mirror of
https://github.com/MillironX/taxprofiler.git
synced 2024-11-22 10:59:55 +00:00
commit
6fecb3eeb7
14 changed files with 396 additions and 38 deletions
7
.github/workflows/ci.yml
vendored
7
.github/workflows/ci.yml
vendored
|
@ -29,8 +29,8 @@ jobs:
|
||||||
- NXF_VER: ""
|
- NXF_VER: ""
|
||||||
NXF_EDGE: "1"
|
NXF_EDGE: "1"
|
||||||
parameters:
|
parameters:
|
||||||
- "--longread_clip false"
|
- "--perform_longread_clip false"
|
||||||
- "--shortread_clip false"
|
- "--perform_shortread_clipmerge false"
|
||||||
- "--shortread_clipmerge_tool fastp"
|
- "--shortread_clipmerge_tool fastp"
|
||||||
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
|
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs --shortread_clipmerge_excludeunmerged"
|
||||||
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs"
|
- "--shortread_clipmerge_tool fastp --shortread_clipmerge_mergepairs"
|
||||||
|
@ -39,6 +39,9 @@ jobs:
|
||||||
- "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
|
- "--shortread_clipmerge_tool adapterremoval --shortread_clipmerge_mergepairs"
|
||||||
- "--shortread_complexityfilter_tool bbduk"
|
- "--shortread_complexityfilter_tool bbduk"
|
||||||
- "--shortread_complexityfilter_tool prinseq"
|
- "--shortread_complexityfilter_tool prinseq"
|
||||||
|
- "--perform_runmerging"
|
||||||
|
- "--perform_runmerging --shortread_clipmerge_mergepairs"
|
||||||
|
- "--shortread_complexityfilter false --perform_shortread_hostremoval"
|
||||||
|
|
||||||
steps:
|
steps:
|
||||||
- name: Check out pipeline code
|
- name: Check out pipeline code
|
||||||
|
|
|
@ -132,6 +132,24 @@ process {
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|
||||||
|
withName: BOWTIE2_BUILD {
|
||||||
|
ext.prefix = { "${meta.id}_${meta.run_accession}" }
|
||||||
|
publishDir = [
|
||||||
|
path: { "${params.outdir}/bowtie2/build" },
|
||||||
|
mode: params.publish_dir_mode,
|
||||||
|
pattern: '*.bt2'
|
||||||
|
]
|
||||||
|
}
|
||||||
|
|
||||||
|
withName: BOWTIE2_ALIGN {
|
||||||
|
ext.prefix = { "${meta.id}_${meta.run_accession}" }
|
||||||
|
publishDir = [
|
||||||
|
path: { "${params.outdir}/bowtie2/align" },
|
||||||
|
mode: params.publish_dir_mode,
|
||||||
|
pattern: '*.{fastq.gz,bam}'
|
||||||
|
]
|
||||||
|
}
|
||||||
|
|
||||||
withName: BBMAP_BBDUK {
|
withName: BBMAP_BBDUK {
|
||||||
ext.args = [
|
ext.args = [
|
||||||
"entropy=${params.shortread_complexityfilter_entropy}",
|
"entropy=${params.shortread_complexityfilter_entropy}",
|
||||||
|
@ -161,9 +179,19 @@ process {
|
||||||
]
|
]
|
||||||
}
|
}
|
||||||
|
|
||||||
|
withName: CAT_FASTQ {
|
||||||
|
ext.prefix = { "${meta.id}" }
|
||||||
|
publishDir = [
|
||||||
|
path: { "${params.outdir}/run_merging/" },
|
||||||
|
mode: params.publish_dir_mode,
|
||||||
|
pattern: '*.fastq.gz',
|
||||||
|
enabled: params.save_runmerged_reads
|
||||||
|
]
|
||||||
|
}
|
||||||
|
|
||||||
withName: MALT_RUN {
|
withName: MALT_RUN {
|
||||||
ext.args = { "${meta.db_params}" }
|
ext.args = { "${meta.db_params}" }
|
||||||
ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
||||||
publishDir = [
|
publishDir = [
|
||||||
path: { "${params.outdir}/malt/${meta.db_name}" },
|
path: { "${params.outdir}/malt/${meta.db_name}" },
|
||||||
mode: params.publish_dir_mode,
|
mode: params.publish_dir_mode,
|
||||||
|
@ -173,7 +201,7 @@ process {
|
||||||
|
|
||||||
withName: KRAKEN2_KRAKEN2 {
|
withName: KRAKEN2_KRAKEN2 {
|
||||||
ext.args = { "${meta.db_params}" }
|
ext.args = { "${meta.db_params}" }
|
||||||
ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
||||||
publishDir = [
|
publishDir = [
|
||||||
path: { "${params.outdir}/kraken2/${meta.db_name}" },
|
path: { "${params.outdir}/kraken2/${meta.db_name}" },
