first commit

defaults

+{
+  "tumor_fastq_1": "",
+  "tumor_fastq_2": "",
+  "normal_fastq_1": "",
+  "normal_fastq_2": "",
+  "read_structure": "",
+  "duplex_umi": "",
+  "regions": "oss://genomics-platform-reference-data/bed/cbcga/S07604514_Padded.bed",
+  "interval_padding": "0",
+  "SENTIEON_LICENSE": "172.25.164.226:8990",
+  "fasta": "GRCh38_full_analysis_set_plus_decoy_hla.fa",
+  "ref_dir": "oss://ivd-product/reference/refGenome/",
+  "ref_flat": "oss://ivd-product/reference/refGenome/refFlat.hg38.txt",
+  "dbmills_dir": "oss://genomics-platform-reference-data/GRCh38.d1.vd1/",
+  "db_mills": "Mills_and_1000G_gold_standard.indels.hg38.vcf",
+  "dbsnp": "dbsnp_146.hg38.vcf",
+  "dbsnp_dir": "oss://genomics-platform-reference-data/GRCh38.d1.vd1/",
+  "annovar_database": "oss://genomics-platform-reference-data/annovar/",
+  "annotsv_database": "oss://ivd-product/reference/AnnotSV/",
+  "germline_resource": "oss://genomics-platform-reference-data/gnomAD/af-only-gnomad.v3.1.1.vcf.gz",
+  "germline_resource_tbi": "oss://genomics-platform-reference-data/gnomAD/af-only-gnomad.v3.1.1.vcf.gz.tbi",
+  "gc": "oss://ivd-product/reference/Sequenza/GRCh38.gc50Base.wig.gz",
+  "sentieon_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/sentieon-genomics:v202112.05",
+  "annovar_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/annovar:v20191024",
+  "manta_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/manta:1.6.0",
+  "annotsv_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/annotsv:3.1.3",
+  "cnvkit_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/cnvkit:0.9.8",
+  "sequenza_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/sequenza:3.0.0",
+  "msisensor_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/msisensor-pro:1.2.0",
+  "tmb_docker": "registry.cn-shanghai.aliyuncs.com/choppy-pipe/tmb_docker:1.0.0",
+  "disk_size": "200",
+  "cluster_config": "OnDemand bcs.a2.3xlarge img-ubuntu-vpc"
+}

inputs

+{
+  "{{ project_name }}.sample_id": "{{ sample_id }}",
+  "{{ project_name }}.tumor_fastq_1": "{{ tumor_fastq_1 }}",
+  "{{ project_name }}.tumor_fastq_2": "{{ tumor_fastq_2 }}",
+  "{{ project_name }}.normal_fastq_1": "{{ normal_fastq_1 }}",
+  "{{ project_name }}.normal_fastq_2": "{{ normal_fastq_2 }}",
+  "{{ project_name }}.read_structure": "{{ read_structure }}",
+  "{{ project_name }}.duplex_umi": "{{ duplex_umi }}",
+  "{{ project_name }}.SENTIEON_LICENSE": "{{ SENTIEON_LICENSE }}",
+  "{{ project_name }}.sentieon_docker": "{{ sentieon_docker }}",
+  "{{ project_name }}.manta_docker": "{{ manta_docker }}",
+  "{{ project_name }}.annovar_docker": "{{ annovar_docker }}",
+  "{{ project_name }}.annotsv_docker": "{{ annotsv_docker }}",
+  "{{ project_name }}.cnvkit_docker": "{{ cnvkit_docker }}",
+  "{{ project_name }}.sequenza_docker": "{{ sequenza_docker }}",
+  "{{ project_name }}.msisensor_docker": "{{ msisensor_docker }}",
+  "{{ project_name }}.tmb_docker": "{{ tmb_docker }}",
+  "{{ project_name }}.platform": "{{ platform }}",
+  "{{ project_name }}.fasta": "{{ fasta }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}",
+  "{{ project_name }}.dbsnp": "{{ dbsnp }}",
+  "{{ project_name }}.dbsnp_dir": "{{ dbsnp_dir }}",
+  "{{ project_name }}.dbmills_dir": "{{ dbmills_dir }}",
+  "{{ project_name }}.db_mills": "{{ db_mills }}",
+  "{{ project_name }}.germline_resource": "{{ germline_resource }}",
+  "{{ project_name }}.germline_resource_tbi": "{{ germline_resource_tbi }}",
+  "{{ project_name }}.regions": "{{ regions }}",
+  "{{ project_name }}.interval_padding": "{{ interval_padding }}",
+  "{{ project_name }}.annovar_database": "{{ annovar_database }}",
+  "{{ project_name }}.annotsv_database": "{{ annotsv_database }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.cluster_config": "{{ cluster_config }}"
+}

