rnaseq/modules/local/deseq2_qc/main.nf at 74c1c82a8c5c3863fb6eef82934ba1ee36654bd1 · pinin4fjords/rnaseq · 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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
nextflow.preview.types = true

record DeSeq2Result {
    pdf:           Path?
    rdata:         Path?
    pca_txt:       Path?
    pca_multiqc:   Path?
    dists_txt:     Path?
    dists_multiqc: Path?
    log:           Path?
    size_factors:  Path?
}

process DESEQ2_QC {
    label "process_medium"

    // (Bio)conda packages have intentionally not been pinned to a specific version
    // This was to avoid the pipeline failing due to package conflicts whilst creating the environment when using -profile conda
    conda "${moduleDir}/environment.yml"
    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/1d/1d425b12748ce54c44c01a535a1ef5867a6e16cbf62c43151012e893444b1673/data' :
        'community.wave.seqera.io/library/r-base_r-optparse_r-ggplot2_r-rcolorbrewer_pruned:9e75394d0bc21987' }"

    input:
    counts: Path
    pca_header_multiqc: Path
    clustering_header_multiqc: Path

    output:
    record(
        pdf:           file("*.pdf",                 optional: true),
        rdata:         file("*.RData",               optional: true),
        pca_txt:       file("*pca.vals.txt",         optional: true),
        pca_multiqc:   file("*pca.vals_mqc.tsv",     optional: true),
        dists_txt:     file("*sample.dists.txt",     optional: true),
        dists_multiqc: file("*sample.dists_mqc.tsv", optional: true),
        log:           file("*.log",                 optional: true),
        size_factors:  file("size_factors",          optional: true)
    )
    tuple val("${task.process}"), val('r-base'), eval('echo $(R --version 2>&1) | sed "s/^.*R version //; s/ .*$//"'), topic: versions
    tuple val("${task.process}"), val('bioconductor-deseq2'), eval('Rscript -e "library(DESeq2); cat(as.character(packageVersion(\'DESeq2\')))"'), topic: versions

    when:
    task.ext.when == null || task.ext.when

    script:
    def args  = task.ext.args  ?: ''
    def args2 = task.ext.args2 ?: ''
    def label_lower = args2.toLowerCase()
    def label_upper = args2.toUpperCase()
    prefix = task.ext.prefix ?: "deseq2"
    """
    deseq2_qc.r \\
        --count_file $counts \\
        --outdir ./ \\
        --cores $task.cpus \\
        --outprefix $prefix \\
        $args

    if [ -f "R_sessionInfo.log" ]; then
        # Handle PCA files
        sed "s/deseq2_pca/${label_lower}_deseq2_pca/g" <$pca_header_multiqc > pca_header.tmp
        sed -i -e "s/DESeq2 PCA/${label_upper} DESeq2 PCA/g" pca_header.tmp
        cat pca_header.tmp *.pca.vals.txt > ${label_lower}.pca.vals_mqc.tsv
        rm pca_header.tmp

        # Handle clustering files
        sed "s/deseq2_clustering/${label_lower}_deseq2_clustering/g" <$clustering_header_multiqc > clustering_header.tmp
        sed -i -e "s/DESeq2 sample/${label_upper} DESeq2 sample/g" clustering_header.tmp
        cat clustering_header.tmp *.sample.dists.txt > ${label_lower}.sample.dists_mqc.tsv
        rm clustering_header.tmp
    fi
    """

    stub:
    def args2 = task.ext.args2 ?: ''
    def label_lower = args2.toLowerCase()
    prefix = task.ext.prefix ?: "deseq2"
    """
    touch ${label_lower}.pca.vals_mqc.tsv
    touch ${label_lower}.sample.dists_mqc.tsv
    touch ${prefix}.dds.RData
    touch ${prefix}.pca.vals.txt
    touch ${prefix}.plots.pdf
    touch ${prefix}.sample.dists.txt
    touch R_sessionInfo.log

    mkdir size_factors
    touch size_factors/${prefix}.size_factors.RData
    for i in `head $counts -n 1 | cut -f3-`;
    do
        touch size_factors/\${i}.size_factors.RData
    done
    """
}