|
||||||
mode: params.publish_dir_mode,
|
mode: params.publish_dir_mode,
|
||||||
|
@ -182,12 +210,13 @@ process {
|
||||||
}
|
}
|
||||||
|
|
||||||
withName: METAPHLAN3 {
|
withName: METAPHLAN3 {
|
||||||
|
ext.args = { "${meta.db_params}" }
|
||||||
|
ext.prefix = params.perform_runmerging ? { "${meta.id}-${meta.db_name}" } : { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
||||||
publishDir = [
|
publishDir = [
|
||||||
path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
|
path: { "${params.outdir}/metaphlan3/${meta.db_name}" },
|
||||||
mode: params.publish_dir_mode,
|
mode: params.publish_dir_mode,
|
||||||
pattern: '*.{biom,txt}'
|
pattern: '*.{biom,txt}'
|
||||||
]
|
]
|
||||||
ext.prefix = { "${meta.id}-${meta.run_accession}-${meta.db_name}" }
|
|
||||||
}
|
}
|
||||||
|
|
||||||
withName: CENTRIFUGE_CENTRIFUGE {
|
withName: CENTRIFUGE_CENTRIFUGE {
|
||||||
|
|
|
@ -28,7 +28,9 @@ params {
|
||||||
run_malt = true
|
run_malt = true
|
||||||
run_metaphlan3 = true
|
run_metaphlan3 = true
|
||||||
run_centrifuge = true
|
run_centrifuge = true
|
||||||
shortread_clipmerge = true
|
perform_shortread_clipmerge = true
|
||||||
longread_clip = false
|
perform_longread_clip = false
|
||||||
shortread_complexityfilter = true
|
perform_shortread_complexityfilter = true
|
||||||
|
perform_shortread_hostremoval = true
|
||||||
|
shortread_hostremoval_reference = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
|
||||||
}
|
}
|
||||||
|
|
|
@ -9,6 +9,12 @@
|
||||||
"bbmap/bbduk": {
|
"bbmap/bbduk": {
|
||||||
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||||
},
|
},
|
||||||
|
"bowtie2/align": {
|
||||||
|
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||||
|
},
|
||||||
|
"bowtie2/build": {
|
||||||
|
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||||
|
},
|
||||||
"cat/fastq": {
|
"cat/fastq": {
|
||||||
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
"git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
|
||||||
},
|
},
|
||||||
|
|
77
modules/nf-core/modules/bowtie2/align/main.nf
generated
Normal file
77
modules/nf-core/modules/bowtie2/align/main.nf
generated
Normal file
|
@ -0,0 +1,77 @@
|
||||||
|
process BOWTIE2_ALIGN {
|
||||||
|
tag "$meta.id"
|
||||||
|
label 'process_high'
|
||||||
|
|
||||||
|
conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4 bioconda::samtools=1.14 conda-forge::pigz=2.6' : null)
|
||||||
|
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||||
|
'https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:4d235f41348a00533f18e47c9669f1ecb327f629-0' :
|
||||||
|
'quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:4d235f41348a00533f18e47c9669f1ecb327f629-0' }"
|
||||||
|
|
||||||
|
input:
|
||||||
|
tuple val(meta), path(reads)
|
||||||
|
path index
|
||||||
|
val save_unaligned
|
||||||
|
|
||||||
|
output:
|
||||||
|
tuple val(meta), path('*.bam') , emit: bam
|
||||||
|
tuple val(meta), path('*.log') , emit: log
|
||||||
|
tuple val(meta), path('*fastq.gz'), emit: fastq, optional:true
|
||||||
|
path "versions.yml" , emit: versions
|
||||||
|
|
||||||
|
when:
|
||||||
|
task.ext.when == null || task.ext.when
|
||||||
|
|
||||||
|
script:
|
||||||
|
def args = task.ext.args ?: ''
|
||||||
|
def args2 = task.ext.args2 ?: ''
|
||||||
|
def prefix = task.ext.prefix ?: "${meta.id}"
|
||||||
|
if (meta.single_end) {
|
||||||
|
def unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ''
|
||||||
|
"""
|
||||||
|
INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
|
||||||
|
bowtie2 \\
|
||||||
|
-x \$INDEX \\
|
||||||
|
-U $reads \\
|
||||||
|
--threads $task.cpus \\
|
||||||
|
$unaligned \\
|
||||||
|
$args \\
|
||||||
