first commit

inputSamplesFileExamples.tsv

-#read1	#read2	#bam	#bai	#vcf	#sample_mark	#sample_name	#_aln.metrics.txt	#_dedup_metrics.txt	#_is_metrics.txt	#_deduped_coverage_metrics.sample_summary
-oss://chinese-quartet/quartet-test-data/fastqfiles/Fudan_DNA_LCL5_R1.fastq.gz	oss://chinese-quartet/quartet-test-data/fastqfiles/Fudan_DNA_LCL5_R2.fastq.gz	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/7a72d0e6-302d-43ca-b6b0-daeaa0236d06/call-Dedup/Fudan_DNA_LCL5.sorted.deduped.bam	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/7a72d0e6-302d-43ca-b6b0-daeaa0236d06/call-Dedup/Fudan_DNA_LCL5.sorted.deduped.bam.bai	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/7a72d0e6-302d-43ca-b6b0-daeaa0236d06/call-Haplotyper/Fudan_DNA_LCL5_hc.vcf	LCL5
-oss://chinese-quartet/quartet-test-data/fastqfiles/Fudan_DNA_LCL6_R1.fastq.gz	oss://chinese-quartet/quartet-test-data/fastqfiles/Fudan_DNA_LCL6_R2.fastq.gz	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/e85d0acb-f750-48b7-87e6-f28766dd16b9/call-Dedup/Fudan_DNA_LCL6.sorted.deduped.bam	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/e85d0acb-f750-48b7-87e6-f28766dd16b9/call-Dedup/Fudan_DNA_LCL6.sorted.deduped.bam.bai	oss://choppy-cromwell-result/test-choppy/wgs_quartettest_renluyao_0827/e85d0acb-f750-48b7-87e6-f28766dd16b9/call-Haplotyper/Fudan_DNA_LCL6_hc.vcf	LCL6
+#read1	#read2	#bam	#bai

tasks/benchmark.wdl

-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
-
-		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip ${vcf} -c > ${sample}.rtg.vcf.gz
-		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.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}
-	    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}
-        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}
-	    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 ${sample}
-        else
-        	echo "only for quartet samples"
-        fi		
-	>>>
-
-	runtime {
-		docker:docker
-		cluster:cluster_config
-		systemDisk:"cloud_ssd 40"
-		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File rtg_vcf = "${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

-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/mergeSentieon.wdl

-task mergeSentieon {
-	Array[File] aln_metrics_header
-	Array[File] aln_metrics_data
-
-	Array[File] dedup_metrics_header
-	Array[File] dedup_metrics_data
-
-	Array[File] is_metrics_header
-	Array[File] is_metrics_data
-
-	Array[File] deduped_coverage_header
-	Array[File] deduped_coverage_data
-
-	String docker
-	String cluster_config
-	String disk_size
-
-	command <<<
-		set -o pipefail
-		set -e
-		cat ${sep=" " aln_metrics_header} | sed -n '1,1p' | cat - ${sep=" " aln_metrics_data} > aln_metrics.txt
-		cat ${sep=" " dedup_metrics_header} | sed -n '1,1p' | cat - ${sep=" " dedup_metrics_data} > dedup_metrics.txt
-		cat ${sep=" " is_metrics_header} | sed -n '1,1p' | cat - ${sep=" " is_metrics_data} > is_metrics.txt
-		cat ${sep=" " deduped_coverage_header} | sed -n '1,1p' | cat - ${sep=" " deduped_coverage_data} > deduped_coverage.txt
-	>>>
-
-	runtime {
-		docker:docker
-		cluster:cluster_config
-		systemDisk:"cloud_ssd 40"
-		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File aln_metrics_merge = "aln_metrics.txt"
-		File dedup_metrics_merge = "dedup_metrics.txt"
-		File is_metrics_merge = "is_metrics.txt"
-		File deduped_coverage_merge = "deduped_coverage.txt"
-	}
-}

tasks/sentieon.wdl

-task sentieon {
-	File aln_metrics
-	File dedup_metrics
-	File is_metrics
-	File deduped_coverage
-	String sample_name
-	String docker
-	String cluster_config
-	String disk_size
-
-	command <<<
-		set -o pipefail
-		set -e
-		cat ${aln_metrics} | sed -n '2,2p'  > aln_metrics.header
-		cat ${aln_metrics} | sed -n '5,5p'  > ${sample_name}.aln_metrics
-		cat ${dedup_metrics} | sed -n '2,2p' > dedup_metrics.header
-		cat ${dedup_metrics} | sed -n '3,3p' > ${sample_name}.dedup_metrics
-		cat ${is_metrics} | sed -n '2,2p' > is_metrics.header
-		cat ${is_metrics} | sed -n '3,3p' > ${sample_name}.is_metrics
-		cat ${deduped_coverage} | sed -n '1,1p' > deduped_coverage.header
-		cat ${deduped_coverage} | sed -n '2,2p' > ${sample_name}.deduped_coverage
-	>>>
-
-	runtime {
-		docker:docker
-		cluster:cluster_config
-		systemDisk:"cloud_ssd 40"
-		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-
-	output {
-		File aln_metrics_header = "aln_metrics.header"
-		File aln_metrics_data = "${sample_name}.aln_metrics"
-		File dedup_metrics_header = "dedup_metrics.header"
-		File dedup_metrics_data = "${sample_name}.dedup_metrics"
-		File is_metrics_header = "is_metrics.header"
-		File is_metrics_data = "${sample_name}.is_metrics"
-		File deduped_coverage_header = "deduped_coverage.header"
-		File deduped_coverage_data = "${sample_name}.deduped_coverage"
-	}
-}

tasks/vcfstat.wdl

-task vcfstat {
-	File rtg_vcf
-	File rtg_vcf_index
-	String sample_name
-	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} > ${sample_name}.stats.txt
-	>>>
-
-	runtime {
-		docker:docker
-    	cluster:cluster_config
-    	systemDisk:"cloud_ssd 40"
-    	dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
-	}
-	output {
-		File vcfnumber="${sample_name}.stats.txt"
-	}
-}

workflow.wdl

 import "./tasks/fastqc.wdl" as fastqc
 import "./tasks/fastqscreen.wdl" as fastqscreen
 import "./tasks/qualimap.wdl" as qualimap
-import "./tasks/sentieon.wdl" as sentieon
 import "./tasks/multiqc.wdl" as multiqc
-import "./tasks/mergeSentieon.wdl" as mergeSentieon
-
 
 workflow {{ project_name }} {
 
 			bai=sample[3]
 		}
 
-		call sentieon.sentieon as sentieon {
-			input:
-			aln_metrics=sample[7],
-			dedup_metrics=sample[8],
-			is_metrics=sample[9],
-			deduped_coverage=sample[10],
-			sample_name=sample[6]
-		}
-
 	}
+	
 	call multiqc.multiqc as multiqc {
 		input:
 		read1_zip=fastqc.read1_zip,
 		zip=qualimap.zip
 	}
 
-	call mergeSentieon.mergeSentieon as mergeSentieon {
-		input:
-		aln_metrics_header=sentieon.aln_metrics_header,
-		aln_metrics_data=sentieon.aln_metrics_data,
-		dedup_metrics_header=sentieon.dedup_metrics_header,
-		dedup_metrics_data=sentieon.dedup_metrics_data,
-		is_metrics_header=sentieon.is_metrics_header,
-		is_metrics_data=sentieon.is_metrics_data,
-		deduped_coverage_header=sentieon.deduped_coverage_header,
-		deduped_coverage_data=sentieon.deduped_coverage_data
-	}
 }