millironx/nf-core_modules
1
0
Fork 0
mirror of https://github.com/MillironX/nf-core_modules.git synced 2024-12-22 02:58:17 +00:00
Code Issues Releases Packages Activity

Merge branch 'master' into bamtools/convert/remove_TODO

Browse source
This commit is contained in:
Sébastien Guizard 2022-05-30 17:36:36 +01:00 committed by GitHub
commit a3ae526521
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
665 changed files with 14101 additions and 2149 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

64
.github/ISSUE_TEMPLATE/bug_report.md vendored
View file

@ -1,64 +0,0 @@
---
name: Bug report
about: Report something that is broken or incorrect
title: "[BUG]"
---
<!--
# nf-core/module bug report
Hi there!
Thanks for telling us about a problem with the modules.
Please delete this text and anything that's not relevant from the template below:
-->
## Check Documentation
I have checked the following places for your error:
- [ ] [nf-core website: troubleshooting](https://nf-co.re/usage/troubleshooting)
- [ ] [nf-core/module documentation](https://github.com/nf-core/modules/blob/master/README.md)
## Description of the bug
<!-- A clear and concise description of what the bug is. -->
## Steps to reproduce
Steps to reproduce the behaviour:
1. Command line: <!-- [e.g. `nextflow run ...`] -->
2. See error: <!-- [Please provide your error message] -->
## Expected behaviour
<!-- A clear and concise description of what you expected to happen. -->
## Log files
Have you provided the following extra information/files:
- [ ] The command used to run the module
- [ ] The `.nextflow.log` file <!-- this is a hidden file in the directory where you launched the module -->
## System
- Hardware: <!-- [e.g. HPC, Desktop, Cloud...] -->
- Executor: <!-- [e.g. slurm, local, awsbatch...] -->
- OS: <!-- [e.g. CentOS Linux, macOS, Linux Mint...] -->
- Version <!-- [e.g. 7, 10.13.6, 18.3...] -->
## Nextflow Installation
- Version: <!-- [e.g. 19.10.0] -->
## Container engine
- Engine: <!-- [e.g. Conda, Docker, Singularity or Podman] -->
- version: <!-- [e.g. 1.0.0] -->
- Image tag: <!-- [e.g. nfcore/module:2.6] -->
## Additional context
<!-- Add any other context about the problem here. -->

52
.github/ISSUE_TEMPLATE/bug_report.yml vendored Normal file
View file

@ -0,0 +1,52 @@
name: Bug report
description: Report something that is broken or incorrect
labels: bug
body:
- type: checkboxes
attributes:
label: Have you checked the docs?
description: I have checked the following places for my error
options:
- label: "[nf-core website: troubleshooting](https://nf-co.re/usage/troubleshooting)"
required: true
- label: "[nf-core modules documentation](https://nf-co.re/docs/contributing/modules)"
required: true
- type: textarea
id: description
attributes:
label: Description of the bug
description: A clear and concise description of what the bug is.
validations:
required: true
- type: textarea
id: command_used
attributes:
label: Command used and terminal output
description: Steps to reproduce the behaviour. Please paste the command you used to launch the pipeline and the output from your terminal.
render: console
placeholder: |
$ nextflow run ...
Some output where something broke
- type: textarea
id: files
attributes:
label: Relevant files
description: |
Please drag and drop the relevant files here. Create a `.zip` archive if the extension is not allowed.
Your verbose log file `.nextflow.log` is often useful _(this is a hidden file in the directory where you launched the pipeline)_ as well as custom Nextflow configuration files.
- type: textarea
id: system
attributes:
label: System information
description: |
* Nextflow version _(eg. 21.10.3)_
* Hardware _(eg. HPC, Desktop, Cloud)_
* Executor _(eg. slurm, local, awsbatch)_
* Container engine and version: _(e.g. Docker 1.0.0, Singularity, Conda, Podman, Shifter or Charliecloud)_
* OS and version: _(eg. CentOS Linux, macOS, Ubuntu 22.04)_
* Image tag: <!-- [e.g. nfcore/cellranger:2.6] -->

32
.github/ISSUE_TEMPLATE/feature_request.md vendored
View file

@ -1,32 +0,0 @@
---
name: Feature request
about: Suggest an idea for nf-core/modules
title: "[FEATURE]"
---
<!--
# nf-core/modules feature request
Hi there!
Thanks for suggesting a new feature for the modules!
Please delete this text and anything that's not relevant from the template below:
-->
## Is your feature request related to a problem? Please describe
<!-- A clear and concise description of what the problem is. -->
<!-- e.g. [I'm always frustrated when ...] -->
## Describe the solution you'd like
<!-- A clear and concise description of what you want to happen. -->
## Describe alternatives you've considered
<!-- A clear and concise description of any alternative solutions or features you've considered. -->
## Additional context
<!-- Add any other context about the feature request here. -->

32
.github/ISSUE_TEMPLATE/feature_request.yml vendored Normal file
View file

@ -0,0 +1,32 @@
name: Feature request
description: Suggest an idea for nf-core/modules
labels: feature
title: "[FEATURE]"
body:
- type: textarea
id: description
attributes:
label: Is your feature request related to a problem? Please describe
description: A clear and concise description of what the bug is.
placeholder: |
<!-- e.g. [I'm always frustrated when ...] -->
validations:
required: true
- type: textarea
id: solution
attributes:
label: Describe the solution you'd like
description: A clear and concise description of the solution you want to happen.
- type: textarea
id: alternatives
attributes:
label: Describe alternatives you've considered
description: A clear and concise description of any alternative solutions or features you've considered.
- type: textarea
id: additional_context
attributes:
label: Additional context
description: Add any other context about the feature request here.

26
.github/ISSUE_TEMPLATE/new_module.md vendored
View file

@ -1,26 +0,0 @@
---
name: New module
about: Suggest a new module for nf-core/modules
title: "new module: TOOL/SUBTOOL"
label: new module
---
<!--
# nf-core/modules new module suggestion
Hi there!
Thanks for suggesting a new module for the modules!
Please delete this text and anything that's not relevant from the template below:
Replace TOOL with the bioconda name for the tool in the following text, so that the link is functional.
Replace TOOL/SUBTOOL in the issue title so that it's understandable.
-->
I think it would be good to have a module for [TOOL](https://bioconda.github.io/recipes/TOOL/README.html)
- [ ] This module does not exist yet with the [`nf-core modules list`](https://github.com/nf-core/tools#list-modules) command
- [ ] There is no [open pull request](https://github.com/nf-core/modules/pulls) for this module
- [ ] There is no [open issue](https://github.com/nf-core/modules/issues) for this module
- [ ] If I'm planning to work on this module, I added myself to the `Assignees` to facilitate tracking who is working on the module

36
.github/ISSUE_TEMPLATE/new_module.yml vendored Normal file
View file

@ -0,0 +1,36 @@
name: New module
description: Suggest a new module for nf-core/modules
title: "new module: TOOL/SUBTOOL"
labels: new module
body:
- type: checkboxes
attributes:
label: Is there an existing module for this?
description: This module does not exist yet with the [`nf-core modules list`](https://github.com/nf-core/tools#list-modules) command
options:
- label: I have searched for the existing module
required: true
- type: checkboxes
attributes:
label: Is there an open PR for this?
description: There is no [open pull request](https://github.com/nf-core/modules/pulls) for this module
options:
- label: I have searched for existing PRs
required: true
- type: checkboxes
attributes:
label: Is there an open issue for this?
description: There is no [open issue](https://github.com/nf-core/modules/issues) for this module
options:
- label: I have searched for existing issues
required: true
- type: checkboxes
attributes:
label: Are you going to work on this?
description: If I'm planning to work on this module, I added myself to the `Assignees` to facilitate tracking who is working on the module
options:
- label: If I'm planning to work on this module, I added myself to the `Assignees` to facilitate tracking who is working on the module
required: false

44
modules/adapterremoval/main.nf
View file

@ -12,15 +12,14 @@ process ADAPTERREMOVAL {
path(adapterlist)
output:
tuple val(meta), path("${prefix}.truncated.gz") , optional: true, emit: singles_truncated
tuple val(meta), path("${prefix}.discarded.gz") , optional: true, emit: discarded
tuple val(meta), path("${prefix}.pair1.truncated.gz") , optional: true, emit: pair1_truncated
tuple val(meta), path("${prefix}.pair2.truncated.gz") , optional: true, emit: pair2_truncated
tuple val(meta), path("${prefix}.collapsed.gz") , optional: true, emit: collapsed
tuple val(meta), path("${prefix}.collapsed.truncated.gz") , optional: true, emit: collapsed_truncated
tuple val(meta), path("${prefix}.paired.gz") , optional: true, emit: paired_interleaved
tuple val(meta), path('*.log') , emit: log
path "versions.yml" , emit: versions
tuple val(meta), path("${prefix}.truncated.fastq.gz") , optional: true, emit: singles_truncated
tuple val(meta), path("${prefix}.discarded.fastq.gz") , optional: true, emit: discarded
tuple val(meta), path("${prefix}.pair{1,2}.truncated.fastq.gz") , optional: true, emit: paired_truncated
tuple val(meta), path("${prefix}.collapsed.fastq.gz") , optional: true, emit: collapsed
tuple val(meta), path("${prefix}.collapsed.truncated.fastq.gz") , optional: true, emit: collapsed_truncated
tuple val(meta), path("${prefix}.paired.fastq.gz") , optional: true, emit: paired_interleaved
tuple val(meta), path('*.settings') , emit: settings
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -38,10 +37,19 @@ process ADAPTERREMOVAL {
$adapterlist \\
--basename ${prefix} \\
--threads ${task.cpus} \\
--settings ${prefix}.log \\
--seed 42 \\
--gzip
ensure_fastq() {
if [ -f "\${1}" ]; then
mv "\${1}" "\${1::-3}.fastq.gz"
fi
}
ensure_fastq '${prefix}.truncated.gz'
ensure_fastq '${prefix}.discarded.gz'
cat <<-END_VERSIONS > versions.yml
"${task.process}":
adapterremoval: \$(AdapterRemoval --version 2>&1 | sed -e "s/AdapterRemoval ver. //g")
@ -56,10 +64,24 @@ process ADAPTERREMOVAL {
$adapterlist \\
--basename ${prefix} \\
--threads $task.cpus \\
--settings ${prefix}.log \\
--seed 42 \\
--gzip
ensure_fastq() {
if [ -f "\${1}" ]; then
mv "\${1}" "\${1::-3}.fastq.gz"
fi
}
ensure_fastq '${prefix}.truncated.gz'
ensure_fastq '${prefix}.discarded.gz'
ensure_fastq '${prefix}.pair1.truncated.gz'
ensure_fastq '${prefix}.pair2.truncated.gz'
ensure_fastq '${prefix}.collapsed.gz'
ensure_fastq '${prefix}.collapsed.truncated.gz'
ensure_fastq '${prefix}.paired.gz'
cat <<-END_VERSIONS > versions.yml
"${task.process}":
adapterremoval: \$(AdapterRemoval --version 2>&1 | sed -e "s/AdapterRemoval ver. //g")

14
modules/adapterremoval/meta.yml
View file

@ -43,43 +43,43 @@ output:
Adapter trimmed FastQ files of either single-end reads, or singleton
'orphaned' reads from merging of paired-end data (i.e., one of the pair
was lost due to filtering thresholds).
pattern: "*.truncated.gz"
pattern: "*.truncated.fastq.gz"
- discarded:
type: file
description: |
Adapter trimmed FastQ files of reads that did not pass filtering
thresholds.
pattern: "*.discarded.gz"
pattern: "*.discarded.fastq.gz"
- pair1_truncated:
type: file
description: |
Adapter trimmed R1 FastQ files of paired-end reads that did not merge
with their respective R2 pair due to long templates. The respective pair
is stored in 'pair2_truncated'.
pattern: "*.pair1.truncated.gz"
pattern: "*.pair1.truncated.fastq.gz"
- pair2_truncated:
type: file
description: |
Adapter trimmed R2 FastQ files of paired-end reads that did not merge
with their respective R1 pair due to long templates. The respective pair
is stored in 'pair1_truncated'.
pattern: "*.pair2.truncated.gz"
pattern: "*.pair2.truncated.fastq.gz"
- collapsed:
type: file
description: |
Collapsed FastQ of paired-end reads that successfully merged with their
respective R1 pair but were not trimmed.
pattern: "*.collapsed.gz"
pattern: "*.collapsed.fastq.gz"
- collapsed_truncated:
type: file
description: |
Collapsed FastQ of paired-end reads that successfully merged with their
respective R1 pair and were trimmed of adapter due to sufficient overlap.
pattern: "*.collapsed.truncated.gz"
pattern: "*.collapsed.truncated.fastq.gz"
- log:
type: file
description: AdapterRemoval log file
pattern: "*.log"
pattern: "*.settings"
- versions:
type: file
description: File containing software versions

4
modules/allelecounter/meta.yml
View file

@ -32,8 +32,8 @@ input:
description: loci file <CHR><tab><POS1>
pattern: "*.{tsv}"
- fasta:
type: file
description: Input genome fasta file. Required when passing CRAM files.
type: file
description: Input genome fasta file. Required when passing CRAM files.
output:
- meta:

41
modules/amplify/predict/main.nf Normal file
View file

@ -0,0 +1,41 @@
def VERSION = '1.0.3' // Version information not provided by tool
process AMPLIFY_PREDICT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::amplify=1.0.3" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/amplify:1.0.3--py36hdfd78af_0':
'quay.io/biocontainers/amplify:1.0.3--py36hdfd78af_0' }"
input:
tuple val(meta), path(faa)
path(model_dir)
output:
tuple val(meta), path('*.tsv'), emit: tsv
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 custom_model_dir = model_dir ? "-md ${model_dir}" : ""
"""
AMPlify \\
$args \\
${custom_model_dir} \\
-s '${faa}'
#rename output, because tool includes date and time in name
mv *.tsv ${prefix}.tsv
cat <<-END_VERSIONS > versions.yml
"${task.process}":
AMPlify: $VERSION
END_VERSIONS
"""
}

47
modules/amplify/predict/meta.yml Normal file
View file

@ -0,0 +1,47 @@
name: "amplify_predict"
description: AMPlify is an attentive deep learning model for antimicrobial peptide prediction.
keywords:
- antimicrobial peptides
- AMPs
- prediction
- model
tools:
- "amplify":
description: "Attentive deep learning model for antimicrobial peptide prediction"
homepage: "https://github.com/bcgsc/AMPlify"
documentation: "https://github.com/bcgsc/AMPlify"
tool_dev_url: "https://github.com/bcgsc/AMPlify"
doi: "https://doi.org/10.1186/s12864-022-08310-4"
licence: "['GPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- faa:
type: file
description: amino acid sequences fasta
pattern: "*.{fa,fa.gz,faa,faa.gz,fasta,fasta.gz}"
- model_dir:
type: directory
description: Directory of where models are stored (optional)
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"
- tsv:
type: file
description: amino acid sequences with prediction (AMP, non-AMP) and probability scores
pattern: "*.{tsv}"
authors:
- "@louperelo"

