Как разделить файл bam, чтобы разделить bams в соответствии с чтениями, сопоставленными с хромосомой

Обратите внимание, что чтение из файла может быть операцией, связанной с вводом-выводом. Если несколько процессов пытаются читать из одного и того же BAM-файла одновременно, они могут конкурировать за одни и те же ресурсы. Обычно мы хотели бы избежать этого, насколько это возможно. Лучшим способом было бы передать все регионы и разделить BAM одним рабочим процессом. Есть много способов сделать это, и лучшее решение зависит от того, что именно вы хотите. Вы даже можете использовать другой параметр, чтобы выбрать, какие хромосомы отделить от каждого BAM. Предполагая, что ваши файлы BAM отсортированы по координатам и проиндексированы, вы можете попробовать:

params.indexed_bams = './path/to/bams/*.bam{,.bai}'
params.chroms = 'chr{{1..22},X,Y}'

process splitBAM {

    tag { sample }

    input:
    tuple val(sample), path(indexed_bam)

    output:
    tuple val(sample), path("*.bam")

    script:
    def bam = indexed_bam.first()

    """
    for chrom in ${params.chroms}
    do
        samtools view \\
            -o "${bam.baseName}.\${chrom}.bam" \\
            "${bam}" \\
            "\${chrom}"
    done
    """
}

workflow {

    indexed_bams = Channel.fromFilePairs( params.indexed_bams )
    
    splitBAM( indexed_bams )

    splitBAM.out.view()
}

Полученные результаты:

$ nextflow run main.nf -ansi-log false
N E X T F L O W  ~  version 23.04.0
Launching `main.nf` [stupefied_marconi] DSL2 - revision: 1383b12928
[91/a7c661] Submitted process > splitBAM (C)
[ce/f579b6] Submitted process > splitBAM (B)
[68/2e62aa] Submitted process > splitBAM (A)
[C, [/path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr1.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr10.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr11.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr12.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr13.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr14.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr15.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr16.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr17.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr18.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr19.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr2.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr20.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr21.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr22.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr3.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr4.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr5.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr6.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr7.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr8.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chr9.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chrX.bam, /path/to/work/91/a7c66188f92fd66331fe235bd923e7/C.chrY.bam]]
[A, [/path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr1.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr10.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr11.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr12.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr13.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr14.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr15.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr16.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr17.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr18.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr19.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr2.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr20.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr21.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr22.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr3.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr4.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr5.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr6.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr7.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr8.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chr9.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chrX.bam, /path/to/work/68/2e62aaee65cfb4791fe3d3b530fc15/A.chrY.bam]]
[B, [/path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr1.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr10.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr11.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr12.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr13.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr14.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr15.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr16.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr17.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr18.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr19.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr2.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr20.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr21.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr22.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr3.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr4.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr5.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr6.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr7.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr8.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chr9.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chrX.bam, /path/to/work/ce/f579b6299acafeaf53a386bd5abd25/B.chrY.bam]]

Обычно вам не нужно этого делать, но для полноты картины вот один из способов разделить файлы BAM, используя список регионов или имен хромосом в файле (по одному в строке). Он просто использует входной квалификатор each, чтобы повторить выполнение для каждого региона в наборе регионов:

params.indexed_bams = './path/to/bams/*.bam{,.bai}'
params.regions = './regions.list'

process splitBAM {

    tag { "${sample}, ${region}" }

    input:
    tuple val(sample), path(indexed_bam)
    each region

    output:
    tuple val(sample), path("${bam.baseName}.${suffix}.bam")

    script:
    bam = indexed_bam.first()
    suffix = region.replaceAll(':', '-')

    """
    samtools view \\
        -o "${bam.baseName}.${suffix}.bam" \\
        "${bam}" \\
        "${region}"
    """
}

workflow {

    Channel
        .fromFilePairs( params.indexed_bams )
        .set { indexed_bams }

    Channel
        .fromPath( params.regions )
        .splitText() { it.trim() }
        .collect()
        .set { regions }

    splitBAM( indexed_bams, regions )

    splitBAM.out.view()
}

Полученные результаты:

