pipeline/wdl/task.wdl

#create project directory

task create_dir {
    String workdir
    command <<<
        if [ ! -d ${workdir} ];then
        mkdir -p ${workdir}/log
        fi
    >>>
}

task annovar {
    String prefix
    String output_dir
    String ref
    String vcf

    command <<<

        if [ ! -d ${output_dir}/mutation ];then
        mkdir ${output_dir}/mutation
        fi

        table_annovar.pl \
        ${vcf} \
        /dataseq/jmdna/software/annovar/humandb/ \
        -buildver hg19 -nastring . -vcfinput -remove -otherinfo \
        -protocol refGene,avsnp150,cosmic91,clinvar_20220320,1000g2015aug_all,1000g2015aug_eas,esp6500siv2_all,exac03nontcga,gnomad_genome,dbnsfp35c,cytoBand \
        -argument '-splicing_threshold 2 -hgvs',,,,,,,,,, \
        --intronhgvs 50 \
        -operation g,f,f,f,f,f,f,f,f,f,r \
        --outfile ${output_dir}/mutation/${prefix}

    >>>
    output {
        String anno = "${output_dir}/mutation/${prefix}.hg19_multianno.txt"
    }
}

task dealwithsnvindel {
    String name
    String anno
    String project
    String output_dir
    String umi
    String tumor_rmdup_bam

    command <<<

        if [ ! -d ${output_dir}/mutation ];then
        mkdir ${output_dir}/mutation
        fi

        if ${umi} ;then
        filter_snpindel_common.pl \
        ${anno} \
        ${project} \
        c \
        ${output_dir}/mutation/${name}.snp.indel.Somatic.anno.hg19_multianno_filtered_pre.txt \
        ${output_dir}/mutation/${name}.snp.indel.Germline.anno.hg19_multianno_filtered.txt \
        ${output_dir}/mutation/${name}.snp.indel.anno.hg19_multianno_tag.txt

        filter_snpindel_umi_correct_f1r1.py \
        ${output_dir}/mutation/${name}.snp.indel.Somatic.anno.hg19_multianno_filtered_pre.txt \
        ${tumor_rmdup_bam} \
        ${output_dir}/mutation/${name}.snp.indel.Somatic.anno.hg19_multianno_filtered.txt

        else
        filter_snpindel_common.pl \
        ${anno} \
        ${project} \
        t \
        ${output_dir}/mutation/${name}.snp.indel.Somatic.anno.hg19_multianno_filtered.txt \
        ${output_dir}/mutation/${name}.snp.indel.Germline.anno.hg19_multianno_filtered.txt \
        ${output_dir}/mutation/${name}.snp.indel.anno.hg19_multianno_tag.txt

    >>>
    output {
        String snvindel_filtered= "${output_dir}/mutation/${name}.snp.indel.Somatic.anno.hg19_multianno_filtered.txt"
        String germline_filtered = "${output_dir}/mutation/${name}.snp.indel.Germline.anno.hg19_multianno_filtered.txt"
    }
}

task tmb {
    String codesDir
    String name
    String output_dir
    String somatic_anno

    command <<<
        perl ${codesDir}/tmb.pl ${output_dir} ${name}
    >>>
    output {
        String tmb="${output_dir}/mutation/${name}.tmb.txt"
    }
}

task fusion {
    String name
    String ref
    String codesDir
    String output_dir
    String rmdupBam
    String cancer
    String project
    String tumor_bamdst_depth

    command <<<

        if [ ! -d ${output_dir}/fusion ];then
        mkdir ${output_dir}/fusion
        fi

        # Extract the discordant paired-end alignments.
        samtools view -b -F 1294 ${rmdupBam} > ${output_dir}/fusion/${name}.discordants.bam

        # Extract the split-read alignments
        samtools view -h ${rmdupBam} \
        | /dataseq/jmdna/software/lumpy-sv/scripts/extractSplitReads_BwaMem -i stdin \
        | samtools view -Sb - \
        > ${output_dir}/fusion/${name}.splitters.bam

        lumpyexpress \
        -B ${rmdupBam} \
        -S ${output_dir}/fusion/${name}.splitters.bam \
        -D ${output_dir}/fusion/${name}.discordants.bam \
        -o ${output_dir}/fusion/${name}.fusion.vcf

        perl ${codesDir}/fusion.filter.pl ${output_dir}/fusion/${name}.fusion.vcf ${output_dir}/fusion/${name}.fusion.filter.vcf

        svtyper \
        -B ${rmdupBam} \
        -i ${output_dir}/fusion/${name}.fusion.filter.vcf \
        -T ${ref} \
        -o ${output_dir}/fusion/${name}.fusion.gt.vcf

        table_annovar.pl \
        ${output_dir}/fusion/${name}.fusion.gt.vcf \
        /dataseq/jmdna/software/annovar/humandb/ \
        -buildver hg19 -nastring . -vcfinput -remove -otherinfo \
        -protocol refGene \
        -operation g \
        --outfile ${output_dir}/fusion/${name}.fusion

        perl ${codesDir}/fusion.reanno.pl ${tumor_bamdst_depth} ${output_dir} ${name}
        perl /home/jm001/test_duantao/database_update/codes/682/fusion_targetTherapy.pl ${codesDir} ${name} ${output_dir} ${project} ${cancer}