|
2> ${prefix}.bowtie2.log \\
|
||||||
|
| samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
|
||||||
|
|
||||||
|
cat <<-END_VERSIONS > versions.yml
|
||||||
|
"${task.process}":
|
||||||
|
bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
|
||||||
|
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
|
||||||
|
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
|
||||||
|
END_VERSIONS
|
||||||
|
"""
|
||||||
|
} else {
|
||||||
|
def unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ''
|
||||||
|
"""
|
||||||
|
INDEX=`find -L ./ -name "*.rev.1.bt2" | sed 's/.rev.1.bt2//'`
|
||||||
|
bowtie2 \\
|
||||||
|
-x \$INDEX \\
|
||||||
|
-1 ${reads[0]} \\
|
||||||
|
-2 ${reads[1]} \\
|
||||||
|
--threads $task.cpus \\
|
||||||
|
$unaligned \\
|
||||||
|
$args \\
|
||||||
|
2> ${prefix}.bowtie2.log \\
|
||||||
|
| samtools view -@ $task.cpus $args2 -bhS -o ${prefix}.bam -
|
||||||
|
|
||||||
|
if [ -f ${prefix}.unmapped.fastq.1.gz ]; then
|
||||||
|
mv ${prefix}.unmapped.fastq.1.gz ${prefix}.unmapped_1.fastq.gz
|
||||||
|
fi
|
||||||
|
if [ -f ${prefix}.unmapped.fastq.2.gz ]; then
|
||||||
|
mv ${prefix}.unmapped.fastq.2.gz ${prefix}.unmapped_2.fastq.gz
|
||||||
|
fi
|
||||||
|
|
||||||
|
cat <<-END_VERSIONS > versions.yml
|
||||||
|
"${task.process}":
|
||||||
|
bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
|
||||||
|
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
|
||||||
|
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
|
||||||
|
END_VERSIONS
|
||||||
|
"""
|
||||||
|
}
|
||||||
|
}
|
51
modules/nf-core/modules/bowtie2/align/meta.yml
generated
Normal file
51
modules/nf-core/modules/bowtie2/align/meta.yml
generated
Normal file
|
@ -0,0 +1,51 @@
|
||||||
|
name: bowtie2_align
|
||||||
|
description: Align reads to a reference genome using bowtie2
|
||||||
|
keywords:
|
||||||
|
- align
|
||||||
|
- fasta
|
||||||
|
- genome
|
||||||
|
- reference
|
||||||
|
tools:
|
||||||
|
- bowtie2:
|
||||||
|
description: |
|
||||||
|
Bowtie 2 is an ultrafast and memory-efficient tool for aligning
|
||||||
|
sequencing reads to long reference sequences.
|
||||||
|
homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
|
||||||
|
documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
|
||||||
|
doi: 10.1038/nmeth.1923
|
||||||
|
licence: ["GPL-3.0-or-later"]
|
||||||
|
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.
|
||||||
|
- index:
|
||||||
|
type: file
|
||||||
|
description: Bowtie2 genome index files
|
||||||
|
pattern: "*.ebwt"
|
||||||
|
output:
|
||||||
|
- bam:
|
||||||
|
type: file
|
||||||
|
description: Output BAM file containing read alignments
|
||||||
|
pattern: "*.{bam}"
|
||||||
|
- versions:
|
||||||
|
type: file
|
||||||
|
description: File containing software versions
|
||||||
|
pattern: "versions.yml"
|
||||||
|
- fastq:
|
||||||
|
type: file
|
||||||
|
description: Unaligned FastQ files
|
||||||
|
pattern: "*.fastq.gz"
|
||||||
|
- log:
|
||||||
|
type: file
|
||||||
|
description: Aligment log
|
||||||
|
pattern: "*.log"
|
||||||
|
authors:
|
||||||
|
- "@joseespinosa"
|
||||||
|
- "@drpatelh"
|
30
modules/nf-core/modules/bowtie2/build/main.nf
generated
Normal file
30
modules/nf-core/modules/bowtie2/build/main.nf
generated
Normal file
|
@ -0,0 +1,30 @@
|
||||||
|
process BOWTIE2_BUILD {
|
||||||
|
tag "$fasta"
|
||||||
|
label 'process_high'
|
||||||
|
|
||||||
|
conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4' : null)
|
||||||
|
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
|
||||||
|
'https://depot.galaxyproject.org/singularity/bowtie2:2.4.4--py39hbb4e92a_0' :
|
||||||
|
'quay.io/biocontainers/bowtie2:2.4.4--py39hbb4e92a_0' }"
|
||||||
|
|
||||||
|
