Merge branch 'master' into firstbranch

This commit is contained in:
Simone Carpanzano 2022-05-02 17:43:33 +02:00 committed by GitHub
commit 3d9c8a6bb1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
271 changed files with 4113 additions and 1038 deletions

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] -->

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. -->

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.

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

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:

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
"""
}

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"

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
"""
}

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"

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}":

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"

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

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

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

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 Licensees business to use the Software in executable object code form only, solely at the Licensees 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 Illuminas 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 Licensees data, monitoring access and use of Licensees data, conducting routine backups and archiving of Licensees 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 Licensees 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 Illuminas 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) ILLUMINAS ENTIRE LIABILITY AND LICENSEE"S EXCLUSIVE REMEDY UNDER THE LIMITED WARRANTY PROVISION OF SECTION 7 ABOVE WILL BE, AT ILLUMINAS 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 ILLUMINAS 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 ILLUMINAS 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 ILLUMINAS 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 Licensees 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 Licensees 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 Illuminas website (www.illumina.com) and such updated Agreement WILL become effective immediately. Licensees continued access to or use of the Software represents Licensees 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.

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>
```

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
"""
}

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"

View file

@ -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 \\

View file

@ -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 \\

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*/*")

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
"""
}

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"

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

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}":

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"

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}":

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"

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

View file

@ -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
"""
}

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
"""
}

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"

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
"""
}

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"

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
"""
}

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"

41
modules/gamma/main.nf Normal file
View file

@ -0,0 +1,41 @@
def VERSION = '2.1' // Version information not provided by tool on CLI
process GAMMA {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::gamma=2.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gamma%3A2.1--hdfd78af_0':
'quay.io/biocontainers/gamma:2.1--hdfd78af_0' }"
input:
tuple val(meta), path(fasta)
path(db)
output:
tuple val(meta), path("*.gamma") , emit: gamma
tuple val(meta), path("*.psl") , emit: psl
tuple val(meta), path("*.gff") , optional:true , emit: gff
tuple val(meta), path("*.fasta"), optional:true , emit: fasta
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}"
"""
GAMMA.py \\
$args \\
$fasta \\
$db \\
$prefix
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gamma: $VERSION
END_VERSIONS
"""
}

63
modules/gamma/meta.yml Normal file
View file

@ -0,0 +1,63 @@
name: "gamma"
description: Gene Allele Mutation Microbial Assessment
keywords:
- gamma
- gene-calling
tools:
- "gamma":
description: "Tool for Gene Allele Mutation Microbial Assessment"
homepage: "https://github.com/rastanton/GAMMA"
documentation: "https://github.com/rastanton/GAMMA"
tool_dev_url: "https://github.com/rastanton/GAMMA"
doi: "10.1093/bioinformatics/btab607"
licence: "['Apache License 2.0']"
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- fasta:
type: file
description: FASTA file
pattern: "*.{fa,fasta}"
- db:
type: file
description: Database in FASTA format
pattern: "*.{fa,fasta}"
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"
- gamma:
type: file
description: GAMMA file with annotated gene matches
pattern: "*.{gamma}"
- psl:
type: file
description: PSL file with all gene matches found
pattern: "*.{psl}"
- gff:
type: file
description: GFF file
pattern: "*.{gff}"
- fasta:
type: file
description: multifasta file of the gene matches
pattern: "*.{fasta}"
authors:
- "@sateeshperi"
- "@rastanton"

View file

@ -14,9 +14,9 @@ process GATK4_APPLYBQSR {
path dict
output:
tuple val(meta), path("*.bam"), emit: bam, optional: true
tuple val(meta), path("*.bam") , emit: bam, optional: true
tuple val(meta), path("*.cram"), emit: cram, optional: true
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -24,8 +24,7 @@ process GATK4_APPLYBQSR {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def interval = intervals ? "-L ${intervals}" : ""
def file_type = input.getExtension()
def interval_command = intervals ? "--intervals $intervals" : ""
def avail_mem = 3
if (!task.memory) {
@ -35,12 +34,12 @@ process GATK4_APPLYBQSR {
}
"""
gatk --java-options "-Xmx${avail_mem}g" ApplyBQSR \\
-R $fasta \\
-I $input \\
--input $input \\
--output ${prefix}.${input.getExtension()} \\
--reference $fasta \\
--bqsr-recal-file $bqsr_table \\
$interval \\
$interval_command \\
--tmp-dir . \\
-O ${prefix}.${file_type} \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -61,6 +61,10 @@ output:
type: file
description: Recalibrated BAM file
pattern: "*.{bam}"
- cram:
type: file
description: Recalibrated CRAM file
pattern: "*.{cram}"
authors:
- "@yocra3"

View file

@ -0,0 +1,51 @@
process GATK4_APPLYBQSR_SPARK {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
'quay.io/biocontainers/gatk4:4.2.3.0--hdfd78af_0' }"
input:
tuple val(meta), path(input), path(input_index), path(bqsr_table), path(intervals)
path fasta
path fai
path dict
output:
tuple val(meta), path("*.bam") , emit: bam, optional: true
tuple val(meta), path("*.cram"), emit: cram, optional: true