    >>>

    output {
        String fusion = "${output_dir}/fusion/${name}.fusion.pos.txt"
    }
}

task tumor_content {
    String name
    String tumor_pileup
    String normal_pileup
    String ref
    String output_dir
    String codesDir
    String gc_wiggle = "/dataseq/jmdna/codes/pancancer_controlsample/hg19.gc200Base.txt.gz"

    command <<<

        sequenza-utils bam2seqz \
        -p -gc ${gc_wiggle} \
        -F ${ref} \
        -n ${normal_pileup} \
        -t ${tumor_pileup} \
        | gzip > ${output_dir}/qc/target_${name}.200base.seqz.gz

        sequenza-utils seqz_binning -w 200 -s ${output_dir}/qc/target_${name}.200base.seqz.gz \
        | gzip  > ${output_dir}/qc/target_${name}.200base.small.seqz.gz

        Rscript ${codesDir}/sequenza.R ${name} ${output_dir}/qc/target_${name}.200base.small.seqz.gz ${output_dir}/qc/sequenza || echo "sequenza failed!"

    >>>
    output {
        String purity = "${output_dir}/qc/sequenza/${name}_CP_contours.pdf"
    }

}

task cnvkit {
    String tumor
    String normal

    String tumor_rmdupBam
    String normal_rmdupBam
    String ref
    String bed
    String output_dir
    String cancer
    String codesDir
    String project
    String accessBed = "/dataseq/jmdna/software/cnvkit-0.9.7/data/access-5k-mappable.hg19.bed"
    String annotateGene = "/dataseq/jmdna/software/cnvkit-0.9.7/data/refFlat.txt"

    command <<<

        if [ ! -d ${output_dir}/cnvkit ];then
        mkdir ${output_dir}/cnvkit
        fi

        cnvkit.py batch \
        ${tumor_rmdupBam} \
        --normal ${normal_rmdupBam} \
        --targets ${bed} \
        --fasta ${ref} \
        --access ${accessBed} \
        --output-reference ${output_dir}/cnvkit/${normal}_reference.cnn \
        --annotate ${annotateGene} \
        --drop-low-coverage --scatter --output-dir ${output_dir}/cnvkit

        cnvkit.py scatter \
        ${output_dir}/cnvkit/${tumor}.rmdup.cnr -s ${output_dir}/cnvkit/${tumor}.rmdup.cns \
        --y-max 3 --y-min -3 \
        --title ${tumor}.cns \
        -o ${output_dir}/cnvkit/${tumor}.cnv.png

        perl ${codesDir}/log2_cn.pl ${output_dir}/cnvkit/${tumor}.rmdup.cns ${output_dir}/cnvkit/${tumor}.rmdup.cns.cn
        perl /home/jm001/test_duantao/database_update/codes/682/cnv_targetTherapy.pl ${codesDir} ${tumor} ${output_dir} ${project} ${cancer}
    >>>

    output {
        String cns = "${output_dir}/cnvkit/${tumor}.rmdup.cns"
        String png = "${output_dir}/cnvkit/${tumor}.cnv.png"
    }

}

task chemo {
    String codesDir
    String output_dir
    String project
    String normal
    String rmdupBam
    command <<<

        if [ ! -d ${output_dir}/chemo ];then
        mkdir ${output_dir}/chemo
        fi

        ${codesDir}/chemo/chemo_panel.py -p ${project} -o ${output_dir} --n ${normal}
    >>>
}

task msi {
    String bed
    String name
    String output_dir
    String tumor_rmdupBam
    String normal_rmdupBam

    command <<<
        if [ ! -d ${output_dir}/msi ];then
        mkdir ${output_dir}/msi
        fi

        msisensor2 msi -d /dataseq/jmdna/software/msisensor2/hg19.microsatellites.list \
        -n ${normal_rmdupBam} \
        -t ${tumor_rmdupBam} \
        -e ${bed} -b 10 -o ${output_dir}/msi/${name}.msi

