first commit

defaults

@@ -0,0 +1,13 @@
+{
+  "SENTIEON_INSTALL_DIR": "/opt/sentieon-genomics",
+  "fasta": "GRCh38.d1.vd1.fa",
+  "dbsnp_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "disk_size": "800",
+  "dbmills_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
+  "cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
+  "SENTIEON_LICENSE": "192.168.0.55:8990",
+  "SENTIEONdocker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-genomics:v2019.11.28",
+  "db_mills": "Mills_and_1000G_gold_standard.indels.hg38.vcf",
+  "dbsnp": "dbsnp_146.hg38.vcf",
+  "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
+}

inputs

@@ -0,0 +1,16 @@
+{
+  "{{ project_name }}.SENTIEON_INSTALL_DIR": "{{ SENTIEON_INSTALL_DIR }}",
+  "{{ project_name }}.fasta": "{{ fasta }}",
+  "{{ project_name }}.dbsnp_dir": "{{ dbsnp_dir }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.corealigner_bam": "{{ corealigner_bam }}",
+  "{{ project_name }}.dbmills_dir": "{{ dbmills_dir }}",
+  "{{ project_name }}.cluster_config": "{{ cluster_config }}",
+  "{{ project_name }}.SENTIEON_LICENSE": "{{ SENTIEON_LICENSE }}",
+  "{{ project_name }}.corealigner_bam_index": "{{ corealigner_bam_index }}",
+  "{{ project_name }}.SENTIEONdocker": "{{ SENTIEONdocker }}",
+  "{{ project_name }}.db_mills": "{{ db_mills }}",
+  "{{ project_name }}.sample": "{{ sample }}",
+  "{{ project_name }}.dbsnp": "{{ dbsnp }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}"
+}

tasks/BQSR.wdl

@@ -0,0 +1,49 @@
+task BQSR {
+	
+    File ref_dir
+    File dbsnp_dir
+    File dbmills_dir
+	String sample
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String fasta
+	String dbsnp
+	String db_mills
+	File realigned_bam
+	File realigned_bam_index
+	String docker
+	String cluster_config
+	String disk_size
+
+	
+	command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+		nt=$(nproc)
+
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${realigned_bam} --algo QualCal -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} ${sample}_recal_data.table
+
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${realigned_bam} -q ${sample}_recal_data.table --algo QualCal -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} ${sample}_recal_data.table.post --algo ReadWriter ${sample}.sorted.deduped.realigned.recaled.bam
+
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt --algo QualCal --plot --before ${sample}_recal_data.table --after ${sample}_recal_data.table.post ${sample}_recal_data.csv
+
+		${SENTIEON_INSTALL_DIR}/bin/sentieon plot QualCal -o ${sample}_bqsrreport.pdf ${sample}_recal_data.csv
+
+	>>>
+	runtime {
+		docker:docker
+		cluster: cluster_config
+		systemDisk: "cloud_ssd 40"
+		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"	
+	}
+
+	output {
+		File recal_table = "${sample}_recal_data.table"
+		File recal_post = "${sample}_recal_data.table.post"
+		File recaled_bam = "${sample}.sorted.deduped.realigned.recaled.bam"
+		File recaled_bam_index = "${sample}.sorted.deduped.realigned.recaled.bam.bai"
+		File recal_csv = "${sample}_recal_data.csv"
+		File bqsrreport_pdf = "${sample}_bqsrreport.pdf"
+	}
+}

tasks/Dedup.wdl

@@ -0,0 +1,44 @@
+task Dedup {
+
+    String SENTIEON_INSTALL_DIR
+    String SENTIEON_LICENSE
+    String sample
+    File sorted_bam
+    File sorted_bam_index
+    
+    String docker
+    String cluster_config
+    String disk_size
+
+    command <<<
+        set -o pipefail
+        set -e
+        export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+        nt=$(nproc)
+        ${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo LocusCollector --fun score_info ${sample}_score.txt
+        ${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo Dedup --rmdup --score_info ${sample}_score.txt --metrics ${sample}_dedup_metrics.txt ${sample}.sorted.deduped.bam
+        sed -n '3p' ${sample}_dedup_metrics.txt | awk -F'\t' '{print "'"${sample}"'""\t"$9*100}' > ${sample}_picard_duplication.txt
+        # ${sample}_marked_dup_metrics.txt can be recognized as the picard output
+        sed '1i\#DuplicationMetrics' ${sample}_dedup_metrics.txt > ${sample}_marked_dup_metrics.txt
+    >>>
+    
+    runtime {
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        File score = "${sample}_score.txt"
+        File dedup_metrics = "${sample}_marked_dup_metrics.txt"
+        File duplication = "${sample}_picard_duplication.txt"
+        File Dedup_bam = "${sample}.sorted.deduped.bam"
+        File Dedup_bam_index = "${sample}.sorted.deduped.bam.bai"
+    }
+}
+
+
+
+
+

