeNum as mergeNum {
-		input:
-		vcfnumber=vcfstat.vcfnumber	
-	}
-
 }