tasks/ANNOVAR.wdl

+task ANNOVAR {
+
+  File vcf
+  String basename = basename(vcf,".vcf")
+  File annovar_database
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    /installations/annovar/table_annovar.pl ${vcf} \
+    ${annovar_database} -buildver hg38 \
+    -out ${basename} -remove \
+    -protocol refGene,cytoBand,genomicSuperDups,clinvar_20220320,intervar_20180118,cosmic95_coding,cosmic95_noncoding,gnomad211_exome,dbnsfp42c,avsnp150 \
+    -operation g,r,r,f,f,f,f,f,f,f \
+    -nastring . -vcfinput -polish -thread $nt
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File avinput = "${basename}.avinput"
+    File multianno_txt = "${basename}.hg38_multianno.txt"
+    File multianno_vcf = "${basename}.hg38_multianno.vcf"
+  }
+}

tasks/AnnotSV.wdl

+task AnnotSV {
+  
+  String sample
+  File somatic_vcf
+  File? germline_vcf
+  File annotsv_database
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    export ANNOTSV=/opt/AnnotSV
+    if [ ${somatic_vcf} ]; then
+      ${ANNOTSV}/bin/AnnotSV -SVinputFile ${somatic_vcf} -outputFile ${sample}.somatic.SV.annotated.tsv -genomeBuild GRCh38 -annotationsDir ${annotsv_database}
+    else
+      ${ANNOTSV}/bin/AnnotSV -SVinputFile ${germline_vcf} -outputFile ${sample}.germline.SV.annotated.tsv -genomeBuild GRCh38 -annotationsDir ${annotsv_database}
+    fi
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File AnnotSV_somatic_SV = "${sample}.somatic.SV.annotated.tsv"
+    File? AnnotSV_germline_SV = "${sample}.germline.SV.annotated.tsv"
+  }
+}

tasks/BQSR.wdl

+task BQSR {
+  
+  File ref_dir
+  File dbsnp_dir
+  File dbmills_dir
+  
+  String sample
+  String SENTIEON_LICENSE
+  String fasta
+  String dbsnp
+  String db_mills
+  File deduped_bam
+  File deduped_bam_index
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+
+    sentieon driver -t $nt \
+    -r ${ref_dir}/${fasta} -i ${deduped_bam} \
+    --algo QualCal \
+    -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} \
+    ${sample}_recal_data.table
+
+    sentieon driver -t $nt \
+    -r ${ref_dir}/${fasta} -i ${deduped_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.recaled.bam
+
+    sentieon driver -t $nt --algo QualCal \
+    --plot --before ${sample}_recal_data.table --after ${sample}_recal_data.table.post ${sample}_recal_data.csv
+
+    sentieon plot bqsr -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.recaled.bam"
+    File recaled_bam_index = "${sample}.sorted.deduped.recaled.bam.bai"
+    File recal_csv = "${sample}_recal_data.csv"
+    File bqsrreport_pdf = "${sample}_bqsrreport.pdf"
+  }
+}

