CNVkit_Sequenza/tasks/CNVkit.wdl

task cnvkit{
    String sample
    File ref_dir
    String fasta
    File ref_flat
    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

        cnvkit.py batch ${tumor_bam} -n ${normal_bam} -m wgs -f ${ref_dir}/${fasta} --annotate ${ref_flat}

        cnvkit.py scatter ${sample}.cnr -s ${sample}.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

        cnvkit.py genemetrics ${sample}.cnr -t 0.2 -m 3 -o ${sample}.ratio_cnv.txt

        cnvkit.py genemetrics ${sample}.cnr -s ${sample}.call.cns -t 0.2 -m 3 -o ${sample}.segment_cnv.txt

        cat ${sample}.ratio_cnv.txt | tail -n+2 | cut -f1 | sort | uniq > ratio_cnv.txt
        cat ${sample}.segment_cnv.txt | tail -n+2 | cut -f1 | sort | uniq > segment_cnv.txt
        comm -12 ratio_cnv.txt segment_cnv.txt > ${sample}.trusted_genes.txt

        awk 'NR==FNR {a[$1]=$2;next} NR!=FNR {if(FNR == 1 || (FNR != 1 && $1 in a)) print $0}' ${sample}.trusted_genes.txt ${sample}.ratio_cnv.txt > ${sample}.ratio_cnv.trusted.txt
        cnvkit.py call ${sample}.ratio_cnv.trusted.txt -m threshold -o ${sample}.ratio_cnv.call.txt
        awk '{if ($6 != 2) print $0}' ${sample}.ratio_cnv.call.txt > ${sample}.ratio_cnv.call.filter.txt

        ls ./

        tar cvf ${sample}.tar ./

    >>

    runtime{
        docker:docker
        cluster:cluster_config
        systemDisk:"cloud_ssd 40"
        dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
    }

    output{
        File out_file = "${sample}.tar"
    }

}