WesPipe/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

import "./tasks/fastqc.wdl" as fastqc
import "./tasks/fastqscreen.wdl" as fastqscreen
import "./tasks/qualimap.wdl" as qualimap

import "./tasks/TNscope.wdl" as TNscope
import "./tasks/VarScan.wdl" as VarScan


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 manta_docker
  String bcftools_docker
  String annovar_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 gc
  File baseline
  File ref_flat
  
  File? regions
  Int? interval_padding
  
  String disk_size
  String cluster_2cpu_4gb
  String cluster_16cpu_32gb
  
  Boolean qc
  String fastqc_docker
  String fastqscreen_docker
  String qualimap_docker
  File screen_ref_dir
  File fastq_screen_conf

  Boolean multi_caller
  String varscan_docker

  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,
      duplex_umi=duplex_umi,
      read_structure=read_structure,
      platform=platform,
      fasta=fasta,
      ref_dir=ref_dir,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call Metrics.Metrics as tumor_Metrics {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.T',
      fasta=fasta,
      ref_dir=ref_dir,
      sorted_bam=tumor_mapping.sorted_bam,
      sorted_bam_index=tumor_mapping.sorted_bam_index,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call Dedup.Dedup as tumor_Dedup {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.T',
      sorted_bam=tumor_mapping.sorted_bam,
      sorted_bam_index=tumor_mapping.sorted_bam_index,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call deduped_Metrics.deduped_Metrics as tumor_deduped_Metrics {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.T',
      fasta=fasta,
      ref_dir=ref_dir,
      deduped_bam=tumor_Dedup.deduped_bam,
      deduped_bam_index=tumor_Dedup.deduped_bam_index,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call BQSR.BQSR as tumor_BQSR {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.T',
      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,
      regions=regions,
      interval_padding=interval_padding,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    if (qc){
      call fastqc.fastqc as tumor_fastqc {
        input:
        sample=sample_id + '.T',
        read1=tumor_fastq_1,
        read2=tumor_fastq_2,
        docker=fastqc_docker,
        disk_size=disk_size,
        cluster_config=cluster_2cpu_4gb
      }
      
      call fastqscreen.fastq_screen as tumor_fastqscreen {
        input:
        sample=sample_id + '.T',
        read1=tumor_fastq_1,
        read2=tumor_fastq_2,
        screen_ref_dir=screen_ref_dir,
        fastq_screen_conf=fastq_screen_conf,
        docker=fastqscreen_docker,
        disk_size=disk_size,
        cluster_config=cluster_2cpu_4gb
      }
      
      call qualimap.qualimap as tumor_qualimap {
        input:
        sample=sample_id + '.T',
        bam=tumor_Dedup.deduped_bam,
        bai=tumor_Dedup.deduped_bam_index,
        covered_bed=regions,
        docker=qualimap_docker,
        disk_size=disk_size,
        cluster_config=cluster_16cpu_32gb
      }
    }
  }
  
  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,
      duplex_umi=duplex_umi,
      read_structure=read_structure,
      platform=platform,
      fasta=fasta,
      ref_dir=ref_dir,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call Metrics.Metrics as normal_Metrics {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.N',
      fasta=fasta,
      ref_dir=ref_dir,
      sorted_bam=normal_mapping.sorted_bam,
      sorted_bam_index=normal_mapping.sorted_bam_index,
      regions=regions,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call Dedup.Dedup as normal_Dedup {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.N',
      sorted_bam=normal_mapping.sorted_bam,
      sorted_bam_index=normal_mapping.sorted_bam_index,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call deduped_Metrics.deduped_Metrics as normal_deduped_Metrics {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.N',
      fasta=fasta,
      ref_dir=ref_dir,
      deduped_bam=normal_Dedup.deduped_bam,
      deduped_bam_index=normal_Dedup.deduped_bam_index,
      regions=regions,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    call BQSR.BQSR as normal_BQSR {
      input:
      SENTIEON_LICENSE=SENTIEON_LICENSE,
      sample=sample_id + '.N',
      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,
      regions=regions,
      interval_padding=interval_padding,
      docker=sentieon_docker,
      disk_size=disk_size,
      cluster_config=cluster_16cpu_32gb
    }

