add realigner and bqsr

README.md

+# README.md
+
+> Author: Yaqing Liu
+>
+> Email: [yaqing.liu@outlook.com](mailto:yaqing.liu@outlook.com)
+> 
+> Last Updates: 23/04/2021
+
+#### Requirements
+
+- choppy
+- Ali-Cloud
+- Linux
+
+#### Introduction
+This APP is used to 
+* convert a FASTQ file to an aligned BAM file.
+* QC the data at the level of FASTQ and BAM, based on FastQC, FastQ Screen and Qualimap.
+
+**Please carefully check the reference genome, bed file, etc.**
+#### Usage
+```
+open-choppy-env
+
+choppy install YaqingLiu/cbcga-wes-qc-latest
+
+choppy samples YaqingLiu/cbcga-wes-qc-latest --no-default
+# sample_id,fastq_1,fastq_2
+
+choppy batch YaqingLiu/cbcga-wes-qc-latest samples.csv -p Project -l Label
+
+# Query the status of all tasks in the project
+choppy query -L Label | grep "status"
+```

defaults

+{
+    "fastqscreen_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqscreen:0.12.0",
+    "fastqc_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqc:0.11.8",
+    "qualimap_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
+    "sentieon_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-genomics:v2019.11.28",
+    "CPU2_GB8_cluster": "OnDemand bcs.ps.g.large img-ubuntu-vpc",
+    "CPU4_GB16_cluster": "OnDemand bcs.ps.g.xlarge img-ubuntu-vpc",
+    "CPU8_GB32_cluster": "OnDemand bcs.ps.g.2xlarge img-ubuntu-vpc",
+    "disk_size": "300",
+    "SENTIEON_INSTALL_DIR": "/opt/sentieon-genomics",
+    "SENTIEON_LICENSE": "192.168.0.55:8990",
+    "covered_bed": "oss://pgx-reference-data/bed/cbcga/S07604514_Covered.bed",
+    "fastq_screen_conf": "oss://pgx-reference-data/fastq_screen_reference/fastq_screen.conf",
+    "screen_ref_dir": "oss://pgx-reference-data/fastq_screen_reference/",
+    "fasta": "GRCh38.d1.vd1.fa",
+    "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
+}

inputs

+{
+  "{{ project_name }}.sample_id": "{{ sample_id }}",
+  "{{ project_name }}.fastq_1": "{{ fastq_1 }}",
+  "{{ project_name }}.fastq_2": "{{ fastq_2 }}",
+  "{{ project_name }}.fastqscreen_docker": "{{ fastqscreen_docker }}",
+  "{{ project_name }}.fastqc_docker": "{{ fastqc_docker }}",
+  "{{ project_name }}.qualimap_docker": "{{ qualimap_docker }}",
+  "{{ project_name }}.sentieon_docker": "{{ sentieon_docker }}",
+  "{{ project_name }}.SENTIEON_INSTALL_DIR": "{{ SENTIEON_INSTALL_DIR }}",
+  "{{ project_name }}.SENTIEON_LICENSE": "{{ SENTIEON_LICENSE }}",
+  "{{ project_name }}.CPU2_GB8_cluster": "{{ CPU2_GB8_cluster }}",
+  "{{ project_name }}.CPU4_GB16_cluster": "{{ CPU4_GB16_cluster }}",
+  "{{ project_name }}.CPU8_GB32_cluster": "{{ CPU8_GB32_cluster }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.covered_bed": "{{ covered_bed }}",
+  "{{ project_name }}.fastq_screen_conf": "{{ fastq_screen_conf }}",
+  "{{ project_name }}.screen_ref_dir": "{{ screen_ref_dir }}",
+  "{{ project_name }}.fasta": "{{ fasta }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}"
+}

tasks/Dedup.wdl

+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 deduped_bam = "${sample}.sorted.deduped.bam"
+        File deduped_bam_index = "${sample}.sorted.deduped.bam.bai"
+    }
+}