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 interval_command = intervals ? "--intervals $intervals" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[GATK ApplyBQSRSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" ApplyBQSRSpark \\
--input $input \\
--output ${prefix}.${input.getExtension()} \\
--reference $fasta \\
--bqsr-recal-file $bqsr_table \\
$interval_command \\
--spark-master local[${task.cpus}] \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,72 @@
name: gatk4_applybqsr_spark
description: Apply base quality score recalibration (BQSR) to a bam file
keywords:
- bqsr
- bam
tools:
- gatk4:
description: |
Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
doi: 10.1158/1538-7445.AM2017-3590
licence: ["Apache-2.0"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- input:
type: file
description: BAM/CRAM file from alignment
pattern: "*.{bam,cram}"
- input_index:
type: file
description: BAI/CRAI file from alignment
pattern: "*.{bai,crai}"
- bqsr_table:
type: file
description: Recalibration table from gatk4_baserecalibrator
- intervals:
type: file
description: Bed file with the genomic regions included in the library (optional)
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
- fai:
type: file
description: Index of reference fasta file
pattern: "*.fasta.fai"
- dict:
type: file
description: GATK sequence dictionary
pattern: "*.dict"
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: Recalibrated BAM file
pattern: "*.{bam}"
- cram:
type: file
description: Recalibrated CRAM file
pattern: "*.{cram}"
authors:
- "@yocra3"
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -8,15 +8,15 @@ process GATK4_APPLYVQSR {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcf), path(tbi), path(recal), path(recalidx), path(tranches)
path fasta
path fai
path dict
tuple val(meta), path(vcf), path(vcf_tbi), path(recal), path(recal_index), path(tranches)
path fasta
path fai
path dict
output:
tuple val(meta), path("*.vcf.gz") , emit: vcf
tuple val(meta), path("*.tbi") , emit: tbi
path "versions.yml" , emit: versions
tuple val(meta), path("*.vcf.gz"), emit: vcf
tuple val(meta), path("*.tbi") , emit: tbi
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -24,7 +24,7 @@ process GATK4_APPLYVQSR {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
refCommand = fasta ? "-R ${fasta} " : ''
def reference_command = fasta ? "--reference $fasta" : ''
def avail_mem = 3
if (!task.memory) {
@ -34,11 +34,12 @@ process GATK4_APPLYVQSR {
}
"""
gatk --java-options "-Xmx${avail_mem}g" ApplyVQSR \\
${refCommand} \\
-V ${vcf} \\
-O ${prefix}.vcf.gz \\
--variant ${vcf} \\
--output ${prefix}.vcf.gz \\
$reference_command \\
--tranches-file $tranches \\
--recal-file $recal \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -29,20 +29,20 @@ input:
type: file
description: VCF file to be recalibrated, this should be the same file as used for the first stage VariantRecalibrator.
pattern: "*.vcf"
- tbi:
- vcf_tbi:
type: file
description: Tbi index for the input vcf file.
description: tabix index for the input vcf file.
pattern: "*.vcf.tbi"
- recal:
type: file
description: Recalibration file produced when the input vcf was run through VariantRecalibrator in stage 1.
pattern: "*.recal"
- recalidx:
- recal_index:
type: file
description: Index file for the recalibration file.
pattern: ".recal.idx"
- tranches:
type: boolean
type: file
description: Tranches file produced when the input vcf was run through VariantRecalibrator in stage 1.
pattern: ".tranches"
- fasta:

View file

@ -9,15 +9,15 @@ process GATK4_BASERECALIBRATOR {
input:
tuple val(meta), path(input), path(input_index), path(intervals)
path fasta
path fai
path dict
path knownSites
path knownSites_tbi
path fasta
path fai
path dict
path known_sites
path known_sites_tbi
output:
tuple val(meta), path("*.table"), emit: table
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -25,8 +25,8 @@ process GATK4_BASERECALIBRATOR {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def intervalsCommand = intervals ? "-L ${intervals}" : ""
def sitesCommand = knownSites.collect{"--known-sites ${it}"}.join(' ')
def interval_command = intervals ? "--intervals $intervals" : ""
def sites_command = known_sites.collect{"--known-sites $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
@ -34,16 +34,15 @@ process GATK4_BASERECALIBRATOR {
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" BaseRecalibrator \
-R $fasta \
-I $input \
$sitesCommand \
$intervalsCommand \
--tmp-dir . \
$args \
-O ${prefix}.table
gatk --java-options "-Xmx${avail_mem}g" BaseRecalibrator \\
--input $input \\
--output ${prefix}.table \\
--reference $fasta \\
$interval_command \\
$sites_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -42,9 +42,14 @@ input:
type: file
description: GATK sequence dictionary
pattern: "*.dict"
- knownSites:
- known_sites:
type: file
description: Bed file with the genomic regions included in the library (optional)
description: VCF files with known sites for indels / snps (optional)
pattern: "*.vcf.gz"
- known_sites_tbi:
type: file
description: Tabix index of the known_sites (optional)
pattern: "*.vcf.gz.tbi"
output:
- meta:
@ -64,3 +69,4 @@ output:
authors:
- "@yocra3"
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -0,0 +1,53 @@
process GATK4_BASERECALIBRATOR_SPARK {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
'broadinstitute/gatk:4.2.3.0' }"
input:
tuple val(meta), path(input), path(input_index), path(intervals)
path fasta
path fai
path dict
path known_sites
path known_sites_tbi
output:
tuple val(meta), path("*.table"), emit: table
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 interval_command = intervals ? "--intervals $intervals" : ""
def sites_command = known_sites.collect{"--known-sites $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK BaseRecalibratorSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" BaseRecalibratorSpark \\
--input $input \\
--output ${prefix}.table \\
--reference $fasta \\
$interval_command \\
$sites_command \\
--spark-master local[${task.cpus}] \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,72 @@
name: gatk4_baserecalibrator_spark
description: Generate recalibration table for Base Quality Score Recalibration (BQSR)
keywords:
- sort
tools:
- gatk4:
description: |
Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
doi: 10.1158/1538-7445.AM2017-3590
licence: ["Apache-2.0"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- input:
type: file
description: BAM/CRAM file from alignment
pattern: "*.{bam,cram}"
- input_index:
type: file
description: BAI/CRAI file from alignment
pattern: "*.{bai,crai}"
- intervals:
type: file
description: Bed file with the genomic regions included in the library (optional)
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
- fai:
type: file
description: Index of reference fasta file
pattern: "*.fasta.fai"
- dict:
type: file
description: GATK sequence dictionary
pattern: "*.dict"
- known_sites:
type: file
description: VCF files with known sites for indels / snps (optional)
pattern: "*.vcf.gz"
- known_sites_tbi:
type: file
description: Tabix index of the known_sites (optional)
pattern: "*.vcf.gz.tbi"
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"
- table:
type: file
description: Recalibration table from BaseRecalibrator
pattern: "*.{table}"
authors:
- "@yocra3"
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -9,7 +9,7 @@ process GATK4_BEDTOINTERVALLIST {
input:
tuple val(meta), path(bed)
path sequence_dict
path dict
output:
tuple val(meta), path('*.interval_list'), emit: interval_list
@ -21,6 +21,7 @@ process GATK4_BEDTOINTERVALLIST {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK BedToIntervalList] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -29,9 +30,10 @@ process GATK4_BEDTOINTERVALLIST {
}
"""
gatk --java-options "-Xmx${avail_mem}g" BedToIntervalList \\
-I $bed \\
-SD $sequence_dict \\
-O ${prefix}.interval_list \\
--INPUT $bed \\
--OUTPUT ${prefix}.interval_list \\
--SEQUENCE_DICTIONARY $dict \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -9,7 +9,6 @@ process GATK4_CALCULATECONTAMINATION {
input:
tuple val(meta), path(pileup), path(matched)
val segmentout
output:
tuple val(meta), path('*.contamination.table'), emit: contamination
@ -22,8 +21,8 @@ process GATK4_CALCULATECONTAMINATION {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def matched_command = matched ? " -matched ${matched} " : ''
def segment_command = segmentout ? " -segments ${prefix}.segmentation.table" : ''
def matched_command = matched ? "--matched-normal $matched" : ''
def avail_mem = 3
if (!task.memory) {
log.info '[GATK CalculateContamination] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -32,10 +31,10 @@ process GATK4_CALCULATECONTAMINATION {
}
"""
gatk --java-options "-Xmx${avail_mem}g" CalculateContamination \\
-I $pileup \\
--input $pileup \\
--output ${prefix}.contamination.table \\
$matched_command \\
-O ${prefix}.contamination.table \\
$segment_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -32,9 +32,6 @@ input:
type: file
description: File containing the pileups summary table of a normal sample that matches with the tumor sample specified in pileup argument. This is an optional input.
pattern: "*.pileups.table"
- segmentout:
type: boolean
description: specifies whether to output the segmentation table.
output:
- contamination:
@ -43,7 +40,7 @@ output:
pattern: "*.contamination.table"
- segmentation:
type: file
description: optional output table containing segmentation of tumor minor allele fractions.
description: output table containing segmentation of tumor minor allele fractions (optional)
pattern: "*.segmentation.table"
- versions:
type: file
@ -52,3 +49,4 @@ output:
authors:
- "@GCJMackenzie"
- "@maxulysse"

View file

@ -9,9 +9,9 @@ process GATK4_COMBINEGVCFS {
input:
tuple val(meta), path(vcf), path(vcf_idx)
path (fasta)
path (fasta_fai)
path (fasta_dict)
path fasta
path fai
path dict
output:
tuple val(meta), path("*.combined.g.vcf.gz"), emit: combined_gvcf
@ -23,21 +23,21 @@ process GATK4_COMBINEGVCFS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
def input_list = vcf.collect{"--variant $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK COMBINEGVCFS] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
def input_files = vcf.collect{"-V ${it}"}.join(' ') // add '-V' to each vcf file
"""
gatk \\
--java-options "-Xmx${avail_mem}g" \\
CombineGVCFs \\
-R ${fasta} \\
-O ${prefix}.combined.g.vcf.gz \\
${args} \\
${input_files}
gatk --java-options "-Xmx${avail_mem}g" CombineGVCFs \\
$input_list \\
--output ${prefix}.combined.g.vcf.gz \\
--reference ${fasta} \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -19,18 +19,11 @@ tools:
licence: ["Apache-2.0"]
input:
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
- fai:
type: file
description: FASTA index file
pattern: "*.{fai}"
- dict:
type: file
description: FASTA dictionary file
pattern: "*.{dict}"
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test' ]
- vcf:
type: file
description: Compressed VCF files
@ -38,7 +31,19 @@ input:
- vcf_idx:
type: file
description: VCF Index file
pattern: "*.{fai}"
pattern: "*.vcf.gz.idx"
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
- fai:
type: file
description: FASTA index file
pattern: "*.fasta.fai"
- dict:
type: file
description: FASTA dictionary file
pattern: "*.dict"
output:
- gvcf:
type: file
@ -53,3 +58,4 @@ authors:
- "@sateeshperi"
- "@mjcipriano"
- "@hseabolt"
- "@maxulysse"

View file

@ -11,14 +11,15 @@ process GATK4_CREATESEQUENCEDICTIONARY {
path fasta
output:
path "*.dict" , emit: dict
path "versions.yml" , emit: versions
path "*.dict" , emit: dict
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
def avail_mem = 6
if (!task.memory) {
log.info '[GATK CreateSequenceDictionary] Available memory not known - defaulting to 6GB. Specify process memory requirements to change this.'
@ -26,10 +27,10 @@ process GATK4_CREATESEQUENCEDICTIONARY {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
CreateSequenceDictionary \\
gatk --java-options "-Xmx${avail_mem}g" CreateSequenceDictionary \\
--REFERENCE $fasta \\
--URI $fasta \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -9,9 +9,9 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
input:
tuple val(meta), path(genomicsdb)
path fasta
path fai
path dict
path fasta
path fai
path dict
output:
tuple val(meta), path("*.vcf.gz"), emit: vcf
@ -24,6 +24,7 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK CreateSomaticPanelOfNormals] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -31,11 +32,11 @@ process GATK4_CREATESOMATICPANELOFNORMALS {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
CreateSomaticPanelOfNormals \\
-R $fasta \\
-V gendb://$genomicsdb \\
-O ${prefix}.vcf.gz \\
gatk --java-options "-Xmx${avail_mem}g" CreateSomaticPanelOfNormals \\
--variant gendb://$genomicsdb \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -44,7 +44,7 @@ output:
pattern: "*.vcf.gz"
- tbi:
type: file
description: Index of vcf file
description: Tabix index of vcf file
pattern: "*vcf.gz.tbi"
- versions:
type: file

View file

@ -8,14 +8,14 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(cram)
path(fasta)
path(fai)
path(dict)
tuple val(meta), path(input)
path fasta
path fai
path dict
output:
tuple val(meta), path('*.metrics'), emit: metrics
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -23,7 +23,7 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def crams = cram.collect(){ x -> "-I ".concat(x.toString()) }.join(" ")
def input_list = input.collect(){"--INPUT $it"}.join(" ")
def avail_mem = 3
if (!task.memory) {
@ -32,12 +32,12 @@ process GATK4_ESTIMATELIBRARYCOMPLEXITY {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" EstimateLibraryComplexity \
${crams} \
-O ${prefix}.metrics \
--REFERENCE_SEQUENCE ${fasta} \
--VALIDATION_STRINGENCY SILENT \
--TMP_DIR . $args
gatk --java-options "-Xmx${avail_mem}g" EstimateLibraryComplexity \\
$input_list \\
--OUTPUT ${prefix}.metrics \\
--REFERENCE_SEQUENCE ${fasta} \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -20,7 +20,7 @@ input:
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- cram:
- input:
type: file
description: BAM/CRAM/SAM file
pattern: "*.{bam,cram,sam}"
@ -54,3 +54,4 @@ output:
authors:
