miRNAseq/tasks/ReadStats.wdl

task ReadStats {
    
    String sample_id
    File in_log_trimAdatper
    File in_log_readFilter
    File in_log_align_miRNA
    File in_log_align_RNA 
    File in_log_align_rn7
    File in_sam_align_RNA

    String cluster_config
    String disk_size

    command <<<
        set -o pipefail
        set -e

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

        n_AdapterNotFound=$(cat ${in_log_trimAdatper} | grep 'reads failed due to too long' | cut -d ':' -f 2 | sed 's/ //g')
        n_Total_forCount=$[$n_Total_Sequence-$n_AdapterNotFound]

        n_Pass_trimAdatper=$(cat ${in_log_trimAdatper} | grep 'reads passed filter' | tail -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        n_Adapter_dimer=$[$n_Total_Sequence-$n_AdapterNotFound-$n_Pass_trimAdatper]
        
        n_Too_short=$(cat ${in_log_readFilter} | grep 'too short' | tail -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        n_Low_quality_singleBase=$(cat ${in_log_readFilter} | grep 'low quality' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        n_Low_quality_tooManyN=$(cat ${in_log_readFilter} | grep 'too many N' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')
        n_Low_quality=$[$n_Low_quality_singleBase+$n_Low_quality_tooManyN]
        n_ForAlign=$(cat ${in_log_readFilter} | grep 'reads passed filter' | head -n 1 | cut -d ':' -f 2 | sed 's/ //g')

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

        n_RNA=$(cat ${in_log_align_RNA} | grep 'at least one reported alignment' | head -n 1 | cut -d ':' -f 2 | cut -d '(' -f 1 | sed 's/ //g')
        n_otGenomic=$(cat ${in_log_align_rn7} | grep 'at least one reported alignment' | head -n 1 | cut -d ':' -f 2 | cut -d '(' -f 1 | sed 's/ //g')

        n_notGenomic=$(cat ${in_log_align_rn7} | grep 'reads that failed to align' | head -n 1 | cut -d ':' -f 2 | cut -d '(' -f 1 | sed 's/ //g' )

                
        groupedReadCount=${sample_id}.trimAdapt.filter.align2RNA.grouped.readCount
        cat ${in_sam_align_RNA} | grep -v '@' | awk '($2!=4)' | cut -f 3 | sed 's/.*;//g' | awk '{a[$1]++}END{for(i in a){printf "%s\t%d\n",i,a[i]}}' > $groupedReadCount


        if [ $(cat $groupedReadCount | grep '^mRNA' | wc -l ) -gt  0 ]
        then
            n_mRNA=$(cat $groupedReadCount | grep '^mRNA' | cut -f 2 )
        else
            n_mRNA=0
        fi

        if [ $(cat $groupedReadCount | grep '^long_non-coding_RNA' | wc -l ) -gt 0 ]
        then
            n_lncRNA=$(cat $groupedReadCount | grep '^long_non-coding_RNA' | cut -f 2 )
        else
            n_lncRNA=0
        fi

        if [ $(cat $groupedReadCount | grep '^ribosomal_RNA' | wc -l ) -gt 0 ]
        then
            n_rRNA=$(cat $groupedReadCount | grep '^ribosomal_RNA' | cut -f 2 )
        else
            n_rRNA=0
        fi

        if [ $(cat $groupedReadCount | grep '^Y_RNA' | wc -l ) -gt 0 ]
        then
            n_YRNA=$(cat $groupedReadCount | grep '^Y_RNA' | cut -f 2 )
        else
            n_YRNA=0
        fi

        if [ $(cat $groupedReadCount | grep -E '^misc_RNA|small|guide_RNA|vault_RNA' | wc -l ) -gt 0 ]
        then
            n_otsmall=$(cat $groupedReadCount | grep -E '^misc_RNA|small|guide_RNA|vault_RNA' | cut -f 2 | awk '{sum+=$1}END{print sum}')
        else
            n_otsmall=0
        fi

        n_otTranscript=$[$n_RNA-$n_mRNA-$n_lncRNA-$n_rRNA-$n_YRNA-$n_otsmall]
        
        file_output=${sample_id}.readStats
        echo -e "Stage\tReadCount" > $file_output
        echo -e "adapter not found\t$n_AdapterNotFound" >> $file_output
        echo -e "adapter dimer\t$n_Adapter_dimer" >> $file_output
        echo -e "too short\t$n_Too_short" >> $file_output
        echo -e "low sequencing quality\t$n_Low_quality" >> $file_output
        echo -e "mature miRNA\t$n_miRNA_mature" >> $file_output
        echo -e "hairpin miRNA\t$n_miRNA_hairpin" >> $file_output
        echo -e "piRNA\t$n_piRNA" >> $file_output
        echo -e "tRNA\t$n_tRNA" >> $file_output
        echo -e "mRNA\t$n_mRNA" >> $file_output
        echo -e "lncRNA\t$n_lncRNA" >> $file_output
        echo -e "rRNA\t$n_rRNA" >> $file_output
        echo -e "YRNA\t$n_YRNA" >> $file_output
        echo -e "other small RNA\t$n_otsmall" >> $file_output
        echo -e "other from transcriptome\t$n_otTranscript" >> $file_output
        echo -e "other from human genome\t$n_otGenomic" >> $file_output
        echo -e "not from human genome\t$n_notGenomic" >> $file_output

    >>>

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

    output {
        File out="${sample_id}.readStats"
        File out_groupedCount="${sample_id}.trimAdapt.filter.align2RNA.grouped.readCount"
    }
}