Added database preparation and final channel for profiling
James Fellows Yates
2 years ago
parent
cf55cc592c
commit
278f5605ca
@ -0,0 +1,25 @@
|
||||
process DATABASE_CHECK {
|
||||
tag "$databasesheet"
|
||||
|
||||
conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
|
||||
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||
'https://depot.galaxyproject.org/singularity/python:3.8.3' :
|
||||
'quay.io/biocontainers/python:3.8.3' }"
|
||||
|
||||
input:
|
||||
path databasesheet
|
||||
|
||||
output:
|
||||
path '*.csv' , emit: csv
|
||||
path "versions.yml", emit: versions
|
||||
|
||||
script: // This script is bundled with the pipeline, in nf-core/taxprofiler/bin/
|
||||
"""
|
||||
cat $databasesheet >> database_sheet.valid.csv
|
||||
|
||||
cat <<-END_VERSIONS > versions.yml
|
||||
"${task.process}":
|
||||
python: \$(python --version | sed 's/Python //g')
|
||||
END_VERSIONS
|
||||
"""
|
||||
}
|
||||
@ -0,0 +1,40 @@
|
||||
//
|
||||
// Check input samplesheet and get read channels
|
||||
//
|
||||
|
||||
include { DATABASE_CHECK } from '../../modules/local/database_check'
|
||||
|
||||
workflow DB_CHECK {
|
||||
take:
|
||||
dbsheet // file: /path/to/dbsheet.csv
|
||||
|
||||
main:
|
||||
|
||||
// TODO: make database sheet check
|
||||
parsed_samplesheet = DATABASE_CHECK ( dbsheet )
|
||||
.csv
|
||||
.splitCsv ( header:true, sep:',' )
|
||||
.dump(tag: "db_split_csv_out")
|
||||
.map { create_db_channels(it) }
|
||||
.dump(tag: "db_channel_prepped")
|
||||
.set{ dbs }
|
||||
|
||||
emit:
|
||||
dbs // channel: [ val(meta), [ db ] ]
|
||||
versions = DATABASE_CHECK.out.versions // channel: [ versions.yml ]
|
||||
}
|
||||
|
||||
def create_db_channels(LinkedHashMap row) {
|
||||
def meta = [:]
|
||||
meta.tool = row.tool
|
||||
meta.db_name = row.db_name
|
||||
meta.db_params = row.db_params
|
||||
|
||||
def array = []
|
||||
if (!file(row.db_path, type: 'dir').exists()) {
|
||||
exit 1, "ERROR: Please check input samplesheet -> database could not be found!\n${row.db_path}"
|
||||
}
|
||||
array = [ meta, file(row.db_path) ]
|
||||
|
||||
return array
|
||||
}
|
||||
@ -0,0 +1,73 @@
|
||||
//
|
||||
// Check input samplesheet and get read channels
|
||||
//
|
||||
|
||||
|
||||
include { FASTP as FASTP_SINGLE } from '../../modules/nf-core/modules/fastp/main'
|
||||
include { FASTP as FASTP_PAIRED } from '../../modules/nf-core/modules/fastp/main'
|
||||
include { FASTQC as FASTQC_POST } from '../../modules/nf-core/modules/fastqc/main'
|
||||
|
||||
workflow FASTQ_PREPROCESSING {
|
||||
take:
|
||||
reads // file: /path/to/samplesheet.csv
|
||||
|
||||
main:
|
||||
ch_versions = Channel.empty()
|
||||
ch_multiqc_files = Channel.empty()
|
||||
|
||||
//
|
||||
// STEP: Read clipping and merging
|
||||
//
|
||||
// TODO give option to clip only and retain pairs
|
||||
// TODO give option to retain singletons (probably fastp option likely)
|
||||
// TODO move to subworkflow
|
||||
|
||||
|
||||
if ( params.fastp_clip_merge ) {
|
||||
|
||||
ch_input_for_fastp = reads
|
||||
.dump(tag: "pre-fastp_branch")
|
||||
.branch{
|
||||
single: it[0]['single_end'] == true
|
||||
paired: it[0]['single_end'] == false
|
||||
}
|
||||
|
||||
ch_input_for_fastp.single.dump(tag: "input_fastp_single")
|
||||
ch_input_for_fastp.paired.dump(tag: "input_fastp_paired")
|
||||
|
||||
FASTP_SINGLE ( ch_input_for_fastp.single, false, false )
|
||||
FASTP_PAIRED ( ch_input_for_fastp.paired, false, true )
|
||||
|
||||
ch_fastp_reads_prepped = FASTP_PAIRED.out.reads_merged
|
||||
.mix( FASTP_SINGLE.out.reads )
|
||||
.map {
|
||||
meta, reads ->
|
||||
def meta_new = meta.clone()
|
||||
meta_new['single_end'] = 1
|
||||
[ meta_new, reads ]
|
||||
}
|
||||
|
||||
FASTQC_POST ( ch_fastp_reads_prepped )
|
||||
|
||||
ch_versions = ch_versions.mix(FASTP_SINGLE.out.versions.first())
|
||||
ch_versions = ch_versions.mix(FASTP_PAIRED.out.versions.first())
|
||||
|
||||
ch_processed_reads = ch_fastp_reads_prepped
|
||||
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_POST.out.zip.collect{it[1]} )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTP_SINGLE.out.json.collect{it[1]} )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTP_PAIRED.out.json.collect{it[1]} )
|
||||
|
||||
ch_multiqc_files.dump(tag: "preprocessing_mqc_final")
|
||||
|
||||
} else {
|
||||
ch_processed_reads = reads
|
||||
}
|
||||
|
||||
|
||||
emit:
|
||||
reads = ch_processed_reads // channel: [ val(meta), [ reads ] ]
|
||||
versions = ch_versions // channel: [ versions.yml ]
|
||||
mqc = ch_multiqc_files
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue