Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

allow storeDir for RunBQSR #1001

Draft
wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

allow storeDir for RunBQSR #1001

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6f78a3a
remove non-path and non-context variables from output channels
anoronh4 Dec 27, 2023
264ced1
fix bug
anoronh4 Dec 27, 2023
cfe13d7
fix overlapping file issue in AlignReads for outputs that share the s…
anoronh4 Dec 31, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 19 additions & 20 deletions pipeline.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -489,27 +489,25 @@ if (params.mapping) {

// Check for FASTQ files which might have different path but contains the same reads, based only on the name of the first read.
def allReadIds = [:]
sortedBam.map { idSample, target, bam, fileID, lane, readIdFile -> def readId = "@" + readIdFile.getSimpleName().replaceAll("@", ":")

// Use the first line of the fastq file (the name of the first read) as unique identifier to check across all the samples if there is any two fastq files contains the same read name, if so, we consider there are some human error of mixing up the same reads into different fastq files
sortedBam
.groupTuple(by:[3])
.map { idSample, target, bam, fileID, lane, readIdFile ->
def idSample_first = idSample instanceof Collection ? idSample.first() : idSample
def target_first = target instanceof Collection ? target.first() : target
// Use the first line of the fastq file (the name of the first read) as unique identifier to check across all the samples if there is any two fastq files contains the same read name, if so, we consider there are some human error of mixing up the same reads into different fastq files
if ( !params.watch ){
if(!TempoUtils.checkDuplicates(allReadIds, readId, idSample + "\t" + bam, "the follwoing samples, since they contain the same read: \n${readId}")){exit 1}
for (i in readIdFile.flatten().unique()){
def readId = "@" + i.getSimpleName().replaceAll("@", ":")
if(!TempoUtils.checkDuplicates(allReadIds, readId, idSample_first + "\t" + fileID, "the following samples, since they contain the same read: \n${readId}")){exit 1}
}
}

[idSample, target, bam, fileID, lane]
}
.groupTuple(by: [3])
.map{ item ->
def idSample = item[0] instanceof Collection ? item[0].first() : item[0]
def target = item[1] instanceof Collection ? item[1].first() : item[1]
def bams = item[2]
[idSample, target, bams]
[idSample_first, target_first, bam.flatten().unique()]
}
.groupTuple(by: [0])
.map{ item ->
def idSample = item[0]
def target = item[1] instanceof Collection ? item[1].first() : item[1]
def bams = item[2].flatten()
def bams = item[2].flatten().unique()
[idSample, bams, target]
}
.set{ groupedBam }
Expand Down Expand Up @@ -581,8 +579,7 @@ if (params.mapping) {
referenceMap.knownIndelsIndex
])
output:
set idSample, target, file("${idSample}.bam"), file("${idSample}.bam.bai") into bamsBQSR4Alfred, bamsBQSR4CollectHsMetrics, bamsBQSR4Tumor, bamsBQSR4Normal, bamsBQSR4QcPileup, bamsBQSR4Qualimap
set idSample, target, val("${file(outDir).toString()}/bams/${idSample}/${idSample}.bam"), val("${file(outDir).toString()}/bams/${idSample}/${idSample}.bam.bai") into bamResults
set idSample, target, file("${idSample}.bam"), file("${idSample}.bam.bai") into bamsBQSR4Alfred, bamsBQSR4CollectHsMetrics, bamsBQSR4Tumor, bamsBQSR4Normal, bamsBQSR4QcPileup, bamsBQSR4Qualimap, bamResults
file("file-size.txt") into bamSize
script:
if (workflow.profile == "juno") {
Expand Down Expand Up @@ -661,13 +658,15 @@ if (params.mapping) {
"""
}

File file = new File(outname)
file.newWriter().withWriter { w ->
File file_bammapping = new File(outname)
file_bammapping.newWriter().withWriter { w ->
w << "SAMPLE\tTARGET\tBAM\tBAI\n"
}

bamResults.subscribe { Object obj ->
file.withWriterAppend { out ->
bamResults.map{ idSample, target, bam, bai ->
[ idSample, target, "${file(outDir).toString()}/bams/${idSample}/${idSample}.bam", "${file(outDir).toString()}/bams/${idSample}/${idSample}.bam.bai" ]
}.subscribe { Object obj ->
file_bammapping.withWriterAppend { out ->
out.println "${obj[0]}\t${obj[1]}\t${obj[2]}\t${obj[3]}"
}
}
Expand Down