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -20,7 +20,8 @@ process GATK4_FASTQTOSAM {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def read_files = meta.single_end ? "-F1 $reads" : "-F1 ${reads[0]} -F2 ${reads[1]}"
def reads_command = meta.single_end ? "--FASTQ $reads" : "--FASTQ ${reads[0]} --FASTQ2 ${reads[1]}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK FastqToSam] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -29,9 +30,10 @@ process GATK4_FASTQTOSAM {
}
"""
gatk --java-options "-Xmx${avail_mem}g" FastqToSam \\
$read_files \\
-O ${prefix}.bam \\
-SM $prefix \\
$reads_command \\
--OUTPUT ${prefix}.bam \\
--SAMPLE_NAME $prefix \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -34,14 +34,14 @@ output:
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: Converted BAM file
pattern: "*.bam"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
authors:
- "@ntoda03"

View file

@ -8,10 +8,10 @@ process GATK4_FILTERMUTECTCALLS {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcf), path(tbi), path(stats), path(orientationbias), path(segmentation), path(contaminationfile), val(contaminationest)
path fasta
path fai
path dict
tuple val(meta), path(vcf), path(vcf_tbi), path(stats), path(orientationbias), path(segmentation), path(table), val(estimate)
path fasta
path fai
path dict
output:
tuple val(meta), path("*.vcf.gz") , emit: vcf
@ -26,20 +26,11 @@ process GATK4_FILTERMUTECTCALLS {
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def orientationbias_options = ''
if (orientationbias) {
orientationbias_options = '--orientation-bias-artifact-priors ' + orientationbias.join(' --orientation-bias-artifact-priors ')
}
def orientationbias_command = orientationbias ? orientationbias.collect{"--orientation-bias-artifact-priors $it"}.join(' ') : ''
def segmentation_command = segmentation ? segmentation.collect{"--tumor-segmentation $it"}.join(' ') : ''
def estimate_command = estimate ? " --contamination-estimate ${estimate} " : ''
def table_command = table ? " --contamination-table ${table} " : ''
def segmentation_options = ''
if (segmentation) {
segmentation_options = '--tumor-segmentation ' + segmentation.join(' --tumor-segmentation ')
}
def contamination_options = contaminationest ? " --contamination-estimate ${contaminationest} " : ''
if (contaminationfile) {
contamination_options = '--contamination-table ' + contaminationfile.join(' --contamination-table ')
}
def avail_mem = 3
if (!task.memory) {
log.info '[GATK FilterMutectCalls] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -48,12 +39,14 @@ process GATK4_FILTERMUTECTCALLS {
}
"""
gatk --java-options "-Xmx${avail_mem}g" FilterMutectCalls \\
-R $fasta \\
-V $vcf \\
$orientationbias_options \\
$segmentation_options \\
$contamination_options \\
-O ${prefix}.vcf.gz \\
--variant $vcf \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
$orientationbias_command \\
$segmentation_command \\
$estimate_command \\
$table_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -26,9 +26,9 @@ input:
type: file
description: compressed vcf file of mutect2calls
pattern: "*.vcf.gz"
- tbi:
- vcf_tbi:
type: file
description: Index of vcf file
description: Tabix index of vcf file
pattern: "*vcf.gz.tbi"
- stats:
type: file
@ -42,13 +42,13 @@ input:
type: list
description: tables containing segmentation information for input vcf. Optional input.
pattern: "*.segmentation.table"
- contaminationfile:
- table:
type: list
description: table(s) containing contamination contamination data for input vcf. Optional input, takes priority over contaminationest.
description: table(s) containing contamination data for input vcf. Optional input, takes priority over estimate.
pattern: "*.contamination.table"
- contaminationest:
- estimate:
type: val
description: estimation of contamination value as a double. Optional input, will only be used if contaminationfile is not specified.
description: estimation of contamination value as a double. Optional input, will only be used if table is not specified.
- fasta:
type: file
description: The reference fasta file
@ -82,3 +82,4 @@ output:
authors:
- "@GCJMackenzie"
- "@maxulysse"

View file

@ -8,7 +8,7 @@ process GATK4_GATHERBQSRREPORTS {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(recal_table)
tuple val(meta), path(table)
output:
tuple val(meta), path("*.table"), emit: table
@ -20,7 +20,7 @@ process GATK4_GATHERBQSRREPORTS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def input = recal_table.collect{"-I ${it}"}.join(' ')
def input_list = table.collect{"--input $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
@ -29,12 +29,11 @@ process GATK4_GATHERBQSRREPORTS {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
GatherBQSRReports \
${input} \
--tmp-dir . \
$args \
--output ${prefix}.table
gatk --java-options "-Xmx${avail_mem}g" GatherBQSRReports \\
$input_list \\
--output ${prefix}.table \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -19,7 +19,7 @@ input:
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- recal_table:
- table:
type: file
description: File(s) containing BQSR table(s)
pattern: "*.table"
@ -30,14 +30,14 @@ output:
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- table:
type: file
description: File containing joined BQSR table
pattern: "*.table"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- recal_table:
type: file
description: File containing joined BQSR table
pattern: "*.table"
authors:
- "@FriederikeHanssen"

View file

@ -10,11 +10,11 @@ process GATK4_GATHERPILEUPSUMMARIES {
input:
tuple val(meta), path(pileup)
path dict
path dict
output:
tuple val(meta), path("*.pileupsummaries.table"), emit: table
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -22,7 +22,7 @@ process GATK4_GATHERPILEUPSUMMARIES {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def input = pileup.collect{ "-I ${it} " }.join(' ')
def input_list = pileup.collect{ "--I $it" }.join(' ')
def avail_mem = 3
if (!task.memory) {
@ -31,11 +31,12 @@ process GATK4_GATHERPILEUPSUMMARIES {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \
GatherPileupSummaries \
--sequence-dictionary ${dict} \
${input} \
-O ${prefix}.pileupsummaries.table
gatk --java-options "-Xmx${avail_mem}g" GatherPileupSummaries \\
$input_list \\
--O ${prefix}.pileupsummaries.table \\
--sequence-dictionary $dict \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -28,14 +28,15 @@ output:
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- table:
type: file
description: pileup summaries table file
pattern: "*.pileupsummaries.table"
- versions:
type: file
description: File containing software versions
pattern: "versions.yml"
- table:
type: file
description: Pileup file
pattern: "*.pileups.table"
authors:
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -8,13 +8,13 @@ process GATK4_GENOMICSDBIMPORT {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcf), path(tbi), path(intervalfile), val(intervalval), path(wspace)
val run_intlist
val run_updatewspace
val input_map
tuple val(meta), path(vcf), path(tbi), path(interval_file), val(interval_value), path(wspace)
val run_intlist
val run_updatewspace