68
modules/antismash/antismashlite/main.nf Normal file
View file

@ -0,0 +1,68 @@
process ANTISMASH_ANTISMASHLITE {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::antismash-lite=6.0.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/antismash-lite:6.0.1--pyhdfd78af_1' :
'quay.io/biocontainers/antismash-lite:6.0.1--pyhdfd78af_1' }"
containerOptions {
workflow.containerEngine == 'singularity' ?
"-B $antismash_dir:/usr/local/lib/python3.8/site-packages/antismash" :
workflow.containerEngine == 'docker' ?
"-v \$PWD/$antismash_dir:/usr/local/lib/python3.8/site-packages/antismash" :
''
}
input:
tuple val(meta), path(sequence_input)
path(databases)
path(antismash_dir) // Optional input: AntiSMASH installation folder. It is not needed for using this module with conda, but required for docker/singularity (see meta.yml).
path(gff)
output:
tuple val(meta), path("${prefix}/clusterblast/*_c*.txt") , optional: true, emit: clusterblast_file
tuple val(meta), path("${prefix}/{css,images,js}") , emit: html_accessory_files
tuple val(meta), path("${prefix}/knownclusterblast/region*/ctg*.html") , optional: true, emit: knownclusterblast_html
tuple val(meta), path("${prefix}/knownclusterblast/*_c*.txt") , optional: true, emit: knownclusterblast_txt
tuple val(meta), path("${prefix}/svg/clusterblast*.svg") , optional: true, emit: svg_files_clusterblast
tuple val(meta), path("${prefix}/svg/knownclusterblast*.svg") , optional: true, emit: svg_files_knownclusterblast
tuple val(meta), path("${prefix}/*.gbk") , emit: gbk_input
tuple val(meta), path("${prefix}/*.json") , emit: json_results
tuple val(meta), path("${prefix}/*.log") , emit: log
tuple val(meta), path("${prefix}/*.zip") , emit: zip
tuple val(meta), path("${prefix}/*region*.gbk") , emit: gbk_results
tuple val(meta), path("${prefix}/clusterblastoutput.txt") , optional: true, emit: clusterblastoutput
tuple val(meta), path("${prefix}/index.html") , emit: html
tuple val(meta), path("${prefix}/knownclusterblastoutput.txt") , optional: true, emit: knownclusterblastoutput
tuple val(meta), path("${prefix}/regions.js") , emit: json_sideloading
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
prefix = task.ext.suffix ? "${meta.id}${task.ext.suffix}" : "${meta.id}"
gff_flag = "--genefinding-gff3 ${gff}"
"""
## We specifically do not include annotations (--genefinding-tool none) as
## this should be run as a separate module for versioning purposes
antismash \\
$args \\
$gff_flag \\
-c $task.cpus \\
--output-dir $prefix \\
--genefinding-tool none \\
--logfile $prefix/${prefix}.log \\
--databases $databases \\
$sequence_input
cat <<-END_VERSIONS > versions.yml
"${task.process}":
antismash-lite: \$(antismash --version | sed 's/antiSMASH //')
END_VERSIONS
"""
}

128
modules/antismash/antismashlite/meta.yml Normal file
View file

@ -0,0 +1,128 @@
name: antismash_antismashlite
description: |
antiSMASH allows the rapid genome-wide identification, annotation
and analysis of secondary metabolite biosynthesis gene clusters.
keywords:
- secondary metabolites
- BGC
- biosynthetic gene cluster
- genome mining
- NRPS
- RiPP
- antibiotics
- prokaryotes
- bacteria
- eukaryotes
- fungi
- antismash
tools:
- antismashlite:
description: "antiSMASH - the antibiotics and Secondary Metabolite Analysis SHell"
homepage: "https://docs.antismash.secondarymetabolites.org"
documentation: "https://docs.antismash.secondarymetabolites.org"
tool_dev_url: "https://github.com/antismash/antismash"
doi: "10.1093/nar/gkab335"
licence: "['AGPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- sequence_input:
type: file
description: nucleotide sequence file (annotated)
pattern: "*.{gbk, gb, gbff, genbank, embl, fasta, fna}"
- databases:
type: directory
description: downloaded AntiSMASH databases e.g. data/databases
pattern: "*/"
- antismash_dir:
type: directory
description: |
A local copy of an AntiSMASH installation folder. This is required when running with
docker and singularity (not required for conda), due to attempted 'modifications' of
files during database checks in the installation directory, something that cannot
be done in immutable docker/singularity containers. Therefore, a local installation
directory needs to be mounted (including all modified files from the downloading step)
to the container as a workaround.
pattern: "*/"
- gff:
type: file
pattern: "*.gff"
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"
- clusterblast_file:
type: file
description: Output of ClusterBlast algorithm
pattern: "clusterblast/*_c*.txt"
- html_accessory_files:
type: directory
description: Accessory files for the HTML output
pattern: "{css/,images/,js/}"
- knownclusterblast_html:
type: file
description: Tables with MIBiG hits in HTML format
pattern: "knownclusterblast/region*/ctg*.html"
- knownclusterblast_txt:
type: file
description: Tables with MIBiG hits
pattern: "knownclusterblast/*_c*.txt"
- svg_files_clusterblast:
type: file
description: SVG images showing the % identity of the aligned hits against their queries
pattern: "svg/clusterblast*.svg"
- svg_files_knownclusterblast:
type: file
description: SVG images showing the % identity of the aligned hits against their queries
pattern: "svg/knownclusterblast*.svg"
- gbk_input:
type: file
description: Nucleotide sequence and annotations in GenBank format; converted from input file
pattern: "*.gbk"
- json_results:
type: file
description: Nucleotide sequence and annotations in JSON format; converted from GenBank file (gbk_input)
pattern: "*.json"
- log:
type: file
description: Contains all the logging output that antiSMASH produced during its run
pattern: "*.log"
- zip:
type: file
description: Contains a compressed version of the output folder in zip format
pattern: "*.zip"
- gbk_results:
type: file
description: Nucleotide sequence and annotations in GenBank format; one file per antiSMASH hit
pattern: "*region*.gbk"
- clusterblastoutput:
type: file
description: Raw BLAST output of known clusters previously predicted by antiSMASH using the built-in ClusterBlast algorithm
pattern: "clusterblastoutput.txt"
- html:
type: file
description: Graphical web view of results in HTML format
patterN: "index.html"
- knownclusterblastoutput:
type: file
description: Raw BLAST output of known clusters of the MIBiG database
pattern: "knownclusterblastoutput.txt"
- json_sideloading:
type: file
description: Sideloaded annotations of protoclusters and/or subregions (see antiSMASH documentation "Annotation sideloading")
pattern: "regions.js"
authors:
- "@jasmezz"

56
modules/antismash/antismashlitedownloaddatabases/main.nf Normal file
View file

@ -0,0 +1,56 @@
process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES {
label 'process_low'
conda (params.enable_conda ? "bioconda::antismash-lite=6.0.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/antismash-lite:6.0.1--pyhdfd78af_1' :
'quay.io/biocontainers/antismash-lite:6.0.1--pyhdfd78af_1' }"
/*
These files are normally downloaded/created by download-antismash-databases itself, and must be retrieved for input by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines. This is solely for use for CI tests of the nf-core/module version of antiSMASH.
Reason: Upon execution, the tool checks if certain database files are present within the container and if not, it tries to create them in /usr/local/bin, for which only root user has write permissions. Mounting those database files with this module prevents the tool from trying to create them.
These files are also emitted as output channels in this module to enable the antismash-lite module to use them as mount volumes to the docker/singularity containers.
*/
containerOptions {
workflow.containerEngine == 'singularity' ?
"-B $database_css:/usr/local/lib/python3.8/site-packages/antismash/outputs/html/css,$database_detection:/usr/local/lib/python3.8/site-packages/antismash/detection,$database_modules:/usr/local/lib/python3.8/site-packages/antismash/modules" :
workflow.containerEngine == 'docker' ?
"-v \$PWD/$database_css:/usr/local/lib/python3.8/site-packages/antismash/outputs/html/css -v \$PWD/$database_detection:/usr/local/lib/python3.8/site-packages/antismash/detection -v \$PWD/$database_modules:/usr/local/lib/python3.8/site-packages/antismash/modules" :
''
}
input:
path database_css
path database_detection
path database_modules
output:
path("antismash_db") , emit: database
path("antismash_dir"), emit: antismash_dir
path "versions.yml", emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
conda = params.enable_conda
"""
download-antismash-databases \\
--database-dir antismash_db \\
$args
if [[ $conda = false ]]; \
then \
cp -r /usr/local/lib/python3.8/site-packages/antismash antismash_dir; \
else \
cp -r \$(python -c 'import antismash;print(antismash.__file__.split("/__")[0])') antismash_dir; \
fi
cat <<-END_VERSIONS > versions.yml
"${task.process}":
antismash-lite: \$(antismash --version | sed 's/antiSMASH //')
END_VERSIONS
"""
}

60
modules/antismash/antismashlitedownloaddatabases/meta.yml Normal file
View file

@ -0,0 +1,60 @@
name: antismash_antismashlitedownloaddatabases
description: antiSMASH allows the rapid genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters. This module downloads the antiSMASH databases.
keywords:
- secondary metabolites
- BGC
- biosynthetic gene cluster
- genome mining
- NRPS
- RiPP
- antibiotics
- prokaryotes
- bacteria
- eukaryotes
- fungi
- antismash
- database
tools:
- antismash:
description: antiSMASH - the antibiotics and Secondary Metabolite Analysis SHell
homepage: https://docs.antismash.secondarymetabolites.org
documentation: https://docs.antismash.secondarymetabolites.org
tool_dev_url: https://github.com/antismash/antismash
doi: "10.1093/nar/gkab335"
licence: ["AGPL v3"]
input:
- database_css:
type: directory
description: |
antismash/outputs/html/css folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
pattern: "css"
- database_detection:
type: directory
description: |
antismash/detection folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
pattern: "detection"
- database_modules:
type: directory
description: |
antismash/modules folder which is being created during the antiSMASH database downloading step. These files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database in pipelines.
pattern: "modules"
output:
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- database:
type: directory
description: Download directory for antiSMASH databases
pattern: "antismash_db"
- antismash_dir:
type: directory
description: |
antismash installation folder which is being modified during the antiSMASH database downloading step. The modified files are normally downloaded by download-antismash-databases itself, and must be retrieved by the user by manually running the command with conda or a standalone installation of antiSMASH. Therefore we do not recommend using this module for production pipelines, but rather require users to specify their own local copy of the antiSMASH database and installation folder in pipelines.
pattern: "antismash_dir"
authors:
- "@jasmezz"

32
modules/arriba/main.nf
View file

@ -2,15 +2,20 @@ process ARRIBA {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::arriba=2.1.0" : null)
conda (params.enable_conda ? "bioconda::arriba=2.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/arriba:2.1.0--h3198e80_1' :
'quay.io/biocontainers/arriba:2.1.0--h3198e80_1' }"
'https://depot.galaxyproject.org/singularity/arriba:2.2.1--hecb563c_2' :
'quay.io/biocontainers/arriba:2.2.1--hecb563c_2' }"
input:
tuple val(meta), path(bam)
path fasta
path gtf
path blacklist
path known_fusions
path structural_variants
path tags
path protein_domains
output:
tuple val(meta), path("*.fusions.tsv") , emit: fusions
@ -23,7 +28,12 @@ process ARRIBA {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def blacklist = (args.contains('-b')) ? '' : '-f blacklist'
def blacklist = blacklist ? "-b $blacklist" : "-f blacklist"
def known_fusions = known_fusions ? "-k $known_fusions" : ""
def structural_variants = structural_variants ? "-d $structual_variants" : ""
def tags = tags ? "-t $tags" : ""
def protein_domains = protein_domains ? "-p $protein_domains" : ""
"""
arriba \\
-x $bam \\
@ -32,6 +42,10 @@ process ARRIBA {
-o ${prefix}.fusions.tsv \\
-O ${prefix}.fusions.discarded.tsv \\
$blacklist \\
$known_fusions \\
$structural_variants \\
$tags \\
$protein_domains \\
$args
cat <<-END_VERSIONS > versions.yml
@ -39,4 +53,14 @@ process ARRIBA {
arriba: \$(arriba -h | grep 'Version:' 2>&1 | sed 's/Version:\s//')
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
echo stub > ${prefix}.fusions.tsv
echo stub > ${prefix}.fusions.discarded.tsv
echo "${task.process}:" > versions.yml
echo ' arriba: 2.2.1' >> versions.yml
"""
}

22
modules/arriba/meta.yml
View file

@ -30,6 +30,26 @@ input:
type: file
description: Annotation GTF file
pattern: "*.{gtf}"
- blacklist:
type: file
description: Blacklist file
pattern: "*.{tsv}"
- known_fusions:
type: file
description: Known fusions file
pattern: "*.{tsv}"
- structural_variants:
type: file
description: Structural variants file
pattern: "*.{tsv}"
- tags:
type: file
description: Tags file
pattern: "*.{tsv}"
- protein_domains:
type: file
description: Protein domains file
pattern: "*.{gff3}"
output:
- meta:
@ -51,4 +71,4 @@ output:
pattern: "*.{fusions.discarded.tsv}"
authors:
- "@praveenraj2018"
- "@praveenraj2018,@rannick"

16
modules/bamtools/split/main.nf
View file

@ -2,10 +2,10 @@ process BAMTOOLS_SPLIT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::bamtools=2.5.1" : null)
conda (params.enable_conda ? "bioconda::bamtools=2.5.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/bamtools:2.5.1--h9a82719_9' :
'quay.io/biocontainers/bamtools:2.5.1--h9a82719_9' }"
'https://depot.galaxyproject.org/singularity/bamtools:2.5.2--hd03093a_0' :
'quay.io/biocontainers/bamtools:2.5.2--hd03093a_0' }"
input:
tuple val(meta), path(bam)
@ -20,11 +20,15 @@ process BAMTOOLS_SPLIT {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def input_list = bam.collect{"-in $it"}.join(' ')
"""
bamtools \\
split \\
-in $bam \\
$args
merge \\
$input_list \\
| bamtools \\
split \\
-stub $prefix \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

3
modules/bamtools/split/meta.yml
View file

@ -23,7 +23,7 @@ input:
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: A BAM file to split
description: A list of one or more BAM files to merge and then split
pattern: "*.bam"
output:
@ -43,3 +43,4 @@ output:
authors:
- "@sguizard"
- "@matthdsm"

6
modules/bbmap/align/main.nf
View file

@ -2,10 +2,10 @@ process BBMAP_ALIGN {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::bbmap=38.92 bioconda::samtools=1.13 pigz=2.6" : null)
conda (params.enable_conda ? "bioconda::bbmap=38.92 bioconda::samtools=1.15.1 pigz=2.6" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:f5f55fc5623bb7b3f725e8d2f86bedacfd879510-0' :
'quay.io/biocontainers/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:f5f55fc5623bb7b3f725e8d2f86bedacfd879510-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:2fee0e0facec1dfe32a1ee4aa516aef7d0296ebf-0' :
'quay.io/biocontainers/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:2fee0e0facec1dfe32a1ee4aa516aef7d0296ebf-0' }"
input:
tuple val(meta), path(fastq)

6
modules/bbmap/pileup/main.nf
View file

@ -2,10 +2,10 @@ process BBMAP_PILEUP {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::bbmap=38.92 bioconda::samtools=1.13 pigz=2.6" : null)
conda (params.enable_conda ? "bioconda::bbmap=38.92 bioconda::samtools=1.15.1 pigz=2.6" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:f5f55fc5623bb7b3f725e8d2f86bedacfd879510-0' :
'quay.io/biocontainers/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:f5f55fc5623bb7b3f725e8d2f86bedacfd879510-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:2fee0e0facec1dfe32a1ee4aa516aef7d0296ebf-0' :
'quay.io/biocontainers/mulled-v2-008daec56b7aaf3f162d7866758142b9f889d690:2fee0e0facec1dfe32a1ee4aa516aef7d0296ebf-0' }"
input:
tuple val(meta), path(bam)

