mirror of
https://github.com/MillironX/taxprofiler.git
synced 2024-11-22 07:59:54 +00:00
Merge pull request #36 from nf-core/complexity-filter-bbduk
Add bbduk and prinseq complexity (entropy or dust-based) short read filtering
This commit is contained in:
commit
e72be724a6
17 changed files with 416 additions and 63 deletions
8
.github/workflows/ci.yml
vendored
8
.github/workflows/ci.yml
vendored
|
@ -29,8 +29,16 @@ jobs:
|
|||
- NXF_VER: ""
|
||||
NXF_EDGE: "1"
|
||||
parameters:
|
||||
- "--longread_clip false"
|
||||
- "--shortread_clip false"
|
||||
- "--shortread_clipmerge_tool fastp"
|
||||
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
|
||||
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs"
|
||||
- "--shortread_clipmerge_tool adapterremoval"
|
||||
- "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
|
||||
- "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
|
||||
- "--shortread_complexityfilter_tool bbduk"
|
||||
- "--shortread_complexityfilter_tool prinseq"
|
||||
|
||||
steps:
|
||||
- name: Check out pipeline code
|
||||
|
|
14
CITATIONS.md
14
CITATIONS.md
|
@ -18,21 +18,27 @@
|
|||
|
||||
- [fastp](https://doi.org/10.1093/bioinformatics/bty560)
|
||||
|
||||
> Chen, Shifu, Yanqing Zhou, Yaru Chen, and Jia Gu. 2018. “Fastp: An Ultra-Fast All-in-One FASTQ Preprocessor.” Bioinformatics 34 (17): i884-90. 10.1093/bioinformatics/bty560.
|
||||
> Chen, Shifu, Yanqing Zhou, Yaru Chen, and Jia Gu. 2018. Fastp: An Ultra-Fast All-in-One FASTQ Preprocessor. Bioinformatics 34 (17): i884-90. 10.1093/bioinformatics/bty560.
|
||||
|
||||
- [AdapterRemoval2](https://doi.org/10.1186/s13104-016-1900-2)
|
||||
|
||||
> Schubert, Mikkel, Stinus Lindgreen, and Ludovic Orlando. 2016. “AdapterRemoval v2: Rapid Adapter Trimming, Identification, and Read Merging.” BMC Research Notes 9 (February): 88. doi:10.1186/s13104-016-1900-2.
|
||||
> Schubert, Mikkel, Stinus Lindgreen, and Ludovic Orlando. 2016. AdapterRemoval v2: Rapid Adapter Trimming, Identification, and Read Merging. BMC Research Notes 9 (February): 88. doi:10.1186/s13104-016-1900-2.
|
||||
|
||||
- [Porechop](https://github.com/rrwick/Porechop)
|
||||
|
||||
- [BBTools](http://sourceforge.net/projects/bbmap/)
|
||||
|
||||
- [PRINSEQ++](https://doi.org/10.7287/peerj.preprints.27553v1)
|
||||
|
||||
> Cantu, Vito Adrian, Jeffrey Sadural, and Robert Edwards. 2019. PRINSEQ++, a Multi-Threaded Tool for Fast and Efficient Quality Control and Preprocessing of Sequencing Datasets. e27553v1. PeerJ Preprints. doi: 10.7287/peerj.preprints.27553v1.
|
||||
|
||||
- [Kraken2](https://doi.org/10.1186/s13059-019-1891-0)
|
||||
|
||||
> Wood, Derrick E., Jennifer Lu, and Ben Langmead. 2019. “Improved Metagenomic Analysis with Kraken 2.” Genome Biology 20 (1): 257. doi: 10.1186/s13059-019-1891-0.
|
||||
> Wood, Derrick E., Jennifer Lu, and Ben Langmead. 2019. Improved Metagenomic Analysis with Kraken 2. Genome Biology 20 (1): 257. doi: 10.1186/s13059-019-1891-0.
|
||||
|
||||
- [MALT](https://doi.org/10.1038/s41559-017-0446-6)
|
||||
|
||||
> Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. “Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico.” Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.
|
||||
> Vågene, Åshild J., Alexander Herbig, Michael G. Campana, Nelly M. Robles García, Christina Warinner, Susanna Sabin, Maria A. Spyrou, et al. 2018. Salmonella Enterica Genomes from Victims of a Major Sixteenth-Century Epidemic in Mexico. Nature Ecology & Evolution 2 (3): 520-28. doi: 10.1038/s41559-017-0446-6.
