CNVkit-test/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? duplex_umi
  String? read_structure
  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"
  }
}