61
modules/bcftools/roh/main.nf Normal file
View file

@ -0,0 +1,61 @@
process BCFTOOLS_ROH {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::bcftools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/bcftools:1.15.1--h0ea216a_0':
'quay.io/biocontainers/bcftools:1.15.1--h0ea216a_0' }"
input:
tuple val(meta), path(vcf), path(tbi)
path af_file
path genetic_map
path regions_file
path samples_file
path targets_file
output:
tuple val(meta), path("*.roh"), emit: roh
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 af_read = af_file ? "--AF-file ${af_file}" : ''
def gen_map = genetic_map ? "--genetic-map ${genetic_map}" : ''
def reg_file = regions_file ? "--regions-file ${regions_file}" : ''
def samp_file = samples_file ? "--samples-file ${samples_file}" : ''
def targ_file = targets_file ? "--targets-file ${targets_file}" : ''
"""
bcftools \\
roh \\
$args \\
$af_read \\
$gen_map \\
$reg_file \\
$samp_file \\
$targ_file \\
-o ${prefix}.roh \\
$vcf
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.roh
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bcftools: \$(bcftools --version 2>&1 | head -n1 | sed 's/^.*bcftools //; s/ .*\$//')
END_VERSIONS
"""
}

55
modules/bcftools/roh/meta.yml Normal file
View file

@ -0,0 +1,55 @@
name: "bcftools_roh"
description: A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered.
keywords:
- roh
tools:
- "roh":
description: "A program for detecting runs of homo/autozygosity. Only bi-allelic sites are considered."
homepage: https://www.htslib.org/
documentation: http://www.htslib.org/doc/bcftools.html
doi: 10.1093/bioinformatics/btp352
licence: ["MIT"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- vcf:
type: file
description: VCF file
pattern: "*.{vcf,.vcf.gz}"
- af_file:
type: file
description: "Read allele frequencies from a tab-delimited file containing the columns: CHROM\tPOS\tREF,ALT\tAF."
- genetic_map:
type: file
description: "Genetic map in the format required also by IMPUTE2."
- regions_file:
type: file
description: "Regions can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
- samples_file:
type: file
description: "File of sample names to include or exclude if prefixed with '^'."
- targets_file:
type: file
description: "Targets can be specified either on command line or in a VCF, BED, or tab-delimited file (the default)."
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"
- roh:
type: file
description: Contains site-specific and/or per-region runs of homo/autozygosity calls.
pattern: "*.{roh}"
authors:
- "@ramprasadn"

2
modules/bclconvert/.gitignore vendored Normal file
View file

@ -0,0 +1,2 @@
bcl-convert
*.rpm

15
modules/bclconvert/Dockerfile Normal file
View file

@ -0,0 +1,15 @@
# Dockerfile to create container with bcl-convert
# Push to nfcore/bclconvert:<VER>
FROM debian:bullseye-slim
LABEL authors="Matthias De Smet <matthias.desmet@ugent.be>" \
description="Docker image containing bcl-convert"
# Disclaimer: this container is not provided nor supported by Illumina
# 'ps' command is need by some nextflow executions to collect system stats
# Install procps and clean apt cache
RUN apt-get update \
&& apt-get install -y \
procps \
&& apt-get clean -y && rm -rf /var/lib/apt/lists/*
COPY bcl-convert /usr/local/bin/bcl-convert
RUN chmod +x /usr/local/bin/bcl-convert

30
modules/bclconvert/LICENSE Normal file
View file

@ -0,0 +1,30 @@
ILLUMINA END-USER SOFTWARE LICENSE AGREEMENT
IMPORTANT-READ CAREFULLY. THIS IS A LICENSE AGREEMENT THAT YOU ARE REQUIRED TO ACCEPT BEFORE, DOWNLOADING, INSTALLING AND USING ANY SOFTWARE MADE AVAILABLE FROM THE ILLUMINA SUPPORT CENTER (https://support.illumina.com).
CAREFULLY READ ALL THE TERMS AND CONDITIONS OF THIS LICENSE AGREEMENT BEFORE PROCEEDING WITH DOWNLOADING, INSTALLING, AND/OR USING THE SOFTWARE. YOU ARE NOT PERMITTED TO DOWNLOAD, INSTALL, AND/OR USE THE SOFTWARE UNTIL YOU HAVE AGREED TO BE BOUND BY ALL OF THE TERMS AND CONDITIONS OF THIS LICENSE AGREEMENT. YOU REPRESENT AND WARRANT THAT YOU ARE DULY AUTHORIZED TO ACCEPT THE TERMS AND CONDITIONS OF THIS LICENSE AGREEMENT ON BEHALF OF YOUR EMPLOYER.
Software made available through the Illumina Support Center is licensed, not sold, to you. Your license to each software program made available through the Illumina Support Center is subject to your prior acceptance of either this Illumina End-User Software License Agreement (“Agreement”), or a custom end user license agreement (“Custom EULA”), if one is provided with the software. Any software that is subject to this Agreement is referred to herein as the “Software.” By accepting this Agreement, you agree the terms and conditions of this Agreement will apply to and govern any and all of your downloads, installations, and uses of each Illumina software program made available through the Illumina Support Center, except that your download, installation, and use of any software provided with a Custom EULA will be governed by the terms and conditions of the Custom EULA.
This Agreement is made and entered into by and between Illumina, Inc., a Delaware corporation, having offices at 5200 Illumina Way, San Diego, CA 92122 (“Illumina”) and you as the end-user of the Software (hereinafter, “Licensee” or “you”). All software, firmware, and associated media, printed materials, and online and electronic documentation, including any updates or upgrades thereof, made available through the Illumina Support Center (collectively, “Software”) provided to Licensee are for use solely by Licensee and the provisions herein WILL apply with respect to such Software.
License Grant. Subject to the terms and conditions of this Agreement, Illumina grants to Licensee, under the following terms and conditions, a personal, non-exclusive, revocable, non-transferable, non-sublicensable license, for its internal end-use purposes only, in the ordinary course of Licensee’s business to use the Software in executable object code form only, solely at the Licensee’s facility to, install and use the Software on a single computer accessible only by Licensee (and not on any public network or server), where the single computer is owned, leased, or otherwise substantially controlled by Licensee, for the purpose of processing and analyzing data generated from an Illumina genetic sequencing instrument owned and operated solely by Licensee (the “Product”). In the case of Software provided by Illumina in non-compiled form, Illumina grants Licensee a personal, non-exclusive, non-sublicenseable, restricted right to compile, install, and use one copy of the Software solely for processing and analyzing data generated from the Product.
License Restrictions. Except as expressly permitted in Section 1, Licensee may not make, have made, import, use, copy, reproduce, distribute, display, publish, sell, re-sell, lease, or sub-license the Software, in whole or in part, except as expressly provided for in this Agreement. Licensee may not modify, improve, translate, reverse engineer, decompile, disassemble, or create derivative works of the Software or otherwise attempt to (a) defeat, avoid, by-pass, remove, deactivate, or otherwise circumvent any software protection mechanisms in the Software including, without limitation, any such mechanism used to restrict or control the functionality of the Software, or (b) derive the source code or the underlying ideas, algorithms, structure, or organization form of the Software. Licensee will not allow, at any time, including during and after the term of the license, the Software or any portions or copies thereof in any form to become available to any third parties. Licensee may use the Software solely with genomic data that is generated using the Product; Licensee may not use the Software with any data generated from other products or instruments. Licensee may not use the Software to perform any data analysis services for any third party.
Ownership. The Software is protected by United States and international intellectual property laws. All right, title, and interest in and to the Software (including associated intellectual property rights) are and will remain vested in Illumina or Illumina’s affiliated companies or licensors. Licensee acknowledges that no rights, license or interest to any Illumina trademarks are granted hereunder. Licensee acknowledges that unauthorized reproduction or distribution of the Software, or any portion of it, may result in severe civil and criminal penalties. Illumina reserves all rights in and to the Software not expressly granted to Licensee under this Agreement.
Upgrades/Updates. Illumina may, at its sole discretion, provide updates or upgrades to the Software. In that case, Licensee WILL have the same rights and obligations under such updates or upgrades as it has for the versions of the Software initially provided to Licensee hereunder. Licensee recognizes that Illumina is not obligated to provide any upgrades or updates to, or support for, the Software.
Data Integrity/Loss. Licensee is responsible for the integrity and availability, including preventing the loss of data that Licensee generates, uses, analyzes, manages, or stores in connection with or through its use of the Software, including without limitation, investigating and implementing industry appropriate policies and procedures regarding the provision of access to Licensee’s data, monitoring access and use of Licensee’s data, conducting routine backups and archiving of Licensee’s data, and ensuring the adequacy of anti-virus software. Accordingly, Licensee agrees that Illumina is not responsible for any inability to access, loss or corruption of data as a result of Licensee’s use of the Software, and Illumina has no liability to Licensee in connection with such inability to access, loss or corruption of data.
Term of License. This Agreement will be in effect from the time Licensee expressly accepts the terms and conditions of this license, or otherwise installs the Software, thereby accepting the terms and conditions contained herein, and will remain in effect until terminated. This license will otherwise terminate upon the conditions set forth in this Agreement, if revoked by Illumina, or if Licensee fails to comply with any term or condition of this Agreement including failure to pay any applicable license fee. Licensee agrees upon termination of this Agreement for any reason to immediately discontinue use of and un-install the Software and destroy all copies of the Software in its possession and/or under its control, and return or destroy, at Illumina’s option, any compact disks, floppy disks or other media provided by Illumina storing the Software thereon (together with any authorized copies thereof), as well as any documentation associated therewith
Limited Warranty. Illumina warrants that, for a period of 6 months from the date of download or installation of the Software by Licensee, the Software will perform in all material respects in accordance with the accompanying documentation available on the Illumina Support Center. EXCEPT AND TO THE EXTENT EXPRESSLY PROVIDED IN THE FOREGOING, AND TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, THE SOFTWARE IS PROVIDED “AS IS” AND ILLUMINA EXPRESSLY DISCLAIMS ALL WARRANTIES AND CONDITIONS REGARDING THE SOFTWARE AND RESULTS GENERATED BY THE SOFTWARE, INCLUDING WITHOUT LIMITATION, TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, ALL OTHER EXPRESS OR IMPLIED WARRANTIES OR CONDITIONS OF MERCHANTABLE QUALITY, NON-INFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE, AND THOSE ARISING BY STATUTE OR OTHERWISE IN LAW OR FROM A COURSE OF DEALING OR USAGE OF TRADE. ILLUMINA DOES NOT WARRANT THAT THE FUNCTIONS CONTAINED IN THE SOFTWARE WILL MEET LICENSEE"S REQUIREMENTS, OR THAT THE OPERATION OF THE SOFTWARE WILL BE ERROR FREE OR UNINTERRUPTED.
Limitation of Liability.
(a) ILLUMINA’S ENTIRE LIABILITY AND LICENSEE"S EXCLUSIVE REMEDY UNDER THE LIMITED WARRANTY PROVISION OF SECTION 7 ABOVE WILL BE, AT ILLUMINA’S OPTION, EITHER (i) RETURN OF THE PRICE PAID FOR THE SOFTWARE, OR (ii) REPAIR OR REPLACEMENT OF THE PORTIONS OF THE SOFTWARE THAT DO NOT COMPLY WITH ILLUMINA’S LIMITED WARRANTY. THIS LIMITED WARRANTY IS VOID AND ILLUMINA WILL HAVE NO LIABILITY AT ALL IF FAILURE OF THE SOFTWARE TO COMPLY WITH ILLUMINA LIMITED WARRANTY HAS RESULTED FROM: (w) FAILURE TO USE THE SOFTWARE IN ACCORDANCE WITH ILLUMINA’S THEN CURRENT USER MANUAL OR THIS AGREEMENT; (x) ACCIDENT, ABUSE, OR MISAPPLICATION; (y) PRODUCTS OR EQUIPMENT NOT SPECIFIED BY ILLUMINA AS BEING COMPATIBLE WITH THE SOFTWARE; OR (z) IF LICENSEE HAS NOT NOTIFIED ILLUMINA IN WRITING OF THE DEFECT WITHIN THE ABOVE WARRANTY PERIOD.
(b) TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT WILL ILLUMINA BE LIABLE UNDER ANY THEORY OF CONTRACT, TORT, STRICT LIABILITY OR OTHER LEGAL OR EQUITABLE THEORY FOR ANY PERSONAL INJURY OR ANY INDIRECT, CONSEQUENTIAL, OR INCIDENTAL DAMAGES, EVEN IF ILLUMINA HAS BEEN ADVISED OF THE POSSIBILITY THEREOF INCLUDING, WITHOUT LIMITATION, LOST PROFITS, LOST DATA, INTERRUPTION OF BUSINESS, LOST BUSINESS REVENUE, OTHER ECONOMIC LOSS, OR ANY LOSS OF RECORDED DATA ARISING OUT OF THE USE OF OR INABILITY TO USE THE SOFTWARE. EXCEPT AND TO THE EXTENT EXPRESSLY PROVIDED IN SECTION 7 AND 8(a) ABOVE OR AS OTHERWISE PERMITTED BY LAW, IN NO EVENT WILL ILLUMINA’S TOTAL LIABILITY TO LICENSEE FOR ALL DAMAGES (OTHER THAN AS MAY BE REQUIRED BY APPLICABLE LAW IN CASES INVOLVING PERSONAL INJURY) EXCEED THE AMOUNT OF $500 USD. THE FOREGOING LIMITATIONS WILL APPLY EVEN IF THE ABOVE STATED REMEDY FAILS OF ITS ESSENTIAL PURPOSE.
Survival. The limitations of liability and ownership rights of Illumina contained herein and Licensee’s obligations following termination of this Agreement WILL survive the termination of this Agreement for any reason.
Research Use Only. The Software is labeled with a For Research Use Only or similar labeling statement and the performance characteristics of the Software have not been established and the Software is not for use in diagnostic procedures. Licensee acknowledges and agrees that (i) the Software has not been approved, cleared, or licensed by the United States Food and Drug Administration or any other regulatory entity whether foreign or domestic for any specific intended use, whether research, commercial, diagnostic, or otherwise, and (ii) Licensee must ensure it has any regulatory approvals that are necessary for Licensee’s intended uses of the Software. Licensee will comply with all applicable laws and regulations when using and maintaining the Software.
General. Licensee may not sublicense, assign, share, pledge, rent or transfer any of its rights under this Agreement in relation to the Software or any portion thereof including documentation. Illumina reserves the right to change this Agreement at any time. When Illumina makes any changes, Illumina will provide the updated Agreement, or a link to it, on Illumina’s website (www.illumina.com) and such updated Agreement WILL become effective immediately. Licensee’s continued access to or use of the Software represents Licensee’s agreement to any revised Agreement. If one or more provisions of this Agreement are found to be invalid or unenforceable, this Agreement WILL not be rendered inoperative but the remaining provisions WILL continue in full force and effect. This Agreement constitutes the entire agreement between the parties with respect to the subject matter of this Agreement and merges all prior communications except that a “hard-copy” form of licensing agreement relating to the Software previously agreed to in writing by Illumina and Licensee WILL supersede and govern in the event of any conflicting provisions.
Governing Law. This Agreement WILL be governed by and construed in accordance with the laws of the state of California, USA, without regard to its conflicts of laws principles, and independent of where a suit or action hereunder may be filed.
U.S. Government End Users. If Licensee is a branch agency or instrumentality of the United States Government, the following provision applies. The Software is a “commercial item” as that term is defined at 48 C.F.R. 2.101, consisting of “commercial computer software” and “commercial computer software documentation,” as such terms are used in 48 C.F.R. 12.212 or 48 C.F.R. 227.7202 (as applicable). Consistent with 48 C.F.R. 12.212 and 48 C.F.R. 227.7202-1 through 227.7202-4, all United States Government end users acquire the Software with only those rights set forth herein.
Contact. Any questions regarding legal rights, duties, obligations, or restrictions associated with the software hereunder should be directed to Illumina, Inc., 5200 Illumina Way, San Diego, CA 92122, Attention: Legal Department, Phone: (858) 202-4500, Fax: (858) 202-4599, web site: www.illumina.com <http://www.illumina.com>.
Third Party Components. The Software may include third party software (“Third Party Programs”). Some of the Third Party Programs are available under open source or free software licenses. The License Agreement accompanying the Licensed Software does not alter any rights or obligations Licensee may have under those open source or free software licenses. The licenses that govern the terms and conditions of use of the Third Party Programs included in the Licensed Software are provided in the READ ME provided with the Software. The READ ME also contains copyright statements for the various open source software components (or portions thereof) that are distributed with the Licensed Software.
END OF END-USER SOFTWARE LICENSE AGREEMENT.