|
||||
|
||||
- [MetaPhlAn3](https://doi.org/10.7554/eLife.65088)
|
||||
|
||||
|
|
|
@ -132,7 +132,6 @@ process {
|
|||
]
|
||||
}
|
||||
|
||||
|
||||
withName: PORECHOP {
|
||||
ext.prefix = { "${meta.id}_${meta.run_accession}" }
|
||||
publishDir = [
|
||||
|
@ -142,11 +141,30 @@ process {
|
|||
]
|
||||
}
|
||||
|
||||
withName: CAT_FASTQ {
|
||||
withName: BBMAP_BBDUK {
|
||||
ext.args = [
|
||||
"entropy=${params.shortread_complexityfilter_entropy}",
|
||||
"entropywindow=${params.shortread_complexityfilter_bbduk_windowsize}",
|
||||
params.shortread_complexityfilter_bbduk_mask ? "entropymask=t" : "entropymask=f"
|
||||
].join(' ').trim()
|
||||
ext.prefix = { "${meta.id}-${meta.run_accession}" }
|
||||
publishDir = [
|
||||
path: { "${params.outdir}/prepared_sequences" },
|
||||
mode: 'copy',
|
||||
pattern: '*.fastq.gz'
|
||||
path: { "${params.outdir}/bbduk/" },
|
||||
mode: params.publish_dir_mode,
|
||||
pattern: '*.{fastq.gz,log}'
|
||||
]
|
||||
}
|
||||
|
||||
withName: PRINSEQPLUSPLUS {
|
||||
ext.args = [
|
||||
params.shortread_complexityfilter_prinseqplusplus_mode == 'dust' ? "-lc_dust=${params.shortread_complexityfilter_prinseqplusplus_dustscore}" : "-lc_entropy=${params.shortread_complexityfilter_entropy}",
|
||||
"-trim_qual_left=0 -trim_qual_left=0 -trim_qual_window=0 -trim_qual_step=0"
|
||||
].join(' ').trim()
|
||||
ext.prefix = { "${meta.id}-${meta.run_accession}" }
|
||||
publishDir = [
|
||||
path: { "${params.outdir}/prinseqplusplus/" },
|
||||
mode: params.publish_dir_mode,
|
||||
pattern: '*{_good_out.fastq.gz,_good_out_R1.fastq.gz,_good_out_R2.fastq.gz,log}'
|
||||
]
|
||||
}
|
||||
|
||||
|
|
|
@ -22,11 +22,12 @@ params {
|
|||
// Input data
|
||||
// TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
|
||||
// TODO nf-core: Give any required params for the test so that command line flags are not needed
|
||||
input = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
|
||||
databases = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
|
||||
run_kraken2 = true
|
||||
run_malt = true
|
||||
run_metaphlan3 = true
|
||||
shortread_clipmerge = true
|
||||
|
||||
input = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
|
||||
databases = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database.csv'
|
||||
run_kraken2 = true
|
||||
run_malt = true
|
||||
run_metaphlan3 = true
|
||||
shortread_clipmerge = true
|
||||
longread_clip = false
|
||||
shortread_complexityfilter = true
|
||||
}
|
||||
|
|
|
@ -6,6 +6,9 @@
|
|||
"adapterremoval": {
|
||||
"git_sha": "879d42c5e28661fe0a5e744c9e2c515868f9e08a"
|
||||
},
|
||||
"bbmap/bbduk": {
|
||||
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||
},
|
||||
"cat/fastq": {
|
||||
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||
},
|
||||
|
@ -33,6 +36,9 @@
|
|||
"porechop": {
|
||||
"git_sha": "e20e57f90b6787ac9a010a980cf6ea98bd990046"
