diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md deleted file mode 100644 index f1122ea3..00000000 --- a/.github/ISSUE_TEMPLATE/bug_report.md +++ /dev/null @@ -1,64 +0,0 @@ ---- -name: Bug report -about: Report something that is broken or incorrect -title: "[BUG]" ---- - - - -## 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 - - - -## Steps to reproduce - -Steps to reproduce the behaviour: - -1. Command line: -2. See error: - -## Expected behaviour - - - -## Log files - -Have you provided the following extra information/files: - -- [ ] The command used to run the module -- [ ] The `.nextflow.log` file - -## System - -- Hardware: -- Executor: -- OS: -- Version - -## Nextflow Installation - -- Version: - -## Container engine - -- Engine: -- version: -- Image tag: - -## Additional context - - diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml new file mode 100644 index 00000000..74907cfe --- /dev/null +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -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: diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md deleted file mode 100644 index 72d6c058..00000000 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ /dev/null @@ -1,32 +0,0 @@ ---- -name: Feature request -about: Suggest an idea for nf-core/modules -title: "[FEATURE]" ---- - - - -## Is your feature request related to a problem? Please describe - - - - - -## Describe the solution you'd like - - - -## Describe alternatives you've considered - - - -## Additional context - - diff --git a/.github/ISSUE_TEMPLATE/feature_request.yml b/.github/ISSUE_TEMPLATE/feature_request.yml new file mode 100644 index 00000000..316fba90 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/feature_request.yml @@ -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: | + + 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. diff --git a/.github/ISSUE_TEMPLATE/new_module.md b/.github/ISSUE_TEMPLATE/new_module.md deleted file mode 100644 index 5c7e61cc..00000000 --- a/.github/ISSUE_TEMPLATE/new_module.md +++ /dev/null @@ -1,26 +0,0 @@ ---- -name: New module -about: Suggest a new module for nf-core/modules -title: "new module: TOOL/SUBTOOL" -label: new module ---- - - - -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 diff --git a/.github/ISSUE_TEMPLATE/new_module.yml b/.github/ISSUE_TEMPLATE/new_module.yml new file mode 100644 index 00000000..2d3e9d47 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/new_module.yml @@ -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 diff --git a/modules/antismash/antismashlitedownloaddatabases/main.nf b/modules/antismash/antismashlitedownloaddatabases/main.nf index 1853d80a..72314eee 100644 --- a/modules/antismash/antismashlitedownloaddatabases/main.nf +++ b/modules/antismash/antismashlitedownloaddatabases/main.nf @@ -7,8 +7,9 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES { 'quay.io/biocontainers/antismash-lite:6.0.1--pyhdfd78af_1' }" /* - These files are normally downloaded 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. + 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 { @@ -26,6 +27,9 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES { output: path("antismash_db") , emit: database + path("css"), emit: css_dir + path("detection"), emit: detection_dir + path("modules"), emit: modules_dir path "versions.yml", emit: versions when: @@ -40,7 +44,7 @@ process ANTISMASH_ANTISMASHLITEDOWNLOADDATABASES { cat <<-END_VERSIONS > versions.yml "${task.process}": - antismash: \$(antismash --version | sed 's/antiSMASH //') + antismash-lite: \$(antismash --version | sed 's/antiSMASH //') END_VERSIONS """ } diff --git a/modules/antismash/antismashlitedownloaddatabases/meta.yml b/modules/antismash/antismashlitedownloaddatabases/meta.yml index ad393bae..619dc8c2 100644 --- a/modules/antismash/antismashlitedownloaddatabases/meta.yml +++ b/modules/antismash/antismashlitedownloaddatabases/meta.yml @@ -27,17 +27,17 @@ 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 use 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. + 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 use 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. + 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 use 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. + 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: @@ -50,6 +50,21 @@ output: type: directory description: Download directory for antiSMASH databases pattern: "antismash_db" + - css_dir: + 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" + - detection_dir: + 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" + - modules_dir: + 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" authors: - "@jasmezz" diff --git a/modules/bamtools/split/main.nf b/modules/bamtools/split/main.nf index 014e5cdb..aaa5b663 100644 --- a/modules/bamtools/split/main.nf +++ b/modules/bamtools/split/main.nf @@ -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}": diff --git a/modules/bamtools/split/meta.yml b/modules/bamtools/split/meta.yml index 0e848212..8af701f0 100644 --- a/modules/bamtools/split/meta.yml +++ b/modules/bamtools/split/meta.yml @@ -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" diff --git a/modules/custom/getchromsizes/main.nf b/modules/custom/getchromsizes/main.nf index bbcfa9be..0eabf3a4 100644 --- a/modules/custom/getchromsizes/main.nf +++ b/modules/custom/getchromsizes/main.nf @@ -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 diff --git a/modules/diamond/blastp/main.nf b/modules/diamond/blastp/main.nf index 955952dc..033186ea 100644 --- a/modules/diamond/blastp/main.nf +++ b/modules/diamond/blastp/main.nf @@ -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}": diff --git a/modules/diamond/blastp/meta.yml b/modules/diamond/blastp/meta.yml index 8ac1d371..3aa81e53 100644 --- a/modules/diamond/blastp/meta.yml +++ b/modules/diamond/blastp/meta.yml @@ -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" diff --git a/modules/diamond/blastx/main.nf b/modules/diamond/blastx/main.nf index 3700bd36..d3272279 100644 --- a/modules/diamond/blastx/main.nf +++ b/modules/diamond/blastx/main.nf @@ -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 "${task.process}": diff --git a/modules/diamond/blastx/meta.yml b/modules/diamond/blastx/meta.yml index 7eb3d7b4..2dcd7bc6 100644 --- a/modules/diamond/blastx/meta.yml +++ b/modules/diamond/blastx/meta.yml @@ -28,12 +28,44 @@ input: type: directory description: Directory containing the nucelotide blast database pattern: "*" + - out_ext: + type: string + description: | + Specify the type of output file to be generated. `blast` corresponds to + BLAST pairwise format. `xml` corresponds to BLAST xml format. + `txt` corresponds to to BLAST tabular format. `tsv` corresponds to + taxonomic classification format. + pattern: "blast|xml|txt|daa|sam|tsv|paf" output: + - blast: + type: file + description: File containing blastp hits + pattern: "*.{blast}" + - xml: + type: file + description: File containing blastp hits + pattern: "*.{xml}" - txt: type: file - description: File containing blastx hits - pattern: "*.{blastx.txt}" + description: File containing hits in tabular BLAST format. + pattern: "*.{txt}" + - daa: + type: file + description: File containing hits DAA format + pattern: "*.{daa}" + - sam: + type: file + description: File containing aligned reads in SAM format + pattern: "*.{sam}" + - tsv: + type: file + description: Tab separated file containing taxonomic classification of hits + pattern: "*.{tsv}" + - paf: + type: file + description: File containing aligned reads in pairwise mapping format format + pattern: "*.{paf}" - versions: type: file description: File containing software versions @@ -41,3 +73,4 @@ output: authors: - "@spficklin" + - "@jfy133" diff --git a/modules/diamond/makedb/main.nf b/modules/diamond/makedb/main.nf index e3d62f00..a76a94e5 100644 --- a/modules/diamond/makedb/main.nf +++ b/modules/diamond/makedb/main.nf @@ -2,12 +2,10 @@ process DIAMOND_MAKEDB { tag "$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 "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/diamond:2.0.9--hdcc8f71_0' : - 'quay.io/biocontainers/diamond:2.0.9--hdcc8f71_0' }" + 'https://depot.galaxyproject.org/singularity/diamond:2.0.15--hb97b32f_0' : + 'quay.io/biocontainers/diamond:2.0.15--hb97b32f_0' }" input: path fasta diff --git a/modules/elprep/merge/main.nf b/modules/elprep/merge/main.nf new file mode 100644 index 00000000..d5ffc497 --- /dev/null +++ b/modules/elprep/merge/main.nf @@ -0,0 +1,43 @@ +process ELPREP_MERGE { + tag "$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 + """ +} diff --git a/modules/elprep/merge/meta.yml b/modules/elprep/merge/meta.yml new file mode 100644 index 00000000..1f49b1a0 --- /dev/null +++ b/modules/elprep/merge/meta.yml @@ -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" diff --git a/modules/gatk4/haplotypecaller/main.nf b/modules/gatk4/haplotypecaller/main.nf index 57f69ecd..2cd9e7d4 100644 --- a/modules/gatk4/haplotypecaller/main.nf +++ b/modules/gatk4/haplotypecaller/main.nf @@ -17,7 +17,7 @@ process GATK4_HAPLOTYPECALLER { 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: diff --git a/modules/gatk4/markduplicates/main.nf b/modules/gatk4/markduplicates/main.nf index e8a98156..2650925b 100644 --- a/modules/gatk4/markduplicates/main.nf +++ b/modules/gatk4/markduplicates/main.nf @@ -12,7 +12,7 @@ process GATK4_MARKDUPLICATES { 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 diff --git a/modules/gatk4/splitncigarreads/main.nf b/modules/gatk4/splitncigarreads/main.nf index f7c559d9..85e5daa8 100644 --- a/modules/gatk4/splitncigarreads/main.nf +++ b/modules/gatk4/splitncigarreads/main.nf @@ -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 +23,7 @@ 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) { @@ -35,6 +36,7 @@ process GATK4_SPLITNCIGARREADS { --input $bam \\ --output ${prefix}.bam \\ --reference $fasta \\ + $interval_command \\ --tmp-dir . \\ $args diff --git a/modules/gatk4/splitncigarreads/meta.yml b/modules/gatk4/splitncigarreads/meta.yml index 407e80bd..76bfdcd3 100644 --- a/modules/gatk4/splitncigarreads/meta.yml +++ b/modules/gatk4/splitncigarreads/meta.yml @@ -23,6 +23,13 @@ input: type: list description: BAM/SAM/CRAM file containing reads pattern: "*.{bam,sam,cram}" + - bai: + type: list + description: BAI/SAI/CRAI index file (optional) + pattern: "*.{bai,sai,crai}" + - intervals: + type: file + description: Bed file with the genomic regions included in the library (optional) - fasta: type: file description: The reference fasta file diff --git a/modules/krona/ktimporttext/main.nf b/modules/krona/ktimporttext/main.nf new file mode 100644 index 00000000..de0cfc22 --- /dev/null +++ b/modules/krona/ktimporttext/main.nf @@ -0,0 +1,34 @@ +process KRONA_KTIMPORTTEXT { + tag "$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 + """ +} diff --git a/modules/krona/ktimporttext/meta.yml b/modules/krona/ktimporttext/meta.yml new file mode 100644 index 00000000..a7108e0d --- /dev/null +++ b/modules/krona/ktimporttext/meta.yml @@ -0,0 +1,47 @@ +name: "krona_ktimporttext" +description: Creates a Krona chart from text files listing quantities and lineages. +keywords: + - plot + - taxonomy + - interactive + - html + - visualisation + - krona chart + - metagenomics +tools: + - krona: + description: Krona Tools is a set of scripts to create Krona charts from several Bioinformatics tools as well as from text and XML files. + homepage: https://github.com/marbl/Krona/wiki/KronaTools + documentation: http://manpages.ubuntu.com/manpages/impish/man1/ktImportTaxonomy.1.html + tool_dev_url: https://github.com/marbl/Krona + doi: 10.1186/1471-2105-12-385 + licence: https://raw.githubusercontent.com/marbl/Krona/master/KronaTools/LICENSE.txt + +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test'] + - report: + type: file + description: "Tab-delimited text file. Each line should be a number followed by a list of wedges to contribute to (starting from the highest level). If no wedges are listed (and just a quantity is given), it will contribute to the top level. If the same lineage is listed more than once, the values will be added. Quantities can be omitted if -q is specified. Lines beginning with '#' will be ignored." + pattern: "*.{txt}" + +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test' ] + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" + - html: + type: file + description: A html file containing an interactive krona plot. + pattern: "*.{html}" + +authors: + - "@jianhong" diff --git a/modules/minimap2/align/main.nf b/modules/minimap2/align/main.nf index fe06f14d..08ac6eef 100644 --- a/modules/minimap2/align/main.nf +++ b/modules/minimap2/align/main.nf @@ -2,18 +2,22 @@ process MINIMAP2_ALIGN { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? 'bioconda::minimap2=2.21' : null) + conda (params.enable_conda ? 'bioconda::minimap2=2.21 bioconda::samtools=1.12' : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/minimap2:2.21--h5bf99c6_0' : - 'quay.io/biocontainers/minimap2:2.21--h5bf99c6_0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' : + 'quay.io/biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' }" input: tuple val(meta), path(reads) path reference + val bam_format + val cigar_paf_format + val cigar_bam output: - tuple val(meta), path("*.paf"), emit: paf - path "versions.yml" , emit: versions + tuple val(meta), path("*.paf"), optional: true, emit: paf + tuple val(meta), path("*.bam"), optional: true, emit: bam + path "versions.yml" , emit: versions when: task.ext.when == null || task.ext.when @@ -22,13 +26,19 @@ process MINIMAP2_ALIGN { def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" def input_reads = meta.single_end ? "$reads" : "${reads[0]} ${reads[1]}" + def bam_output = bam_format ? "-a | samtools sort | samtools view -@ ${task.cpus} -b -h -o ${prefix}.bam" : "-o ${prefix}.paf" + def cigar_paf = cigar_paf_format && !bam_format ? "-c" : '' + def set_cigar_bam = cigar_bam && bam_format ? "-L" : '' """ minimap2 \\ $args \\ -t $task.cpus \\ $reference \\ $input_reads \\ - > ${prefix}.paf + $cigar_paf \\ + $set_cigar_bam \\ + $bam_output + cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/minimap2/align/meta.yml b/modules/minimap2/align/meta.yml index 89e24283..991b39a0 100644 --- a/modules/minimap2/align/meta.yml +++ b/modules/minimap2/align/meta.yml @@ -29,6 +29,17 @@ input: type: file description: | Reference database in FASTA format. + - bam_format: + type: boolean + description: Specify that output should be in BAM format + - cigar_paf_format: + type: boolean + description: Specify that output CIGAR should be in PAF format + - cigar_bam: + type: boolean + description: | + Write CIGAR with >65535 ops at the CG tag. This is recommended when + doing XYZ (https://github.com/lh3/minimap2#working-with-65535-cigar-operations) output: - meta: type: map @@ -39,9 +50,16 @@ output: type: file description: Alignment in PAF format pattern: "*.paf" + - bam: + type: file + description: Alignment in BAM format + pattern: "*.bam" - versions: type: file description: File containing software versions pattern: "versions.yml" authors: - "@heuermh" + - "@sofstam" + - "@sateeshperi" + - "@jfy133" diff --git a/modules/phantompeakqualtools/main.nf b/modules/phantompeakqualtools/main.nf index 0362b2e7..d8f73342 100644 --- a/modules/phantompeakqualtools/main.nf +++ b/modules/phantompeakqualtools/main.nf @@ -22,11 +22,12 @@ process PHANTOMPEAKQUALTOOLS { task.ext.when == null || task.ext.when script: - def args = task.ext.args ?: '' + def args = task.ext.args ?: '' + def args2 = task.ext.args2 ?: '' def prefix = task.ext.prefix ?: "${meta.id}" """ RUN_SPP=`which run_spp.R` - Rscript $args -e "library(caTools); source(\\"\$RUN_SPP\\")" -c="$bam" -savp="${prefix}.spp.pdf" -savd="${prefix}.spp.Rdata" -out="${prefix}.spp.out" + Rscript $args -e "library(caTools); source(\\"\$RUN_SPP\\")" -c="$bam" -savp="${prefix}.spp.pdf" -savd="${prefix}.spp.Rdata" -out="${prefix}.spp.out" $args2 cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/addorreplacereadgroups/main.nf b/modules/picard/addorreplacereadgroups/main.nf index 8e1d10af..fd102f67 100644 --- a/modules/picard/addorreplacereadgroups/main.nf +++ b/modules/picard/addorreplacereadgroups/main.nf @@ -2,10 +2,10 @@ process PICARD_ADDORREPLACEREADGROUPS { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::picard=2.26.9" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.9--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.9--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -38,12 +38,12 @@ process PICARD_ADDORREPLACEREADGROUPS { -Xmx${avail_mem}g \\ --INPUT ${bam} \\ --OUTPUT ${prefix}.bam \\ - -ID ${ID} \\ - -LB ${LIBRARY} \\ - -PL ${PLATFORM} \\ - -PU ${BARCODE} \\ - -SM ${SAMPLE} \\ - -CREATE_INDEX true + --RGID ${ID} \\ + --RGLB ${LIBRARY} \\ + --RGPL ${PLATFORM} \\ + --RGPU ${BARCODE} \\ + --RGSM ${SAMPLE} \\ + --CREATE_INDEX true cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/cleansam/main.nf b/modules/picard/cleansam/main.nf index fb435911..62989565 100644 --- a/modules/picard/cleansam/main.nf +++ b/modules/picard/cleansam/main.nf @@ -2,10 +2,10 @@ process PICARD_CLEANSAM { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.9" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.9--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.9--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -31,8 +31,8 @@ process PICARD_CLEANSAM { -Xmx${avail_mem}g \\ CleanSam \\ ${args} \\ - -I ${bam} \\ - -O ${prefix}.bam + --INPUT ${bam} \\ + --OUTPUT ${prefix}.bam cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/collecthsmetrics/main.nf b/modules/picard/collecthsmetrics/main.nf index ef7a9b9f..317aff4b 100644 --- a/modules/picard/collecthsmetrics/main.nf +++ b/modules/picard/collecthsmetrics/main.nf @@ -2,10 +2,10 @@ process PICARD_COLLECTHSMETRICS { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -38,10 +38,10 @@ process PICARD_COLLECTHSMETRICS { CollectHsMetrics \\ $args \\ $reference \\ - -BAIT_INTERVALS $bait_intervals \\ - -TARGET_INTERVALS $target_intervals \\ - -INPUT $bam \\ - -OUTPUT ${prefix}.CollectHsMetrics.coverage_metrics + --BAIT_INTERVALS $bait_intervals \\ + --TARGET_INTERVALS $target_intervals \\ + --INPUT $bam \\ + --OUTPUT ${prefix}.CollectHsMetrics.coverage_metrics cat <<-END_VERSIONS > versions.yml diff --git a/modules/picard/collectmultiplemetrics/main.nf b/modules/picard/collectmultiplemetrics/main.nf index 340463a8..a653b549 100644 --- a/modules/picard/collectmultiplemetrics/main.nf +++ b/modules/picard/collectmultiplemetrics/main.nf @@ -2,10 +2,10 @@ process PICARD_COLLECTMULTIPLEMETRICS { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -33,9 +33,9 @@ process PICARD_COLLECTMULTIPLEMETRICS { -Xmx${avail_mem}g \\ CollectMultipleMetrics \\ $args \\ - INPUT=$bam \\ - OUTPUT=${prefix}.CollectMultipleMetrics \\ - REFERENCE_SEQUENCE=$fasta + --INPUT $bam \\ + --OUTPUT ${prefix}.CollectMultipleMetrics \\ + --REFERENCE_SEQUENCE $fasta cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/collectwgsmetrics/main.nf b/modules/picard/collectwgsmetrics/main.nf index f4efaa4c..e6dd49e9 100644 --- a/modules/picard/collectwgsmetrics/main.nf +++ b/modules/picard/collectwgsmetrics/main.nf @@ -2,13 +2,13 @@ process PICARD_COLLECTWGSMETRICS { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: - tuple val(meta), path(bam), path(bai) + tuple val(meta), path(bam) path fasta output: @@ -32,9 +32,10 @@ process PICARD_COLLECTWGSMETRICS { -Xmx${avail_mem}g \\ CollectWgsMetrics \\ $args \\ - INPUT=$bam \\ - OUTPUT=${prefix}.CollectWgsMetrics.coverage_metrics \\ - REFERENCE_SEQUENCE=$fasta + --INPUT $bam \\ + --OUTPUT ${prefix}.CollectWgsMetrics.coverage_metrics \\ + --REFERENCE_SEQUENCE $fasta + cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/createsequencedictionary/main.nf b/modules/picard/createsequencedictionary/main.nf index 96069e9f..2348c496 100644 --- a/modules/picard/createsequencedictionary/main.nf +++ b/modules/picard/createsequencedictionary/main.nf @@ -2,10 +2,10 @@ process PICARD_CREATESEQUENCEDICTIONARY { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.9" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.9--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.9--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(fasta) @@ -31,8 +31,8 @@ process PICARD_CREATESEQUENCEDICTIONARY { -Xmx${avail_mem}g \\ CreateSequenceDictionary \\ $args \\ - R=$fasta \\ - O=${prefix}.dict + --REFERENCE $fasta \\ + --OUTPUT ${prefix}.dict cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/crosscheckfingerprints/main.nf b/modules/picard/crosscheckfingerprints/main.nf index b3dface5..d3b59402 100644 --- a/modules/picard/crosscheckfingerprints/main.nf +++ b/modules/picard/crosscheckfingerprints/main.nf @@ -2,10 +2,10 @@ process PICARD_CROSSCHECKFINGERPRINTS { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(input1) diff --git a/modules/picard/filtersamreads/main.nf b/modules/picard/filtersamreads/main.nf index ab75abfa..adedcdc2 100644 --- a/modules/picard/filtersamreads/main.nf +++ b/modules/picard/filtersamreads/main.nf @@ -2,10 +2,10 @@ process PICARD_FILTERSAMREADS { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam), path(readlist) diff --git a/modules/picard/fixmateinformation/main.nf b/modules/picard/fixmateinformation/main.nf index 763f3bb4..539b1082 100644 --- a/modules/picard/fixmateinformation/main.nf +++ b/modules/picard/fixmateinformation/main.nf @@ -2,10 +2,10 @@ process PICARD_FIXMATEINFORMATION { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::picard=2.26.9" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.9--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.9--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -31,8 +31,8 @@ process PICARD_FIXMATEINFORMATION { picard \\ FixMateInformation \\ -Xmx${avail_mem}g \\ - -I ${bam} \\ - -O ${prefix}.bam \\ + --INPUT ${bam} \\ + --OUTPUT ${prefix}.bam \\ --VALIDATION_STRINGENCY ${STRINGENCY} cat <<-END_VERSIONS > versions.yml diff --git a/modules/picard/liftovervcf/main.nf b/modules/picard/liftovervcf/main.nf index cdbd637e..c92abfeb 100644 --- a/modules/picard/liftovervcf/main.nf +++ b/modules/picard/liftovervcf/main.nf @@ -2,10 +2,10 @@ process PICARD_LIFTOVERVCF { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(input_vcf) @@ -35,11 +35,11 @@ process PICARD_LIFTOVERVCF { -Xmx${avail_mem}g \\ LiftoverVcf \\ $args \\ - I=$input_vcf \\ - O=${prefix}.lifted.vcf.gz \\ - CHAIN=$chain \\ - REJECT=${prefix}.unlifted.vcf.gz \\ - R=$fasta + --INPUT $input_vcf \\ + --OUTPUT ${prefix}.lifted.vcf.gz \\ + --CHAIN $chain \\ + --REJECT ${prefix}.unlifted.vcf.gz \\ + --REFERENCE_SEQUENCE $fasta cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/markduplicates/main.nf b/modules/picard/markduplicates/main.nf index e754a587..1565c647 100644 --- a/modules/picard/markduplicates/main.nf +++ b/modules/picard/markduplicates/main.nf @@ -2,10 +2,10 @@ process PICARD_MARKDUPLICATES { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) @@ -33,9 +33,9 @@ process PICARD_MARKDUPLICATES { -Xmx${avail_mem}g \\ MarkDuplicates \\ $args \\ - I=$bam \\ - O=${prefix}.bam \\ - M=${prefix}.MarkDuplicates.metrics.txt + --INPUT $bam \\ + --OUTPUT ${prefix}.bam \\ + --METRICS_FILE ${prefix}.MarkDuplicates.metrics.txt cat <<-END_VERSIONS > versions.yml "${task.process}": diff --git a/modules/picard/mergesamfiles/main.nf b/modules/picard/mergesamfiles/main.nf index ef5c3980..1e32c63a 100644 --- a/modules/picard/mergesamfiles/main.nf +++ b/modules/picard/mergesamfiles/main.nf @@ -2,10 +2,10 @@ process PICARD_MERGESAMFILES { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bams) @@ -33,8 +33,8 @@ process PICARD_MERGESAMFILES { -Xmx${avail_mem}g \\ MergeSamFiles \\ $args \\ - ${'INPUT='+bam_files.join(' INPUT=')} \\ - OUTPUT=${prefix}.bam + ${'--INPUT '+bam_files.join(' --INPUT ')} \\ + --OUTPUT ${prefix}.bam cat <<-END_VERSIONS > versions.yml "${task.process}": picard: \$( echo \$(picard MergeSamFiles --version 2>&1) | grep -o 'Version:.*' | cut -f2- -d:) diff --git a/modules/picard/sortsam/main.nf b/modules/picard/sortsam/main.nf index adec17cb..cee60fd1 100644 --- a/modules/picard/sortsam/main.nf +++ b/modules/picard/sortsam/main.nf @@ -2,10 +2,10 @@ process PICARD_SORTSAM { tag "$meta.id" label 'process_low' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(bam) diff --git a/modules/picard/sortvcf/main.nf b/modules/picard/sortvcf/main.nf index 4047545e..fb8dbb79 100644 --- a/modules/picard/sortvcf/main.nf +++ b/modules/picard/sortvcf/main.nf @@ -2,10 +2,10 @@ process PICARD_SORTVCF { tag "$meta.id" label 'process_medium' - conda (params.enable_conda ? "bioconda::picard=2.26.10" : null) + conda (params.enable_conda ? "bioconda::picard=2.27.1" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/picard:2.26.10--hdfd78af_0' : - 'quay.io/biocontainers/picard:2.26.10--hdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/picard:2.27.1--hdfd78af_0' : + 'quay.io/biocontainers/picard:2.27.1--hdfd78af_0' }" input: tuple val(meta), path(vcf) @@ -22,8 +22,8 @@ process PICARD_SORTVCF { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" - def seq_dict = sequence_dict ? "-SEQUENCE_DICTIONARY $sequence_dict" : "" - def reference = reference ? "-REFERENCE_SEQUENCE $reference" : "" + def seq_dict = sequence_dict ? "--SEQUENCE_DICTIONARY $sequence_dict" : "" + def reference = reference ? "--REFERENCE_SEQUENCE $reference" : "" def avail_mem = 3 if (!task.memory) { log.info '[Picard SortVcf] Available memory not known - defaulting to 3GB. Specify process memory requirements to change this.' diff --git a/modules/rsem/calculateexpression/main.nf b/modules/rsem/calculateexpression/main.nf index cf147a63..1ab3a635 100644 --- a/modules/rsem/calculateexpression/main.nf +++ b/modules/rsem/calculateexpression/main.nf @@ -2,10 +2,10 @@ process RSEM_CALCULATEEXPRESSION { tag "$meta.id" label 'process_high' - conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) + conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' : - 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' : + 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" input: tuple val(meta), path(reads) diff --git a/modules/rsem/preparereference/main.nf b/modules/rsem/preparereference/main.nf index 2d2ca205..da11be45 100644 --- a/modules/rsem/preparereference/main.nf +++ b/modules/rsem/preparereference/main.nf @@ -2,10 +2,10 @@ process RSEM_PREPAREREFERENCE { tag "$fasta" label 'process_high' - conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.6a" : null) + conda (params.enable_conda ? "bioconda::rsem=1.3.3 bioconda::star=2.7.10a" : null) container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' : - 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:606b713ec440e799d53a2b51a6e79dbfd28ecf3e-0' }" + 'https://depot.galaxyproject.org/singularity/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' : + 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0' }" input: path fasta, stageAs: "rsem/*" diff --git a/modules/samtools/bamtocram/main.nf b/modules/samtools/bamtocram/main.nf new file mode 100644 index 00000000..b49c308f --- /dev/null +++ b/modules/samtools/bamtocram/main.nf @@ -0,0 +1,35 @@ +//There is a -L option to only output alignments in interval, might be an option for exons/panel data? +process SAMTOOLS_BAMTOCRAM { + tag "$meta.id" + label 'process_medium' + + conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null) + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : + 'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }" + + input: + tuple val(meta), path(input), path(index) + path fasta + path fai + + output: + tuple val(meta), path("*.cram"), path("*.crai"), emit: cram_crai + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + samtools view --threads ${task.cpus} --reference ${fasta} -C $args $input > ${prefix}.cram + samtools index -@${task.cpus} ${prefix}.cram + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//') + END_VERSIONS + """ +} diff --git a/modules/samtools/bamtocram/meta.yml b/modules/samtools/bamtocram/meta.yml new file mode 100644 index 00000000..037704c6 --- /dev/null +++ b/modules/samtools/bamtocram/meta.yml @@ -0,0 +1,52 @@ +name: samtools_bamtocram +description: filter/convert and then index CRAM file +keywords: + - view + - index + - bam + - cram +tools: + - samtools: + description: | + SAMtools is a set of utilities for interacting with and post-processing + short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li. + These files are generated as output by short read aligners like BWA. + homepage: http://www.htslib.org/ + documentation: hhttp://www.htslib.org/doc/samtools.html + doi: 10.1093/bioinformatics/btp352 + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - input: + type: file + description: BAM/SAM file + pattern: "*.{bam,sam}" + - index: + type: file + description: BAM/SAM index file + pattern: "*.{bai,sai}" + - fasta: + type: file + description: Reference file to create the CRAM file + pattern: "*.{fasta,fa}" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - cram_crai: + type: file + description: filtered/converted CRAM file + index + pattern: "*{.cram,.crai}" + - version: + type: file + description: File containing software version + pattern: "*.{version.txt}" +authors: + - "@FriederikeHanssen" + - "@maxulysse" diff --git a/modules/tabix/tabix/main.nf b/modules/tabix/tabix/main.nf index c9dab068..e155e468 100644 --- a/modules/tabix/tabix/main.nf +++ b/modules/tabix/tabix/main.nf @@ -11,7 +11,8 @@ process TABIX_TABIX { tuple val(meta), path(tab) output: - tuple val(meta), path("*.tbi"), emit: tbi + tuple val(meta), path("*.tbi"), optional:true, emit: tbi + tuple val(meta), path("*.csi"), optional:true, emit: csi path "versions.yml" , emit: versions when: diff --git a/modules/tabix/tabix/meta.yml b/modules/tabix/tabix/meta.yml index 89478abe..fcc6e524 100644 --- a/modules/tabix/tabix/meta.yml +++ b/modules/tabix/tabix/meta.yml @@ -31,6 +31,10 @@ output: type: file description: tabix index file pattern: "*.{tbi}" + - csi: + type: file + description: coordinate sorted index file + pattern: "*.{csi}" - versions: type: file description: File containing software versions diff --git a/modules/tiddit/sv/main.nf b/modules/tiddit/sv/main.nf index 1bf7146a..b3e3813c 100644 --- a/modules/tiddit/sv/main.nf +++ b/modules/tiddit/sv/main.nf @@ -24,7 +24,7 @@ process TIDDIT_SV { script: def args = task.ext.args ?: '' def prefix = task.ext.prefix ?: "${meta.id}" - def reference = fasta == "dummy_file.txt" ? "--ref $fasta" : "" + def reference = fasta ? "--ref $fasta" : "" """ tiddit \\ --sv \\ diff --git a/modules/trimgalore/main.nf b/modules/trimgalore/main.nf index 9487c799..3a3fca90 100644 --- a/modules/trimgalore/main.nf +++ b/modules/trimgalore/main.nf @@ -11,12 +11,13 @@ process TRIMGALORE { tuple val(meta), path(reads) output: - tuple val(meta), path("*.fq.gz") , emit: reads - tuple val(meta), path("*report.txt"), emit: log - path "versions.yml" , emit: versions + tuple val(meta), path("*{trimmed,val}*.fq.gz"), emit: reads + tuple val(meta), path("*report.txt") , emit: log + path "versions.yml" , emit: versions - tuple val(meta), path("*.html"), emit: html optional true - tuple val(meta), path("*.zip") , emit: zip optional true + tuple val(meta), path("*unpaired*.fq.gz") , emit: unpaired, optional: true + tuple val(meta), path("*.html") , emit: html , optional: true + tuple val(meta), path("*.zip") , emit: zip , optional: true when: task.ext.when == null || task.ext.when @@ -52,6 +53,7 @@ process TRIMGALORE { $c_r1 \\ $tpc_r1 \\ ${prefix}.fastq.gz + cat <<-END_VERSIONS > versions.yml "${task.process}": trimgalore: \$(echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//') @@ -73,6 +75,7 @@ process TRIMGALORE { $tpc_r2 \\ ${prefix}_1.fastq.gz \\ ${prefix}_2.fastq.gz + cat <<-END_VERSIONS > versions.yml "${task.process}": trimgalore: \$(echo \$(trim_galore --version 2>&1) | sed 's/^.*version //; s/Last.*\$//') diff --git a/modules/trimgalore/meta.yml b/modules/trimgalore/meta.yml index e99a8833..439f566d 100644 --- a/modules/trimgalore/meta.yml +++ b/modules/trimgalore/meta.yml @@ -37,6 +37,11 @@ output: List of input adapter trimmed FastQ files of size 1 and 2 for single-end and paired-end data, respectively. pattern: "*.