17
modules/bclconvert/README.md Normal file
View file

@ -0,0 +1,17 @@
# Updating the docker container and making a new module release
bcl-convert is a commercial tool from Illumina. The container provided for the bcl-convert nf-core module is not provided nor supported by Illumina. Updating the bcl-convert versions in the container and pushing the update to Dockerhub needs to be done manually.
1. Navigate to the appropriate download page. - [BCL Convert](https://support.illumina.com/sequencing/sequencing_software/bcl-convert/downloads.html): download the rpm of the desired bcl-convert version with `curl` or `wget`.
2. Unpack the RPM package using `rpm2cpio bcl-convert-*.rpm | cpio -i --make-directories`. Place the executable located in `<unpack_dir>/usr/bin/bcl-convert` in the same folder where the Dockerfile lies.
3. Create and test the container:
```bash
docker build . -t nfcore/bclconvert:<VERSION>
```
4. Access rights are needed to push the container to the Dockerhub nfcore organization, please ask a core team member to do so.
```bash
docker push nfcore/bclconvert:<VERSION>
```

81
modules/bclconvert/main.nf Normal file
View file

@ -0,0 +1,81 @@
process BCLCONVERT {
tag '$samplesheet'
label 'process_high'
if (params.enable_conda) {
exit 1, "Conda environments cannot be used when using bcl-convert. Please use docker or singularity containers."
}
container "nfcore/bclconvert:3.9.3"
input:
path samplesheet
path run_dir
output:
path "*.fastq.gz" ,emit: fastq
path "Reports/*.{csv,xml,bin}" ,emit: reports
path "Logs/*.{log,txt}" ,emit: logs
path "InterOp/*.bin" ,emit: interop
path "versions.yml" ,emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
"""
bcl-convert \
$args \\
--output-directory . \\
--bcl-input-directory ${run_dir} \\
--sample-sheet ${samplesheet} \\
--bcl-num-parallel-tiles ${task.cpus}
mkdir InterOp
cp ${run_dir}/InterOp/*.bin InterOp/
mv Reports/*.bin InterOp/
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bclconvert: \$(bcl-convert -V 2>&1 | head -n 1 | sed 's/^.*Version //')
END_VERSIONS
"""
stub:
"""
echo "sample1_S1_L001_R1_001" > sample1_S1_L001_R1_001.fastq.gz
echo "sample1_S1_L001_R2_001" > sample1_S1_L001_R2_001.fastq.gz
echo "sample1_S1_L002_R1_001" > sample1_S1_L002_R1_001.fastq.gz
echo "sample1_S1_L002_R2_001" > sample1_S1_L002_R2_001.fastq.gz
echo "sample2_S2_L001_R1_001" > sample2_S2_L001_R1_001.fastq.gz
echo "sample2_S2_L001_R2_001" > sample2_S2_L001_R2_001.fastq.gz
echo "sample2_S2_L002_R1_001" > sample2_S2_L002_R1_001.fastq.gz
echo "sample2_S2_L002_R2_001" > sample2_S2_L002_R2_001.fastq.gz
mkdir Reports
echo "Adapter_Metrics" > Reports/Adapter_Metrics.csv
echo "Demultiplex_Stats" > Reports/Demultiplex_Stats.csv
echo "fastq_list" > Reports/fastq_list.csv
echo "Index_Hopping_Counts" > Reports/Index_Hopping_Counts.csv
echo "IndexMetricsOut" > Reports/IndexMetricsOut.bin
echo "Quality_Metrics" > Reports/Quality_Metrics.csv
echo "RunInfo" > Reports/RunInfo.xml
echo "SampleSheet" > Reports/SampleSheet.csv
echo "Top_Unknown_Barcodes" > Reports/Top_Unknown_Barcodes.csv
mkdir Logs
echo "Errors" > Logs/Errors.log
echo "FastqComplete" > Logs/FastqComplete.txt
echo "Info" > Logs/Info.log
echo "Warnings" > Logs/Warnings.log
mkdir InterOp/
echo "InterOp" > InterOp/InterOp.bin
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bclconvert: \$(bcl-convert -V 2>&1 | head -n 1 | sed 's/^.*Version //')
END_VERSIONS
"""
}

45
modules/bclconvert/meta.yml Normal file
View file

@ -0,0 +1,45 @@
name: "bclconvert"
description: Demultiplex Illumina BCL files
keywords:
- demultiplex
- illumina
- fastq
tools:
- "bclconvert":
description: "Demultiplex Illumina BCL files"
homepage: "https://support.illumina.com/sequencing/sequencing_software/bcl-convert.html"
documentation: "https://support-docs.illumina.com/SW/BCL_Convert/Content/SW/FrontPages/BCL_Convert.htm"
licence: "ILLUMINA"
input:
- samplesheet:
type: file
description: "Input samplesheet"
pattern: "*.{csv}"
- run_dir:
type: directory
description: "Input run directory containing RunInfo.xml and BCL data"
output:
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- fastq:
type: file
description: Demultiplexed FASTQ files
pattern: "*.{fastq.gz}"
- reports:
type: file
description: Demultiplexing Reports
pattern: "Reports/*.{csv,xml}"
- logs:
type: file
description: Log files
pattern: "Logs/*.{log,txt}"
- interop:
type: file
description: Interop files
pattern: "Interop/*.{bin}"
authors:
- "@matthdsm"

38
modules/bedtools/split/main.nf Normal file
View file

@ -0,0 +1,38 @@
process BEDTOOLS_SPLIT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::bedtools=2.30.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/bedtools:2.30.0--h468198e_3':
'quay.io/biocontainers/bedtools:2.30.0--h7d7f7ad_2' }"
input:
tuple val(meta), path(bed)
val(number_of_files)
output:
tuple val(meta), path("*.bed"), emit: beds
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}"
"""
bedtools \\
split \\
$args \\
-i $bed \\
-p $prefix \\
-n $number_of_files
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bedtools: \$(bedtools --version | sed -e "s/bedtools v//g")
END_VERSIONS
"""
}

41
modules/bedtools/split/meta.yml Normal file
View file

@ -0,0 +1,41 @@
name: "bedtools_split"
description: Split BED files into several smaller BED files
keywords:
- sort
tools:
- "bedtools":
description: "A powerful toolset for genome arithmetic"
documentation: "https://bedtools.readthedocs.io/en/latest/content/tools/sort.html"
licence: "['MIT', 'GPL v2']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: BED file
pattern: "*.bed"
- bed:
type: value
description: The number of files to split the BED into
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"
- beds:
type: file
description: list of split BED files
pattern: "*.bed"
authors:
- "@nvnieuwk"

6
modules/biobambam/bammarkduplicates2/main.nf
View file

@ -2,10 +2,8 @@ process BIOBAMBAM_BAMMARKDUPLICATES2 {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::biobambam=2.0.182" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/biobambam:2.0.182--h7d875b9_0':
'quay.io/biocontainers/biobambam:2.0.182--h7d875b9_0' }"
conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/biobambam:2.0.183--h9f5acd7_1' : 'quay.io/biocontainers/biobambam:2.0.183--h9f5acd7_1'}"
input:
tuple val(meta), path(bam)

38
modules/biobambam/bammerge/main.nf Normal file
View file

@ -0,0 +1,38 @@
process BIOBAMBAM_BAMMERGE {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/biobambam:2.0.183--h9f5acd7_1':
'quay.io/biocontainers/biobambam:2.0.183--h9f5acd7_1' }"
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("${prefix}.bam") ,emit: bam
tuple val(meta), path("*.bai") ,optional:true, emit: bam_index
tuple val(meta), path("*.md5") ,optional:true, emit: checksum
path "versions.yml" ,emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
def input_string = bam.join(" I=")
"""
bammerge \\
I=${input_string} \\
$args \\
> ${prefix}.bam
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bammerge: \$( bammerge --version |& sed '1!d; s/.*version //; s/.\$//' )
END_VERSIONS
"""
}

46
modules/biobambam/bammerge/meta.yml Normal file
View file

@ -0,0 +1,46 @@
name: biobambam_bammerge
description: Merge a list of sorted bam files
keywords:
- merge
- bam
tools:
- biobambam:
description: |
biobambam is a set of tools for early stage alignment file processing.
homepage: https://gitlab.com/german.tischler/biobambam2
documentation: https://gitlab.com/german.tischler/biobambam2/-/blob/master/README.md
doi: 10.1186/1751-0473-9-13
licence: ["GPL v3"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: List containing 1 or more bam files
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: Merged BAM file
pattern: "*.bam"
- bam_index:
type: file
description: BAM index file
pattern: "*"
- checksum:
type: file
description: Checksum file
pattern: "*"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@matthdsm"

46
modules/biobambam/bamsormadup/main.nf Normal file
View file

@ -0,0 +1,46 @@
process BIOBAMBAM_BAMSORMADUP {
tag "$meta.id"
label "process_medium"
conda (params.enable_conda ? "bioconda::biobambam=2.0.183" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? 'https://depot.galaxyproject.org/singularity/biobambam:2.0.183--h9f5acd7_1' : 'quay.io/biocontainers/biobambam:2.0.183--h9f5acd7_1'}"
input:
tuple val(meta), path(bams)
path(fasta)
output:
tuple val(meta), path("*.{bam,cram}") ,emit: bam
tuple val(meta), path("*.bam.bai") ,optional:true, emit: bam_index
tuple val(meta), path("*.metrics.txt") ,emit: metrics
path "versions.yml" ,emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def suffix = args.contains("outputformat=cram") ? "cram" : "bam"
def input_string = bams.join(" I=")
if (args.contains("outputformat=cram") && reference == null) error "Reference required for CRAM output."
"""
bamcat \\
I=${input_string} \\
level=0 \\
| bamsormadup \\
$args \\
M=${prefix}.metrics.txt \\
tmpfile=$prefix \\
threads=$task.cpus \\
> ${prefix}.${suffix}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
bamcat: \$(echo \$(bamsormadup --version 2>&1) | sed 's/^This is biobambam2 version //; s/..biobambam2 is .*\$//' )
bamsormadup: \$(echo \$(bamsormadup --version 2>&1) | sed 's/^This is biobambam2 version //; s/..biobambam2 is .*\$//' )
END_VERSIONS
"""
}

52
modules/biobambam/bamsormadup/meta.yml Normal file
View file

@ -0,0 +1,52 @@
name: biobambam_bamsormadup
description: Parallel sorting and duplicate marking
keywords:
- markduplicates
- sort
- bam
- cram
tools:
- biobambam:
description: |
biobambam is a set of tools for early stage alignment file processing.
homepage: https://gitlab.com/german.tischler/biobambam2
documentation: https://gitlab.com/german.tischler/biobambam2/-/blob/master/README.md
doi: 10.1186/1751-0473-9-13
licence: ["GPL v3"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bams:
type: file
description: List containing 1 or more bam files
- fasta:
type: file
description: Reference genome in FASTA format (optional)
pattern: "*.{fa,fasta}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: BAM/CRAM file with duplicate reads marked/removed
pattern: "*.{bam,cram}"
- bam_index:
type: file
description: BAM index file
pattern: "*.{bai}"
- metrics:
type: file
description: Duplicate metrics file generated by biobambam
pattern: "*.{metrics.txt}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@matthdsm"

6
modules/bowtie/align/main.nf
View file

@ -2,10 +2,10 @@ process BOWTIE_ALIGN {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? 'bioconda::bowtie=1.3.0 bioconda::samtools=1.11' : null)
conda (params.enable_conda ? 'bioconda::bowtie=1.3.0 bioconda::samtools=1.15.1' : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:9e14e16c284d6860574cf5b624bbc44c793cb024-0' :
'quay.io/biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:9e14e16c284d6860574cf5b624bbc44c793cb024-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:676c5bcfe34af6097728fea60fb7ea83f94a4a5f-0' :
'quay.io/biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:676c5bcfe34af6097728fea60fb7ea83f94a4a5f-0' }"
input:
tuple val(meta), path(reads)

106
modules/bowtie2/align/main.nf
View file

@ -1,77 +1,71 @@
process BOWTIE2_ALIGN {
tag "$meta.id"
label 'process_high'
label "process_high"
conda (params.enable_conda ? 'bioconda::bowtie2=2.4.4 bioconda::samtools=1.14 conda-forge::pigz=2.6' : null)
container "${ 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' }"
conda (params.enable_conda ? "bioconda::bowtie2=2.4.4 bioconda::samtools=1.15.1 conda-forge::pigz=2.6" : null)
container "${ workflow.containerEngine == "singularity" && !task.ext.singularity_pull_docker_container ?
"https://depot.galaxyproject.org/singularity/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" :
"quay.io/biocontainers/mulled-v2-ac74a7f02cebcfcc07d8e8d1d750af9c83b4d45a:1744f68fe955578c63054b55309e05b41c37a80d-0" }"
input:
tuple val(meta), path(reads)
path index
val save_unaligned
val sort_bam
output:
tuple val(meta), path('*.bam') , emit: bam
tuple val(meta), path('*.log') , emit: log
tuple val(meta), path('*fastq.gz'), emit: fastq, optional:true
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*.log") , emit: log
tuple val(meta), path("*fastq.gz"), emit: fastq, optional:true
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
def args = task.ext.args ?: ""
def args2 = task.ext.args2 ?: ""
def prefix = task.ext.prefix ?: "${meta.id}"
def unaligned = ""
def reads_args = ""
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
"""
unaligned = save_unaligned ? "--un-gz ${prefix}.unmapped.fastq.gz" : ""
reads_args = "-U ${reads}"
} 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
"""
unaligned = save_unaligned ? "--un-conc-gz ${prefix}.unmapped.fastq.gz" : ""
reads_args = "-1 ${reads[0]} -2 ${reads[1]}"
}
def samtools_command = sort_bam ? 'sort' : 'view'
"""
INDEX=`find -L ./ -name "*.rev.1.bt2" | sed "s/.rev.1.bt2//"`
[ -z "\$INDEX" ] && INDEX=`find -L ./ -name "*.rev.1.bt2l" | sed "s/.rev.1.bt2l//"`
[ -z "\$INDEX" ] && echo "Bowtie2 index files not found" 1>&2 && exit 1
bowtie2 \\
-x \$INDEX \\
$reads_args \\
--threads $task.cpus \\
$unaligned \\
$args \\
2> ${prefix}.bowtie2.log \\
| samtools $samtools_command $args2 --threads $task.cpus -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
"""
}

9
modules/bowtie2/align/meta.yml
View file

@ -29,6 +29,15 @@ input:
type: file
description: Bowtie2 genome index files
pattern: "*.ebwt"
- save_unaligned:
type: boolean
description: |
Save reads that do not map to the reference (true) or discard them (false)
(default: false)
- sort_bam:
type: boolean
description: use samtools sort (true) or samtools view (false)
pattern: "true or false"
output:
- bam:
type: file

