rnaseq-engineering/tasks/fastp.wdl

task fastp {
    File read1
    File read2
    String sample_id
    String adapter_sequence
    String adapter_sequence_r2
    String docker
    String cluster
    String disk_size
    String umi_loc	
    String trim_adapter
    Int trim_front1
    Int trim_tail1
    Int max_len1
    Int trim_front2
    Int trim_tail2
    Int max_len2
    Int length_required
    Int umi_len
    Int qualified_quality_phred
    Int length_required1

	command <<<
    nt=$(nproc)
    
    ## Trim
    if [ "${trim_adapter}" != 'true' ]; then
    cp ${read1} ${sample_id}_R1.fq.gz
	cp ${read2} ${sample_id}_R2.fq.gz
    else
    fastp --thread $nt -l ${length_required} -q ${qualified_quality_phred} -u ${length_required1} --adapter_sequence ${adapter_sequence} --adapter_sequence_r2 ${adapter_sequence_r2} --detect_adapter_for_pe --trim_front1 ${trim_front1} --trim_tail1 ${trim_tail1} --max_len1 ${max_len1} --trim_front2 ${trim_front2} --trim_tail2 ${trim_tail2} --max_len2 ${max_len2} -i ${read1} -I ${read2} -o ${sample_id}_R1.fq.gz -O ${sample_id}_R2.fq.gz -j ${sample_id}.json -h ${sample_id}.html
    fi
   >>>
   
   runtime { 
		docker: docker
		cluster: cluster
		systemDisk: "cloud_ssd 40"
		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
   }

   output {
      File json = "${sample_id}.json"
      File report = "${sample_id}.html"
      File trim_R1 = "${sample_id}_R1.fq.gz"
      File trim_R2 = "${sample_id}_R2.fq.gz"
   }
}