$ nextflow run main.nf 
N E X T F L O W  ~  version 23.04.0
Launching `main.nf` [grave_mcnulty] DSL2 - revision: 33a7a22c3b
executor >  local (72)
[a1/2ee71d] process > splitBAM (C, chr12) [100%] 72 of 72 ✔
[A, /path/to/work/60/3bc1fdbe20235076c5af4493a62977/A.chr6.bam]
[A, /path/to/work/a0/4c16d0871aea79e57bf674a1f32949/A.chr3.bam]
[A, /path/to/work/8c/e509e5b9aeea580fbf5cdb46c0a437/A.chr8.bam]
[A, /path/to/work/db/f96b1dd7bf07b26107afa814d82734/A.chr5.bam]
[A, /path/to/work/c8/49d20ee82c6c23b1e33b6974ba4551/A.chr7.bam]
[A, /path/to/work/43/a604a70bbac2f901b5ec18ede98f91/A.chr4.bam]
[A, /path/to/work/70/5ec915a5ae34cc16438fc3406bd921/A.chr1.bam]
[A, /path/to/work/f5/68049cedf63567004985524086051d/A.chr2.bam]
[A, /path/to/work/4d/4dd4b99aae0b8b2babef02a43e72f4/A.chr13.bam]
[A, /path/to/work/ff/2d2135e427e1c6c8d512065ca55055/A.chr10.bam]
[A, /path/to/work/65/024bdd698ca9da7c4ff7a98901f294/A.chr9.bam]
[A, /path/to/work/a5/b61625c6286d5a8719b7071ccea024/A.chr11.bam]
[A, /path/to/work/81/312802de9d1e6fda74501ebbc0aaaf/A.chr14.bam]
[A, /path/to/work/96/1a3956318fa953c2f10b12faecab22/A.chr18.bam]
[A, /path/to/work/20/276ac5a68a6edea88da145ff18c616/A.chr12.bam]
[A, /path/to/work/de/6c4eb41cb84b2e41bae058dde608f5/A.chr20.bam]
[A, /path/to/work/f4/4cba375ea0ab6bea2193475e56c20b/A.chr21.bam]
[A, /path/to/work/7d/a8ccf0ad38c5bd4f32979997998f39/A.chr19.bam]
[A, /path/to/work/17/e8a8c3123d8ca6440b1255e3fab001/A.chr15.bam]
[A, /path/to/work/ab/ee4398ad8bfb947322b19f703fd036/A.chr22.bam]
[A, /path/to/work/54/66707f7e243d4c765acfb057f686fa/A.chrX.bam]
[A, /path/to/work/bf/7cf4b2b22f733b95004e09bcb17a24/A.chrY.bam]
[A, /path/to/work/3f/cd987b9656f6affbc25e1fd73383ba/A.chr16.bam]
[A, /path/to/work/6f/1b076c7fe87a2f1fd366067b2a71f6/A.chr17.bam]
[B, /path/to/work/a2/d821e1520c628ff6e7bf229986bc40/B.chr4.bam]
[B, /path/to/work/ef/a4522fba782d6ab785be1492d426c1/B.chr13.bam]
[B, /path/to/work/00/ed80767027319a5fa63c6c9954a156/B.chr6.bam]
[B, /path/to/work/5e/efc8b4a52067a93a3020a30719c164/B.chr1.bam]
[B, /path/to/work/00/3336b1853123aa3dcede250e5f4ab9/B.chr2.bam]
[B, /path/to/work/65/e19c9845313f23134caf7a96c6fd6d/B.chr3.bam]
[B, /path/to/work/33/63857490a462c3573a84d7f184ad0e/B.chr5.bam]
[B, /path/to/work/c5/7cd52e2378dc077849fb95b2d4c6a3/B.chr11.bam]
[B, /path/to/work/66/8f0b18f23e9a7b2fcf966b721eff81/B.chr14.bam]
[B, /path/to/work/6c/6425122de40c637907d3fc403d6bfb/B.chr7.bam]