84
modules/busco/main.nf Normal file
View file

@ -0,0 +1,84 @@
process BUSCO {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::busco=5.3.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/busco:5.3.2--pyhdfd78af_0':
'quay.io/biocontainers/busco:5.3.2--pyhdfd78af_0' }"
input:
tuple val(meta), path('tmp_input/*')
each lineage // Required: lineage to check against, "auto" enables --auto-lineage instead
path busco_lineages_path // Recommended: path to busco lineages - downloads if not set
path config_file // Optional: busco configuration file
output:
tuple val(meta), path("*-busco.batch_summary.txt"), emit: batch_summary
tuple val(meta), path("short_summary.*.txt") , emit: short_summaries_txt, optional: true
tuple val(meta), path("short_summary.*.json") , emit: short_summaries_json, optional: true
tuple val(meta), path("*-busco") , emit: busco_dir
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}-${lineage}"
def busco_config = config_file ? "--config $config_file" : ''
def busco_lineage = lineage.equals('auto') ? '--auto-lineage' : "--lineage_dataset ${lineage}"
def busco_lineage_dir = busco_lineages_path ? "--offline --download_path ${busco_lineages_path}" : ''
"""
# Nextflow changes the container --entrypoint to /bin/bash (container default entrypoint: /usr/local/env-execute)
# Check for container variable initialisation script and source it.
if [ -f "/usr/local/env-activate.sh" ]; then
set +u # Otherwise, errors out because of various unbound variables
. "/usr/local/env-activate.sh"
set -u
fi
# If the augustus config directory is not writable, then copy to writeable area
if [ ! -w "\${AUGUSTUS_CONFIG_PATH}" ]; then
# Create writable tmp directory for augustus
AUG_CONF_DIR=\$( mktemp -d -p \$PWD )
cp -r \$AUGUSTUS_CONFIG_PATH/* \$AUG_CONF_DIR
export AUGUSTUS_CONFIG_PATH=\$AUG_CONF_DIR
echo "New AUGUSTUS_CONFIG_PATH=\${AUGUSTUS_CONFIG_PATH}"
fi
# Ensure the input is uncompressed
INPUT_SEQS=input_seqs
mkdir "\$INPUT_SEQS"
cd "\$INPUT_SEQS"
for FASTA in ../tmp_input/*; do
if [ "\${FASTA##*.}" == 'gz' ]; then
gzip -cdf "\$FASTA" > \$( basename "\$FASTA" .gz )
else
ln -s "\$FASTA" .
fi
done
cd ..
busco \\
--cpu $task.cpus \\
--in "\$INPUT_SEQS" \\
--out ${prefix}-busco \\
$busco_lineage \\
$busco_lineage_dir \\
$busco_config \\
$args
# clean up
rm -rf "\$INPUT_SEQS"
# Move files to avoid staging/publishing issues
mv ${prefix}-busco/batch_summary.txt ${prefix}-busco.batch_summary.txt
mv ${prefix}-busco/*/short_summary.*.{json,txt} . || echo "Short summaries were not available: No genes were found."
cat <<-END_VERSIONS > versions.yml
"${task.process}":
busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
END_VERSIONS
"""
}

69
modules/busco/meta.yml Normal file
View file

@ -0,0 +1,69 @@
name: busco
description: Benchmarking Universal Single Copy Orthologs
keywords:
- quality control
- genome
- transcriptome
- proteome
tools:
- busco:
description: BUSCO provides measures for quantitative assessment of genome assembly, gene set, and transcriptome completeness based on evolutionarily informed expectations of gene content from near-universal single-copy orthologs selected from OrthoDB.
homepage: https://busco.ezlab.org/
documentation: https://busco.ezlab.org/busco_userguide.html
tool_dev_url: https://gitlab.com/ezlab/busco
doi: "10.1007/978-1-4939-9173-0_14"
licence: ["MIT"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- fasta:
type: file
description: Nucleic or amino acid sequence file in FASTA format.
pattern: "*.{fasta,fna,fa,fasta.gz,fna.gz,fa.gz}"
- lineage:
type: value
description: The BUSCO lineage to use, or "auto" to automatically select lineage
- busco_lineages_path:
type: directory
description: Path to local BUSCO lineages directory.
- config_file:
type: file
description: Path to BUSCO config file.
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- batch_summary:
type: file
description: Summary of all sequence files analyzed
pattern: "*-busco.batch_summary.txt"
- short_summaries_txt:
type: file
description: Short Busco summary in plain text format
pattern: "short_summary.*.txt"
- short_summaries_json:
type: file
description: Short Busco summary in JSON format
pattern: "short_summary.*.json"
- busco_dir:
type: directory
description: BUSCO lineage specific output
pattern: "*-busco"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@priyanka-surana"
- "@charles-plessy"
- "@mahesh-panchal"
- "@muffato"
- "@jvhagey"

8
modules/bwa/mem/main.nf
View file

@ -2,10 +2,10 @@ process BWA_MEM {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' }"
input:
tuple val(meta), path(reads)
@ -23,14 +23,12 @@ process BWA_MEM {
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def read_group = meta.read_group ? "-R ${meta.read_group}" : ""
def samtools_command = sort_bam ? 'sort' : 'view'
"""
INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'`
bwa mem \\
$args \\
$read_group \\
-t $task.cpus \\
\$INDEX \\
$reads \\

6
modules/bwa/sampe/main.nf
View file

@ -2,10 +2,10 @@ process BWA_SAMPE {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' }"
input:
tuple val(meta), path(reads), path(sai)

6
modules/bwa/samse/main.nf
View file

@ -2,10 +2,10 @@ process BWA_SAMSE {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::bwa=0.7.17 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:c56a3aabc8d64e52d5b9da1e8ecec2031668596d-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' :
'quay.io/biocontainers/mulled-v2-fe8faa35dbf6dc65a0f7f5d4ea12e31a79f73e40:8110a70be2bfe7f75a2ea7f2a89cda4cc7732095-0' }"
input:
tuple val(meta), path(reads), path(sai)

8
modules/bwamem2/mem/main.nf
View file

@ -2,10 +2,10 @@ process BWAMEM2_MEM {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? "bioconda::bwa-mem2=2.2.1 bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::bwa-mem2=2.2.1 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:8ee25ae85d7a2bacac3e3139db209aff3d605a18-0' :
'quay.io/biocontainers/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:8ee25ae85d7a2bacac3e3139db209aff3d605a18-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:38aed4501da19db366dc7c8d52d31d94e760cfaf-0' :
'quay.io/biocontainers/mulled-v2-e5d375990341c5aef3c9aff74f96f66f65375ef6:38aed4501da19db366dc7c8d52d31d94e760cfaf-0' }"
input:
tuple val(meta), path(reads)
@ -23,7 +23,6 @@ process BWAMEM2_MEM {
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def read_group = meta.read_group ? "-R ${meta.read_group}" : ""
def samtools_command = sort_bam ? 'sort' : 'view'
"""
INDEX=`find -L ./ -name "*.amb" | sed 's/.amb//'`
@ -31,7 +30,6 @@ process BWAMEM2_MEM {
bwa-mem2 \\
mem \\
$args \\
$read_group \\
-t $task.cpus \\
\$INDEX \\
$reads \\

4
modules/cat/fastq/main.nf
View file

@ -4,8 +4,8 @@ process CAT_FASTQ {
conda (params.enable_conda ? "conda-forge::sed=4.7" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://containers.biocontainers.pro/s3/SingImgsRepo/biocontainers/v1.2.0_cv1/biocontainers_v1.2.0_cv1.img' :
'biocontainers/biocontainers:v1.2.0_cv1' }"
'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
'ubuntu:20.04' }"
input:
tuple val(meta), path(reads, stageAs: "input*/*")

10
modules/centrifuge/main.nf → modules/centrifuge/centrifuge/main.nf
View file

@ -1,4 +1,4 @@
process CENTRIFUGE {
process CENTRIFUGE_CENTRIFUGE {
tag "$meta.id"
label 'process_high'
@ -17,7 +17,6 @@ process CENTRIFUGE {
output:
tuple val(meta), path('*report.txt') , emit: report
tuple val(meta), path('*results.txt') , emit: results
tuple val(meta), path('*kreport.txt') , emit: kreport
tuple val(meta), path('*.sam') , optional: true, emit: sam
tuple val(meta), path('*.mapped.fastq{,.1,.2}.gz') , optional: true, emit: fastq_mapped
tuple val(meta), path('*.unmapped.fastq{,.1,.2}.gz') , optional: true, emit: fastq_unmapped
@ -30,7 +29,6 @@ process CENTRIFUGE {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def paired = meta.single_end ? "-U ${reads}" : "-1 ${reads[0]} -2 ${reads[1]}"
def db_name = db.toString().replace(".tar.gz","")
def unaligned = ''
def aligned = ''
if (meta.single_end) {
@ -42,9 +40,10 @@ process CENTRIFUGE {
}
def sam_output = sam_format ? "--out-fmt 'sam'" : ''
"""
tar -xf $db
## we add "-no-name ._" to ensure silly Mac OSX metafiles files aren't included
db_name=`find -L ${db} -name "*.1.cf" -not -name "._*" | sed 's/.1.cf//'`
centrifuge \\
-x $db_name \\
-x \$db_name \\
-p $task.cpus \\
$paired \\
--report-file ${prefix}.report.txt \\
@ -53,7 +52,6 @@ process CENTRIFUGE {
$aligned \\
$sam_output \\
$args
centrifuge-kreport -x $db_name ${prefix}.results.txt > ${prefix}.kreport.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":

11
modules/centrifuge/meta.yml → modules/centrifuge/centrifuge/meta.yml
View file

@ -1,4 +1,4 @@
name: centrifuge
name: centrifuge_centrifuge
description: Classifies metagenomic sequence data
keywords:
- classify
@ -25,8 +25,7 @@ input:
respectively.
- db:
type: directory
description: Centrifuge database in .tar.gz format
pattern: "*.tar.gz"
description: Path to directory containing centrifuge database files
- save_unaligned:
type: value
description: If true unmapped fastq files are saved
@ -49,12 +48,6 @@ output:
description: |
File containing classification results
pattern: "*.{results.txt}"
- kreport:
type: file
description: |
File containing kraken-style report from centrifuge
out files.
pattern: "*.{kreport.txt}"
- fastq_unmapped:
type: file
description: Unmapped fastq files

33
modules/centrifuge/kreport/main.nf Normal file
View file

@ -0,0 +1,33 @@
process CENTRIFUGE_KREPORT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::centrifuge=1.0.4_beta" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/centrifuge:1.0.4_beta--h9a82719_6':
'quay.io/biocontainers/centrifuge:1.0.4_beta--h9a82719_6' }"
input:
tuple val(meta), path(results)
path db
output:
tuple val(meta), path('*.txt') , emit: kreport
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}"
"""
db_name=`find -L ${db} -name "*.1.cf" -not -name "._*" | sed 's/.1.cf//'`
centrifuge-kreport -x \$db_name ${results} > ${prefix}.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
centrifuge: \$( centrifuge --version | sed -n 1p | sed 's/^.*centrifuge-class version //')
END_VERSIONS
"""
}

41
modules/centrifuge/kreport/meta.yml Normal file
View file

@ -0,0 +1,41 @@
name: "centrifuge_kreport"
description: Creates Kraken-style reports from centrifuge out files
keywords:
- metagenomics
tools:
- centrifuge:
description: Centrifuge is a classifier for metagenomic sequences.
homepage: https://ccb.jhu.edu/software/centrifuge/
documentation: https://ccb.jhu.edu/software/centrifuge/manual.shtml
doi: 10.1101/gr.210641.116
licence: ["GPL v3"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- results:
type: file
description: File containing the centrifuge classification results
pattern: "*.{txt}"
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"
- kreport:
type: file
description: |
File containing kraken-style report from centrifuge
out files.
pattern: "*.{txt}"
authors:
- "@sofstam"
- "@jfy133"

6
modules/chromap/chromap/main.nf
View file

@ -2,10 +2,10 @@ process CHROMAP_CHROMAP {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::chromap=0.2.1 bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::chromap=0.2.1 bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:bd74d08a359024829a7aec1638a28607bbcd8a58-0' :
'quay.io/biocontainers/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:bd74d08a359024829a7aec1638a28607bbcd8a58-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:963e4fe6a85c548a4018585660aed79780a175d3-0' :
'quay.io/biocontainers/mulled-v2-1f09f39f20b1c4ee36581dc81cc323c70e661633:963e4fe6a85c548a4018585660aed79780a175d3-0' }"
input:
tuple val(meta), path(reads)

36
modules/cnvkit/antitarget/main.nf Normal file
View file

@ -0,0 +1,36 @@
process CNVKIT_ANTITARGET {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
input:
tuple val(meta), path(targets)
output:
tuple val(meta), path("*.bed"), emit: bed
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}"
"""
cnvkit.py \\
antitarget \\
$targets \\
--output ${prefix}.antitarget.bed \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}

44
modules/cnvkit/antitarget/meta.yml Normal file
View file

@ -0,0 +1,44 @@
name: cnvkit_antitarget
description:
keywords:
- cvnkit
- antitarget
tools:
- cnvkit:
description: |
CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
tool_dev_url: "https://github.com/etal/cnvkit"
doi: 10.1371/journal.pcbi.1004873
licence: ["Apache-2.0"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- targets:
type: file
description: File containing genomic regions
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bed:
type: file
description: File containing off-target regions
pattern: "*.{bed}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@SusiJo"

46
modules/cnvkit/batch/main.nf
View file

@ -2,10 +2,10 @@ process CNVKIT_BATCH {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9' : null)
conda (params.enable_conda ? 'bioconda::cnvkit=0.9.9 bioconda::samtools=1.15.1' : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0' :
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' :
'quay.io/biocontainers/mulled-v2-780d630a9bb6a0ff2e7b6f730906fd703e40e98f:304d1c5ab610f216e77c61420ebe85f1e7c5968a-0' }"
input:
tuple val(meta), path(tumor), path(normal)
@ -18,6 +18,8 @@ process CNVKIT_BATCH {
tuple val(meta), path("*.cnn"), emit: cnn, optional: true
tuple val(meta), path("*.cnr"), emit: cnr, optional: true
tuple val(meta), path("*.cns"), emit: cns, optional: true
tuple val(meta), path("*.pdf"), emit: pdf, optional: true
tuple val(meta), path("*.png"), emit: png, optional: true
path "versions.yml" , emit: versions
when:
@ -25,21 +27,39 @@ process CNVKIT_BATCH {
script:
def args = task.ext.args ?: ''
def normal_args = normal ? "--normal $normal" : ""
def fasta_args = fasta ? "--fasta $fasta" : ""
// execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
// input pair is assumed to have same extension if both exist
def is_cram = tumor.Extension == "cram" ? true : false
def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
// do not run samtools on normal samples in tumor_only mode
def normal_exists = normal ? true: false
// tumor_only mode does not need fasta & target
// instead it requires a pre-computed reference.cnn which is built from fasta & target
def (normal_out, normal_args, fasta_args) = ["", "", ""]
if (normal_exists){
def normal_prefix = normal.BaseName
normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
normal_args = normal_prefix ? "--normal $normal_out" : ""
fasta_args = fasta ? "--fasta $fasta" : ""
}
def target_args = targets ? "--targets $targets" : ""
def reference_args = reference ? "--reference $reference" : ""
def target_args = ""
if (args.contains("--method wgs") || args.contains("-m wgs")) {
target_args = targets ? "--targets $targets" : ""
}
else {
target_args = "--targets $targets"
}
"""
if $is_cram; then
samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
if $normal_exists; then
samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
fi
fi
cnvkit.py \\
batch \\
$tumor \\
$tumor_out \\
$normal_args \\
$fasta_args \\
$reference_args \\

32
modules/cnvkit/batch/meta.yml
View file

@ -11,27 +11,6 @@ tools:
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
licence: ["Apache-2.0"]
params:
- outdir:
type: string
description: |
The pipeline's output directory. By default, the module will
output files into `$params.outdir/<SOFTWARE>`
- publish_dir_mode:
type: string
description: |
Value for the Nextflow `publishDir` mode parameter.
Available: symlink, rellink, link, copy, copyNoFollow, move.
- enable_conda:
type: boolean
description: |
Run the module with Conda using the software specified
via the `conda` directive
- singularity_pull_docker_container:
type: boolean
description: |
Instead of directly downloading Singularity images for use with Singularity,
force the workflow to pull and convert Docker containers instead.
input:
- meta:
type: map
@ -49,7 +28,7 @@ input:
- fasta:
type: file
description: |
Input reference genome fasta file
Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
- targetfile:
type: file
description: |
@ -80,6 +59,14 @@ output:
type: file
description: File containing copy number segment information
pattern: "*.{cns}"
- pdf:
type: file
description: File with plot of copy numbers or segments on chromosomes
pattern: "*.{pdf}"
- png:
type: file
description: File with plot of bin-level log2 coverages and segmentation calls
pattern: "*.{png}"
- versions:
type: file
description: File containing software versions
@ -91,3 +78,4 @@ authors:
- "@drpatelh"
- "@fbdtemme"
- "@lassefolkersen"
- "@SusiJo"