|
||||
},
|
||||
"prinseqplusplus": {
|
||||
"git_sha": "f1c5384c31e985591716afdd732cf8c2ae29d05b"
|
||||
},
|
||||
"untar": {
|
||||
"git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918"
|
||||
}
|
||||
|
|
43
modules/nf-core/modules/bbmap/bbduk/main.nf
generated
Normal file
43
modules/nf-core/modules/bbmap/bbduk/main.nf
generated
Normal file
|
@ -0,0 +1,43 @@
|
|||
process BBMAP_BBDUK {
|
||||
tag "$meta.id"
|
||||
label 'process_medium'
|
||||
|
||||
conda (params.enable_conda ? "bioconda::bbmap=38.90" : null)
|
||||
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||
'https://depot.galaxyproject.org/singularity/bbmap:38.90--he522d1c_1' :
|
||||
'quay.io/biocontainers/bbmap:38.90--he522d1c_1' }"
|
||||
|
||||
input:
|
||||
tuple val(meta), path(reads)
|
||||
path contaminants
|
||||
|
||||
output:
|
||||
tuple val(meta), path('*.fastq.gz'), emit: reads
|
||||
tuple val(meta), path('*.log') , emit: log
|
||||
path "versions.yml" , emit: versions
|
||||
|
||||
when:
|
||||
task.ext.when == null || task.ext.when
|
||||
|
||||
script:
|
||||
def args = task.ext.args ?: ''
|
||||
def prefix = task.ext.prefix ?: "${meta.id}"
|
||||
def raw = meta.single_end ? "in=${reads[0]}" : "in1=${reads[0]} in2=${reads[1]}"
|
||||
def trimmed = meta.single_end ? "out=${prefix}.fastq.gz" : "out1=${prefix}_1.fastq.gz out2=${prefix}_2.fastq.gz"
|
||||
def contaminants_fa = contaminants ? "ref=$contaminants" : ''
|
||||
"""
|
||||
maxmem=\$(echo \"$task.memory\"| sed 's/ GB/g/g')
|
||||
bbduk.sh \\
|
||||
-Xmx\$maxmem \\
|
||||
$raw \\
|
||||
$trimmed \\
|
||||
threads=$task.cpus \\
|
||||
$args \\
|
||||
$contaminants_fa \\
|
||||
&> ${prefix}.bbduk.log
|
||||
cat <<-END_VERSIONS > versions.yml
|
||||
"${task.process}":
|
||||
bbmap: \$(bbversion.sh)
|
||||
END_VERSIONS
|
||||
"""
|
||||
}
|
52
modules/nf-core/modules/bbmap/bbduk/meta.yml
generated
Normal file
52
modules/nf-core/modules/bbmap/bbduk/meta.yml
generated
Normal file
|
@ -0,0 +1,52 @@
|
|||
name: bbmap_bbduk
|
||||
description: Adapter and quality trimming of sequencing reads
|
||||
keywords:
|
||||
- trimming
|
||||
- adapter trimming
|
||||
- quality trimming
|
||||
tools:
|
||||
- bbmap:
|
||||
description: BBMap is a short read aligner, as well as various other bioinformatic tools.
|
||||
homepage: https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/
|
||||
documentation: https://jgi.doe.gov/data-and-tools/bbtools/bb-tools-user-guide/
|
||||
tool_dev_url: None
|
||||
doi: ""
|
||||
licence: ["UC-LBL license (see package)"]
|
||||
|
||||
input:
|
||||
- meta:
|
||||
type: map
|
||||
description: |
|
||||
Groovy Map containing sample information
|
||||
e.g. [ id:'test', single_end:false ]
|
||||
- reads:
|
||||
type: file
|
||||
description: |
|
||||
List of input FastQ files of size 1 and 2 for single-end and paired-end data,
|
||||
respectively.
