miRNAseq/tasks/ReadStats.wdl

task ReadStats {
    
    String sample_ID
    File in_log_trimAdatper
    File in_log_readFilter
    File in_log_align_mature
   
    String cluster_config
    String disk_size

    command <<<
        set -o pipefail
        set -e

        Total_input=$(cat ${in_log_trimAdatper} | grep 'total reads' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')

        Pass_trimAdatper=$(cat ${in_log_trimAdatper} | grep 'reads passed filter' | tail -n 1  | cut -d ':' -f 2 | sed 's/ //g')
        Adapter_dimer=$(bc<<<$Total_input-$Pass_trimAdatper)

        Too_short=$(cat ${in_log_readFilter} | grep 'too short' | tail -n 1 | cut -d ':' -f 2 | sed 's/ //g')

        Low_quality_singleBase=$(cat ${in_log_readFilter} | grep 'low quality' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        Low_quality_tooManyN=$(cat ${in_log_readFilter} | grep 'too many N' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        Low_quality=$(bc<<<$Low_quality_singleBase+$Low_quality_tooManyN)

        ForAlign=$(cat ${in_log_readFilter} | grep 'reads passed filter' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')

        Align_miRNA_mature=$(cat ${in_log_align_mature} | grep 'at least one reported alignment' | head -n 1 | cut -d ':' -f 2 | cut -d '(' -f 1 | sed 's/ //g')

        echo -e "Stage\tReadCount" > ${sample_ID}.readStats
        echo -e "Total Input\t$Total_input" >> ${sample_ID}.readStats
        echo -e "Adapter Dimer\t$Adapter_dimer" >> ${sample_ID}.readStats
        echo -e "Too Short\t$Too_short" >> ${sample_ID}.readStats
        echo -e "Low Quality\t$Low_quality" >> ${sample_ID}.readStats
        echo -e "For Align\t$ForAlign" >> ${sample_ID}.readStats
        echo -e "Mature miRNA\t$Align_miRNA_mature" >> ${sample_ID}.readStats
    
    >>>

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

    output {
        File out="${sample_ID}.readStats"
    }
}