40
modules/cnvkit/reference/main.nf Normal file
View file

@ -0,0 +1,40 @@
process CNVKIT_REFERENCE {
tag "$fasta"
label 'process_low'
conda (params.enable_conda ? "bioconda::cnvkit=0.9.9" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvkit:0.9.9--pyhdfd78af_0':
'quay.io/biocontainers/cnvkit:0.9.9--pyhdfd78af_0' }"
input:
path fasta
path targets
path antitargets
output:
path "*.cnn" , emit: cnn
path "versions.yml", emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: targets.BaseName
"""
cnvkit.py \\
reference \\
--fasta $fasta \\
--targets $targets \\
--antitargets $antitargets \\
--output ${prefix}.reference.cnn \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
END_VERSIONS
"""
}

47
modules/cnvkit/reference/meta.yml Normal file
View file

@ -0,0 +1,47 @@
name: cnvkit_reference
description:
keywords:
- cnvkit
- reference
tools:
- cnvkit:
description: |
CNVkit is a Python library and command-line software toolkit to infer and visualize copy number from high-throughput DNA sequencing data.
It is designed for use with hybrid capture, including both whole-exome and custom target panels, and short-read sequencing platforms such as Illumina and Ion Torrent.
homepage: https://cnvkit.readthedocs.io/en/stable/index.html
documentation: https://cnvkit.readthedocs.io/en/stable/index.html
tool_dev_url: https://github.com/etal/cnvkit
doi: 10.1371/journal.pcbi.1004873
licence: ["Apache-2.0"]
input:
- fasta:
type: file
description: File containing reference genome
pattern: "*.{fasta}"
- targets:
type: file
description: File containing genomic regions
pattern: "*.{bed}"
- antitargets:
type: file
description: File containing off-target genomic regions
pattern: "*.{bed}"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- reference:
type: file
description: File containing a copy-number reference (required for CNV calling in tumor_only mode)
pattern: "*.{cnn}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@SusiJo"

28
modules/cnvpytor/callcnvs/main.nf
View file

@ -2,32 +2,42 @@ process CNVPYTOR_CALLCNVS {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
input:
tuple val(meta), path(pytor)
val bin_sizes
output:
tuple val(meta), path("*.tsv"), emit: cnvs
path "versions.yml" , emit: versions
tuple val(meta), path("${pytor.baseName}.pytor") , emit: pytor
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: '1000'
def prefix = task.ext.prefix ?: "${meta.id}"
def bins = bin_sizes ?: '1000'
"""
cnvpytor \\
-root $pytor \\
-call $args > ${prefix}.tsv
-call $bin_sizes
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
stub:
"""
touch ${pytor.baseName}.pytor
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
}

11
modules/cnvpytor/callcnvs/meta.yml
View file

@ -17,8 +17,11 @@ input:
e.g. [ id:'test']
- pytor:
type: file
description: cnvpytor root file
description: pytor file containing partitions of read depth histograms using mean-shift method
pattern: "*.{pytor}"
- bin_sizes:
type: string
description: list of binsizes separated by space e.g. "1000 10000" and "1000"
output:
- meta:
@ -26,10 +29,10 @@ output:
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- cnvs:
- pytor:
type: file
description: file containing identified copy numer variations
pattern: "*.{tsv}"
description: pytor files containing cnv calls
pattern: "*.{pytor}"
- versions:
type: file
description: File containing software versions

24
modules/cnvpytor/histogram/main.nf
View file

@ -2,13 +2,15 @@ process CNVPYTOR_HISTOGRAM {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
input:
tuple val(meta), path(pytor)
val bin_sizes
output:
tuple val(meta), path("${pytor.baseName}.pytor") , emit: pytor
@ -18,15 +20,25 @@ process CNVPYTOR_HISTOGRAM {
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: '1000'
def bins = bin_sizes ?: '1000'
"""
cnvpytor \\
-root $pytor \\
-his $args
-his $bins
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
stub:
"""
touch ${pytor.baseName}.pytor
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
}

4
modules/cnvpytor/histogram/meta.yml
View file

@ -22,6 +22,9 @@ input:
type: file
description: pytor file containing read depth data
pattern: "*.{pytor}"
- bin_sizes:
type: string
description: list of binsizes separated by space e.g. "1000 10000" and "1000"
output:
- meta:
@ -40,3 +43,4 @@ output:
authors:
- "@sima-r"
- "@ramprasadn"

19
modules/cnvpytor/importreaddepth/main.nf
View file

@ -2,10 +2,10 @@ process CNVPYTOR_IMPORTREADDEPTH {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
input:
tuple val(meta), path(input_file), path(index)
@ -32,7 +32,18 @@ process CNVPYTOR_IMPORTREADDEPTH {
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.pytor
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
}

1
modules/cnvpytor/importreaddepth/meta.yml
View file

@ -52,3 +52,4 @@ output:
authors:
- "@sima-r"
- "@ramprasadn"

23
modules/cnvpytor/partition/main.nf
View file

@ -2,13 +2,14 @@ process CNVPYTOR_PARTITION {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::cnvpytor=1.0" : null)
conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvpytor:1.0--py39h6a678da_2':
'quay.io/biocontainers/cnvpytor:1.0--py39h6a678da_2' }"
'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
input:
tuple val(meta), path(pytor)
val bin_sizes
output:
tuple val(meta), path("${pytor.baseName}.pytor"), emit: pytor
@ -18,15 +19,25 @@ process CNVPYTOR_PARTITION {
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: '1000'
def bins = bin_sizes ?: '1000'
"""
cnvpytor \\
-root $pytor \\
-partition $args
-partition $bins
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/^.*pyCNVnator //; s/Using.*\$//' ))
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
stub:
"""
touch ${pytor.baseName}.pytor
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
}

4
modules/cnvpytor/partition/meta.yml
View file

@ -22,6 +22,9 @@ input:
type: file
description: pytor file containing read depth data
pattern: "*.{pytor}"
- bin_sizes:
type: string
description: list of binsizes separated by space e.g. "1000 10000" and "1000"
output:
- meta:
@ -40,3 +43,4 @@ output:
authors:
- "@sima-r"
- "@ramprasadn"

60
modules/cnvpytor/view/main.nf Normal file
View file

@ -0,0 +1,60 @@
process CNVPYTOR_VIEW {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::cnvpytor=1.2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/cnvpytor:1.2.1--pyhdfd78af_0':
'quay.io/biocontainers/cnvpytor:1.2.1--pyhdfd78af_0' }"
input:
tuple val(meta), path(pytor_files)
val bin_sizes
val output_format
output:
tuple val(meta), path("*.vcf"), emit: vcf , optional: true
tuple val(meta), path("*.tsv"), emit: tsv , optional: true
tuple val(meta), path("*.xls"), emit: xls , optional: true
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def output_suffix = output_format ?: 'vcf'
def bins = bin_sizes ?: '1000'
def input = pytor_files.join(" ")
def prefix = task.ext.prefix ?: "${meta.id}"
"""
python3 <<CODE
import cnvpytor,os
binsizes = "${bins}".split(" ")
for binsize in binsizes:
file_list = "${input}".split(" ")
app = cnvpytor.Viewer(file_list, params={} )
outputfile = "{}_{}.{}".format("${prefix}",binsize.strip(),"${output_suffix}")
app.print_filename = outputfile
app.bin_size = int(binsize)
app.print_calls_file()
CODE
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
stub:
def output_suffix = output_format ?: 'vcf'
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.${output_suffix}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
cnvpytor: \$(echo \$(cnvpytor --version 2>&1) | sed 's/CNVpytor //' ))
END_VERSIONS
"""
}

56
modules/cnvpytor/view/meta.yml Normal file
View file

@ -0,0 +1,56 @@
name: cnvpytor_view
description: view function to generate vcfs
keywords:
- cnv calling
tools:
- cnvpytor:
description: calling CNVs using read depth
homepage: https://github.com/abyzovlab/CNVpytor
documentation: https://github.com/abyzovlab/CNVpytor
tool_dev_url: https://github.com/abyzovlab/CNVpytor
doi: "10.1101/2021.01.27.428472v1"
licence: ["MIT"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- pytor_files:
type: file
description: pytor file containing cnv calls. To merge calls from multiple samples use a list of files.
pattern: "*.{pytor}"
- bin_sizes:
type: string
description: list of binsizes separated by space e.g. "1000 10000" and "1000"
- output_format:
type: string
description: output format of the cnv calls. Valid entries are "tsv", "vcf", and "xls"
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- tsv:
type: file
description: tsv file containing cnv calls
pattern: "*.{tsv}"
- vcf:
type: file
description: vcf file containing cnv calls
pattern: "*.{vcf}"
- xls:
type: file
description: xls file containing cnv calls
pattern: "*.{xls}"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@sima-r"
- "@ramprasadn"

13
modules/controlfreec/assesssignificance/main.nf
View file

@ -21,7 +21,7 @@ process CONTROLFREEC_ASSESSSIGNIFICANCE {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
"""
cat /usr/local/bin/assess_significance.R | R --slave --args ${cnvs} ${ratio}
cat \$(which assess_significance.R) | R --slave --args ${cnvs} ${ratio}
mv *.p.value.txt ${prefix}.p.value.txt
@ -30,4 +30,15 @@ process CONTROLFREEC_ASSESSSIGNIFICANCE {
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.p.value.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
}

20
modules/controlfreec/freec/main.nf
View file

@ -21,7 +21,7 @@ process CONTROLFREEC_FREEC {
output:
tuple val(meta), path("*_ratio.BedGraph") , emit: bedgraph, optional: true
tuple val(meta), path("*_control.cpn") , emit: control_cpn
tuple val(meta), path("*_control.cpn") , emit: control_cpn, optional: true
tuple val(meta), path("*_sample.cpn") , emit: sample_cpn
tuple val(meta), path("GC_profile.*.cpn") , emit: gcprofile_cpn, optional:true
tuple val(meta), path("*_BAF.txt") , emit: BAF
@ -155,4 +155,22 @@ process CONTROLFREEC_FREEC {
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}_ratio.BedGraph
touch ${prefix}_sample.cpn
touch GC_profile.${prefix}.cpn
touch ${prefix}_BAF.txt
touch ${prefix}_CNVs
touch ${prefix}_info.txt
touch ${prefix}_ratio.txt
touch config.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
}

11
modules/controlfreec/freec2bed/main.nf
View file

@ -28,4 +28,15 @@ process CONTROLFREEC_FREEC2BED {
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.bed
cat <<-END_VERSIONS > versions.yml
"${task.process}":
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
}

11
modules/controlfreec/freec2circos/main.nf
View file

@ -28,4 +28,15 @@ process CONTROLFREEC_FREEC2CIRCOS {
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}.circos.txt
cat <<-END_VERSIONS > versions.yml
"${task.process}":
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
}

14
modules/controlfreec/makegraph/main.nf
View file

@ -25,12 +25,24 @@ process CONTROLFREEC_MAKEGRAPH {
def prefix = task.ext.prefix ?: "${meta.id}"
def baf = baf ?: ""
"""
cat /usr/local/bin/makeGraph.R | R --slave --args ${args} ${ratio} ${baf}
cat \$(which makeGraph.R) | R --slave --args ${args} ${ratio} ${baf}
mv *_BAF.txt.png ${prefix}_BAF.png
mv *_ratio.txt.log2.png ${prefix}_ratio.log2.png
mv *_ratio.txt.png ${prefix}_ratio.png
cat <<-END_VERSIONS > versions.yml
"${task.process}":
controlfreec: \$(echo \$(freec -version 2>&1) | sed 's/^.*Control-FREEC //; s/:.*\$//' | sed -e "s/Control-FREEC v//g" )
END_VERSIONS
"""
stub:
def prefix = task.ext.prefix ?: "${meta.id}"
"""
touch ${prefix}_BAF.png
touch ${prefix}_ratio.log2.png
touch ${prefix}_ratio.png
cat <<-END_VERSIONS > versions.yml
"${task.process}":

6
modules/custom/getchromsizes/main.nf
View file

@ -2,10 +2,10 @@ process CUSTOM_GETCHROMSIZES {
tag "$fasta"
label 'process_low'
conda (params.enable_conda ? "bioconda::samtools=1.15" : null)
conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/samtools:1.15--h1170115_1' :
'quay.io/biocontainers/samtools:1.15--h1170115_1' }"
'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
input:
path fasta

20
modules/custom/sratoolsncbisettings/main.nf Normal file
View file

@ -0,0 +1,20 @@
process CUSTOM_SRATOOLSNCBISETTINGS {
tag 'ncbi-settings'
label 'process_low'
conda (params.enable_conda ? 'bioconda::sra-tools=2.11.0' : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/sra-tools:2.11.0--pl5321ha49a11a_3' :
'quay.io/biocontainers/sra-tools:2.11.0--pl5321ha49a11a_3' }"
output:
path('*.mkfg') , emit: ncbi_settings
path 'versions.yml', emit: versions
when:
task.ext.when == null || task.ext.when
shell:
config = "/LIBS/GUID = \"${UUID.randomUUID().toString()}\"\\n/libs/cloud/report_instance_identity = \"true\"\\n"
template 'detect_ncbi_settings.sh'
}

28
modules/custom/sratoolsncbisettings/meta.yml Normal file
View file

@ -0,0 +1,28 @@
name: "sratoolsncbisettings"
description: Test for the presence of suitable NCBI settings or create them on the fly.
keywords:
- NCBI
- settings
- sra-tools
- prefetch
- fasterq-dump
tools:
- "sratools":
description: "SRA Toolkit and SDK from NCBI"
homepage: https://github.com/ncbi/sra-tools
documentation: https://github.com/ncbi/sra-tools/wiki
tool_dev_url: https://github.com/ncbi/sra-tools
licence: "['Public Domain']"
output:
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- ncbi_settings:
type: file
description: An NCBI user settings file.
pattern: "*.mkfg"
authors:
- "@Midnighter"

45
modules/custom/sratoolsncbisettings/templates/detect_ncbi_settings.sh Normal file
View file

@ -0,0 +1,45 @@
#!/usr/bin/env bash
set -u
# Get the expected NCBI settings path and define the environment variable
# `NCBI_SETTINGS`.
eval "$(vdb-config -o n NCBI_SETTINGS | sed 's/[" ]//g')"
# If the user settings do not exist yet, create a file suitable for `prefetch`
# and `fasterq-dump`. If an existing settings file does not contain the required
# values, error out with a helpful message.
if [[ ! -f "${NCBI_SETTINGS}" ]]; then
printf '!{config}' > 'user-settings.mkfg'
else
prefetch --help &> /dev/null
if [[ $? = 78 ]]; then
echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
"missing the required entries for /LIBS/GUID and"\
"/libs/cloud/report_instance_identity."\
"Feel free to add the following to your settings file:" >&2
echo "$(printf '!{config}')" >&2
exit 1
fi
fasterq-dump --help &> /dev/null
if [[ $? = 78 ]]; then
echo "You have an existing vdb-config at '${NCBI_SETTINGS}' but it is"\
"missing the required entries for /LIBS/GUID and"\
"/libs/cloud/report_instance_identity."\
"Feel free to add the following to your settings file:" >&2
echo "$(printf '!{config}')" >&2
exit 1
fi
if [[ "${NCBI_SETTINGS}" != *.mkfg ]]; then
echo "The detected settings '${NCBI_SETTINGS}' do not have the required"\
"file extension '.mkfg'." >&2
exit 1
fi
cp "${NCBI_SETTINGS}" ./
fi
cat <<-END_VERSIONS > versions.yml
"!{task.process}":
sratools: $(vdb-config --version 2>&1 | grep -Eo '[0-9.]+')
END_VERSIONS