    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_16cpu_32gb
    }

    call bcftools.bcftools as Haplotyper_bcftools {
      input:
      vcf=Haplotyper.vcf,
      fasta=fasta,
      ref_dir=ref_dir,
      docker=bcftools_docker,
      cluster_config=cluster_2cpu_4gb,
      disk_size=disk_size
    }

    if (qc){
      call fastqc.fastqc as normal_fastqc {
        input:
        sample=sample_id + '.N',
        read1=normal_fastq_1,
        read2=normal_fastq_2,
        docker=fastqc_docker,
        disk_size=disk_size,
        cluster_config=cluster_2cpu_4gb
      }
      
      call fastqscreen.fastq_screen as normal_fastqscreen {
        input:
        sample=sample_id + '.N',
        read1=normal_fastq_1,
        read2=normal_fastq_2,
        screen_ref_dir=screen_ref_dir,
        fastq_screen_conf=fastq_screen_conf,
        docker=fastqscreen_docker,
        disk_size=disk_size,
        cluster_config=cluster_2cpu_4gb
      }
      
      call qualimap.qualimap as normal_qualimap {
        input:
        sample=sample_id + '.N',
        bam=normal_Dedup.deduped_bam,
        bai=normal_Dedup.deduped_bam_index,
        covered_bed=regions,
        docker=qualimap_docker,
        disk_size=disk_size,
        cluster_config=cluster_16cpu_32gb
      }
    }
  }

  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_16cpu_32gb,
    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_2cpu_4gb,
    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_16cpu_32gb,
    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_2cpu_4gb,
    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_16cpu_32gb,
    disk_size=disk_size
  }
  
  call MSIsensor.MSIsensor as MSIsensor {
    input:
    sample=sample_id,
    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_2cpu_4gb,
    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_16cpu_32gb,
    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_2cpu_4gb,
    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,
    hrd=HRD.hrd,
    docker=cnvkit_docker,
    cluster_config=cluster_2cpu_4gb,
    disk_size=disk_size
  }
  
  call VarScan.VarScan as VarScan {
    input:
    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,
    ref_dir=ref_dir,
    fasta=fasta,
    docker=varscan_docker,
    disk_size=disk_size,
    cluster_config=cluster_16cpu_32gb
  }
  
  call bcftools.bcftools as VarScan_bcftools {
    input:
    vcf=VarScan.varscan_somatic,
    fasta=fasta,
    ref_dir=ref_dir,
    docker=bcftools_docker,
    cluster_config=cluster_2cpu_4gb,
    disk_size=disk_size
  }
  
  call ANNOVAR.ANNOVAR as VarScan_ANNOVAR {
    input:
    vcf=VarScan_bcftools.norm_vcf,
    annovar_database=annovar_database,
    docker=annovar_docker,
    cluster_config=cluster_16cpu_32gb,
    disk_size=disk_size
  }
  
  call TNscope.TNscope as TNscope {
    input:
    SENTIEON_LICENSE=SENTIEON_LICENSE,
    sample=sample_id,
    normal_recaled_bam=normal_BQSR.recaled_bam,
    normal_recaled_bam_index=normal_BQSR.recaled_bam_index,
    tumor_recaled_bam=tumor_BQSR.recaled_bam,
    tumor_recaled_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,
    dbsnp=dbsnp,
    dbsnp_dir=dbsnp_dir,
    docker=sentieon_docker,
    cluster_config=cluster_16cpu_32gb,
    disk_size=disk_size
  }
  
  call bcftools.bcftools as TNscope_bcftools {
    input:
    vcf=TNscope.TNscope_vcf,
    fasta=fasta,
    ref_dir=ref_dir,
    docker=bcftools_docker,
    cluster_config=cluster_2cpu_4gb,
    disk_size=disk_size
  }
  
  call ANNOVAR.ANNOVAR as TNscope_ANNOVAR {
    input:
    vcf=TNscope_bcftools.norm_vcf,
    annovar_database=annovar_database,
    docker=annovar_docker,
    cluster_config=cluster_16cpu_32gb,
    disk_size=disk_size
  }
}