tasks/CNVkit.wdl

+task CNVkit {
+
+  String sample
+  File tumor_bam
+  File tumor_bam_index
+  File? normal_bam
+  File? normal_bam_index
+  File regions
+  File ref_dir
+  String fasta
+  File ref_flat
+  String docker
+  String cluster_config
+  String disk_size
+  
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    mkdir -p /cromwell_root/tmp/cnvkit
+    cd /cromwell_root/tmp/cnvkit
+    
+    cnvkit.py access ${ref_dir}/${fasta} -o access.bed
+    # Prepare the target bed
+    cnvkit.py target ${regions} --annotate ${ref_flat} --split --short-names -o my_baits.bed
+    if [ ${normal_bam} ]; then
+      cnvkit.py autobin ${tumor_bam} ${normal_bam} -t my_baits.bed -g access.bed
+    else
+      cnvkit.py autobin ${tumor_bam} -t my_baits.bed -g access.bed
+    fi
+    
+    # For each sample...
+    cnvkit.py coverage ${tumor_bam} my_baits.target.bed -o ${sample}.T.targetcoverage.cnn
+    cnvkit.py coverage ${tumor_bam} my_baits.antitarget.bed -o ${sample}.T.antitargetcoverage.cnn
+    if [ ${normal_bam} ]; then
+      cnvkit.py coverage ${normal_bam} my_baits.target.bed -o ${sample}.N.targetcoverage.cnn
+      cnvkit.py coverage ${normal_bam} my_baits.antitarget.bed -o ${sample}.N.antitargetcoverage.cnn
+      # With paired or pooled normals
+      cnvkit.py reference *.N.{,anti}targetcoverage.cnn --fasta ${ref_dir}/${fasta} -o reference.cnn
+    else
+      # With no control sample
+      cnvkit.py reference -o reference.cnn -f ${ref_dir}/${fasta} -t my_baits.target.bed -a my_baits.antitarget.bed
+    fi
+    
+    # For each tumor sample...
+    cnvkit.py fix ${sample}.T.targetcoverage.cnn ${sample}.T.antitargetcoverage.cnn reference.cnn -o ${sample}.cnr
+    cnvkit.py segment ${sample}.cnr -o ${sample}.cns
+    
+    # Check noise
+    cnvkit.py metrics ${sample}.cnr -s ${sample}.cns > ${sample}.stats
+
+    # Derive each segment's absolute integer copy number, ploidy must be int value
+    purity=`awk -F'\t' '{print $6}' ${hrd} | sed -n '2p'`
+    cnvkit.py call ${sample}.cns -y -m clonal --purity ${purity} -o ${sample}.call.cns
+    
+    # Plot the results
+    cnvkit.py scatter ${sample}.cnr -s ${sample}.call.cns -o ${sample}.scatter.pdf
+    cnvkit.py diagram ${sample}.cnr -s ${sample}.call.cns -o ${sample}.diagram.pdf
+    cnvkit.py heatmap ${sample}.cnr ${sample}.call.cns -o ${sample}.heatmap.pdf
+    
+    # Genemetrics
+    mkdir gainloss
+    cnvkit.py genemetrics ${sample}.cnr -s ${sample}.call.cns -t 0 -m 0 -o ${sample}.cnv.txt
+    # Filter genes
+    cnvkit.py genemetrics ${sample}.cnr -t 0.2 -m 3 -o ${sample}.ratio-genes.txt
+    cnvkit.py genemetrics ${sample}.cnr -s ${sample}.call.cns -t 0.2 -m 3 -o ${sample}.segment-genes.txt
+    cat ${sample}.ratio-genes.txt | tail -n+2 | cut -f1 | sort | uniq > ratio-genes.txt
+    cat ${sample}.segment-genes.txt | tail -n+2 | cut -f1 | sort | uniq > segment-genes.txt
+    comm -12 ratio-genes.txt segment-genes.txt > trusted_cnv_genes.txt
+    for gene in `cat trusted_cnv_genes.txt`
+    do
+      cnvkit.py scatter ${sample}.cnr -s ${sample}.call.cns -g $gene -o ./gainloss/${sample}.$gene.scatter.pdf
+    done
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File scatter_pdf = "${sample}.scatter.pdf"
+    File diagram_pdf = "${sample}.diagram.pdf"
+    File heatmap_pdf = "${sample}.heatmap.pdf"
+    File cnr = "${sample}.cnr"
+    File cns = "${sample}.cns"
+    File stats = "${sample}.stats"
+    File call_cns = "${sample}.call.cns"
+    File genemetrics = "${sample}.cnv.txt"
+    File gainloss_genes = "/cromwell_root/tmp/cnvkit/trusted_cnv_genes.txt"
+    Array[File] gainloss = glob("/cromwell_root/tmp/cnvkit/gainloss/*")
+  }
+}

tasks/Dedup.wdl

+task Dedup {
+  
+  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 driver -t $nt -i ${sorted_bam} --algo LocusCollector --fun score_info ${sample}_score.txt
+    sentieon driver -t $nt -i ${sorted_bam} --algo Dedup --rmdup --score_info ${sample}_score.txt --metrics ${sample}_dedup_metrics.txt ${sample}.sorted.deduped.bam
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+
+  output {
+    File score = "${sample}_score.txt"
+    File dedup_metrics = "${sample}_dedup_metrics.txt"
+    File deduped_bam = "${sample}.sorted.deduped.bam"
+    File deduped_bam_index = "${sample}.sorted.deduped.bam.bai"
+  }
+}