|
||||
- contaminants:
|
||||
type: file
|
||||
description: |
|
||||
Reference files containing adapter and/or contaminant sequences for sequence kmer matching
|
||||
|
||||
output:
|
||||
- meta:
|
||||
type: map
|
||||
description: |
|
||||
Groovy Map containing sample information
|
||||
e.g. [ id:'test', single_end:false ]
|
||||
- reads:
|
||||
type: file
|
||||
description: The trimmed/modified fastq reads
|
||||
pattern: "*fastq.gz"
|
||||
- versions:
|
||||
type: file
|
||||
description: File containing software versions
|
||||
pattern: "versions.yml"
|
||||
- log:
|
||||
type: file
|
||||
description: Bbduk log file
|
||||
pattern: "*bbduk.log"
|
||||
|
||||
authors:
|
||||
- "@MGordon09"
|
61
modules/nf-core/modules/prinseqplusplus/main.nf
generated
Normal file
61
modules/nf-core/modules/prinseqplusplus/main.nf
generated
Normal file
|
@ -0,0 +1,61 @@
|
|||
process PRINSEQPLUSPLUS {
|
||||
tag "$meta.id"
|
||||
label 'process_low'
|
||||
|
||||
conda (params.enable_conda ? "bioconda::prinseq-plus-plus=1.2.3" : null)
|
||||
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||
'https://depot.galaxyproject.org/singularity/prinseq-plus-plus:1.2.3--hc90279e_1':
|
||||
'quay.io/biocontainers/prinseq-plus-plus:1.2.3--hc90279e_1' }"
|
||||
|
||||
input:
|
||||
tuple val(meta), path(reads)
|
||||
|
||||
output:
|
||||
tuple val(meta), path("*_good_out*.fastq.gz") , emit: good_reads
|
||||
tuple val(meta), path("*_single_out*.fastq.gz"), optional: true, emit: single_reads
|
||||
tuple val(meta), path("*_bad_out*.fastq.gz") , optional: true, emit: bad_reads
|
||||
tuple val(meta), path("*.log") , emit: log
|
||||
path "versions.yml" , emit: versions
|
||||
|
||||
when:
|
||||
task.ext.when == null || task.ext.when
|
||||
|
||||
script:
|
||||
def args = task.ext.args ?: ''
|
||||
def prefix = task.ext.prefix ?: "${meta.id}"
|
||||
|
||||
if (meta.single_end) {
|
||||
"""
|
||||
prinseq++ \\
|
||||
-threads $task.cpus \\
|
||||
-fastq ${reads} \\
|
||||
-out_name ${prefix} \\
|
||||
-out_gz \\
|
||||
-VERBOSE 1 \\
|
||||
$args \\
|
||||
| tee ${prefix}.log
|
||||
|
||||
cat <<-END_VERSIONS > versions.yml
|
||||
"${task.process}":
|
||||
prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
|
||||
END_VERSIONS
|
||||
"""
|
||||
} else {
|
||||
"""
|
||||
prinseq++ \\
|
||||
-threads $task.cpus \\
|
||||
-fastq ${reads[0]} \\
|
||||
-fastq2 ${reads[1]} \\
|
||||
-out_name ${prefix} \\
|
||||
-out_gz \\
|
||||
-VERBOSE 1 \\
|
||||
$args \\
|
||||
| tee ${prefix}.log
|
||||
|
||||
cat <<-END_VERSIONS > versions.yml
|
||||
"${task.process}":
|
||||
prinseqplusplus: \$(echo \$(prinseq++ --version | cut -f 2 -d ' ' ))
|
||||
END_VERSIONS
|
||||
"""
|
||||
}
|
||||
}
|
60
modules/nf-core/modules/prinseqplusplus/meta.yml
generated
Normal file
60
modules/nf-core/modules/prinseqplusplus/meta.yml
generated
Normal file
|
@ -0,0 +1,60 @@
|
|||
name: "prinseqplusplus"
|
||||
description: PRINSEQ++ is a C++ implementation of the prinseq-lite.pl program. It can be used to filter, reformat or trim genomic and metagenomic sequence data
|
||||
keywords:
|
||||
- fastq
|
||||
- fasta
|
||||
- filter
|
||||
- trim
|
||||
tools:
|
||||
- "prinseqplusplus":
|
||||
description: "PRINSEQ++ - Multi-threaded C++ sequence cleaning"
|
||||
homepage: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
|
||||
documentation: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
|
||||
tool_dev_url: "https://github.com/Adrian-Cantu/PRINSEQ-plus-plus"
|
||||
doi: "10.7287/peerj.preprints.27553v1"
|
||||
licence: "['GPL v2']"
|
||||
|
||||
input:
|
||||
- meta:
|
||||
type: map
|
||||
description: |
|
||||
Groovy Map containing sample information
|
||||
e.g. [ id:'test', single_end:false ]
|
||||
- reads:
|
||||
type: file
|
||||
description: |
|
||||
List of input FastQ files of size 1 and 2 for single-end and paired-end
|
||||
data, respectively.