val input_map
output:
tuple val(meta), path("${prefix}") , optional:true, emit: genomicsdb
tuple val(meta), path("$prefix") , optional:true, emit: genomicsdb
tuple val(meta), path("$updated_db") , optional:true, emit: updatedb
tuple val(meta), path("*.interval_list"), optional:true, emit: intervallist
path "versions.yml" , emit: versions
@ -27,22 +27,22 @@ process GATK4_GENOMICSDBIMPORT {
prefix = task.ext.prefix ?: "${meta.id}"
// settings for running default create gendb mode
inputs_command = input_map ? "--sample-name-map ${vcf[0]}" : "${'-V ' + vcf.join(' -V ')}"
dir_command = "--genomicsdb-workspace-path ${prefix}"
intervals_command = intervalfile ? " -L ${intervalfile} " : " -L ${intervalval} "
input_command = input_map ? "--sample-name-map ${vcf[0]}" : vcf.collect(){"--variant $it"}.join(' ')
genomicsdb_command = "--genomicsdb-workspace-path ${prefix}"
interval_command = interval_file ? "--intervals ${interval_file}" : "--intervals ${interval_value}"
// settings changed for running get intervals list mode if run_intlist is true
if (run_intlist) {
inputs_command = ''
dir_command = "--genomicsdb-update-workspace-path ${wspace}"
intervals_command = "--output-interval-list-to-file ${prefix}.interval_list"
genomicsdb_command = "--genomicsdb-update-workspace-path ${wspace}"
interval_command = "--output-interval-list-to-file ${prefix}.interval_list"
}
// settings changed for running update gendb mode. inputs_command same as default, update_db forces module to emit the updated gendb
// settings changed for running update gendb mode. input_command same as default, update_db forces module to emit the updated gendb
if (run_updatewspace) {
dir_command = "--genomicsdb-update-workspace-path ${wspace}"
intervals_command = ''
updated_db = wspace.toString()
genomicsdb_command = "--genomicsdb-update-workspace-path ${wspace}"
interval_command = ''
updated_db = "${wspace}"
}
def avail_mem = 3
@ -53,9 +53,10 @@ process GATK4_GENOMICSDBIMPORT {
}
"""
gatk --java-options "-Xmx${avail_mem}g" GenomicsDBImport \\
$inputs_command \\
$dir_command \\
$intervals_command \\
$input_command \\
$genomicsdb_command \\
$interval_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -10,10 +10,10 @@ process GATK4_GENOTYPEGVCFS {
input:
tuple val(meta), path(gvcf), path(gvcf_index), path(intervals), path(intervals_index)
path fasta
path fasta_index
path fasta_dict
path fai
path dict
path dbsnp
path dbsnp_index
path dbsnp_tbi
output:
tuple val(meta), path("*.vcf.gz"), emit: vcf
@ -26,9 +26,10 @@ process GATK4_GENOTYPEGVCFS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def dbsnp_options = dbsnp ? "-D ${dbsnp}" : ""
def interval_options = intervals ? "-L ${intervals}" : ""
def gvcf_options = gvcf.name.endsWith(".vcf") || gvcf.name.endsWith(".vcf.gz") ? "$gvcf" : "gendb://$gvcf"
def gvcf_command = gvcf.name.endsWith(".vcf") || gvcf.name.endsWith(".vcf.gz") ? "$gvcf" : "gendb://$gvcf"
def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
def interval_command = intervals ? "--intervals $intervals" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[GATK GenotypeGVCFs] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -36,14 +37,14 @@ process GATK4_GENOTYPEGVCFS {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
GenotypeGVCFs \\
$args \\
$interval_options \\
$dbsnp_options \\
-R $fasta \\
-V $gvcf_options \\
-O ${prefix}.vcf.gz
gatk --java-options "-Xmx${avail_mem}g" GenotypeGVCFs \\
--variant $gvcf_command \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
$interval_command \\
$dbsnp_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -21,10 +21,15 @@ input:
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- gvcf:
type: tuple of files
type: file
description: |
Tuple of gVCF(.gz) file (first) and its index (second) or the path to a GenomicsDB (and empty)
pattern: ["*.{vcf,vcf.gz}", "*.{idx,tbi}"]
gVCF(.gz) file or to a GenomicsDB
pattern: "*.{vcf,vcf.gz}"
- gvcf_index:
type: file
description: |
index of gvcf file, or empty when providing GenomicsDB
pattern: "*.{idx,tbi}"
- intervals:
type: file
description: Interval file with the genomic regions included in the library (optional)
@ -35,11 +40,11 @@ input:
type: file
description: Reference fasta file
pattern: "*.fasta"
- fasta_index:
- fai:
type: file
description: Reference fasta index file
pattern: "*.fai"
- fasta_dict:
- dict:
type: file
description: Reference fasta sequence dict file
pattern: "*.dict"
@ -47,8 +52,8 @@ input:
type: file
description: dbSNP VCF file
pattern: "*.vcf.gz"
- dbsnp_index:
type: tuple of files
- dbsnp_tbi:
type: file
description: dbSNP VCF index file
pattern: "*.tbi"
@ -73,3 +78,4 @@ output:
authors:
- "@santiagorevale"
- "@maxulysse"

View file

@ -9,15 +9,15 @@ process GATK4_GETPILEUPSUMMARIES {
input:
tuple val(meta), path(input), path(index), path(intervals)
path fasta
path fai
path dict
path variants
path variants_tbi
path fasta
path fai
path dict
path variants
path variants_tbi
output:
tuple val(meta), path('*.pileups.table'), emit: table
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -25,8 +25,8 @@ process GATK4_GETPILEUPSUMMARIES {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def sitesCommand = intervals ? " -L ${intervals} " : " -L ${variants} "
def reference = fasta ? " -R ${fasta}" :""
def interval_command = intervals ? "--intervals $intervals" : ""
def reference_command = fasta ? "--reference $fasta" : ''
def avail_mem = 3
if (!task.memory) {
@ -36,11 +36,12 @@ process GATK4_GETPILEUPSUMMARIES {
}
"""
gatk --java-options "-Xmx${avail_mem}g" GetPileupSummaries \\
-I $input \\
-V $variants \\
$sitesCommand \\
${reference} \\
-O ${prefix}.pileups.table \\
--input $input \\
--variant $variants \\
--output ${prefix}.pileups.table \\
$reference_command \\
$sites_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -9,15 +9,15 @@ process GATK4_HAPLOTYPECALLER {
input:
tuple val(meta), path(input), path(input_index), path(intervals)
path fasta
path fai
path dict
path dbsnp
path dbsnp_tbi
path fasta
path fai
path dict
path dbsnp
path dbsnp_tbi
output:
tuple val(meta), path("*.vcf.gz"), emit: vcf
tuple val(meta), path("*.tbi") , emit: tbi
tuple val(meta), path("*.tbi") , optional:true, emit: tbi
path "versions.yml" , emit: versions
when:
@ -26,25 +26,24 @@ process GATK4_HAPLOTYPECALLER {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def interval_option = intervals ? "-L ${intervals}" : ""
def dbsnp_option = dbsnp ? "-D ${dbsnp}" : ""
def avail_mem = 3
def dbsnp_command = dbsnp ? "--dbsnp $dbsnp" : ""
def interval_command = intervals ? "--intervals $intervals" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[GATK HaplotypeCaller] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
gatk \\
--java-options "-Xmx${avail_mem}g" \\
HaplotypeCaller \\
-R $fasta \\
-I $input \\
${dbsnp_option} \\
${interval_option} \\
-O ${prefix}.vcf.gz \\
$args \\
--tmp-dir .
gatk --java-options "-Xmx${avail_mem}g" HaplotypeCaller \\
--input $input \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
$dbsnp_command \\
$interval_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -19,6 +19,7 @@ process GATK4_INDEXFEATUREFILE {