input:
|
||||||
|
path fasta
|
||||||
|
|
||||||
|
output:
|
||||||
|
path 'bowtie2' , emit: index
|
||||||
|
path "versions.yml" , emit: versions
|
||||||
|
|
||||||
|
when:
|
||||||
|
task.ext.when == null || task.ext.when
|
||||||
|
|
||||||
|
script:
|
||||||
|
def args = task.ext.args ?: ''
|
||||||
|
"""
|
||||||
|
mkdir bowtie2
|
||||||
|
bowtie2-build $args --threads $task.cpus $fasta bowtie2/${fasta.baseName}
|
||||||
|
cat <<-END_VERSIONS > versions.yml
|
||||||
|
"${task.process}":
|
||||||
|
bowtie2: \$(echo \$(bowtie2 --version 2>&1) | sed 's/^.*bowtie2-align-s version //; s/ .*\$//')
|
||||||
|
END_VERSIONS
|
||||||
|
"""
|
||||||
|
}
|
33
modules/nf-core/modules/bowtie2/build/meta.yml
generated
Normal file
33
modules/nf-core/modules/bowtie2/build/meta.yml
generated
Normal file
|
@ -0,0 +1,33 @@
|
||||||
|
name: bowtie2_build
|
||||||
|
description: Builds bowtie index for reference genome
|
||||||
|
keywords:
|
||||||
|
- build
|
||||||
|
- index
|
||||||
|
- fasta
|
||||||
|
- genome
|
||||||
|
- reference
|
||||||
|
tools:
|
||||||
|
- bowtie2:
|
||||||
|
description: |
|
||||||
|
Bowtie 2 is an ultrafast and memory-efficient tool for aligning
|
||||||
|
sequencing reads to long reference sequences.
|
||||||
|
homepage: http://bowtie-bio.sourceforge.net/bowtie2/index.shtml
|
||||||
|
documentation: http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
|
||||||
|
doi: 10.1038/nmeth.1923
|
||||||
|
licence: ["GPL-3.0-or-later"]
|
||||||
|
input:
|
||||||
|
- fasta:
|
||||||
|
type: file
|
||||||
|
description: Input genome fasta file
|
||||||
|
output:
|
||||||
|
- index:
|
||||||
|
type: file
|
||||||
|
description: Bowtie2 genome index files
|
||||||
|
pattern: "*.bt2"
|
||||||
|
- versions:
|
||||||
|
type: file
|
||||||
|
description: File containing software versions
|
||||||
|
pattern: "versions.yml"
|
||||||
|
authors:
|
||||||
|
- "@joseespinosa"
|
||||||
|
- "@drpatelh"
|
|
@ -55,7 +55,7 @@ params {
|
||||||
databases = null
|
databases = null
|
||||||
|
|
||||||
// FASTQ preprocessing
|
// FASTQ preprocessing
|
||||||
shortread_clipmerge = false
|
perform_shortread_clipmerge = false
|
||||||
shortread_clipmerge_tool = 'fastp'
|
shortread_clipmerge_tool = 'fastp'
|
||||||
shortread_clipmerge_skipadaptertrim = false
|
shortread_clipmerge_skipadaptertrim = false
|
||||||
shortread_clipmerge_mergepairs = false
|
shortread_clipmerge_mergepairs = false
|
||||||
|
@ -63,11 +63,11 @@ params {
|
||||||
shortread_clipmerge_adapter1 = null
|
shortread_clipmerge_adapter1 = null
|
||||||
shortread_clipmerge_adapter2 = null
|
shortread_clipmerge_adapter2 = null
|
||||||
shortread_clipmerge_minlength = 15
|
shortread_clipmerge_minlength = 15
|
||||||
longread_clip = false
|
perform_longread_clip = false
|
||||||
save_preprocessed_reads = false
|
save_preprocessed_reads = false
|
||||||
|
|
||||||
// Complexity filtering
|
// Complexity filtering
|
||||||
shortread_complexityfilter = false
|
perform_shortread_complexityfilter = false
|
||||||
shortread_complexityfilter_tool = 'bbduk'
|
shortread_complexityfilter_tool = 'bbduk'
|
||||||
shortread_complexityfilter_entropy = 0.3
|
shortread_complexityfilter_entropy = 0.3
|
||||||
shortread_complexityfilter_bbduk_windowsize = 50
|
shortread_complexityfilter_bbduk_windowsize = 50
|
||||||
|
@ -76,6 +76,14 @@ params {
|
||||||
shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
|
shortread_complexityfilter_prinseqplusplus_dustscore = 0.5
|
||||||
save_complexityfiltered_reads = false
|
save_complexityfiltered_reads = false
|
||||||
|
|
||||||
|
// run merging
|
||||||
|
perform_runmerging = false
|
||||||
|
save_runmerged_reads = false
|
||||||
|
|
||||||
|
// Host Removal