tasks/HRD.wdl

+task HRD {
+  
+  String sample
+  File ref_dir
+  String fasta
+  File gc
+  File tumor_bam
+  File tumor_bam_index
+  File? normal_bam
+  File? normal_bam_index
+  String docker
+  String cluster_config
+  String disk_size
+  
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    output_dir="/cromwell_root/tmp"
+    mkdir ${output_dir}
+    seqz=${output_dir}'/'${sample}'.seqz.gz'
+    small=${output_dir}'/'${sample}'.small.seqz.gz'
+    
+    # bam2seqz
+    sequenza-utils bam2seqz -gc ${gc} --fasta ${ref_dir}/${fasta} -n ${normal_bam} -t ${tumor_bam} -o $seqz -C chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chr22 chrX chrY --parallel 24
+    
+    # merge and remove
+    cd ${output_dir}
+    zcat ${sample}_*.seqz.gz | awk '{if (NR == 1 || (NR != 1 && $1 != "chromosome")) {print $0}}' | bgzip > $seqz
+    tabix -f -s 1 -b 2 -e 2 -S 1 $seqz
+    rm ${sample}_*.seqz.gz; rm ${sample}_*.seqz.gz.tbi
+    
+    # seqz_binning: WES: 50; WGS: 200
+    sequenza-utils seqz_binning --seqz $seqz -w 50 -o $small
+    
+    # analysis in r
+    Rscript ~/sequenza.r ${output_dir} ${sample}
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    hrd="${sample}.HRD.txt"
+    alternative_fit="${sample}_alternative_fit.pdf"
+    alternative_solutions="${sample}_alternative_solutions.txt"
+    chromosome_depths="${sample}_chromosome_depths.pdf"
+    chromosome_view="${sample}_chromosome_view.pdf"
+    CN_bars="${sample}_CN_bars.pdf"
+    confints_CP="${sample}_confints_CP.txt"
+    contours_CP="${sample}_contours_CP.pdf"
+    CP_contours="${sample}_CP_contours.pdf"
+    gc_plots="${sample}_gc_plots.pdf"
+    genome_view="${sample}_genome_view.pdf"
+    model_fit="${sample}_model_fit.pdf"
+    mutations="${sample}_mutations.txt"
+    scarHRD_input="${sample}_scarHRD_input.txt"
+    segments="${sample}_segments.txt"
+    sequenza_cp_table="${sample}_sequenza_cp_table.RData"
+    sequenza_extract="${sample}_sequenza_extract.RData"
+    sequenza_log="${sample}_sequenza_log.txt"
+    small_seqz="${sample}.small.seqz.gz"
+    small_seqz_index="${sample}.small.seqz.gz.tbi"
+  }
+}

tasks/Haplotyper.wdl

+task Haplotyper {
+  
+  File ref_dir
+  String fasta
+  File dbsnp_dir
+  
+  String SENTIEON_LICENSE
+  File recaled_bam
+  File recaled_bam_index
+  String dbsnp
+  String sample
+  String docker
+  String cluster_config
+  String disk_size
+  
+  File? regions
+  Int? interval_padding
+  
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+    
+    if [ ${regions} ]; then
+      INTERVAL="--interval ${regions} --interval_padding ${interval_padding}"
+    else
+      INTERVAL=""
+    fi
+
+    sentieon driver -t $nt \
+    --interval ${regions} -r ${ref_dir}/${fasta} \
+    -i ${recaled_bam} \
+    --algo Haplotyper -d ${dbsnp_dir}/${dbsnp} \
+    ${sample}.Haplotyper.vcf
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File vcf = "${sample}.Haplotyper.vcf"
+    File vcf_idx = "${sample}.Haplotyper.vcf.idx"
+  }
+}
+
+

tasks/MSIsensor.wdl

+task MSIsensor {
+  
+  File ref_dir
+  String fasta
+  File tumor_bam
+  File tumor_bam_index
+  File? normal_bam
+  File? normal_bam_index
+  File baseline
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    # MSI
+		mkdir -p /cromwell_root/tmp/${sample}
+    msisensor-pro scan -d ${ref_dir}/${fasta} -o reference.list
+    if [ ${normal_recaled_bam} ]; then
+      msisensor-pro msi -d reference.list -n ${normal_bam} -t ${tumor_bam} -o /cromwell_root/tmp/${sample}
+    else
+      msisensor-pro pro -d ${baseline} -t ${tumor_bam} -o /cromwell_root/tmp/${sample}
+    fi
+    cp /cromwell_root/tmp/${sample} ${sample}.MSI.txt
+
+    # TMB
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File msi = "${sample}.MSI.txt"
+  }
+}