|
||||
|
||||
output:
|
||||
- meta:
|
||||
type: map
|
||||
description: |
|
||||
Groovy Map containing sample information
|
||||
e.g. [ id:'test', single_end:false ]
|
||||
- versions:
|
||||
type: file
|
||||
description: File containing software versions
|
||||
pattern: "versions.yml"
|
||||
- good_reads:
|
||||
type: file
|
||||
description: Reads passing filter(s) in gzipped FASTQ format
|
||||
pattern: "*_good_out_{R1,R2}.fastq.gz"
|
||||
- single_reads:
|
||||
type: file
|
||||
description: |
|
||||
Single reads without the pair passing filter(s) in gzipped FASTQ format
|
||||
pattern: "*_single_out_{R1,R2}.fastq.gz"
|
||||
- bad_reads:
|
||||
type: file
|
||||
description: |
|
||||
Reads without not passing filter(s) in gzipped FASTQ format
|
||||
pattern: "*_bad_out_{R1,R2}.fastq.gz"
|
||||
- log:
|
||||
type: file
|
||||
description: |
|
||||
Verbose level 2 STDOUT information in a log file
|
||||
pattern: "*.log"
|
||||
|
||||
authors:
|
||||
- "@jfy133"
|
|
@ -51,7 +51,7 @@ params {
|
|||
max_cpus = 16
|
||||
max_time = '240.h'
|
||||
|
||||
// Databaess
|
||||
// Databases
|
||||
databases = null
|
||||
|
||||
// FASTQ preprocessing
|
||||
|
@ -65,6 +65,16 @@ params {
|
|||
shortread_clipmerge_minlength = 15
|
||||
longread_clip = false
|
||||
|
||||
// Complexity filtering
|
||||
shortread_complexityfilter = false
|
||||
shortread_complexityfilter_tool = 'bbduk'
|
||||
shortread_complexityfilter_entropy = 0.3
|
||||
shortread_complexityfilter_bbduk_windowsize = 50
|
||||
shortread_complexityfilter_bbduk_mask = false
|
||||
shortread_complexityfilter_prinseqplusplus_mode = 'entropy'
|
||||
shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
|
||||
|
||||
|
||||
// MALT
|
||||
run_malt = false
|
||||
malt_mode = 'BlastN'
|
||||
|
|
|
@ -266,8 +266,7 @@
|
|||
"type": "boolean"
|
||||
},
|
||||
"shortread_clipmerge_excludeunmerged": {
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
"type": "boolean"
|
||||
},
|
||||
"longread_clip": {
|
||||
"type": "boolean"
|
||||
|
@ -308,6 +307,33 @@
|
|||
"shortread_clipmerge_minlength": {
|
||||
"type": "integer",
|
||||
"default": 15
|
||||
},
|
||||
"shortread_complexityfilter_tool": {
|
||||
"type": "string",
|
||||
"default": "bbduk"
|
||||
},
|
||||
"shortread_complexityfilter_bbduk_windowsize": {
|
||||
"type": "integer",
|
||||
"default": 50
|
||||
},
|
||||
"shortread_complexityfilter_bbduk_mask": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"shortread_complexityfilter": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"shortread_complexityfilter_entropy": {
|
||||
"type": "number",
|
||||
"default": 0.3
|
||||
},
|
||||
"shortread_complexityfilter_prinseqplusplus_mode": {
|
||||
"type": "string",
|
||||
"default": "entropy",
|
||||
"enum": ["entropy", "dust"]
|
||||
},
|
||||
"shortread_complexityfilter_prinseqplusplus_dustscore": {
|
||||
"type": "number",
|
||||
"default": 0.5
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
Process long raw reads with porechop
|
||||
*/
|
||||
//
|
||||
// Process long raw reads with porechop
|
||||
//
|
||||
|
||||
include { FASTQC as FASTQC_PROCESSED } from '../../modules/nf-core/modules/fastqc/main'
|
||||
include { PORECHOP } from '../../modules/nf-core/modules/porechop/main'
|
||||
|
@ -25,7 +25,7 @@ workflow LONGREAD_PREPROCESSING {
|
|||
|
||||
FASTQC_PROCESSED ( PORECHOP.out.reads )
|
||||
ch_versions = ch_versions.mix(PORECHOP.out.versions.first())
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip.collect{it[1]} )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
|
||||
|
||||
|
||||
emit:
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
Process short raw reads with AdapterRemoval
|
||||
*/
|
||||
//
|
||||
// Process short raw reads with AdapterRemoval
|
||||
//
|
||||
|
||||
include { ADAPTERREMOVAL as ADAPTERREMOVAL_SINGLE } from '../../modules/nf-core/modules/adapterremoval/main'
|
||||
include { ADAPTERREMOVAL as ADAPTERREMOVAL_PAIRED } from '../../modules/nf-core/modules/adapterremoval/main'
|
||||
|
@ -38,11 +38,17 @@ workflow SHORTREAD_ADAPTERREMOVAL {
|
|||
ADAPTERREMOVAL_PAIRED.out.singles_truncated,
|
||||
ADAPTERREMOVAL_PAIRED.out.paired_truncated
|
||||
)
|
||||
.map { meta, reads ->
|
||||
def meta_new = meta.clone()
|
||||
meta_new.single_end = true
|
||||
[meta_new, reads]
|
||||
}
|
||||
.groupTuple()
|
||||
// Paired-end reads cause a nested tuple during grouping.