|
||||||
|
perform_shortread_hostremoval = false
|
||||||
|
shortread_hostremoval_reference = null
|
||||||
|
shortread_hostremoval_index = null
|
||||||
|
|
||||||
// MALT
|
// MALT
|
||||||
run_malt = false
|
run_malt = false
|
||||||
|
|
|
@ -262,15 +262,9 @@
|
||||||
"type": "string",
|
"type": "string",
|
||||||
"default": "None"
|
"default": "None"
|
||||||
},
|
},
|
||||||
"shortread_clipmerge": {
|
|
||||||
"type": "boolean"
|
|
||||||
},
|
|
||||||
"shortread_clipmerge_excludeunmerged": {
|
"shortread_clipmerge_excludeunmerged": {
|
||||||
"type": "boolean"
|
"type": "boolean"
|
||||||
},
|
},
|
||||||
"longread_clip": {
|
|
||||||
"type": "boolean"
|
|
||||||
},
|
|
||||||
"run_malt": {
|
"run_malt": {
|
||||||
"type": "boolean"
|
"type": "boolean"
|
||||||
},
|
},
|
||||||
|
@ -321,8 +315,7 @@
|
||||||
"default": 15
|
"default": 15
|
||||||
},
|
},
|
||||||
"save_preprocessed_reads": {
|
"save_preprocessed_reads": {
|
||||||
"type": "boolean",
|
"type": "boolean"
|
||||||
"default": false
|
|
||||||
},
|
},
|
||||||
"shortread_complexityfilter_tool": {
|
"shortread_complexityfilter_tool": {
|
||||||
"type": "string",
|
"type": "string",
|
||||||
|
@ -335,9 +328,6 @@
|
||||||
"shortread_complexityfilter_bbduk_mask": {
|
"shortread_complexityfilter_bbduk_mask": {
|
||||||
"type": "boolean"
|
"type": "boolean"
|
||||||
},
|
},
|
||||||
"shortread_complexityfilter": {
|
|
||||||
"type": "boolean"
|
|
||||||
},
|
|
||||||
"shortread_complexityfilter_entropy": {
|
"shortread_complexityfilter_entropy": {
|
||||||
"type": "number",
|
"type": "number",
|
||||||
"default": 0.3
|
"default": 0.3
|
||||||
|
@ -352,8 +342,33 @@
|
||||||
"default": 0.5
|
"default": 0.5
|
||||||
},
|
},
|
||||||
"save_complexityfiltered_reads": {
|
"save_complexityfiltered_reads": {
|
||||||
"type": "boolean",
|
"type": "boolean"
|
||||||
"default": false
|
},
|
||||||
|
"save_runmerged_reads": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"perform_shortread_clipmerge": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"perform_longread_clip": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"perform_shortread_complexityfilter": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"perform_runmerging": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"perform_shortread_hostremoval": {
|
||||||
|
"type": "boolean"
|
||||||
|
},
|
||||||
|
"shortread_hostremoval_reference": {
|
||||||
|
"type": "string",
|
||||||
|
"default": null
|
||||||
|
},
|
||||||
|
"shortread_hostremoval_index": {
|
||||||
|
"type": "string",
|
||||||
|
"default": null
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -9,8 +9,7 @@ include { METAPHLAN3 } from '../../modules/nf-core/modules/meta
|
||||||
|
|
||||||
workflow PROFILING {
|
workflow PROFILING {
|
||||||
take:
|
take:
|
||||||
shortreads // [ [ meta ], [ reads ] ]
|
reads // [ [ meta ], [ reads ] ]
|
||||||
longreads // [ [ meta ], [ reads ] ]
|
|
||||||
databases // [ [ meta ], path ]
|
databases // [ [ meta ], path ]
|
||||||
|
|
||||||
main:
|
main:
|
||||||
|
@ -23,8 +22,14 @@ workflow PROFILING {
|
||||||
*/
|
*/
|
||||||
|
|
||||||
// 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]
|
// 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 = shortreads
|
ch_input_for_profiling = reads
|
||||||
.mix( longreads )
|
.map {
|
||||||
|
meta, reads ->
|
||||||
|
def meta_new = meta.clone()
|
||||||
|
pairtype = meta_new['single_end'] ? '_se' : '_pe'
|
||||||
|
meta_new['id'] = meta_new['id'] + pairtype
|
||||||
|
[meta_new, reads]
|
||||||
|
}
|
||||||
.combine(databases)
|
.combine(databases)
|
||||||
.branch {
|
.branch {
|
||||||
malt: it[2]['tool'] == 'malt'
|
malt: it[2]['tool'] == 'malt'