    >>>
    output {
        String target="${output_dir}/MSI/${name}.msi"
    }
}

task hla {
    String inputDir
    String output_dir
    String normal

    command <<<
        if [ ! -d ${output_dir}/neoantigen ];then
        mkdir -p ${output_dir}/neoantigen/HLA
        fi

        razers3 -tc 10 -i 95 -m 1 -dr 0 \
        -o ${output_dir}/neoantigen/HLA/fished_1.bam /dataseq/jmdna/software/OptiType-1.3.5/data/hla_reference_dna.fasta \
        ${inputDir}/*_${normal}_*1.fq.gz

        samtools bam2fq ${output_dir}/neoantigen/HLA/fished_1.bam > ${output_dir}/neoantigen/HLA/${normal}_1_fished.fastq
        rm ${output_dir}/neoantigen/HLA/fished_1.bam

        razers3 -tc 10 -i 95 -m 1 -dr 0 \
        -o ${output_dir}/neoantigen/HLA/fished_2.bam /dataseq/jmdna/software/OptiType-1.3.5/data/hla_reference_dna.fasta \
        ${inputDir}/*_${normal}_*2.fq.gz

        samtools bam2fq ${output_dir}/neoantigen/HLA/fished_2.bam > ${output_dir}/neoantigen/HLA/${normal}_2_fished.fastq
        rm ${output_dir}/neoantigen/HLA/fished_2.bam

        /dataseq/jmdna/software/OptiType-1.3.5/OptiTypePipeline.py \
        -i ${output_dir}/neoantigen/HLA/${normal}_1_fished.fastq  ${output_dir}/neoantigen/HLA/${normal}_2_fished.fastq \
        --dna -v --prefix ${normal} -o ${output_dir}/neoantigen/HLA/

    >>>
    output {
        String hla = "${output_dir}/neoantigen/HLA/${normal}_result.tsv"
    }
}

task neoantigen {
    String codesDir
    String output_dir
    String name
    String normal
    String somatic_hc_vcf
    String hla
    command <<<
        sh /home/jm001/test_duantao/database_update/test_project/20230814_test/predict_neoantigen.sh ${output_dir} ${name} ${name} ${codesDir}
    >>>
    output {
        String neoantigen = "${output_dir}/neoantigen/MHC_Class_I/${name}.all_epitopes.netchop.txt"
    }
}

task hereditary {
    String codesDir
    String name
    String output_dir
    String project
    String germline_filtered
    command <<<

        ${codesDir}/hereditary/hereditary.py -p ${project} -o ${output_dir} --n ${name}
    >>>

    output {
        String hereditary_pre = "${output_dir}/hereditary/${name}.hereditary.pre.txt"
    }
}

task conpair {
    String codesDir
    String name
    String tumor_rmdupBam
    String normal_rmdupBam
    String output_dir
    String ref

    command <<<

        if [ ! -d ${output_dir}/conpair ];then
        mkdir -p ${output_dir}/conpair
        fi

        python3 /dataseq/jmdna/software/Conpair-master/scripts/run_gatk_pileup_for_sample.py \
        -M /dataseq/jmdna/software/Conpair-master/data/markers/GRCh37.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.bed \
        -B ${tumor_rmdupBam} \
        -O ${output_dir}/conpair/${name}.tumor.gatk.mpileup \
        -R ${ref} \
        -G /dataseq/jmdna/software/GenomeAnalysisTK.3.7.jar

        python3 /dataseq/jmdna/software/Conpair-master/scripts/run_gatk_pileup_for_sample.py \
        -M /dataseq/jmdna/software/Conpair-master/data/markers/GRCh37.autosomes.phase3_shapeit2_mvncall_integrated.20130502.SNV.genotype.sselect_v4_MAF_0.4_LD_0.8.bed \
        -B ${normal_rmdupBam} \
        -O ${output_dir}/conpair/${name}.normal.gatk.mpileup \
        -R ${ref} \
        -G /dataseq/jmdna/software/GenomeAnalysisTK.3.7.jar

        sed -i 's/^chr//g' ${output_dir}/conpair/${name}.tumor.gatk.mpileup
        sed -i 's/^chr//g' ${output_dir}/conpair/${name}.normal.gatk.mpileup

        python3 /dataseq/jmdna/software/Conpair-master/scripts/verify_concordance.py \
        -H \
        -T ${output_dir}/conpair/${name}.tumor.gatk.mpileup \
        -N ${output_dir}/conpair/${name}.normal.gatk.mpileup \
        -O ${output_dir}/conpair/${name}_concordance.txt

        python3 /dataseq/jmdna/software/Conpair-master/scripts/estimate_tumor_normal_contamination.py \
        -T ${output_dir}/conpair/${name}.tumor.gatk.mpileup \
        -N ${output_dir}/conpair/${name}.normal.gatk.mpileup \
        -O ${output_dir}/conpair/${name}_contamination.txt