|
||||
// We want to present a flat list of files to `CAT_FASTQ`.
|
||||
.map { meta, fastq -> [meta, fastq.flatten()] }
|
||||
|
||||
|
||||
CAT_FASTQ(ch_concat_fastq)
|
||||
|
||||
ch_adapterremoval_reads_prepped = CAT_FASTQ.out.reads
|
||||
|
@ -56,10 +62,13 @@ workflow SHORTREAD_ADAPTERREMOVAL {
|
|||
ADAPTERREMOVAL_PAIRED.out.collapsed_truncated
|
||||
)
|
||||
.map { meta, reads ->
|
||||
meta.single_end = true
|
||||
[meta, reads]
|
||||
def meta_new = meta.clone()
|
||||
meta_new.single_end = true
|
||||
[meta_new, reads]
|
||||
}
|
||||
.groupTuple()
|
||||
.map { meta, fastq -> [meta, fastq.flatten()] }
|
||||
|
||||
|
||||
CAT_FASTQ(ch_concat_fastq)
|
||||
|
||||
|
@ -75,9 +84,10 @@ workflow SHORTREAD_ADAPTERREMOVAL {
|
|||
|
||||
ch_versions = ch_versions.mix( ADAPTERREMOVAL_SINGLE.out.versions.first() )
|
||||
ch_versions = ch_versions.mix( ADAPTERREMOVAL_PAIRED.out.versions.first() )
|
||||
|
||||
ch_multiqc_files = ch_multiqc_files.mix(
|
||||
ADAPTERREMOVAL_PAIRED.out.settings.collect{it[1]},
|
||||
ADAPTERREMOVAL_SINGLE.out.settings.collect{it[1]}
|
||||
ADAPTERREMOVAL_PAIRED.out.settings,
|
||||
ADAPTERREMOVAL_SINGLE.out.settings
|
||||
)
|
||||
|
||||
emit:
|
||||
|
|
32
subworkflows/local/shortread_complexityfiltering.nf
Normal file
32
subworkflows/local/shortread_complexityfiltering.nf
Normal file
|
@ -0,0 +1,32 @@
|
|||
//
|
||||
// Check input samplesheet and get read channels
|
||||
//
|
||||
|
||||
include { BBMAP_BBDUK } from '../../modules/nf-core/modules/bbmap/bbduk/main'
|
||||
include { PRINSEQPLUSPLUS } from '../../modules/nf-core/modules/prinseqplusplus/main'
|
||||
|
||||
workflow SHORTREAD_COMPLEXITYFILTERING {
|
||||
take:
|
||||
reads // [ [ meta ], [ reads ] ]
|
||||
|
||||
main:
|
||||
ch_versions = Channel.empty()
|
||||
ch_multiqc_files = Channel.empty()
|
||||
|
||||
if ( params.shortread_complexityfilter_tool == 'bbduk' ) {
|
||||
ch_filtered_reads = BBMAP_BBDUK ( reads, [] ).reads
|
||||
ch_versions = ch_versions.mix( BBMAP_BBDUK.out.versions.first() )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( BBMAP_BBDUK.out.log )
|
||||
} else if ( params.shortread_complexityfilter_tool == 'prinseqplusplus' ) {
|
||||
ch_filtered_reads = PRINSEQPLUSPLUS ( reads ).good_reads
|
||||
ch_versions = ch_versions.mix( PRINSEQPLUSPLUS.out.versions.first() )
|
||||
} else {
|
||||
ch_filtered_reads = reads
|
||||
}
|
||||
|
||||
emit:
|
||||
reads = ch_filtered_reads // channel: [ val(meta), [ reads ] ]
|
||||
versions = ch_versions // channel: [ versions.yml ]
|
||||
mqc = ch_multiqc_files
|
||||
}
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
/*
|
||||
Process short raw reads with FastP
|
||||
*/
|
||||
//
|
||||
// Process short raw reads with FastP
|
||||
//
|
||||
|
||||
include { FASTP as FASTP_SINGLE } from '../../modules/nf-core/modules/fastp/main'
|
||||
include { FASTP as FASTP_PAIRED } from '../../modules/nf-core/modules/fastp/main'
|
||||
|
@ -44,8 +44,8 @@ workflow SHORTREAD_FASTP {
|
|||
|
||||
ch_processed_reads = ch_fastp_reads_prepped
|
||||
|
||||
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 = ch_multiqc_files.mix( FASTP_SINGLE.out.json )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTP_PAIRED.out.json )
|
||||
|
||||
emit:
|
||||
reads = ch_processed_reads // channel: [ val(meta), [ reads ] ]
|
||||
|
|
|
@ -1,5 +1,5 @@
|
|||
//
|
||||
// Check input samplesheet and get read channels
|
||||
// Perform read trimming and merging
|
||||
//
|
||||
|
||||
|
||||