|
||||||
|
|
|
@ -28,8 +28,8 @@ workflow SHORTREAD_FASTP {
|
||||||
.map {
|
.map {
|
||||||
meta, reads ->
|
meta, reads ->
|
||||||
def meta_new = meta.clone()
|
def meta_new = meta.clone()
|
||||||
meta_new['single_end'] = 1
|
meta_new['single_end'] = true
|
||||||
[ meta_new, reads ]
|
[ meta_new, [ reads ].flatten() ]
|
||||||
}
|
}
|
||||||
|
|
||||||
ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )
|
ch_fastp_reads_prepped = ch_fastp_reads_prepped_pe.mix( FASTP_SINGLE.out.reads )
|
||||||
|
|
34
subworkflows/local/shortread_hostremoval.nf
Normal file
34
subworkflows/local/shortread_hostremoval.nf
Normal file
|
@ -0,0 +1,34 @@
|
||||||
|
//
|
||||||
|
// Remove host reads via alignment and export off-target reads
|
||||||
|
//
|
||||||
|
|
||||||
|
include { BOWTIE2_BUILD } from '../../modules/nf-core/modules/bowtie2/build/main'
|
||||||
|
include { BOWTIE2_ALIGN } from '../../modules/nf-core/modules/bowtie2/align/main'
|
||||||
|
|
||||||
|
workflow SHORTREAD_HOSTREMOVAL {
|
||||||
|
take:
|
||||||
|
reads // [ [ meta ], [ reads ] ]
|
||||||
|
reference // /path/to/fasta
|
||||||
|
index // /path/to/index
|
||||||
|
|
||||||
|
main:
|
||||||
|
ch_versions = Channel.empty()
|
||||||
|
ch_multiqc_files = Channel.empty()
|
||||||
|
|
||||||
|
if ( !params.shortread_hostremoval_index ) {
|
||||||
|
ch_bowtie2_index = BOWTIE2_BUILD ( reference ).index
|
||||||
|
ch_versions = ch_versions.mix( BOWTIE2_BUILD.out.versions )
|
||||||
|
} else {
|
||||||
|
ch_bowtie2_index = index.first()
|
||||||
|
}
|
||||||
|
|
||||||
|
BOWTIE2_ALIGN ( reads, ch_bowtie2_index, true )
|
||||||
|
ch_versions = ch_versions.mix( BOWTIE2_ALIGN.out.versions.first() )
|
||||||
|
ch_multiqc_files = ch_multiqc_files.mix( BOWTIE2_ALIGN.out.log )
|
||||||
|
|
||||||
|
emit:
|
||||||
|
reads = BOWTIE2_ALIGN.out.fastq // channel: [ val(meta), [ reads ] ]
|
||||||
|
versions = ch_versions // channel: [ versions.yml ]
|
||||||
|
mqc = ch_multiqc_files
|
||||||
|
}
|
||||||
|
|
|
@ -11,7 +11,9 @@ WorkflowTaxprofiler.initialise(params, log)
|
||||||
|
|
||||||
// TODO nf-core: Add all file path parameters for the pipeline to the list below
|
// TODO nf-core: Add all file path parameters for the pipeline to the list below
|
||||||
// Check input path parameters to see if they exist
|
// Check input path parameters to see if they exist
|
||||||
def checkPathParamList = [ params.input, params.databases, params.multiqc_config ]
|
def checkPathParamList = [ params.input, params.databases, params.shortread_hostremoval_reference,
|
||||||
|
params.shortread_hostremoval_index, params.multiqc_config
|
||||||
|
]
|
||||||
for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
|
for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
|
||||||
|
|
||||||
// Check mandatory parameters
|
// Check mandatory parameters
|
||||||
|
@ -20,6 +22,12 @@ if (params.databases) { ch_databases = file(params.databases) } else { exit 1, '
|
||||||
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_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"
|
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"
|
||||||
|
|
||||||
|
if (params.perform_shortread_hostremoval && !params.shortread_hostremoval_reference) { exit 1, "[nf-core/taxprofiler] error: --shortread_hostremoval requested but no --shortread_hostremoval_reference FASTA supplied. Check input." }
|
||||||
|
if (!params.shortread_hostremoval_reference && params.shortread_hostremoval_reference_index) { exit 1, "[nf-core/taxprofiler] error: --shortread_hostremoval_index provided but no --shortread_hostremoval_reference FASTA supplied. Check input." }
|
||||||
|
|
||||||
|