    >>>
    output {
        String concordance = "${output_dir}/conpair/${name}_concordance.txt"
        String contamination = "${output_dir}/conpair/${name}_contamination.txt"
    }
}

task mmr {
    String codesDir
    String name
    String output_dir
    String germline_filtered
    command <<<
        if [ ! -d ${output_dir}/MMR ];then
        mkdir -p ${output_dir}/MMR
        fi
        perl ${codesDir}/mmr_controlsample.pl ${output_dir} ${name}
    >>>
    output {
        String mmr = "${output_dir}/MMR/${name}_mmr.txt"
    }
}

task hrr {
    String codesDir
    String name
    String output_dir
    String germline_filtered
    command <<<
        if [ ! -d ${output_dir}/HRR ];then
        mkdir -p ${output_dir}/HRR
        fi
        perl ${codesDir}/hrr_controlsample_tissue.pl ${output_dir} ${name}
    >>>
    output {
        String hrr = "${output_dir}/HRR/${name}_hrr.txt"
    }
}

task hotspot {
    String name
    String output_dir
    String ref
    String rmdupBam
    String codesDir
    command <<<
        if [ ! -d ${output_dir}/mutation/hotspot/ ];then
        mkdir -p ${output_dir}/mutation/hotspot/
        fi

        samtools mpileup -Bq 20 -Q 20  \
        -f ${ref} \
        -l ${codesDir}/hotspot.bed \
        -o ${output_dir}/mutation/hotspot/${name}.hotspot.pileup \
        ${rmdupBam}

        java -jar $VARSCAN mpileup2cns \
        ${output_dir}/mutation/hotspot/${name}.hotspot.pileup \
        --min-var-freq 0.005 \
        --min-avg-qual 20 \
        --output-vcf 1 \
        --variants 1 \
        --p-value 0.99 \
        --min-reads2 2 \
        --strand-filter 0 \
        > ${output_dir}/mutation/hotspot/${name}.hotspot.L.snp.indel.vcf

        java -jar $VARSCAN mpileup2cns \
        ${output_dir}/mutation/hotspot/${name}.hotspot.pileup \
        --min-var-freq 0.01 \
        --min-avg-qual 20 \
        --output-vcf 1 \
        --variants 1 \
        --p-value 0.05 \
        --min-reads2 3 \
        --strand-filter 1 \
        > ${output_dir}/mutation/hotspot/${name}.hotspot.H.snp.indel.vcf

        perl ${codesDir}/hotspot.hvl.pl ${output_dir} ${name}

        if [ -e "${output_dir}/mutation/hotspot/${name}.hotspot.snp.indel.vcf" ]; then
        table_annovar.pl \
        ${output_dir}/mutation/hotspot/${name}.hotspot.snp.indel.vcf \
        /dataseq/jmdna/software/annovar/humandb/ \
        -buildver hg19 -nastring . -vcfinput -remove -otherinfo \
        -protocol refGene \
        -argument '-hgvs' \
        -operation g \
        --outfile ${output_dir}/mutation/hotspot/${name}.hotspot.snp.indel.anno
        perl ${codesDir}/hotspot.filter.pl ${output_dir} ${name}
        fi

    >>>
    output {
        String  hotspot = "${output_dir}/mutation/hotspot/${name}.hotspot.H.snp.indel.vcf"
    }
}

task auto_report {
    String cancer
    String codesDir
    String output_dir

    String normal
    String tumor

    String cnv_cns
    String cnv_png

    String fusion_pos
    String snvindel_filtered

    String tmb
    String mmr
    String hrr
    String hereditary_pre

    command <<<

        if [ ! -d ${output_dir}/report ];then
        mkdir -p ${output_dir}/report
        fi

        perl /home/jm001/test_duantao/database_update/codes/682/indication.pl ${output_dir} ${cancer}
        python3 ${codesDir}/drug_dedup.py ${output_dir} ${tumor}
        perl ${codesDir}/file_format_change.pl ${output_dir} ${tumor}
        python3 ${codesDir}/report_template/682gene_tissue_control_report.py ${output_dir} ${tumor} ${normal} ${cancer}

        ln -s  ${cnv_cns} ${output_dir}/report/
        ln -s  ${cnv_png} ${output_dir}/report/

        ln -s  ${fusion_pos} ${output_dir}/report/
        ln -s ${snvindel_filtered} ${output_dir}/report/

        ln -s ${tmb} ${output_dir}/report/

        ln -s ${mmr} ${output_dir}/report/

        ln -s ${hrr} ${output_dir}/report/

        ln -s ${hereditary_pre} ${output_dir}/report/

    >>>
}