29
modules/dastool/dastool/main.nf
View file

@ -2,27 +2,28 @@ process DASTOOL_DASTOOL {
tag "$meta.id"
label 'process_medium'
conda (params.enable_conda ? "bioconda::das_tool=1.1.3" : null)
conda (params.enable_conda ? "bioconda::das_tool=1.1.4" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/das_tool:1.1.3--r41hdfd78af_0' :
'quay.io/biocontainers/das_tool:1.1.3--r41hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/das_tool:1.1.4--r41hdfd78af_1' :
'quay.io/biocontainers/das_tool:1.1.4--r41hdfd78af_1' }"
input:
tuple val(meta), path(contigs), path(bins)
path(proteins)
path(db_directory)
val(search_engine)
output:
tuple val(meta), path("*.log") , emit: log
tuple val(meta), path("*_summary.txt") , emit: summary
tuple val(meta), path("*_DASTool_scaffolds2bin.txt") , emit: scaffolds2bin
tuple val(meta), path("*_summary.tsv") , optional: true, emit: summary
tuple val(meta), path("*_DASTool_contig2bin.tsv") , optional: true, emit: contig2bin
tuple val(meta), path("*.eval") , optional: true, emit: eval
tuple val(meta), path("*_DASTool_bins/*.fa") , optional: true, emit: bins
tuple val(meta), path("*.pdf") , optional: true, emit: pdfs
tuple val(meta), path("*.proteins.faa") , optional: true, emit: fasta_proteins
tuple val(meta), path("*.candidates.faa") , optional: true, emit: fasta_proteins
tuple val(meta), path("*.faa") , optional: true, emit: candidates_faa
tuple val(meta), path("*.archaea.scg") , optional: true, emit: fasta_archaea_scg
tuple val(meta), path("*.bacteria.scg") , optional: true, emit: fasta_bacteria_scg
tuple val(meta), path("*.b6") , optional: true, emit: b6
tuple val(meta), path("*.seqlength") , optional: true, emit: seqlength
path "versions.yml" , emit: versions
@ -33,17 +34,12 @@ process DASTOOL_DASTOOL {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def bin_list = bins instanceof List ? bins.join(",") : "$bins"
def engine = search_engine ? "--search_engine $search_engine" : "--search_engine diamond"
def db_dir = db_directory ? "--db_directory $db_directory" : ""
def clean_contigs = contigs.toString() - ".gz"
def decompress_contigs = contigs.toString() == clean_contigs ? "" : "gunzip -q -f $contigs"
def decompress_proteins = proteins ? "gunzip -f $proteins" : ""
def clean_proteins = proteins ? proteins.toString() - ".gz" : ""
def proteins_pred = proteins ? "--proteins $clean_proteins" : ""
if (! search_engine) {
log.info('[DAS_Tool] Default search engine (USEARCH) is proprietary software and not available in bioconda. Using DIAMOND as alternative.')
}
def decompress_proteins = proteins ? "gunzip -f $proteins" : ""
def proteins_pred = proteins ? "-p $clean_proteins" : ""
"""
$decompress_proteins
@ -53,15 +49,14 @@ process DASTOOL_DASTOOL {
$args \\
$proteins_pred \\
$db_dir \\
$engine \\
-t $task.cpus \\
--bins $bin_list \\
-i $bin_list \\
-c $clean_contigs \\
-o $prefix
cat <<-END_VERSIONS > versions.yml
"${task.process}":
dastool: \$( DAS_Tool --version 2>&1 | grep "DAS Tool" | sed 's/DAS Tool version //' )
dastool: \$( DAS_Tool --version 2>&1 | grep "DAS Tool" | sed 's/DAS Tool //' )
END_VERSIONS
"""
}

18
modules/dastool/dastool/meta.yml
View file

@ -34,8 +34,8 @@ input:
pattern: "*.{fa.gz,fas.gz,fasta.gz}"
- bins:
type: file
description: "Scaffolds2bin tabular file generated with dastool/scaffolds2bin"
pattern: "*.scaffolds2bin.tsv"
description: "FastaToContig2Bin tabular file generated with dastool/fastatocontig2bin"
pattern: "*.tsv"
- proteins:
type: file
description: Predicted proteins in prodigal fasta format (>scaffoldID_geneNo)
@ -43,9 +43,6 @@ input:
- db_directory:
type: file
description: (optional) Directory of single copy gene database.
- search_engine:
type: val
description: Engine used for single copy gene identification. USEARCH is not supported due to it being proprietary [blast/diamond]
output:
- meta:
@ -65,14 +62,17 @@ output:
type: file
description: Summary of output bins including quality and completeness estimates
pattern: "*summary.txt"
- scaffolds2bin:
- contig2bin:
type: file
description: Scaffolds to bin file of output bins
pattern: "*.scaffolds2bin.txt"
pattern: "*.contig2bin.txt"
- eval:
type: file
description: Quality and completeness estimates of input bin sets
pattern: "*.eval"
- bins:
description: Final refined bins in fasta format
pattern: "*.fa"
- pdfs:
type: file
description: Plots showing the amount of high quality bins and score distribution of bins per method
@ -89,6 +89,10 @@ output:
type: file
description: Results of bacterial single-copy-gene prediction
pattern: "*.bacteria.scg"
- b6:
type: file
description: Results in b6 format
pattern: "*.b6"
- seqlength:
type: file
description: Summary of contig lengths

41
modules/dastool/fastatocontig2bin/main.nf Normal file
View file

@ -0,0 +1,41 @@
process DASTOOL_FASTATOCONTIG2BIN {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::das_tool=1.1.4" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/das_tool:1.1.4--r41hdfd78af_1' :
'quay.io/biocontainers/das_tool:1.1.4--r41hdfd78af_1' }"
input:
tuple val(meta), path(fasta)
val(extension)
output:
tuple val(meta), path("*.tsv"), emit: fastatocontig2bin
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 file_extension = extension ? extension : "fasta"
def clean_fasta = fasta.toString() - ".gz"
def decompress_fasta = fasta.toString() == clean_fasta ? "" : "gunzip -q -f $fasta"
"""
$decompress_fasta
Fasta_to_Contig2Bin.sh \\
$args \\
-i . \\
-e $file_extension \\
> ${prefix}.tsv
cat <<-END_VERSIONS > versions.yml
"${task.process}":
dastool: \$( DAS_Tool --version 2>&1 | grep "DAS Tool" | sed 's/DAS Tool //' )
END_VERSIONS
"""
}

56
modules/dastool/fastatocontig2bin/meta.yml Normal file
View file

@ -0,0 +1,56 @@
name: dastool_fastatocontig2bin
description: Helper script to convert a set of bins in fasta format to tabular scaffolds2bin format
keywords:
- binning
- das tool
- table
- de novo
- bins
- contigs
- assembly
- das_tool
tools:
- dastool:
description: |
DAS Tool is an automated method that integrates the results
of a flexible number of binning algorithms to calculate an optimized, non-redundant
set of bins from a single assembly.
homepage: https://github.com/cmks/DAS_Tool
documentation: https://github.com/cmks/DAS_Tool
tool_dev_url: https://github.com/cmks/DAS_Tool
doi: "10.1038/s41564-018-0171-1"
licence: ["BSD"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- fasta:
type: file
description: Fasta of list of fasta files recommended to be gathered via with .collect() of bins
pattern: "*.{fa,fa.gz,fas,fas.gz,fna,fna.gz,fasta,fasta.gz}"
- extension:
type: val
description: Fasta file extension (fa | fas | fasta | ...), without .gz suffix, if gzipped input.
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"
- fastatocontig2bin:
type: file
description: tabular contig2bin file for DAS tool input
pattern: "*.tsv"
authors:
- "@maxibor"
- "@jfy133"

40
modules/diamond/blastp/main.nf
View file

@ -2,20 +2,26 @@ process DIAMOND_BLASTP {
tag "$meta.id"
label 'process_medium'
// Dimaond is limited to v2.0.9 because there is not a
// singularity version higher than this at the current time.
conda (params.enable_conda ? "bioconda::diamond=2.0.9" : null)
conda (params.enable_conda ? "bioconda::diamond=2.0.15" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/diamond:2.0.9--hdcc8f71_0' :
'quay.io/biocontainers/diamond:2.0.9--hdcc8f71_0' }"
'https://depot.galaxyproject.org/singularity/diamond:2.0.15--hb97b32f_0' :
'quay.io/biocontainers/diamond:2.0.15--hb97b32f_0' }"
input:
tuple val(meta), path(fasta)
path db
path db
val out_ext
val blast_columns
output:
tuple val(meta), path('*.txt'), emit: txt
path "versions.yml" , emit: versions
tuple val(meta), path('*.blast'), optional: true, emit: blast
tuple val(meta), path('*.xml') , optional: true, emit: xml
tuple val(meta), path('*.txt') , optional: true, emit: txt
tuple val(meta), path('*.daa') , optional: true, emit: daa
tuple val(meta), path('*.sam') , optional: true, emit: sam
tuple val(meta), path('*.tsv') , optional: true, emit: tsv
tuple val(meta), path('*.paf') , optional: true, emit: paf
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -23,6 +29,21 @@ process DIAMOND_BLASTP {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def columns = blast_columns ? "${blast_columns}" : ''
switch ( out_ext ) {
case "blast": outfmt = 0; break
case "xml": outfmt = 5; break
case "txt": outfmt = 6; break
case "daa": outfmt = 100; break
case "sam": outfmt = 101; break
case "tsv": outfmt = 102; break
case "paf": outfmt = 103; break
default:
outfmt = '6';
out_ext = 'txt';
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)");
break
}
"""
DB=`find -L ./ -name "*.dmnd" | sed 's/.dmnd//'`
@ -31,8 +52,9 @@ process DIAMOND_BLASTP {
--threads $task.cpus \\
--db \$DB \\
--query $fasta \\
--outfmt ${outfmt} ${columns} \\
$args \\
--out ${prefix}.txt
--out ${prefix}.${out_ext}
cat <<-END_VERSIONS > versions.yml
"${task.process}":

43
modules/diamond/blastp/meta.yml
View file

@ -28,12 +28,50 @@ input:
type: directory
description: Directory containing the protein blast database
pattern: "*"
- out_ext:
type: string
description: |
Specify the type of output file to be generated. `blast` corresponds to
BLAST pairwise format. `xml` corresponds to BLAST xml format.
`txt` corresponds to to BLAST tabular format. `tsv` corresponds to
taxonomic classification format.
pattern: "blast|xml|txt|daa|sam|tsv|paf"
- blast_columns:
type: string
description: |
Optional space separated list of DIAMOND tabular BLAST output keywords
used for in conjunction with the 'txt' out_ext option (--outfmt 6). See
DIAMOND documnetation for more information.
output:
- txt:
- blast:
type: file
description: File containing blastp hits
pattern: "*.{blastp.txt}"
pattern: "*.{blast}"
- xml:
type: file
description: File containing blastp hits
pattern: "*.{xml}"
- txt:
type: file
description: File containing hits in tabular BLAST format.
pattern: "*.{txt}"
- daa:
type: file
description: File containing hits DAA format
pattern: "*.{daa}"
- sam:
type: file
description: File containing aligned reads in SAM format
pattern: "*.{sam}"
- tsv:
type: file
description: Tab separated file containing taxonomic classification of hits
pattern: "*.{tsv}"
- paf:
type: file
description: File containing aligned reads in pairwise mapping format format
pattern: "*.{paf}"
- versions:
type: file
description: File containing software versions
@ -41,3 +79,4 @@ output:
authors:
- "@spficklin"
- "@jfy133"

40
modules/diamond/blastx/main.nf
View file

@ -2,20 +2,26 @@ process DIAMOND_BLASTX {
tag "$meta.id"
label 'process_medium'
// Dimaond is limited to v2.0.9 because there is not a
// singularity version higher than this at the current time.
conda (params.enable_conda ? "bioconda::diamond=2.0.9" : null)
conda (params.enable_conda ? "bioconda::diamond=2.0.15" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/diamond:2.0.9--hdcc8f71_0' :
'quay.io/biocontainers/diamond:2.0.9--hdcc8f71_0' }"
'https://depot.galaxyproject.org/singularity/diamond:2.0.15--hb97b32f_0' :
'quay.io/biocontainers/diamond:2.0.15--hb97b32f_0' }"
input:
tuple val(meta), path(fasta)
path db
path db
val out_ext
val blast_columns
output:
tuple val(meta), path('*.txt'), emit: txt
path "versions.yml" , emit: versions
tuple val(meta), path('*.blast'), optional: true, emit: blast
tuple val(meta), path('*.xml') , optional: true, emit: xml
tuple val(meta), path('*.txt') , optional: true, emit: txt
tuple val(meta), path('*.daa') , optional: true, emit: daa
tuple val(meta), path('*.sam') , optional: true, emit: sam
tuple val(meta), path('*.tsv') , optional: true, emit: tsv
tuple val(meta), path('*.paf') , optional: true, emit: paf
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -23,6 +29,21 @@ process DIAMOND_BLASTX {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def columns = blast_columns ? "${blast_columns}" : ''
switch ( out_ext ) {
case "blast": outfmt = 0; break
case "xml": outfmt = 5; break
case "txt": outfmt = 6; break
case "daa": outfmt = 100; break
case "sam": outfmt = 101; break
case "tsv": outfmt = 102; break
case "paf": outfmt = 103; break
default:
outfmt = '6';
out_ext = 'txt';
log.warn("Unknown output file format provided (${out_ext}): selecting DIAMOND default of tabular BLAST output (txt)");
break
}
"""
DB=`find -L ./ -name "*.dmnd" | sed 's/.dmnd//'`
@ -31,8 +52,9 @@ process DIAMOND_BLASTX {
--threads $task.cpus \\
--db \$DB \\
--query $fasta \\
--outfmt ${outfmt} ${columns} \\
$args \\
--out ${prefix}.txt
--out ${prefix}.${out_ext}
cat <<-END_VERSIONS > versions.yml
"${task.process}":

37
modules/diamond/blastx/meta.yml
View file

@ -28,12 +28,44 @@ input:
type: directory
description: Directory containing the nucelotide blast database
pattern: "*"
- out_ext:
type: string
description: |
Specify the type of output file to be generated. `blast` corresponds to
BLAST pairwise format. `xml` corresponds to BLAST xml format.
`txt` corresponds to to BLAST tabular format. `tsv` corresponds to
taxonomic classification format.
pattern: "blast|xml|txt|daa|sam|tsv|paf"
output:
- blast:
type: file
description: File containing blastp hits
pattern: "*.{blast}"
- xml:
type: file
description: File containing blastp hits
pattern: "*.{xml}"
- txt:
type: file
description: File containing blastx hits
pattern: "*.{blastx.txt}"
description: File containing hits in tabular BLAST format.
pattern: "*.{txt}"
- daa:
type: file
description: File containing hits DAA format
pattern: "*.{daa}"
- sam:
type: file
description: File containing aligned reads in SAM format
pattern: "*.{sam}"
- tsv:
type: file
description: Tab separated file containing taxonomic classification of hits
pattern: "*.{tsv}"
- paf:
type: file
description: File containing aligned reads in pairwise mapping format format
pattern: "*.{paf}"
- versions:
type: file
description: File containing software versions
@ -41,3 +73,4 @@ output:
authors:
- "@spficklin"
- "@jfy133"