if (params.shortread_hostremoval_reference ) { ch_reference = file(params.shortread_hostremoval_reference) }
|
||||||
|
if (params.shortread_hostremoval_index ) { ch_reference_index = file(params.shortread_hostremoval_index ) } else { ch_reference_index = [] }
|
||||||
|
|
||||||
/*
|
/*
|
||||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||||
CONFIG FILES
|
CONFIG FILES
|
||||||
|
@ -43,6 +51,7 @@ include { INPUT_CHECK } from '../subworkflows/local/input_check'
|
||||||
include { DB_CHECK } from '../subworkflows/local/db_check'
|
include { DB_CHECK } from '../subworkflows/local/db_check'
|
||||||
include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing'
|
include { SHORTREAD_PREPROCESSING } from '../subworkflows/local/shortread_preprocessing'
|
||||||
include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing'
|
include { LONGREAD_PREPROCESSING } from '../subworkflows/local/longread_preprocessing'
|
||||||
|
include { SHORTREAD_HOSTREMOVAL } from '../subworkflows/local/shortread_hostremoval'
|
||||||
include { SHORTREAD_COMPLEXITYFILTERING } from '../subworkflows/local/shortread_complexityfiltering'
|
include { SHORTREAD_COMPLEXITYFILTERING } from '../subworkflows/local/shortread_complexityfiltering'
|
||||||
include { PROFILING } from '../subworkflows/local/profiling'
|
include { PROFILING } from '../subworkflows/local/profiling'
|
||||||
|
|
||||||
|
@ -101,16 +110,17 @@ workflow TAXPROFILER {
|
||||||
/*
|
/*
|
||||||
SUBWORKFLOW: PERFORM PREPROCESSING
|
SUBWORKFLOW: PERFORM PREPROCESSING
|
||||||
*/
|
*/
|
||||||
if ( params.shortread_clipmerge ) {
|
if ( params.perform_shortread_clipmerge ) {
|
||||||
|
|
||||||
ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq ).reads
|
ch_shortreads_preprocessed = SHORTREAD_PREPROCESSING ( INPUT_CHECK.out.fastq ).reads
|
||||||
} else {
|
} else {
|
||||||
ch_shortreads_preprocessed = INPUT_CHECK.out.fastq
|
ch_shortreads_preprocessed = INPUT_CHECK.out.fastq
|
||||||
}
|
}
|
||||||
|
|
||||||
if ( params.longread_clip ) {
|
if ( params.perform_longread_clip ) {
|
||||||
ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
|
ch_longreads_preprocessed = LONGREAD_PREPROCESSING ( INPUT_CHECK.out.nanopore ).reads
|
||||||
.map { it -> [ it[0], [it[1]] ] }
|
.map { it -> [ it[0], [it[1]] ] }
|
||||||
|
ch_versions = ch_versions.mix(LONGREAD_PREPROCESSING.out.versions.first())
|
||||||
} else {
|
} else {
|
||||||
ch_longreads_preprocessed = INPUT_CHECK.out.nanopore
|
ch_longreads_preprocessed = INPUT_CHECK.out.nanopore
|
||||||
}
|
}
|
||||||
|
@ -119,17 +129,63 @@ workflow TAXPROFILER {
|
||||||
SUBWORKFLOW: COMPLEXITY FILTERING
|
SUBWORKFLOW: COMPLEXITY FILTERING
|
||||||
*/
|
*/
|
||||||
|
|
||||||
if ( params.shortread_complexityfilter ) {
|
if ( params.perform_shortread_complexityfilter ) {
|
||||||
ch_shortreads_filtered = SHORTREAD_COMPLEXITYFILTERING ( ch_shortreads_preprocessed ).reads
|
ch_shortreads_filtered = SHORTREAD_COMPLEXITYFILTERING ( ch_shortreads_preprocessed ).reads
|
||||||
} else {
|
} else {
|
||||||
ch_shortreads_filtered = ch_shortreads_preprocessed
|
ch_shortreads_filtered = ch_shortreads_preprocessed
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
SUBWORKFLOW: HOST REMOVAL
|
||||||
|
*/
|
||||||
|
|
||||||
|
if ( params.perform_shortread_hostremoval ) {
|
||||||
|
ch_shortreads_hostremoved = SHORTREAD_HOSTREMOVAL ( ch_shortreads_filtered, ch_reference, ch_reference_index ).reads
|
||||||
|
ch_versions = ch_versions.mix(SHORTREAD_HOSTREMOVAL.out.versions.first())
|
||||||
|
} else {
|
||||||
|
ch_shortreads_hostremoved = ch_shortreads_filtered
|
||||||
|
}
|
||||||
|
|
||||||
|
if ( params.perform_runmerging ) {
|
||||||
|
|
||||||
|
ch_reads_for_cat_branch = ch_shortreads_hostremoved
|