|
@ -9,7 +9,7 @@ include { FASTQC as FASTQC_PROCESSED } from '../../modules/nf-core/modules
|
|||
|
||||
workflow SHORTREAD_PREPROCESSING {
|
||||
take:
|
||||
reads // file: /path/to/samplesheet.csv
|
||||
reads // [ [ meta ], [ reads ] ]
|
||||
|
||||
main:
|
||||
ch_versions = Channel.empty()
|
||||
|
@ -29,7 +29,7 @@ workflow SHORTREAD_PREPROCESSING {
|
|||
|
||||
FASTQC_PROCESSED ( ch_processed_reads )
|
||||
ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip.collect{it[1]} )
|
||||
ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
|
||||
|
||||
emit:
|
||||
reads = ch_processed_reads // channel: [ val(meta), [ reads ] ]
|
||||
|
|
|
@ -17,7 +17,7 @@ for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true
|
|||
// Check mandatory parameters
|
||||
if (params.input ) { ch_input = file(params.input) } else { exit 1, 'Input samplesheet not specified!' }
|
||||
if (params.databases) { ch_databases = file(params.databases) } else { exit 1, 'Input database sheet not specified!' }
|
||||
if (params.shortread_clipmerge_mergepairs && params.run_malt ) log.warn "[nf-core/taxprofiler] warning: MALT does not except uncollapsed paired-reads. Pairs will be profiled as separate files."
|
||||
if (params.shortread_clipmerge_mergepairs && params.run_malt ) log.warn "[nf-core/taxprofiler] warning: MALT does not accept uncollapsed paired-reads. Pairs will be profiled as separate files."
|
||||
if (params.shortread_clipmerge_excludeunmerged && !params.shortread_clipmerge_mergepairs) exit 1, "[nf-core/taxprofiler] error: cannot include unmerged reads when merging not turned on. Please specify --shortread_clipmerge_mergepairs"
|
||||
|
||||
/*
|
||||
|
@ -40,9 +40,10 @@ ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath(params.multi
|
|||
//
|
||||
include { INPUT_CHECK } from '../subworkflows/local/input_check'
|
||||
|
||||
include { DB_CHECK } from '../subworkflows/local/db_check'
|
||||
include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing'
|
||||
include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing'
|
||||
include { DB_CHECK } from '../subworkflows/local/db_check'
|
||||
include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing'
|
||||
include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing'
|
||||
include { SHORTREAD_COMPLEXITYFILTERING } from '../subworkflows/local/shortread_complexityfiltering'
|
||||
|
||||
/*
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
@ -90,7 +91,7 @@ workflow TAXPROFILER {
|
|||
/*
|
||||
MODULE: Run FastQC
|
||||
*/
|
||||
ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore ).dump(tag: "input_to_fastq")
|
||||
ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore )
|
||||
|
||||
FASTQC (
|
||||
ch_input_for_fastqc
|
||||
|
@ -98,10 +99,6 @@ workflow TAXPROFILER {
|
|||
|
||||
ch_versions = ch_versions.mix(FASTQC.out.versions.first())
|
||||
|
||||
CUSTOM_DUMPSOFTWAREVERSIONS (
|
||||
ch_versions.unique().collectFile(name: 'collated_versions.yml')
|
||||
)
|
||||
|
||||
/*
|
||||
SUBWORKFLOW: PERFORM PREPROCESSING
|
||||
*/
|
||||
|
@ -114,17 +111,26 @@ workflow TAXPROFILER {
|
|||
if ( params.longread_clip ) {
|
||||
ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
|
||||
.map { it -> [ it[0], [it[1]] ] }
|
||||
ch_versions = ch_versions.mix(LONGREAD_PREPROCESSING.out.versions.first())
|
||||
} else {
|
||||
ch_longreads_preprocessed = INPUT_CHECK.out.nanopore
|
||||
}
|
||||
|
||||
/*
|
||||
SUBWORKFLOW: COMPLEXITY FILTERING
|
||||
*/
|
||||