tasks/Realigner.wdl

@@ -0,0 +1,42 @@
+task Realigner {
+
+    File ref_dir
+    File dbmills_dir
+
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String sample
+	String fasta
+
+	File Dedup_bam
+	File Dedup_bam_index
+	String db_mills
+	String docker	
+	String cluster_config
+	String disk_size
+
+
+	command <<<
+	set -o pipefail
+	set -e
+	export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+	nt=$(nproc)
+	${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${Dedup_bam} --algo Realigner -k ${dbmills_dir}/${db_mills} ${sample}.sorted.deduped.realigned.bam
+	
+	>>>
+
+	runtime {
+		docker:docker
+		cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File realigner_bam = "${sample}.sorted.deduped.realigned.bam"
+		File realigner_bam_index = "${sample}.sorted.deduped.realigned.bam.bai"
+
+	}
+}
+
+

tasks/TNscope.wdl

@@ -0,0 +1,43 @@
+task TNscope {
+
+	File ref_dir
+    File dbsnp_dir
+    String sample
+
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String tumor_name
+	String normal_name
+	String docker
+	String cluster_config
+
+	String fasta
+	File corealigner_bam
+	File corealigner_bam_index
+	String dbsnp
+	String disk_size
+
+	
+	
+	command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+		nt=$(nproc)
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${corealigner_bam} --algo TNscope --tumor_sample ${tumor_name} --normal_sample ${normal_name} --dbsnp ${dbsnp_dir}/${dbsnp} ${sample}.TNscope.TN.vcf
+		
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File TNscope_vcf= "${sample}.TNscope.TN.vcf"
+		File TNscope_vcf_index = "${sample}.TNscope.TN.vcf.idx"
+	}
+
+}

tasks/TNseq.wdl

@@ -0,0 +1,44 @@
+task TNseq {
+	
+    File ref_dir
+    File dbsnp_dir
+    String sample
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String tumor_name
+	String normal_name
+	String docker
+	String cluster_config
+
+	String fasta
+	File corealigner_bam
+	File corealigner_bam_index
+	String dbsnp
+	String disk_size
+
+	
+	
+	command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+		nt=$(nproc)
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${corealigner_bam} --algo TNhaplotyper --tumor_sample ${tumor_name} --normal_sample ${normal_name} --dbsnp ${dbsnp_dir}/${dbsnp} ${sample}.TNseq.TN.vcf
+		
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File TNseq_vcf= "${sample}.TNseq.TN.vcf"
+		File TNseq_vcf_index = "${sample}.TNseq.TN.vcf.idx"
+	}
+
+}
+
+

tasks/corealigner.wdl

@@ -0,0 +1,45 @@
+task corealigner {
+	
+    File ref_dir
+    File dbsnp_dir
+    File dbmills_dir
+
+	String sample
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String docker
+	String cluster_config
+	String fasta
+
+	String dbsnp
+	String db_mills
+	File tumor_recaled_bam
+	File tumor_recaled_bam_index
+	File normal_recaled_bam
+	File normal_recaled_bam_index
+	String disk_size
+
+
+	command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+		nt=$(nproc)
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${tumor_recaled_bam} -i ${normal_recaled_bam} --algo Realigner -k ${dbmills_dir}/${db_mills} -k ${dbsnp_dir}/${dbsnp} ${sample}_corealigned.bam				
+	>>>
+	
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File corealigner_bam = "${sample}_corealigned.bam"
+		File corealigner_bam_index = "${sample}_corealigned.bam.bai"
+	}	
+}
+
+
+