script:
def args = task.ext.args ?: ''
def avail_mem = 3
if (!task.memory) {
log.info '[GATK IndexFeatureFile] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -26,10 +27,10 @@ process GATK4_INDEXFEATUREFILE {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
IndexFeatureFile \\
$args \\
-I $feature_file
gatk --java-options "-Xmx${avail_mem}g" IndexFeatureFile \\
--input $feature_file \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -8,7 +8,7 @@ process GATK4_INTERVALLISTTOBED {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(interval)
tuple val(meta), path(intervals)
output:
tuple val(meta), path("*.bed"), emit: bed
@ -29,8 +29,9 @@ process GATK4_INTERVALLISTTOBED {
}
"""
gatk --java-options "-Xmx${avail_mem}g" IntervalListToBed \\
--INPUT ${interval} \\
--INPUT $intervals \\
--OUTPUT ${prefix}.bed \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,11 +8,11 @@ process GATK4_INTERVALLISTTOOLS {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(interval_list)
tuple val(meta), path(intervals)
output:
tuple val(meta), path("*_split/*/*.interval_list"), emit: interval_list
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -20,6 +20,7 @@ process GATK4_INTERVALLISTTOOLS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK IntervalListTools] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -30,10 +31,10 @@ process GATK4_INTERVALLISTTOOLS {
mkdir ${prefix}_split
gatk --java-options "-Xmx${avail_mem}g" \\
IntervalListTools \\
-I ${interval_list} \\
-O ${prefix}_split \\
gatk --java-options "-Xmx${avail_mem}g" IntervalListTools \\
--INPUT $intervals \\
--OUTPUT ${prefix}_split \\
--TMP_DIR . \\
$args
python3 <<CODE

View file

@ -20,8 +20,8 @@ process GATK4_LEARNREADORIENTATIONMODEL {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def inputs_list = []
f1r2.each() { a -> inputs_list.add(" -I " + a) }
def input_list = f1r2.collect{"--input $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK LearnReadOrientationModel] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -29,10 +29,10 @@ process GATK4_LEARNREADORIENTATIONMODEL {
avail_mem = task.memory.giga
}
"""
gatk --java-options "-Xmx${avail_mem}g" \\
LearnReadOrientationModel \\
${inputs_list.join(' ')} \\
-O ${prefix}.tar.gz \\
gatk --java-options "-Xmx${avail_mem}g" LearnReadOrientationModel \\
$input_list \\
--output ${prefix}.tar.gz \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,11 +8,11 @@ process GATK4_MARKDUPLICATES {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(bams)
tuple val(meta), path(bam)
output:
tuple val(meta), path("*.bam") , emit: bam
tuple val(meta), path("*.bai") , emit: bai
tuple val(meta), path("*.bai") , optional:true, emit: bai
tuple val(meta), path("*.metrics"), emit: metrics
path "versions.yml" , emit: versions
@ -22,7 +22,8 @@ process GATK4_MARKDUPLICATES {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def bam_list = bams.collect(){ bam -> "--INPUT ".concat(bam.toString()) }.join(" ")
def input_list = bam.collect{"--INPUT $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MarkDuplicates] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -31,11 +32,10 @@ process GATK4_MARKDUPLICATES {
}
"""
gatk --java-options "-Xmx${avail_mem}g" MarkDuplicates \\
$bam_list \\
$input_list \\
--OUTPUT ${prefix}.bam \\
--METRICS_FILE ${prefix}.metrics \\
--TMP_DIR . \\
--CREATE_INDEX true \\
--OUTPUT ${prefix}.bam \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -49,3 +49,4 @@ output:
authors:
- "@ajodeh-juma"
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -0,0 +1,50 @@
process GATK4_MARKDUPLICATES_SPARK {
tag "$meta.id"
label 'process_high'
conda (params.enable_conda ? "bioconda::gatk4=4.2.3.0" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/gatk4:4.2.3.0--hdfd78af_0' :
'broadinstitute/gatk:4.2.3.0' }"
input:
tuple val(meta), path(bam)
path fasta
path fasta_fai
path dict
output:
tuple val(meta), path("${prefix}"), emit: output
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
script:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
def input_list = bam.collect{"--input $it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MarkDuplicatesSpark] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
} else {
avail_mem = task.memory.giga
}
"""
export SPARK_USER=spark3
gatk --java-options "-Xmx${avail_mem}g" MarkDuplicatesSpark \\
$input_list \\
--output $prefix \\
--reference $fasta \\
--spark-master local[${task.cpus}] \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml
"${task.process}":
gatk4: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
END_VERSIONS
"""
}

View file

@ -0,0 +1,60 @@
name: gatk4_markduplicates_spark
description: This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.
keywords:
- markduplicates
- bam
- sort
tools:
- gatk4:
description:
Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
with a primary focus on variant discovery and genotyping. Its powerful processing engine
and high-performance computing features make it capable of taking on projects of any size.
homepage: https://gatk.broadinstitute.org/hc/en-us
documentation: https://gatk.broadinstitute.org/hc/en-us/articles/360037052812-MarkDuplicates-Picard-
tool_dev_url: https://github.com/broadinstitute/gatk
doi: 10.1158/1538-7445.AM2017-3590
licence: ["MIT"]
input:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- bam:
type: file
description: Sorted BAM file
pattern: "*.{bam}"
- fasta:
type: file
description: The reference fasta file
pattern: "*.fasta"
- fai:
type: file
description: Index of reference fasta file
pattern: "*.fasta.fai"
- dict:
type: file
description: GATK sequence dictionary
pattern: "*.dict"
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: Marked duplicates BAM file
pattern: "*.{bam}"
authors:
- "@ajodeh-juma"
- "@FriederikeHanssen"
- "@maxulysse"

View file

@ -22,6 +22,7 @@ process GATK4_MERGEBAMALIGNMENT {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MergeBamAlignment] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -30,10 +31,11 @@ process GATK4_MERGEBAMALIGNMENT {
}
"""
gatk --java-options "-Xmx${avail_mem}g" MergeBamAlignment \\
-ALIGNED $aligned \\
-UNMAPPED $unmapped \\
-R $fasta \\
-O ${prefix}.bam \\
--UNMAPPED_BAM $unmapped \\
--ALIGNED_BAM $aligned \\
--OUTPUT ${prefix}.bam \\
--REFERENCE_SEQUENCE $fasta \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -9,6 +9,7 @@ process GATK4_MERGEMUTECTSTATS {
input:
tuple val(meta), path(stats)
output:
tuple val(meta), path("*.vcf.gz.stats"), emit: stats
path "versions.yml" , emit: versions
@ -19,7 +20,7 @@ process GATK4_MERGEMUTECTSTATS {
script:
def args = task.ext.args ?: ''
prefix = task.ext.prefix ?: "${meta.id}"
def input = stats.collect{ " -stats ${it} "}.join()
def input_list = stats.collect{ "--stats ${it}"}.join(' ')
def avail_mem = 3
if (!task.memory) {
@ -29,8 +30,9 @@ process GATK4_MERGEMUTECTSTATS {
}
"""
gatk --java-options "-Xmx${avail_mem}g" MergeMutectStats \\
${input} \\
-output ${meta.id}.vcf.gz.stats \\
$input_list \\
--output ${prefix}.vcf.gz.stats \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,9 +8,8 @@ process GATK4_MERGEVCFS {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcfs)
