nf-core_sarek/subworkflows/local/mapping_csv.nf at c738f0b38401f79283d9dfac8dde3923046ccdc5 · maxulysse/nf-core_sarek · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
/*
========================================================================================
    MAPPING_CSV
========================================================================================
*/

workflow MAPPING_CSV {
    take:
        bam_indexed         // channel: [mandatory] meta, bam, bai
        save_bam_mapped     // boolean: [mandatory] save_bam_mapped
        skip_markduplicates // boolean: [mandatory] skip_markduplicates

    main:
        if (save_bam_mapped) {
            csv_bam_mapped = bam_indexed.map { meta, bam, bai -> [meta] }
            // Creating csv files to restart from this step
            csv_bam_mapped.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta ->
                patient = meta.patient[0]
                sample  = meta.sample[0]
                gender  = meta.gender[0]
                status  = meta.status[0]
                bam   = "${params.outdir}/preprocessing/${sample}/mapped/${sample}.bam"
                bai   = "${params.outdir}/preprocessing/${sample}/mapped/${sample}.bam.bai"
                ["mapped_${sample}.csv", "patient,gender,status,sample,bam,bai\n${patient},${gender},${status},${sample},${bam},${bai}\n"]
            }.collectFile(name: "mapped.csv", keepHeader: true, skip: 1, sort: true, storeDir: "${params.outdir}/preprocessing/csv")
        }

        if (skip_markduplicates) {
            csv_bam_mapped = bam_indexed.map { meta, bam, bai -> [meta] }
            // Creating csv files to restart from this step
            csv_bam_mapped.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta ->
                patient = meta.patient[0]
                sample  = meta.sample[0]
                gender  = meta.gender[0]
                status  = meta.status[0]
                bam   = "${params.outdir}/preprocessing/${sample}/mapped/${sample}.bam"
                bai   = "${params.outdir}/preprocessing/${sample}/mapped/${sample}.bam.bai"
                table = "${params.outdir}/preprocessing/${sample}/recal_table/${sample}.recal.table"
                ["mapped_no_markduplicates_${sample}.csv", "patient,gender,status,sample,bam,bai,table\n${patient},${gender},${status},${sample},${bam},${bai},${table}\n"]
            }.collectFile(name: 'mapped_no_markduplicates.csv', keepHeader: true, skip: 1, sort: true, storeDir: "${params.outdir}/preprocessing/csv")
        }
}