tasks/deduped_Metrics.wdl

@@ -0,0 +1,46 @@
+task deduped_Metrics {
+
+    File ref_dir
+    
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String sample
+	String fasta
+	File Dedup_bam
+	File Dedup_bam_index
+	String docker
+	String cluster_config
+	String disk_size
+
+
+	command <<<
+		set -o pipefail
+		set -e
+		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+		nt=$(nproc)
+		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${Dedup_bam} --algo CoverageMetrics --omit_base_output ${sample}_deduped_coverage_metrics --algo MeanQualityByCycle ${sample}_deduped_mq_metrics.txt --algo QualDistribution ${sample}_deduped_qd_metrics.txt --algo GCBias --summary ${sample}_deduped_gc_summary.txt ${sample}_deduped_gc_metrics.txt --algo AlignmentStat ${sample}_deduped_aln_metrics.txt --algo InsertSizeMetricAlgo ${sample}_deduped_is_metrics.txt --algo QualityYield ${sample}_deduped_QualityYield.txt --algo WgsMetricsAlgo ${sample}_deduped_WgsMetricsAlgo.txt
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/" 
+	}
+
+	output {
+		File deduped_coverage_metrics_sample_summary = "${sample}_deduped_coverage_metrics.sample_summary"
+		File deduped_coverage_metrics_sample_statistics = "${sample}_deduped_coverage_metrics.sample_statistics"
+		File deduped_coverage_metrics_sample_interval_statistics = "${sample}_deduped_coverage_metrics.sample_interval_statistics"
+		File deduped_coverage_metrics_sample_cumulative_coverage_proportions = "${sample}_deduped_coverage_metrics.sample_cumulative_coverage_proportions"
+		File deduped_coverage_metrics_sample_cumulative_coverage_counts = "${sample}_deduped_coverage_metrics.sample_cumulative_coverage_counts"
+		File deduped_mean_quality = "${sample}_deduped_mq_metrics.txt"
+		File deduped_qd_metrics = "${sample}_deduped_qd_metrics.txt"
+		File deduped_gc_summary = "${sample}_deduped_gc_summary.txt"
+		File deduped_gc_metrics = "${sample}_deduped_gc_metrics.txt"
+		File dedeuped_aln_metrics = "${sample}_deduped_aln_metrics.txt"
+		File deduped_is_metrics = "${sample}_deduped_is_metrics.txt"
+		File deduped_QualityYield = "${sample}_deduped_QualityYield.txt"
+		File deduped_wgsmetrics = "${sample}_deduped_WgsMetricsAlgo.txt"
+	}
+}

tasks/fastqc.wdl

@@ -0,0 +1,37 @@
+task fastqc {
+	File tumor_read1
+	File tumor_read2
+	File normal_read1
+	File normal_read2
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		fastqc -t $nt -o ./ ${tumor_read1}
+		fastqc -t $nt -o ./ ${tumor_read2}
+		fastqc -t $nt -o ./ ${normal_read1}
+		fastqc -t $nt -o ./ ${normal_read2}
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File tumor_read1_html = sub(basename(tumor_read1), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File tumor_read1_zip = sub(basename(tumor_read1), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+		File tumor_read2_html = sub(basename(tumor_read2), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File tumor_read2_zip = sub(basename(tumor_read2), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+		File normal_read1_html = sub(basename(normal_read1), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File normal_read1_zip = sub(basename(normal_read1), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+		File normal_read2_html = sub(basename(normal_read2), "\\.(fastq|fq)\\.gz$", "_fastqc.html")
+		File normal_read2_zip = sub(basename(normal_read2), "\\.(fastq|fq)\\.gz$", "_fastqc.zip")
+
+	}
+}