path ref_dict
val use_ref_dict
tuple val(meta), path(vcf)
path dict
output:
tuple val(meta), path('*.vcf.gz'), emit: vcf
@ -22,13 +21,9 @@ process GATK4_MERGEVCFS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def input_list = vcf.collect{ "--INPUT $it"}.join(' ')
def reference_command = dict ? "--SEQUENCE_DICTIONARY $dict" : ""
// Make list of VCFs to merge
def input = ""
for (vcf in vcfs) {
input += " I=${vcf}"
}
def ref = use_ref_dict ? "D=${ref_dict}" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[GATK MergeVcfs] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -37,9 +32,10 @@ process GATK4_MERGEVCFS {
}
"""
gatk --java-options "-Xmx${avail_mem}g" MergeVcfs \\
$input \\
O=${prefix}.vcf.gz \\
$ref \\
$input_list \\
--OUTPUT ${prefix}.vcf.gz \\
$reference_command \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,10 +8,7 @@ process GATK4_MUTECT2 {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta) , path(input) , path(input_index) , path(intervals), val(which_norm)
val run_single
val run_pon
val run_mito
tuple val(meta), path(input), path(input_index), path(intervals)
path fasta
path fai
path dict
@ -33,28 +30,10 @@ process GATK4_MUTECT2 {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def panels_command = ''
def normals_command = ''
def inputs_command = '-I ' + input.join( ' -I ')
def interval = intervals ? "-L ${intervals}" : ""
if(run_pon) {
panels_command = ''
normals_command = ''
} else if(run_single) {
panels_command = " --germline-resource $germline_resource --panel-of-normals $panel_of_normals"
normals_command = ''
} else if(run_mito){
panels_command = "-L ${intervals} --mitochondria-mode"
normals_command = ''
} else {
panels_command = " --germline-resource $germline_resource --panel-of-normals $panel_of_normals --f1r2-tar-gz ${prefix}.f1r2.tar.gz"
normals_command = '-normal ' + which_norm.join( ' -normal ')
}
def inputs = input.collect{ "--input $it"}.join(" ")
def interval_command = intervals ? "--intervals $intervals" : ""
def pon_command = panel_of_normals ? "--panel-of-normals $panel_of_normals" : ""
def gr_command = germline_resource ? "--germline-resource $germline_resource" : ""
def avail_mem = 3
if (!task.memory) {
@ -64,12 +43,13 @@ process GATK4_MUTECT2 {
}
"""
gatk --java-options "-Xmx${avail_mem}g" Mutect2 \\
-R ${fasta} \\
${inputs_command} \\
${normals_command} \\
${panels_command} \\
${interval} \\
-O ${prefix}.vcf.gz \\
$inputs \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
$pon_command \\
$gr_command \\
$interval_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -34,22 +34,6 @@ input:
type: File/string
description: Specify region the tools is run on.
pattern: ".{bed,interval_list}/chrM"
- which_norm:
type: list
description: optional list of sample headers contained in the normal sample bam files (these are required for tumor_normal_pair mode)
pattern: "testN"
- run_single:
type: boolean
description: Specify whether or not to run in tumor_single mode instead of tumor_normal_pair mode (will be ignored if run_pon is also true)
pattern: "true/false"
- run_pon:
type: boolean
description: Specify whether or not to run in panel_of_normal mode instead of tumor_normal_pair mode
pattern: "true/false"
- run_mito:
type: boolean
description: Specify whether or not to run in mitochondria-mode instead of tumor_normal_pair mode
pattern: "true/false"
- fasta:
type: file
description: The reference fasta file

View file

@ -20,6 +20,7 @@ process GATK4_REVERTSAM {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK RevertSam] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -28,8 +29,9 @@ process GATK4_REVERTSAM {
}
"""
gatk --java-options "-Xmx${avail_mem}g" RevertSam \\
I=$bam \\
O=${prefix}.reverted.bam \\
--INPUT $bam \\
--OUTPUT ${prefix}.reverted.bam \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -20,7 +20,8 @@ process GATK4_SAMTOFASTQ {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def output = meta.single_end ? "FASTQ=${prefix}.fastq.gz" : "FASTQ=${prefix}_1.fastq.gz SECOND_END_FASTQ=${prefix}_2.fastq.gz"
def output = meta.single_end ? "--FASTQ ${prefix}.fastq.gz" : "--FASTQ ${prefix}_1.fastq.gz --SECOND_END_FASTQ ${prefix}_2.fastq.gz"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK SamToFastq] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -29,8 +30,9 @@ process GATK4_SAMTOFASTQ {
}
"""
gatk --java-options "-Xmx${avail_mem}g" SamToFastq \\
I=$bam \\
--INPUT $bam \\
$output \\
--TMP_DIR . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -21,6 +21,7 @@ process GATK4_SELECTVARIANTS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK VariantFiltration] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -29,8 +30,9 @@ process GATK4_SELECTVARIANTS {
}
"""
gatk --java-options "-Xmx${avail_mem}G" SelectVariants \\
-V $vcf \\
-O ${prefix}.selectvariants.vcf.gz \\
--variant $vcf \\
--output ${prefix}.selectvariants.vcf.gz \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,7 +8,7 @@ process GATK4_SPLITNCIGARREADS {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(bam)
tuple val(meta), path(bam), path(bai), path(intervals)
path fasta
path fai
path dict
@ -23,6 +23,8 @@ process GATK4_SPLITNCIGARREADS {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def interval_command = intervals ? "--intervals $intervals" : ""
def avail_mem = 3
if (!task.memory) {
log.info '[GATK SplitNCigarReads] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -31,9 +33,11 @@ process GATK4_SPLITNCIGARREADS {
}
"""
gatk --java-options "-Xmx${avail_mem}g" SplitNCigarReads \\
-R $fasta \\
-I $bam \\
-O ${prefix}.bam \\
--input $bam \\
--output ${prefix}.bam \\
--reference $fasta \\
$interval_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -23,6 +23,13 @@ input:
type: list
description: BAM/SAM/CRAM file containing reads
pattern: "*.{bam,sam,cram}"
- bai:
type: list
description: BAI/SAI/CRAI index file (optional)
pattern: "*.{bai,sai,crai}"
- intervals:
type: file
description: Bed file with the genomic regions included in the library (optional)
- fasta:
type: file
description: The reference fasta file

View file

@ -8,7 +8,7 @@ process GATK4_VARIANTFILTRATION {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcf), path(vcf_tbi)
tuple val(meta), path(vcf), path(tbi)
path fasta
path fai
path dict
@ -24,6 +24,7 @@ process GATK4_VARIANTFILTRATION {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
def avail_mem = 3
if (!task.memory) {
log.info '[GATK VariantFiltration] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.'
@ -32,9 +33,10 @@ process GATK4_VARIANTFILTRATION {
}
"""
gatk --java-options "-Xmx${avail_mem}G" VariantFiltration \\
-R $fasta \\
-V $vcf \\
-O ${prefix}.vcf.gz \\
--variant $vcf \\
--output ${prefix}.vcf.gz \\
--reference $fasta \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -8,11 +8,11 @@ process GATK4_VARIANTRECALIBRATOR {
'quay.io/biocontainers/gatk4:4.2.5.0--hdfd78af_0' }"
input:
tuple val(meta), path(vcf) , path(tbi)
path fasta
path fai
path dict
tuple path(resvcfs), path(restbis), val(reslabels)
tuple val(meta), path(vcf), path(tbi)