tasks/Manta.wdl

+task Manta {
+  
+  File ref_dir
+	File fasta
+  File regions
+  File tumor_bam
+  File tumor_bam_index
+  File? normal_bam
+  File? normal_bam_index
+	String sample
+	String docker
+	String cluster_config
+	String disk_size
+  
+	command <<<
+    set -o pipefail
+    set -e
+		nt=$(nproc)
+    
+    MANTA_INSTALL_PATH="/opt/manta-1.6.0.centos6_x86_64"
+    MANTA_ANALYSIS_PATH="/cromwell_root/tmp"
+		mkdir -p ${MANTA_ANALYSIS_PATH}
+    
+    # input files
+    if [ ${normal_bam} ]; then
+      INPUT="--normalBam ${normal_bam} --tumorBam ${tumor_bam}"
+    else
+      INPUT="--tumorBam ${tumor_bam}"
+    fi
+    # configManta
+    ${MANTA_INSTALL_PATH}/bin/configManta.py \
+    $INPUT \
+    --callRegions ${regions} --exome \
+    --referenceFasta ${ref_dir}/${fasta} \
+    --runDir ${MANTA_ANALYSIS_PATH}
+    # runWorkflow
+    ${MANTA_ANALYSIS_PATH}/runWorkflow.py -j $nt
+    # results
+    if [ ${normal_bam} ]; then
+      cp ${MANTA_ANALYSIS_PATH}/results/variants/somaticSV.vcf.gz ${sample}.Manta.somaticSV.vcf.gz
+      cp ${MANTA_ANALYSIS_PATH}/results/variants/diploidSV.vcf.gz ${sample}.Manta.germlineSV.vcf.gz
+    else
+      cp ${MANTA_ANALYSIS_PATH}/results/variants/tumorSV.vcf.gz ${sample}.Manta.somaticSV.vcf.gz
+    fi
+	>>>
+  
+	runtime {
+		docker:docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+  
+	output {
+		File somatic_vcf = "${sample}.Manta.somaticSV.vcf.gz"
+		File? germline_vcf = "${sample}.Manta.germlineSV.vcf.gz"
+	}
+}

tasks/Metrics.wdl

+task Metrics {
+
+  File ref_dir
+  String SENTIEON_LICENSE
+  String sample
+  String docker
+  String cluster_config
+
+  String fasta
+  File sorted_bam
+  File sorted_bam_index
+  String disk_size
+
+  File? regions
+
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+    
+    if [ ${regions} ]; then
+      INTERVAL="--interval ${regions}"
+    else
+      INTERVAL=""
+    fi
+    
+    sentieon driver -t $nt \
+    -r ${ref_dir}/${fasta} $INTERVAL \
+    -i ${sorted_bam} \
+    --algo CoverageMetrics --omit_base_output ${sample}_coverage_metrics \
+    --algo MeanQualityByCycle ${sample}_mq_metrics.txt \
+    --algo QualDistribution ${sample}_qd_metrics.txt \
+    --algo GCBias --summary ${sample}_gc_summary.txt ${sample}_gc_metrics.txt \
+    --algo AlignmentStat ${sample}_aln_metrics.txt \
+    --algo InsertSizeMetricAlgo ${sample}_is_metrics.txt \
+    --algo QualityYield ${sample}_QualityYield.txt \
+    --algo WgsMetricsAlgo ${sample}_WgsMetricsAlgo.txt
+    
+    sentieon plot metrics -o ${sample}_metrics_report.pdf gc=${sample}_gc_metrics.txt qd=${sample}_qd_metrics.txt mq=${sample}_mq_metrics.txt isize=${sample}_is_metrics.txt
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+
+  output {
+    File coverage_metrics_sample_summary = "${sample}_coverage_metrics.sample_summary"
+    File coverage_metrics_sample_statistics = "${sample}_coverage_metrics.sample_statistics"
+    File coverage_metrics_sample_interval_statistics = "${sample}_coverage_metrics.sample_interval_statistics"
+    File coverage_metrics_sample_cumulative_coverage_proportions = "${sample}_coverage_metrics.sample_cumulative_coverage_proportions"
+    File coverage_metrics_sample_cumulative_coverage_counts = "${sample}_coverage_metrics.sample_cumulative_coverage_counts"
+    File qd_metrics = "${sample}_qd_metrics.txt"
+    File mq_metrics = "${sample}_mq_metrics.txt"
+    File is_metrics = "${sample}_is_metrics.txt"
+    File gc_summary = "${sample}_gc_summary.txt"
+    File gc_metrics = "${sample}_gc_metrics.txt"
+    File aln_metrics = "${sample}_aln_metrics.txt"
+    File QualityYield = "${sample}_QualityYield.txt"
+    File wgsmetrics = "${sample}_WgsMetricsAlgo.txt"
+    File qd_metrics_pdf = "${sample}_qd_metrics.pdf"
+    File mq_metrics_pdf = "${sample}_mq_metrics.pdf"
+    File is_metrics_pdf = "${sample}_is_metrics.pdf"
+    File gc_metrics_pdf = "${sample}_gc_metrics.pdf"
+  }
+}

tasks/TMB.wdl

+task TMB {
+
+  File regions
+  File snpindel_txt
+  String docker
+  String cluster_config
+  String disk_size
+  
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    sort -k1,1 -k2,2n ${regions} | bedtools merge -i - > merged.bed
+    size=`awk -F'\t' 'BEGIN{SUM=0}{SUM+=$3-$2}END{print SUM}' merged.bed`
+    
+    # analysis in python
+    python ~/tmb.py ${snpindel_txt} ${size} ${sample}
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    snp_indel="${sample}.snp_indel.txt"
+    tmb="${sample}.TMB.txt"
+  }
+}