|
||||
if ( params.shortread_complexityfilter ) {
|
||||
ch_shortreads_filtered = SHORTREAD_COMPLEXITYFILTERING ( ch_shortreads_preprocessed ).reads
|
||||
} else {
|
||||
ch_shortreads_filtered = ch_shortreads_preprocessed
|
||||
}
|
||||
|
||||
/*
|
||||
COMBINE READS WITH POSSIBLE DATABASES
|
||||
*/
|
||||
|
||||
// e.g. output [DUMP: reads_plus_db] [['id':'2612', 'run_accession':'combined', 'instrument_platform':'ILLUMINA', 'single_end':1], <reads_path>/2612.merged.fastq.gz, ['tool':'malt', 'db_name':'mal95', 'db_params':'"-id 90"'], <db_path>/malt90]
|
||||
ch_input_for_profiling = ch_shortreads_preprocessed
|
||||
ch_input_for_profiling = ch_shortreads_filtered
|
||||
.mix( ch_longreads_preprocessed )
|
||||
.combine(DB_CHECK.out.dbs)
|
||||
.branch {
|
||||
|
@ -165,7 +171,6 @@ workflow TAXPROFILER {
|
|||
}
|
||||
|
||||
ch_input_for_metaphlan3 = ch_input_for_profiling.metaphlan3
|
||||
.dump(tag: "input_metaphlan3")
|
||||
.multiMap {
|
||||
it ->
|
||||
reads: [it[0] + it[2], it[1]]
|
||||
|
@ -190,6 +195,12 @@ workflow TAXPROFILER {
|
|||
/*
|
||||
MODULE: MultiQC
|
||||
*/
|
||||
|
||||
CUSTOM_DUMPSOFTWAREVERSIONS (
|
||||
ch_versions.unique().collectFile(name: 'collated_versions.yml')
|
||||
)
|
||||
|
||||
|
||||
workflow_summary = WorkflowTaxprofiler.paramsSummaryMultiqc(workflow, summary_params)
|
||||
ch_workflow_summary = Channel.value(workflow_summary)
|
||||
|
||||
|
@ -201,21 +212,30 @@ workflow TAXPROFILER {
|
|||
ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
|
||||
|
||||
if (params.shortread_clipmerge) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix(SHORTREAD_PREPROCESSING.out.mqc)
|
||||
}
|
||||
if (params.longread_clip) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix(LONGREAD_PREPROCESSING.out.mqc)
|
||||
}
|
||||
if (params.run_kraken2) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix(KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([]))
|
||||
ch_versions = ch_versions.mix(KRAKEN2_KRAKEN2.out.versions.first())
|
||||
}
|
||||
if (params.run_malt) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix(MALT_RUN.out.log.collect{it[1]}.ifEmpty([]))
|
||||
ch_versions = ch_versions.mix(MALT_RUN.out.versions.first())
|
||||
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||
ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions )
|
||||
}
|
||||
|
||||
if (params.longread_clip) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix( LONGREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||
ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions )
|
||||
}
|
||||
|
||||
if (params.shortread_complexityfilter){
|
||||
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_COMPLEXITYFILTERING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||
ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
|
||||
}
|
||||
|
||||
if (params.run_kraken2) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix( KRAKEN2_KRAKEN2.out.txt.collect{it[1]}.ifEmpty([]) )
|
||||
ch_versions = ch_versions.mix( KRAKEN2_KRAKEN2.out.versions.first() )
|
||||
}
|
||||
|
||||
if (params.run_malt) {
|
||||
ch_multiqc_files = ch_multiqc_files.mix( MALT_RUN.out.log.collect{it[1]}.ifEmpty([]) )
|
||||
ch_versions = ch_versions.mix( MALT_RUN.out.versions.first() )
|
||||
}
|
||||
|
||||
// TODO MALT results overwriting per database?
|
||||
// TODO Versions for Karken/MALT not report?
|
||||
// TODO create multiQC module for metaphlan
|
||||
MULTIQC (
|
||||
|
|
Loading…
Reference in a new issue