tasks/fastqscreen.wdl

@@ -0,0 +1,48 @@
+task fastqscreen {
+	File tumor_read1
+	File tumor_read2
+	File normal_read1
+	File normal_read2
+	File screen_ref_dir
+	File fastq_screen_conf
+	String tumor_read1name = basename(tumor_read1,".fastq.gz")
+	String tumor_read2name = basename(tumor_read2,".fastq.gz")
+	String normal_read1name = basename(normal_read1,".fastq.gz")
+	String normal_read2name = basename(normal_read2,".fastq.gz")
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		mkdir -p /cromwell_root/tmp
+		cp -r ${screen_ref_dir} /cromwell_root/tmp/
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${tumor_read1}
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${tumor_read2}
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${normal_read1}
+		fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${normal_read2}
+	>>>
+
+	runtime {
+		docker:docker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File tumor_png1 = "${tumor_read1name}_screen.png"
+		File tumor_txt1 = "${tumor_read1name}_screen.txt"
+		File tumor_html1 = "${tumor_read1name}_screen.html"
+		File tumor_png2 = "${tumor_read2name}_screen.png"
+		File tumor_txt2 = "${tumor_read2name}_screen.txt"
+		File tumor_html2 = "${tumor_read2name}_screen.html"
+		File normal_png1 = "${normal_read1name}_screen.png"
+		File normal_txt1 = "${normal_read1name}_screen.txt"
+		File normal_html1 = "${normal_read1name}_screen.html"
+		File normal_png2 = "${normal_read2name}_screen.png"
+		File normal_txt2 = "${normal_read2name}_screen.txt"
+		File normal_html2 = "${normal_read2name}_screen.html"
+	}
+}

tasks/mapping.wdl

@@ -0,0 +1,36 @@
+task mapping {
+    
+    String sample
+    File fastq_1
+    File fastq_2
+
+    String SENTIEON_INSTALL_DIR
+    String SENTIEON_LICENSE
+    String group
+    String pl
+    File ref_dir
+    String fasta
+    
+    String docker
+    String cluster_config
+    String disk_size
+
+    command <<<
+        set -o pipefail
+        set -e	
+        export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+        nt=$(nproc)
+        ${SENTIEON_INSTALL_DIR}/bin/bwa mem -M -R "@RG\tID:${group}\tSM:${sample}\tPL:${pl}" -t $nt -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} | ${SENTIEON_INSTALL_DIR}/bin/sentieon util sort -o ${sample}.sorted.bam -t $nt --sam2bam -i -
+    >>>
+
+    runtime {
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    output {
+        File sorted_bam = "${sample}.sorted.bam"
+        File sorted_bam_index = "${sample}.sorted.bam.bai"
+    }
+}

tasks/qualimap.wdl

@@ -0,0 +1,27 @@
+task qualimap {
+	File bam
+	File bai
+	String bamname = basename(bam,".bam")
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e
+		nt=$(nproc)
+		/opt/qualimap/qualimap bamqc -bam ${bam} -outformat PDF:HTML -nt $nt -outdir ${bamname} --java-mem-size=60G 
+		tar -zcvf ${bamname}_qualimap.zip ${bamname}
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File zip = "${bamname}_qualimap.zip"
+	}
+}

workflow.wdl

@@ -0,0 +1,59 @@
+import "./tasks/TNseq.wdl" as TNseq
+import "./tasks/TNscope.wdl" as TNscope
+
+
+workflow {{ project_name }} {
+
+	File corealigner_bam
+	File corealigner_bam_index
+
+	String SENTIEON_INSTALL_DIR
+	String SENTIEON_LICENSE
+	String sample
+	String SENTIEONdocker
+
+	String fasta
+	File ref_dir
+	File dbmills_dir
+	String db_mills
+	File dbsnp_dir
+	String dbsnp
+	String disk_size
+	String cluster_config
+
+	call TNseq.TNseq as TNseq {
+		input:
+		SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+		SENTIEON_LICENSE=SENTIEON_LICENSE,
+		fasta=fasta,
+		ref_dir=ref_dir,
+		corealigner_bam=corealigner_bam,
+		corealigner_bam_index=corealigner_bam_index,
+		dbsnp=dbsnp,
+		dbsnp_dir=dbsnp_dir,
+		tumor_name=sample + "tumor",
+		normal_name=sample + "normal",
+		docker=SENTIEONdocker,
+		sample=sample,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+
+	call TNscope.TNscope as TNscope {
+		input:
+		SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+		SENTIEON_LICENSE=SENTIEON_LICENSE,
+		fasta=fasta,
+		ref_dir=ref_dir,
+		corealigner_bam=corealigner_bam,
+		corealigner_bam_index=corealigner_bam_index,
+		dbsnp=dbsnp,
+		dbsnp_dir=dbsnp_dir,
+		tumor_name=sample + "tumor",
+		normal_name=sample + "normal",
+		docker=SENTIEONdocker,
+		sample=sample,
+		disk_size=disk_size,
+		cluster_config=cluster_config
+	}
+}