tasks/TNseq.wdl

+task TNseq {
+  
+  String sample
+  String SENTIEON_LICENSE
+  File tumor_bam
+  File tumor_bam_index
+  File? normal_bam
+  File? normal_bam_index
+  String tumor_name
+  String normal_name
+  
+  File ref_dir
+  String fasta
+  File germline_resource
+  File germline_resource_tbi
+  File? regions
+  Int? interval_padding
+  
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+    
+    if [ ${regions} ]; then
+      INTERVAL="--interval ${regions} --interval_padding ${interval_padding}"
+    else
+      INTERVAL=""
+    fi
+    
+    if [ ${normal_bam} ]; then
+      INPUT="-i ${tumor_bam} -i ${normal_bam}"
+      SAMPLE="--tumor_sample ${tumor_name} --normal_sample ${normal_name}"
+    else
+      INPUT="-i ${tumor_bam}"
+      SAMPLE="--tumor_sample ${tumor_name}"
+    fi
+    
+    sentieon driver -t $nt -r ${ref_dir}/${fasta} \
+    $INPUT $INTERVAL \
+    --algo TNhaplotyper2 $SAMPLE \
+    --germline_vcf ${germline_resource} \
+    ${sample}.TNseq.raw.vcf \
+    --algo OrientationBias --tumor_sample ${tumor_name} \
+    ${sample}.orientation \
+    --algo ContaminationModel $SAMPLE \
+    --vcf ${germline_resource} \
+    --tumor_segments ${sample}.contamination.segments \
+    ${sample}.contamination
+    
+    sentieon driver -t $nt \
+    -r ${ref_dir}/${fasta} \
+    --algo TNfilter $SAMPLE \
+    -v ${sample}.TNseq.raw.vcf \
+    --contamination ${sample}.contamination \
+    --tumor_segments ${sample}.contamination.segments \
+    --orientation_priors ${sample}.orientation \
+    ${sample}.TNseq.vcf
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File vcf = "${sample}.TNseq.vcf"
+    File vcf_index = "${sample}.TNseq.vcf.idx"
+    File contamination = "${sample}.contamination"
+    File contamination_segments = "${sample}.contamination.segments"
+    File orientation = "${sample}.orientation"
+  }
+}

tasks/bcftools.wdl

+task bcftools {
+  
+  File ref_dir
+  String fasta
+  File vcf
+  String basename = basename(vcf,".vcf")
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    bcftools norm -m -both ${vcf} | bcftools norm -f ${ref_dir}/${fasta} -Ov -o ${basename}.norm.vcf
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File norm_vcf = "${basename}.norm.vcf"
+  }
+}

tasks/deduped_Metrics.wdl

+task deduped_Metrics {
+
+  File ref_dir
+  String SENTIEON_LICENSE
+  String sample
+  String fasta
+  File deduped_bam
+  File deduped_bam_index
+  String docker
+  String cluster_config
+  String disk_size
+  
+  File? regions
+
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+
+    if [ ${regions} ]; then
+      INTERVAL="--interval ${regions}"
+    else
+      INTERVAL=""
+    fi
+
+    sentieon driver -t $nt \
+    -r ${ref_dir}/${fasta} $INTERVAL \
+    -i ${deduped_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/mapping.wdl

+task mapping {
+
+  File ref_dir
+  String fasta
+  File fastq_1
+  File fastq_2
+  
+  String SENTIEON_LICENSE
+  String group
+  String sample
+  String platform
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+    nt=$(nproc)
+    
+    if [ ${read_structure} ]; then
+      if [ ${duplex_umi} == "true" ]; then
+        READ_STRUCTURE="-d ${read_structure}"
+      fi
+      sentieon umi extract $READ_STRUCTURE ${fastq_1} ${fastq_2} | \
+      sentieon bwa mem -p -C -R "@RG\tID:${group}\tSM:${sample}\tPL:${platform}" -t $nt -K 10000000 ${ref_dir}/${fasta} - | \
+      sentieon umi consensus -o ${sample}.umi_consensus.fastq.gz
+      
+      sentieon bwa mem -p -C -R "@RG\tID:${group}\tSM:${sample}\tPL:${platform}" -t $nt -K 10000000 $fasta ${sample}.umi_consensus.fastq.gz | \
+      sentieon util sort --umi_post_process --sam2bam -i - -o ${sample}.sorted.bam
+    else
+      sentieon bwa mem -R "@RG\tID:${group}\tSM:${sample}\tPL:${platform}" \
+      -t $nt -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} | \
+      sentieon util sort -o ${sample}.sorted.bam -t $nt --sam2bam -i -
+    fi
+    
+  >>>
+
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  output {
+    File sorted_bam = "${sample}.sorted.bam"
+    File sorted_bam_index = "${sample}.sorted.bam.bai"
+  }
+}