tasks/Metrics.wdl

+task Metrics {
+
+    File ref_dir
+    String SENTIEON_INSTALL_DIR
+    String SENTIEON_LICENSE
+    String sample
+    String fasta
+    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 -r ${ref_dir}/${fasta} -t $nt -i ${sorted_bam} --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 CoverageMetrics --omit_base_output ${sample}_coverage_metrics
+
+        ${SENTIEON_INSTALL_DIR}/bin/sentieon plot metrics -o ${sample}_metrics_report.pdf gc=${sample}_gc_metrics.txt qd=${sample}_qd_metrics.txt mq=${sample}_mq_metrics.txt isize=${sample}_is_metrics.txt
+    >>>
+    
+    runtime {
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    output {
+        File qd_metrics = "${sample}_qd_metrics.txt"
+        File qd_metrics_pdf = "${sample}_qd_metrics.pdf"
+        File mq_metrics = "${sample}_mq_metrics.txt"
+        File mq_metrics_pdf = "${sample}_mq_metrics.pdf"
+        File is_metrics = "${sample}_is_metrics.txt"
+        File is_metrics_pdf = "${sample}_is_metrics.pdf"
+        File gc_summary = "${sample}_gc_summary.txt"
+        File gc_metrics = "${sample}_gc_metrics.txt"
+        File gc_metrics_pdf = "${sample}_gc_metrics.pdf"
+        File aln_metrics = "${sample}_aln_metrics.txt"
+        File coverage_metrics_sample_summary = "${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"
+    }
+
+}

tasks/deduped_Metrics.wdl

+task deduped_Metrics {
+
+    File ref_dir
+    String SENTIEON_INSTALL_DIR
+    String SENTIEON_LICENSE
+    String sample
+    String fasta
+    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_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -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/fastqc.wdl

+task fastqc {
+    
+    String sample
+    File read1
+    File read2
+    
+    String docker
+    String cluster_config
+    String disk_size
+
+    command <<<
+        set -o pipefail
+        set -e
+        nt=$(nproc)
+        ln -s ${read1} ${sample}_R1.fastq.gz
+        ln -s ${read2} ${sample}_R2.fastq.gz
+        fastqc -t $nt -o ./ ${sample}_R1.fastq.gz
+        fastqc -t $nt -o ./ ${sample}_R2.fastq.gz
+    >>>
+
+    runtime {
+        docker:docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    output {
+        File read1_html="${sample}_R1_fastqc.html"
+        File read1_zip="${sample}_R1_fastqc.zip"
+        File read2_html="${sample}_R2_fastqc.html"
+        File read2_zip="${sample}_R2_fastqc.zip"
+    }
+}

tasks/fastqscreen.wdl

+task fastq_screen {
+    
+    String sample
+    File read1
+    File read2
+    File screen_ref_dir
+    File fastq_screen_conf
+
+    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/
+        ln -s ${read1} ${sample}_R1.fastq.gz
+        ln -s ${read2} ${sample}_R2.fastq.gz
+        fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${sample}_R1.fastq.gz
+        fastq_screen --aligner bowtie2 --conf ${fastq_screen_conf} --top 100000 --threads $nt ${sample}_R2.fastq.gz
+    >>>
+
+    runtime {
+        docker:docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        File png1 = "${sample}_R1_screen.png"
+        File txt1 = "${sample}_R1_screen.txt"
+        File html1 = "${sample}_R1_screen.html"
+        File png2 = "${sample}_R2_screen.png"
+        File txt2 = "${sample}_R2_screen.txt"
+        File html2 = "${sample}_R2_screen.html"
+    }
+}

tasks/mapping.wdl

+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

+task qualimap {
+    
+    String sample
+    File bam
+    File bai
+    File covered_bed
+    
+    String docker
+    String cluster_config
+    String disk_size
+
+    command <<<
+        set -o pipefail
+        set -e
+        nt=$(nproc)
+        awk 'BEGIN{OFS="\t"}{sub("\r","",$3);print $1,$2,$3,"",0,"."}' ${covered_bed} > new.bed
+        /opt/qualimap/qualimap bamqc -bam ${bam} -gff new.bed -outformat PDF:HTML -nt $nt -outdir ${sample} --java-mem-size=32G
+        cat ${sample}/genome_results.txt | grep duplication | awk -F "= |%" '{print "'"${sample}"'""\t"$2}' > ${sample}_qualimap_duplication.txt
+        tar -zcvf ${sample}_qualimap.tar ${sample}
+    >>>
+
+    runtime {
+        docker:docker
+        cluster:cluster_config
+        systemDisk:"cloud_ssd 40"
+        dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    
+    output {
+        File tar = "${sample}_qualimap.tar"
+        File duplication = "${sample}_qualimap_duplication.txt"
+    }
+}

