miRNAseq/tasks/TrimAdapt.wdl

task TrimAdapt {
    String sample_id
    File in_fastq

    String adapter_seq
    Int randomBase_in_adapter
    Int sequencing_length

    String docker
    String cluster_config
    String disk_size


    command <<<
        set -o pipefail
        set -e
        nt=$(nproc)
        
        echo -e "Trim adapter's invariant part." > ${sample_id}.trimAdapt.log
        
        fastp --thread $nt -Q \
            --length_required 0 \
            --length_limit $[${sequencing_length}-1] \
            --adapter_sequence ${adapter_seq} \
            -i ${in_fastq} \
            -o ${sample_id}.trimAdapt.fastq.tmp.gz \
            2>> ${sample_id}.trimAdapt.log

        if [ ${randomBase_in_adapter} -gt 0 ]
        then
            echo -e "\nTrim ${randomBase_in_adapter} random base from both sides\n" >> ${sample_id}.trimAdapt.log
            fastp --thread $nt -A -Q -L \
                --trim_front1 ${randomBase_in_adapter} --trim_tail1 ${randomBase_in_adapter} \
                -i ${sample_id}.trimAdapt.fastq.tmp.gz \
                -o ${sample_id}.trimAdapt.fastq.gz \
                2>> ${sample_id}.trimAdapt.log
        else
            mv ${sample_id}.trimAdapt.fastq.tmp.gz ${sample_id}.trimAdapt.fastq.gz
        fi

        echo -e "Length\tReadCount" > ${sample_id}.trimAdapt.lengthDistribute
        zcat ${sample_id}.trimAdapt.fastq.gz | paste - - - - | cut -f 2 | \
            awk '{a[length($1)]++}END{for(i in a){print i,a[i]}}' | sort -n \
            >> ${sample_id}.trimAdapt.lengthDistribute

    >>>

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

    output {
        File out_fastq="${sample_id}.trimAdapt.fastq.gz"
        File out_log="${sample_id}.trimAdapt.log"
        File out_lengthDistribute="${sample_id}.trimAdapt.lengthDistribute"
    }
}