workflow.wdl

+import "./tasks/mapping.wdl" as mapping
+import "./tasks/Metrics.wdl" as Metrics
+import "./tasks/Dedup.wdl" as Dedup
+import "./tasks/deduped_Metrics.wdl" as deduped_Metrics
+import "./tasks/BQSR.wdl" as BQSR
+import "./tasks/Haplotyper.wdl" as Haplotyper
+import "./tasks/TNseq.wdl" as TNseq
+import "./tasks/bcftools.wdl" as bcftools
+import "./tasks/ANNOVAR.wdl" as ANNOVAR
+import "./tasks/Manta.wdl" as Manta
+import "./tasks/AnnotSV.wdl" as AnnotSV
+import "./tasks/CNVkit.wdl" as CNVkit
+import "./tasks/MSIsensor.wdl" as MSIsensor
+import "./tasks/HRD.wdl" as HRD
+import "./tasks/TMB.wdl" as TMB
+
+workflow {{ project_name }} {
+  
+  String sample_id
+  File? tumor_fastq_1
+  File? tumor_fastq_2
+  File? normal_fastq_1
+  File? normal_fastq_2
+  String? duplex_umi
+  String? read_structure
+  
+  String SENTIEON_LICENSE
+  String sentieon_docker
+  String annovar_docker
+  String manta_docker
+  String annotsv_docker
+  String cnvkit_docker
+  String sequenza_docker
+  String msisensor_docker
+  String tmb_docker
+  
+  String platform
+  File ref_dir
+  String fasta
+  File dbmills_dir
+  String db_mills
+  File dbsnp_dir
+  String dbsnp
+  File germline_resource
+  File germline_resource_tbi
+  File annovar_database
+  File annotsv_database
+  
+  File? regions
+  Int? interval_padding
+  
+  String disk_size
+  String cluster_config
+  
+  if (tumor_fastq_1!= "") {
+    call mapping.mapping as tumor_mapping {
+      input:
+      group=sample_id + '.T',
+      sample=sample_id + '.T',
+      fastq_1=tumor_fastq_1,
+      fastq_2=tumor_fastq_2,
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      pl=pl,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call Metrics.Metrics as tumor_Metrics {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      sorted_bam=tumor_mapping.sorted_bam,
+      sorted_bam_index=tumor_mapping.sorted_bam_index,
+      sample=sample_id + '.T',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call Dedup.Dedup as tumor_Dedup {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      sorted_bam=tumor_mapping.sorted_bam,
+      sorted_bam_index=tumor_mapping.sorted_bam_index,
+      sample=sample_id + '.T',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call deduped_Metrics.deduped_Metrics as tumor_deduped_Metrics {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      deduped_bam=tumor_Dedup.deduped_bam,
+      deduped_bam_index=tumor_Dedup.deduped_bam_index,
+      sample=sample_id + '.T',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call BQSR.BQSR as tumor_BQSR {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      deduped_bam=tumor_Dedup.deduped_bam,
+      deduped_bam_index=tumor_Dedup.deduped_bam_index,
+      db_mills=db_mills,
+      dbmills_dir=dbmills_dir,
+      dbsnp=dbsnp,
+      dbsnp_dir=dbsnp_dir,
+      sample=sample_id + '.T',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+  }
+  
+  if (normal_fastq_1!= "") {
+    call mapping.mapping as normal_mapping {
+      input:
+      group=sample_id + '.N',
+      sample=sample_id + '.N',
+      fastq_1=normal_fastq_1,
+      fastq_2=normal_fastq_2,
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      platform=platform,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call Metrics.Metrics as normal_Metrics {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      sorted_bam=normal_mapping.sorted_bam,
+      sorted_bam_index=normal_mapping.sorted_bam_index,
+      sample=sample_id + '.N',
+      regions=regions,
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call Dedup.Dedup as normal_Dedup {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      sorted_bam=normal_mapping.sorted_bam,
+      sorted_bam_index=normal_mapping.sorted_bam_index,
+      sample=sample_id + '.N',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call deduped_Metrics.deduped_Metrics as normal_deduped_Metrics {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      deduped_bam=normal_Dedup.deduped_bam,
+      deduped_bam_index=normal_Dedup.deduped_bam_index,
+      sample=sample_id + '.N',
+      regions=regions,