[B, /path/to/work/83/96973f5b21fdba623415c2f28d6587/B.chr15.bam]
[B, /path/to/work/be/26fd9f8b591caee13687c6908c6484/B.chr18.bam]
[B, /path/to/work/8a/9d080d0565c2b2b0e8984bac3af281/B.chr10.bam]
[B, /path/to/work/6f/bef89622a976e6219218d548484a9e/B.chr9.bam]
[B, /path/to/work/ea/2e42a4188eb1c46a3c192e4e53e75b/B.chr8.bam]
[B, /path/to/work/0a/dfa6ab659a21c3fc85c86cd99a8535/B.chr12.bam]
[B, /path/to/work/79/9322435a6b125adc9edf2616d51334/B.chrY.bam]
[B, /path/to/work/bb/71d75443d17680959aebfb410aafcd/B.chr20.bam]
[B, /path/to/work/99/20374da262707f5ac49969d6a5b307/B.chr16.bam]
[B, /path/to/work/80/4aff0eba480ef85ed5e1ab0bf4a11b/B.chr19.bam]
[B, /path/to/work/a9/abdd5b73f237185c57c1a816a94d5b/B.chrX.bam]
[B, /path/to/work/38/7861f2efc4754da157336d3d967d95/B.chr22.bam]
[B, /path/to/work/7b/5d328513b7bf6d03a2dc558898ff12/B.chr17.bam]
[C, /path/to/work/b3/81ac227bafa5eb95093d10cfd6b550/C.chr1.bam]
[C, /path/to/work/52/1220d524cdf2689052cd6cd0fc85de/C.chr3.bam]
[B, /path/to/work/1d/ba60a1afde1ab4dd2c469c6ff12bf8/B.chr21.bam]
[C, /path/to/work/90/1d146f3fa4e62bafbf96000ff2e4d5/C.chr4.bam]
[C, /path/to/work/50/fe8e2b2bf7cfcc522b4b465a1e6103/C.chr5.bam]
[C, /path/to/work/03/546d76f47d359c7561a8deba0c8389/C.chr8.bam]
[C, /path/to/work/e6/19629fd4b206dfb9e5f9a6ef6da78d/C.chr6.bam]
[C, /path/to/work/b6/a1993d8ee8837ba70ed12daf21a418/C.chr2.bam]
[C, /path/to/work/d8/d1bfc3254ea2205ac2a3cc210674db/C.chr11.bam]
[C, /path/to/work/4b/ef5c546102d29442f13217392e9ef2/C.chr13.bam]
[C, /path/to/work/72/848ab4f83561983e2fa6d74969a78d/C.chr15.bam]
[C, /path/to/work/df/afc23ff7ec596c5d51691fa4b67c43/C.chr7.bam]
[C, /path/to/work/52/0f4bab67efa1b013b69a42f2c211f7/C.chr9.bam]
[C, /path/to/work/a4/ceb86ff5c6b091af4c2c963ce4fda9/C.chr19.bam]
[C, /path/to/work/e7/a8928450a870464a08c372a0a96fc3/C.chr10.bam]
[C, /path/to/work/98/f1b2ce8fd5d498e77209cbc13e2898/C.chr14.bam]
[C, /path/to/work/73/d0edcdd7d922fc5a80842779421f48/C.chr21.bam]
[C, /path/to/work/4e/27d1000ef50e2672638b43e5bf24e0/C.chr17.bam]
[C, /path/to/work/b0/183bfdb6bb2f3702d9e7208aaf268d/C.chr18.bam]
[C, /path/to/work/c3/658b0323b33e7e0d0ddd1e14277edb/C.chrY.bam]
[C, /path/to/work/d4/06cef9ebb33f887eaf487f60cb5431/C.chrX.bam]
[C, /path/to/work/67/634d6a2ad97626c2afd4bc0dfe8ee7/C.chr16.bam]
[C, /path/to/work/35/cb224aa30c1f7fa89cb0e9f725361c/C.chr22.bam]
[C, /path/to/work/93/ed9f77df92b1c697764c1eff796dba/C.chr20.bam]
[C, /path/to/work/a1/2ee71d49591ebb8e827dde9adc602c/C.chr12.bam]