||||||
|
.mix( ch_longreads_preprocessed )
|
||||||
|
.map {
|
||||||
|
meta, reads ->
|
||||||
|
def meta_new = meta.clone()
|
||||||
|
meta_new.remove('run_accession')
|
||||||
|
[ meta_new, reads ]
|
||||||
|
}
|
||||||
|
.groupTuple()
|
||||||
|
.map {
|
||||||
|
meta, reads ->
|
||||||
|
[ meta, reads.flatten() ]
|
||||||
|
}
|
||||||
|
.branch {
|
||||||
|
meta, reads ->
|
||||||
|
// we can't concatenate files if there is not a second run, we branch
|
||||||
|
// here to separate them out, and mix back in after for efficiency
|
||||||
|
cat: ( meta.single_end && reads.size() > 1 ) || ( !meta.single_end && reads.size() > 2 )
|
||||||
|
skip: true
|
||||||
|
}
|
||||||
|
|
||||||
|
ch_reads_runmerged = CAT_FASTQ ( ch_reads_for_cat_branch.cat ).reads
|
||||||
|
.mix( ch_reads_for_cat_branch.skip )
|
||||||
|
.map {
|
||||||
|
meta, reads ->
|
||||||
|
[ meta, [ reads ].flatten() ]
|
||||||
|
}
|
||||||
|
|
||||||
|
} else {
|
||||||
|
ch_reads_runmerged = ch_shortreads_hostremoved
|
||||||
|
.mix( ch_longreads_preprocessed )
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
SUBWORKFLOW: PROFILING
|
SUBWORKFLOW: PROFILING
|
||||||
*/
|
*/
|
||||||
|
|
||||||
PROFILING ( ch_shortreads_filtered, ch_longreads_preprocessed, DB_CHECK.out.dbs )
|
PROFILING ( ch_reads_runmerged, DB_CHECK.out.dbs )
|
||||||
ch_versions = ch_versions.mix( PROFILING.out.versions )
|
ch_versions = ch_versions.mix( PROFILING.out.versions )
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
@ -151,21 +207,30 @@ workflow TAXPROFILER {
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
|
ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
|
||||||
ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
|
ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
|
||||||
|
|
||||||
if (params.shortread_clipmerge) {
|
if (params.perform_shortread_clipmerge) {
|
||||||
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||||
ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions )
|
ch_versions = ch_versions.mix( SHORTREAD_PREPROCESSING.out.versions )
|
||||||
}
|
}
|
||||||
|
|
||||||
if (params.longread_clip) {
|
if (params.perform_longread_clip) {
|
||||||
ch_multiqc_files = ch_multiqc_files.mix( LONGREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
ch_multiqc_files = ch_multiqc_files.mix( LONGREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||||
ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions )
|
ch_versions = ch_versions.mix( LONGREAD_PREPROCESSING.out.versions )
|
||||||
}
|
}
|
||||||
|
|
||||||
if (params.shortread_complexityfilter){
|
if (params.perform_shortread_complexityfilter){
|
||||||
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_COMPLEXITYFILTERING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_COMPLEXITYFILTERING.out.mqc.collect{it[1]}.ifEmpty([]) )
|
||||||
ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
|
ch_versions = ch_versions.mix( SHORTREAD_COMPLEXITYFILTERING.out.versions )
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if (params.perform_shortread_hostremoval) {
|
||||||
|
ch_multiqc_files = ch_multiqc_files.mix(SHORTREAD_HOSTREMOVAL.out.mqc.collect{it[1]}.ifEmpty([]))
|
||||||
|
ch_versions = ch_versions.mix(SHORTREAD_HOSTREMOVAL.out.versions)
|
||||||
|
}
|
||||||
|
|
||||||
|
if (params.perform_runmerging){
|
||||||
|
ch_versions = ch_versions.mix(CAT_FASTQ.out.versions)
|
||||||
|
}
|
||||||
|
|
||||||
ch_multiqc_files = ch_multiqc_files.mix( PROFILING.out.mqc )
|
ch_multiqc_files = ch_multiqc_files.mix( PROFILING.out.mqc )
|
||||||
|
|
||||||
// TODO create multiQC module for metaphlan
|
// TODO create multiQC module for metaphlan
|
||||||
|
|
Loading…
Reference in a new issue