tuple path(vcfs), path(tbis), val(labels)
path fasta
path fai
path dict
output:
tuple val(meta), path("*.recal") , emit: recal
@ -27,8 +27,8 @@ process GATK4_VARIANTRECALIBRATOR {
script:
def args = task.ext.args ?: ''
def prefix = task.ext.prefix ?: "${meta.id}"
refCommand = fasta ? "-R ${fasta} " : ''
resourceCommand = '--resource:' + reslabels.join( ' --resource:')
def reference_command = fasta ? "--reference $fasta " : ''
def resource_command = labels.collect{"--resource:$it"}.join(' ')
def avail_mem = 3
if (!task.memory) {
@ -38,11 +38,12 @@ process GATK4_VARIANTRECALIBRATOR {
}
"""
gatk --java-options "-Xmx${avail_mem}g" VariantRecalibrator \\
${refCommand} \\
-V ${vcf} \\
-O ${prefix}.recal \\
--variant $vcf \\
--output ${prefix}.recal \\
--tranches-file ${prefix}.tranches \\
${resourceCommand} \\
$reference_command \\
$resource_command \\
--tmp-dir . \\
$args
cat <<-END_VERSIONS > versions.yml

View file

@ -4,8 +4,8 @@ process GUNZIP {
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(archive)

View file

@ -9,11 +9,11 @@ process KAIJU_KAIJU {
input:
tuple val(meta), path(reads)
tuple path(db), path(dbnodes)
path(db)
output:
tuple val(meta), path('*.tsv'), emit: results
path "versions.yml" , emit: versions
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -23,11 +23,13 @@ process KAIJU_KAIJU {
def prefix = task.ext.prefix ?: "${meta.id}"
def input = meta.single_end ? "-i ${reads}" : "-i ${reads[0]} -j ${reads[1]}"
"""
dbnodes=`find -L ${db} -name "*nodes.dmp"`
dbname=`find -L ${db} -name "*.fmi" -not -name "._*"`
kaiju \\
$args \\
-z $task.cpus \\
-t ${dbnodes} \\
-f ${db} \\
-t \$dbnodes \\
-f \$dbname \\
-o ${prefix}.tsv \\
$input

View file

@ -50,3 +50,4 @@ output:
authors:
- "@talnor"
- "@sofstam"
- "@jfy133"

View file

@ -0,0 +1,40 @@
process KAIJU_KAIJU2TABLE {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::kaiju=1.8.2" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/kaiju:1.8.2--h5b5514e_1':
'quay.io/biocontainers/kaiju:1.8.2--h2e03b76_0' }"
input:
tuple val(meta), path(results)
path db
val taxon_rank
output:
tuple val(meta), path('*.txt'), emit: summary
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}"
"""
dbnodes=`find -L ${db} -name "*nodes.dmp"`
dbname=`find -L ${db} -name "*.fmi" -not -name "._*"`
kaiju2table $args \\
-t \$dbnodes \\
-n \$dbname \\
-r ${taxon_rank} \\
-o ${prefix}.txt \\
${results}
cat <<-END_VERSIONS > versions.yml
"${task.process}":
kaiju: \$(echo \$( kaiju -h 2>&1 | sed -n 1p | sed 's/^.*Kaiju //' ))
END_VERSIONS
"""
}

View file

@ -0,0 +1,50 @@
name: "kaiju_kaiju2table"
description: write your description here
keywords:
- classify
- metagenomics
tools:
- kaiju:
description: Fast and sensitive taxonomic classification for metagenomics
homepage: https://kaiju.binf.ku.dk/
documentation: https://github.com/bioinformatics-centre/kaiju/blob/master/README.md
tool_dev_url: https://github.com/bioinformatics-centre/kaiju
doi: "10.1038/ncomms11257"
licence: ["GNU 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 kaiju classification results
pattern: "*.{txt}"
- taxon_rank:
type: string
description: |
Taxonomic rank to display in report
pattern: "phylum|class|order|family|genus|species"
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"
- results:
type: file
description: |
Summary table for a given taxonomic rank
pattern: "*.{tsv}"
authors:
- "@sofstam"
- "@talnor"
- "@jfy133"

View file

@ -10,12 +10,15 @@ process KRAKEN2_KRAKEN2 {
input:
tuple val(meta), path(reads)
path db
val save_output_fastqs
val save_reads_assignment
output:
tuple val(meta), path('*classified*') , emit: classified
tuple val(meta), path('*unclassified*'), emit: unclassified
tuple val(meta), path('*report.txt') , emit: txt
path "versions.yml" , emit: versions
tuple val(meta), path('*classified*') , optional:true, emit: classified_reads_fastq
tuple val(meta), path('*unclassified*') , optional:true, emit: unclassified_reads_fastq
tuple val(meta), path('*classifiedreads*'), optional:true, emit: classified_reads_assignment
tuple val(meta), path('*report.txt') , emit: report
path "versions.yml" , emit: versions
when:
task.ext.when == null || task.ext.when
@ -26,19 +29,25 @@ process KRAKEN2_KRAKEN2 {
def paired = meta.single_end ? "" : "--paired"
def classified = meta.single_end ? "${prefix}.classified.fastq" : "${prefix}.classified#.fastq"
def unclassified = meta.single_end ? "${prefix}.unclassified.fastq" : "${prefix}.unclassified#.fastq"
def classified_command = save_output_fastqs ? "--classified-out ${classified}" : ""
def unclassified_command = save_output_fastqs ? "--unclassified-out ${unclassified}" : ""
def readclassification_command = save_reads_assignment ? "--output ${prefix}.kraken2.classifiedreads.txt" : ""
def compress_reads_command = save_output_fastqs ? "pigz -p $task.cpus *.fastq" : ""
"""
kraken2 \\
--db $db \\
--threads $task.cpus \\
--unclassified-out $unclassified \\
--classified-out $classified \\
--report ${prefix}.kraken2.report.txt \\
--gzip-compressed \\
$unclassified_command \\
$classified_command \\
$readclassification_command \\
$paired \\
$args \\
$reads
pigz -p $task.cpus *.fastq
$compress_reads_command
cat <<-END_VERSIONS > versions.yml
"${task.process}":

View file

@ -27,25 +27,40 @@ input:
- db:
type: directory
description: Kraken2 database
- save_output_fastqs:
type: boolean
description: |
If true, optional commands are added to save classified and unclassified reads
as fastq files
- save_reads_assignment:
type: boolean
description: |
If true, an optional command is added to save a file reporting the taxonomic
classification of each input read
output:
- meta:
type: map
description: |
Groovy Map containing sample information
e.g. [ id:'test', single_end:false ]
- classified:
- classified_reads_fastq:
type: file
description: |
Reads classified to belong to any of the taxa
Reads classified as belonging to any of the taxa
on the Kraken2 database.
pattern: "*{fastq.gz}"
- unclassified:
- unclassified_reads_fastq:
type: file
description: |
Reads not classified to belong to any of the taxa
Reads not classified to any of the taxa
on the Kraken2 database.
pattern: "*{fastq.gz}"
- txt:
- classified_reads_assignment:
type: file
description: |
Kraken2 output file indicating the taxonomic assignment of
each input read
- report:
type: file
description: |
Kraken2 report containing stats about classified

View file

@ -0,0 +1,34 @@
process KRONA_KTIMPORTTEXT {
tag "$meta.id"
label 'process_low'
conda (params.enable_conda ? "bioconda::krona=2.8.1" : null)
container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
'https://depot.galaxyproject.org/singularity/krona:2.8.1--pl5321hdfd78af_1':
'quay.io/biocontainers/krona:2.8.1--pl5321hdfd78af_1' }"
input:
tuple val(meta), path(report)
output:
tuple val(meta), path ('*.html'), emit: html
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}"
"""
ktImportText \\
$args \\
-o ${prefix}.html \\
$report
cat <<-END_VERSIONS > versions.yml
"${task.process}":
krona: \$( echo \$(ktImportText 2>&1) | sed 's/^.*KronaTools //g; s/- ktImportText.*\$//g')
END_VERSIONS
"""
}

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