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call BQSR.BQSR as normal_BQSR {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      deduped_bam=normal_Dedup.deduped_bam,
+      deduped_bam_index=normal_Dedup.deduped_bam_index,
+      db_mills=db_mills,
+      dbmills_dir=dbmills_dir,
+      dbsnp=dbsnp,
+      dbsnp_dir=dbsnp_dir,
+      sample=sample_id + '.N',
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call Haplotyper.Haplotyper as Haplotyper {
+      input:
+      SENTIEON_LICENSE=SENTIEON_LICENSE,
+      sample=sample_id + '.N',
+      fasta=fasta,
+      ref_dir=ref_dir,
+      recaled_bam=normal_BQSR.recaled_bam,
+      recaled_bam_index=normal_BQSR.recaled_bam_index,
+      dbsnp=dbsnp,
+      dbsnp_dir=dbsnp_dir,
+      regions=regions,
+      docker=sentieon_docker,
+      disk_size=disk_size,
+      cluster_config=cluster_config
+    }
+
+    call bcftools.bcftools as Haplotyper_bcftools {
+      input:
+      vcf=Haplotyper.vcf,
+      fasta=fasta,
+      ref_dir=ref_dir,
+      docker=bcftools_docker,
+      cluster_config=cluster_config,
+      disk_size=disk_size
+    }
+  }
+  
+	call Manta.Manta as Manta {
+		input:
+    sample=sample_id,
+		fasta=fasta,
+		ref_dir=ref_dir,
+    regions=regions,
+    normal_bam=normal_BQSR.recaled_bam,
+    normal_bam_index=normal_BQSR.recaled_bam_index,
+    tumor_bam=tumor_BQSR.recaled_bam,
+    tumor_bam_index=tumor_BQSR.recaled_bam_index,
+		docker=manta_docker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+  
+  call AnnotSV.AnnotSV as Manta_AnnotSV {
+    input:
+    sample=sample_id,
+    somatic_vcf=Manta.somatic_vcf,
+    germline_vcf=Manta.germline_vcf,
+    annotsv_database=annotsv_database,
+    docker=annotsv_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call TNseq.TNseq as TNseq {
+    input:
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    sample=sample_id,
+    normal_bam=normal_BQSR.recaled_bam,
+    normal_bam_index=normal_BQSR.recaled_bam_index,
+    tumor_bam=tumor_BQSR.recaled_bam,
+    tumor_bam_index=tumor_BQSR.recaled_bam_index,
+    normal_name=sample_id + ".N",
+    tumor_name=sample_id + ".T",
+    fasta=fasta,
+    ref_dir=ref_dir,
+    regions=regions,
+    interval_padding=interval_padding,
+    germline_resource=germline_resource,
+    germline_resource_tbi=germline_resource_tbi,
+    docker=sentieon_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call bcftools.bcftools as TNseq_bcftools {
+    input:
+    vcf=TNseq.vcf,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    docker=bcftools_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call ANNOVAR.ANNOVAR as TNseq_ANNOVAR {
+    input:
+    vcf=TNseq_bcftools.norm_vcf,
+    annovar_database=annovar_database,
+    docker=annovar_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call CNVkit.CNVkit as CNVkit {
+    input:
+    sample=sample_id,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    regions=regions,
+    ref_flat=ref_flat,
+    normal_bam=normal_BQSR.recaled_bam,
+    normal_bam_index=normal_BQSR.recaled_bam_index,
+    tumor_bam=tumor_BQSR.recaled_bam,
+    tumor_bam_index=tumor_BQSR.recaled_bam_index,
+    docker=cnvkit_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call MSIsensor.MSIsensor as MSIsensor {
+    input:
+    fasta=fasta,
+    ref_dir=ref_dir,
+    normal_bam=normal_BQSR.recaled_bam,
+    normal_bam_index=normal_BQSR.recaled_bam_index,
+    tumor_bam=tumor_BQSR.recaled_bam,
+    tumor_bam_index=tumor_BQSR.recaled_bam_index,
+    baseline=baseline,
+    docker=msisensor_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call HRD.HRD as HRD {
+    input:
+    sample=sample_id,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    gc=gc,
+    normal_bam=normal_BQSR.recaled_bam,
+    normal_bam_index=normal_BQSR.recaled_bam_index,
+    tumor_bam=tumor_BQSR.recaled_bam,
+    tumor_bam_index=tumor_BQSR.recaled_bam_index,
+    docker=sequenza_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+  
+  call TMB.TMB as TMB {
+    input:
+    sample=sample_id,
+    regions=regions,
+    snpindel_txt=TNseq_ANNOVAR.multianno_txt,
+    docker=tmb_docker,
+    cluster_config=cluster_config,
+    disk_size=disk_size
+  }
+}