workflow.wdl

+import "./tasks/fastqc.wdl" as fastqc
+import "./tasks/fastqscreen.wdl" as fastqscreen
+import "./tasks/qualimap.wdl" as qualimap
+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/Realigner.wdl" as Realigner
+import "./tasks/BQSR.wdl" as BQSR
+
+
+workflow {{ project_name }} {
+  String sample_id
+  File fastq_1
+  File fastq_2
+
+  File screen_ref_dir
+  File fastq_screen_conf
+  File ref_dir
+  String fasta
+  File covered_bed
+
+  String SENTIEON_INSTALL_DIR
+  String SENTIEON_LICENSE
+  String sentieon_docker
+  String fastqc_docker
+  String fastqscreen_docker
+  String qualimap_docker
+  String CPU8_GB32_cluster
+  String CPU4_GB16_cluster
+  String CPU2_GB8_cluster
+  String disk_size
+
+  call fastqc.fastqc as fastqc {
+    input:
+    sample=sample_id,
+    read1=fastq_1,
+    read2=fastq_2,
+    docker=fastqc_docker,
+    disk_size=disk_size,
+    cluster_config=CPU8_GB32_cluster
+  }
+
+  call fastqscreen.fastq_screen as fastqscreen {
+    input:
+    sample=sample_id,
+    read1=fastq_1,
+    read2=fastq_2,
+    screen_ref_dir=screen_ref_dir,
+    fastq_screen_conf=fastq_screen_conf,
+    docker=fastqscreen_docker,
+    disk_size=disk_size,
+    cluster_config=CPU2_GB8_cluster
+  }
+
+  call mapping.mapping as mapping {
+    input: 
+    group=sample_id,
+    sample=sample_id,
+    fastq_1=fastq_1,
+    fastq_2=fastq_2,
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    pl="ILLUMINAL",
+    fasta=fasta,
+    ref_dir=ref_dir,
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=CPU8_GB32_cluster
+  }
+
+  call Metrics.Metrics as Metrics {
+    input:
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    sorted_bam=mapping.sorted_bam,
+    sorted_bam_index=mapping.sorted_bam_index,
+    sample=sample_id,
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=CPU2_GB8_cluster
+  }
+
+  call Dedup.Dedup as Dedup {
+    input:
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    sorted_bam=mapping.sorted_bam,
+    sorted_bam_index=mapping.sorted_bam_index,
+    sample=sample_id,
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=CPU8_GB32_cluster
+  }
+
+  call deduped_Metrics.deduped_Metrics as deduped_Metrics {
+    input:
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    deduped_bam=Dedup.deduped_bam,
+    deduped_bam_index=Dedup.deduped_bam_index,
+    sample=sample_id,
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=CPU2_GB8_cluster
+  }
+  
+  call qualimap.qualimap as qualimap {
+    input:
+    sample=sample_id,
+    bam=Dedup.deduped_bam,
+    bai=Dedup.deduped_bam_index,
+    covered_bed=covered_bed,
+    docker=qualimap_docker,
+    disk_size=disk_size,
+    cluster_config=CPU8_GB32_cluster
+  }
+  
+  call Realigner.Realigner as Realigner {
+    input:
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    deduped_bam=Dedup.deduped_bam,
+    deduped_bam_index=Dedup.deduped_bam_index,
+    db_mills=db_mills,
+    dbmills_dir=dbmills_dir,
+    sample=sample_id + '_tumor',
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=cluster_config
+  }
+
+  call BQSR.BQSR as BQSR {
+    input:
+    SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
+    SENTIEON_LICENSE=SENTIEON_LICENSE,
+    fasta=fasta,
+    ref_dir=ref_dir,
+    realigned_bam=Realigner.realigner_bam,
+    realigned_bam_index=Realigner.realigner_bam_index,
+    db_mills=db_mills,
+    dbmills_dir=dbmills_dir,
+    dbsnp=dbsnp,
+    dbsnp_dir=dbsnp_dir,
+    sample=sample_id + '_tumor',
+    docker=sentieon_docker,
+    disk_size=disk_size,
+    cluster_config=cluster_config
+  }
+
+  output {
+    File fastqc_read1_html = fastqc.read1_html
+    File fastqc_read1_zip = fastqc.read1_zip
+    File fastqc_read2_html = fastqc.read2_html
+    File fastqc_read2_zip = fastqc.read2_zip
+    File fastqscreen_png1 = fastqscreen.png1
+    File fastqscreen_txt1 = fastqscreen.txt1
+    File fastqscreen_html1 = fastqscreen.html1
+    File fastqscreen_png2 = fastqscreen.png2
+    File fastqscreen_txt2 = fastqscreen.txt2
+    File fastqscreen_html2 = fastqscreen.html2
+    File qualimap_tar = qualimap.tar
+    File qualimap_duplication = qualimap.duplication
+    File Dedup_dedup_metrics = Dedup.dedup_metrics
+    File Dedup_duplication = Dedup.duplication
+    File deduped_bam = Dedup.deduped_bam
+    File deduped_bam_index = Dedup.deduped_bam_index
+    File Metrics_aln_metrics = Metrics.aln_metrics
+    File Metrics_gc_metrics = Metrics.gc_metrics
+    File Metrics_gc_summary = Metrics.gc_summary
+    File Metrics_is_metrics = Metrics.is_metrics
+  }
+}