8
modules/diamond/makedb/main.nf
View file

@ -2,12 +2,10 @@ process DIAMOND_MAKEDB {
tag "$fasta"
label 'process_medium'
// Dimaond is limited to v2.0.9 because there is not a
// singularity version higher than this at the current time.
conda (params.enable_conda ? 'bioconda::diamond=2.0.9' : null)
conda (params.enable_conda ? "bioconda::diamond=2.0.15" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/diamond:2.0.9--hdcc8f71_0' :
'quay.io/biocontainers/diamond:2.0.9--hdcc8f71_0' }"
'https://depot.galaxyproject.org/singularity/diamond:2.0.15--hb97b32f_0' :
'quay.io/biocontainers/diamond:2.0.15--hb97b32f_0' }"
input:
path fasta

59
modules/dragmap/align/main.nf
View file

@ -2,10 +2,10 @@ process DRAGMAP_ALIGN {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? "bioconda::dragmap=1.2.1 bioconda::samtools=1.14 conda-forge::pigz=2.3.4" : null)
conda (params.enable_conda ? "bioconda::dragmap=1.2.1 bioconda::samtools=1.15.1 conda-forge::pigz=2.3.4" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:f7aad9060cde739c95685fc5ff6d6f7e3ec629c8-0':
'quay.io/biocontainers/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:f7aad9060cde739c95685fc5ff6d6f7e3ec629c8-0' }"
'https://depot.galaxyproject.org/singularity/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:5ebebbc128cd624282eaa37d2c7fe01505a91a69-0':
'quay.io/biocontainers/mulled-v2-580d344d9d4a496cd403932da8765f9e0187774d:5ebebbc128cd624282eaa37d2c7fe01505a91a69-0' }"
input:
tuple val(meta), path(reads)
@ -24,44 +24,23 @@ process DRAGMAP_ALIGN {
def args = task.ext.args ?: ''
def args2 = task.ext.args2 ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def read_group = meta.read_group ? "--RGSM ${meta.read_group}" : ""
def reads_command = meta.single_end ? "-1 $reads" : "-1 ${reads[0]} -2 ${reads[1]}"
def samtools_command = sort_bam ? 'sort' : 'view'
if (meta.single_end) {
"""
dragen-os \\
-r $hashmap \\
$args \\
$read_group \\
--num-threads $task.cpus \\
-1 $reads \\
2> ${prefix}.dragmap.log \\
| samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.bam -
cat <<-END_VERSIONS > versions.yml
"${task.process}":
dragmap: \$(echo \$(dragen-os --version 2>&1))
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
END_VERSIONS
"""
} else {
"""
dragen-os \\
-r $hashmap \\
$args \\
$read_group \\
--num-threads $task.cpus \\
-1 ${reads[0]} \\
-2 ${reads[1]} \\
2> ${prefix}.dragmap.log \\
| samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.bam -
"""
dragen-os \\
-r $hashmap \\
$args \\
--num-threads $task.cpus \\
$reads_command \\
2> ${prefix}.dragmap.log \\
| samtools $samtools_command $args2 --threads $task.cpus -o ${prefix}.bam -
cat <<-END_VERSIONS > versions.yml
"${task.process}":
dragmap: \$(echo \$(dragen-os --version 2>&1))
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
END_VERSIONS
"""
}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
dragmap: \$(echo \$(dragen-os --version 2>&1))
samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
pigz: \$( pigz --version 2>&1 | sed 's/pigz //g' )
END_VERSIONS
"""
}

6
modules/dshbio/exportsegments/main.nf
View file

@ -2,10 +2,10 @@ process DSHBIO_EXPORTSEGMENTS {
tag "${meta.id}"
label 'process_medium'
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.8" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.8--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.8--hdfd78af_0' }"
input:
tuple val(meta), path(gfa)

6
modules/dshbio/filterbed/main.nf
View file

@ -2,10 +2,10 @@ process DSHBIO_FILTERBED {
tag "${meta.id}"
label 'process_medium'
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.8" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.8--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.8--hdfd78af_0' }"
input:
tuple val(meta), path(bed)

6
modules/dshbio/filtergff3/main.nf
View file

@ -2,10 +2,10 @@ process DSHBIO_FILTERGFF3 {
tag "${meta.id}"
label 'process_medium'
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.8" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.8--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.8--hdfd78af_0' }"
input:
tuple val(meta), path(gff3)

6
modules/dshbio/splitbed/main.nf
View file

@ -2,10 +2,10 @@ process DSHBIO_SPLITBED {
tag "${meta.id}"
label 'process_medium'
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.8" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.8--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.8--hdfd78af_0' }"
input:
tuple val(meta), path(bed)

6
modules/dshbio/splitgff3/main.nf
View file

@ -2,10 +2,10 @@ process DSHBIO_SPLITGFF3 {
tag "${meta.id}"
label 'process_medium'
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.7" : null)
conda (params.enable_conda ? "bioconda::dsh-bio=2.0.8" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.7--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.7--hdfd78af_0' }"
'https://depot.galaxyproject.org/singularity/dsh-bio:2.0.8--hdfd78af_0' :
'quay.io/biocontainers/dsh-bio:2.0.8--hdfd78af_0' }"
input:
tuple val(meta), path(gff3)

89
modules/elprep/filter/main.nf Normal file
View file

@ -0,0 +1,89 @@
process ELPREP_FILTER {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
input:
tuple val(meta), path(bam)
val(run_haplotypecaller)
val(run_bqsr)
path(reference_sequences)
path(filter_regions_bed)
path(reference_elfasta)
path(known_sites_elsites)
path(target_regions_bed)
path(intermediate_bqsr_tables)
val(bqsr_tables_only)
val(get_activity_profile)
val(get_assembly_regions)
output:
tuple val(meta), path("output/**.{bam,sam}") ,emit: bam
tuple val(meta), path("*.metrics.txt") ,optional: true, emit: metrics
tuple val(meta), path("*.recall") ,optional: true, emit: recall
tuple val(meta), path("*.vcf.gz") ,optional: true, emit: gvcf
tuple val(meta), path("*.table") ,optional: true, emit: table
tuple val(meta), path("*.activity_profile.igv") ,optional: true, emit: activity_profile
tuple val(meta), path("*.assembly_regions.igv") ,optional: true, emit: assembly_regions
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 suffix = args.contains("--output-type sam") ? "sam" : "bam"
// filter args
def reference_sequences_cmd = reference_sequences ? " --replace-reference-sequences ${reference_sequences}" : ""
def filter_regions_cmd = filter_regions_bed ? " --filter-non-overlapping-reads ${filter_regions_bed}" : ""
// markdup args
def markdup_cmd = args.contains("--mark-duplicates") ? " --mark-optical-duplicates ${prefix}.metrics.txt": ""
// variant calling args
def haplotyper_cmd = run_haplotypecaller ? " --haplotypecaller ${prefix}.g.vcf.gz": ""
def fasta_cmd = reference_elfasta ? " --reference ${reference_elfasta}": ""
def known_sites_cmd = known_sites_elsites ? " --known-sites ${known_sites_elsites}": ""
def target_regions_cmd = target_regions_bed ? " --target-regions ${target_regions_bed}": ""
// bqsr args
def bqsr_cmd = run_bqsr ? " --bqsr ${prefix}.recall": ""
def bqsr_tables_only_cmd = bqsr_tables_only ? " --bqsr-tables-only ${prefix}.table": ""
def intermediate_bqsr_cmd = intermediate_bqsr_tables ? " --bqsr-apply .": ""
// misc
def activity_profile_cmd = get_activity_profile ? " --activity-profile ${prefix}.activity_profile.igv": ""
def assembly_regions_cmd = get_assembly_regions ? " --assembly-regions ${prefix}.assembly_regions.igv": ""
"""
elprep filter ${bam} output/${prefix}.${suffix} \\
${reference_sequences_cmd} \\
${filter_regions_cmd} \\
${markdup_cmd} \\
${haplotyper_cmd} \\
${fasta_cmd} \\
${known_sites_cmd} \\
${target_regions_cmd} \\
${bqsr_cmd} \\
${bqsr_tables_only_cmd} \\
${intermediate_bqsr_cmd} \\
${activity_profile_cmd} \\
${assembly_regions_cmd} \\
--nr-of-threads ${task.cpus} \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
END_VERSIONS
"""
}

106
modules/elprep/filter/meta.yml Normal file
View file

@ -0,0 +1,106 @@
name: "elprep_filter"
description: "Filter, sort and markdup sam/bam files, with optional BQSR and variant calling."
keywords:
- sort
- bam
- sam
- filter
- variant calling
tools:
- "elprep":
description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
homepage: "https://github.com/ExaScience/elprep"
documentation: "https://github.com/ExaScience/elprep"
tool_dev_url: "https://github.com/ExaScience/elprep"
doi: "10.1371/journal.pone.0244471"
licence: "['AGPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: Input SAM/BAM file
pattern: "*.{bam,sam}"
- run_haplotypecaller:
type: boolean
description: Run variant calling on the input files. Needed to generate gvcf output.
- run_bqsr:
type: boolean
description: Run BQSR on the input files. Needed to generate recall metrics.
- reference_sequences:
type: file
description: Optional SAM header to replace existing header.
pattern: "*.sam"
- filter_regions_bed:
type: file
description: Optional BED file containing regions to filter.
pattern: "*.bed"
- reference_elfasta:
type: file
description: Elfasta file, required for BQSR and variant calling.
pattern: "*.elfasta"
- known_sites:
type: file
description: Optional elsites file containing known SNPs for BQSR.
pattern: "*.elsites"
- target_regions_bed:
type: file
description: Optional BED file containing target regions for BQSR and variant calling.
pattern: "*.bed"
- intermediate_bqsr_tables:
type: file
description: Optional list of BQSR tables, used when parsing files created by `elprep split`
pattern: "*.table"
- bqsr_tables_only:
type: boolean
description: Write intermediate BQSR tables, used when parsing files created by `elprep split`.
- get_activity_profile:
type: boolean
description: Get the activity profile calculated by the haplotypecaller to the given file in IGV format.
- get_assembly_regions:
type: boolean
description: Get the assembly regions calculated by haplotypecaller to the speficied file in IGV format.
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"
- bam:
type: file
description: Sorted, markdup, optionally BQSR BAM/SAM file
pattern: "*.{bam,sam}"
- metrics:
type: file
description: Optional duplicate metrics file generated by elprep
pattern: "*.{metrics.txt}"
- recall:
type: file
description: Optional recall metrics file generated by elprep
pattern: "*.{recall}"
- gvcf:
type: file
description: Optional GVCF output file
pattern: "*.{vcf.gz}"
- table:
type: file
description: Optional intermediate BQSR table output file
pattern: "*.{table}"
- activity_profile:
type: file
description: Optional activity profile output file
pattern: "*.{activity_profile.igv}"
- assembly_regions:
type: file
description: Optional activity regions output file
pattern: "*.{assembly_regions.igv}"
authors:
- "@matthdsm"

43
modules/elprep/merge/main.nf Normal file
View file

@ -0,0 +1,43 @@
process ELPREP_MERGE {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("output/**.{bam,sam}") , emit: bam
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 suffix = args.contains("--output-type sam") ? "sam" : "bam"
def single_end = meta.single_end ? " --single-end" : ""
"""
# create directory and move all input so elprep can find and merge them before splitting
mkdir input
mv ${bam} input/
elprep merge \\
input/ \\
output/${prefix}.${suffix} \\
$args \\
${single_end} \\
--nr-of-threads $task.cpus
cat <<-END_VERSIONS > versions.yml
"${task.process}":
elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
END_VERSIONS
"""
}

44
modules/elprep/merge/meta.yml Normal file
View file

@ -0,0 +1,44 @@
name: "elprep_merge"
description: Merge split bam/sam chunks in one file
keywords:
- bam
- sam
- merge
tools:
- "elprep":
description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
homepage: "https://github.com/ExaScience/elprep"
documentation: "https://github.com/ExaScience/elprep"
tool_dev_url: "https://github.com/ExaScience/elprep"
doi: "10.1371/journal.pone.0244471"
licence: "['AGPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: List of BAM/SAM chunks to merge
pattern: "*.{bam,sam}"
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"
- bam:
type: file
description: Merged BAM/SAM file
pattern: "*.{bam,sam}"
authors:
- "@matthdsm"

45
modules/elprep/split/main.nf Normal file
View file

@ -0,0 +1,45 @@
process ELPREP_SPLIT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::elprep=5.1.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/elprep:5.1.2--he881be0_0':
'quay.io/biocontainers/elprep:5.1.2--he881be0_0' }"
input:
tuple val(meta), path(bam)
output:
tuple val(meta), path("output/**.{bam,sam}"), emit: bam
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 single_end = meta.single_end ? " --single-end": ""
"""
# create directory and move all input so elprep can find and merge them before splitting
mkdir input
mv ${bam} input/
mkdir ${prefix}
elprep split \\
input \\
output/ \\
$args \\
$single_end \\
--nr-of-threads $task.cpus \\
--output-prefix $prefix
cat <<-END_VERSIONS > versions.yml
"${task.process}":
elprep: \$(elprep 2>&1 | head -n2 | tail -n1 |sed 's/^.*version //;s/ compiled.*\$//')
END_VERSIONS
"""
}

43
modules/elprep/split/meta.yml Normal file
View file

@ -0,0 +1,43 @@
name: "elprep_split"
description: Split bam file into manageable chunks
keywords:
- bam
- split by chromosome
tools:
- "elprep":
description: "elPrep is a high-performance tool for preparing .sam/.bam files for variant calling in sequencing pipelines. It can be used as a drop-in replacement for SAMtools/Picard/GATK4."
homepage: "https://github.com/ExaScience/elprep"
documentation: "https://github.com/ExaScience/elprep"
tool_dev_url: "https://github.com/ExaScience/elprep"
doi: "10.1371"
licence: "['AGPL v3']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: List of BAM/SAM files
pattern: "*.{bam,sam}"
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"
- bam:
type: file
description: List of split BAM/SAM files
pattern: "*.{bam,sam}"
authors:
- "@matthdsm"

11
modules/ensemblvep/Dockerfile
View file

@ -8,13 +8,14 @@ LABEL \
COPY environment.yml /
RUN conda env create -f /environment.yml && conda clean -a
# Add conda installation dir to PATH (instead of doing 'conda activate')
ENV PATH /opt/conda/envs/nf-core-vep-104.3/bin:$PATH
# Setup default ARG variables
ARG GENOME=GRCh38
ARG SPECIES=homo_sapiens
ARG VEP_VERSION=99
ARG VEP_VERSION=104
ARG VEP_TAG=104.3
# Add conda installation dir to PATH (instead of doing 'conda activate')
ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH
# Download Genome
RUN vep_install \
@ -27,4 +28,4 @@ RUN vep_install \
--NO_BIOPERL --NO_HTSLIB --NO_TEST --NO_UPDATE
# Dump the details of the installed packages to a file for posterity
RUN conda env export --name nf-core-vep-104.3 > nf-core-vep-104.3.yml
RUN conda env export --name nf-core-vep-${VEP_TAG} > nf-core-vep-${VEP_TAG}.yml

5
modules/ensemblvep/build.sh
View file

@ -10,11 +10,12 @@ build_push() {
VEP_TAG=$4
docker build \
. \
-t nfcore/vep:${VEP_TAG}.${GENOME} \
software/vep/. \
--build-arg GENOME=${GENOME} \
--build-arg SPECIES=${SPECIES} \
--build-arg VEP_VERSION=${VEP_VERSION}
--build-arg VEP_VERSION=${VEP_VERSION} \
--build-arg VEP_TAG=${VEP_TAG}
docker push nfcore/vep:${VEP_TAG}.${GENOME}
}

1
modules/ensemblvep/main.nf
View file

@ -13,6 +13,7 @@ process ENSEMBLVEP {
val species
val cache_version
path cache
path extra_files
output:
tuple val(meta), path("*.ann.vcf"), emit: vcf

Some files were not shown because too many files have changed in this diff Show more