{fq.gz}" + - unpaired: + type: file + description: | + FastQ files containing unpaired reads from read 1 or read 2 + pattern: "*unpaired*.fq.gz" - html: type: file description: FastQC report (optional) diff --git a/subworkflows/nf-core/bam_qc_picard/main.nf b/subworkflows/nf-core/bam_qc_picard/main.nf new file mode 100644 index 00000000..e38697c3 --- /dev/null +++ b/subworkflows/nf-core/bam_qc_picard/main.nf @@ -0,0 +1,41 @@ +// +// Run QC steps on BAM/CRAM files using Picard +// + +include { PICARD_COLLECTMULTIPLEMETRICS } from '../../../modules/picard/collectmultiplemetrics/main' +include { PICARD_COLLECTWGSMETRICS } from '../../../modules/picard/collectwgsmetrics/main' +include { PICARD_COLLECTHSMETRICS } from '../../../modules/picard/collecthsmetrics/main' + +workflow BAM_QC_PICARD { + take: + ch_bam // channel: [ val(meta), [ bam ]] + ch_fasta // channel: [ fasta ] + ch_fasta_fai // channel: [ fasta_fai ] + ch_bait_interval // channel: [ bait_interval ] + ch_target_interval // channel: [ target_interval ] + + main: + ch_versions = Channel.empty() + ch_coverage_metrics = Channel.empty() + + PICARD_COLLECTMULTIPLEMETRICS( ch_bam, ch_fasta ) + ch_versions = ch_versions.mix(PICARD_COLLECTMULTIPLEMETRICS.out.versions.first()) + + if (ch_bait_interval || ch_target_interval) { + if (!ch_bait_interval) log.error("Bait interval channel is empty") + if (!ch_target_interval) log.error("Target interval channel is empty") + PICARD_COLLECTHSMETRICS( ch_bam, ch_fasta, ch_fasta_fai, ch_bait_interval, ch_target_interval ) + ch_coverage_metrics = ch_coverage_metrics.mix(PICARD_COLLECTHSMETRICS.out.metrics) + ch_versions = ch_versions.mix(PICARD_COLLECTHSMETRICS.out.versions.first()) + } else { + PICARD_COLLECTWGSMETRICS( ch_bam, ch_fasta ) + ch_versions = ch_versions.mix(PICARD_COLLECTWGSMETRICS.out.versions.first()) + ch_coverage_metrics = ch_coverage_metrics.mix(PICARD_COLLECTWGSMETRICS.out.metrics) + } + + emit: + coverage_metrics = ch_coverage_metrics // channel: [ val(meta), [ coverage_metrics ] ] + multiple_metrics = PICARD_COLLECTMULTIPLEMETRICS.out.metrics // channel: [ val(meta), [ multiple_metrics ] ] + + versions = ch_versions // channel: [ versions.yml ] +} diff --git a/subworkflows/nf-core/bam_qc_picard/meta.yml b/subworkflows/nf-core/bam_qc_picard/meta.yml new file mode 100644 index 00000000..c45215d1 --- /dev/null +++ b/subworkflows/nf-core/bam_qc_picard/meta.yml @@ -0,0 +1,60 @@ +name: bam_qc +description: Produces comprehensive statistics from BAM file +keywords: + - statistics + - counts + - hs_metrics + - wgs_metrics + - bam + - sam + - cram +modules: + - picard/collectmultiplemetrics + - picard/collectwgsmetrics + - picard/collecthsmetrics +input: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - bam: + type: file + description: BAM/CRAM/SAM file + pattern: "*.{bam,cram,sam}" + - fasta: + type: optional file + description: Reference fasta file + pattern: "*.{fasta,fa}" + - fasta_fai: + type: optional file + description: Reference fasta file index + pattern: "*.{fasta,fa}.fai" + - bait_intervals: + type: optional file + description: An interval list file that contains the locations of the baits used. + pattern: "baits.interval_list" + - target_intervals: + type: optional file + description: An interval list file that contains the locations of the targets. + pattern: "targets.interval_list" +output: + - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - coverage_metrics: + type: file + description: Alignment metrics files generated by picard CollectHsMetrics or CollectWgsMetrics + pattern: "*_metrics.txt" + - multiple_metrics: + type: file + description: Alignment metrics files generated by picard CollectMultipleMetrics + pattern: "*_{metrics}" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@matthdsm" diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml index dcb4e967..41b68042 100644 --- a/tests/config/pytest_modules.yml +++ b/tests/config/pytest_modules.yml @@ -607,6 +607,10 @@ elprep/filter: - modules/elprep/filter/** - tests/modules/elprep/filter/** +elprep/merge: + - modules/elprep/merge/** + - tests/modules/elprep/merge/** + elprep/split: - modules/elprep/split/** - tests/modules/elprep/split/** @@ -1054,6 +1058,10 @@ krona/ktimporttaxonomy: - modules/krona/ktimporttaxonomy/** - tests/modules/krona/ktimporttaxonomy/** +krona/ktimporttext: + - modules/krona/ktimporttext/** + - tests/modules/krona/ktimporttext/** + last/dotplot: - modules/last/dotplot/** - tests/modules/last/dotplot/** @@ -1599,6 +1607,10 @@ samtools/bam2fq: - modules/samtools/bam2fq/** - tests/modules/samtools/bam2fq/** +samtools/bamtocram: + - modules/samtools/bamtocram/** + - tests/modules/samtools/bamtocram/** + samtools/collatefastq: - modules/samtools/collatefastq/** - tests/modules/samtools/collatefastq/** diff --git a/tests/config/test_data.config b/tests/config/test_data.config index f6ea242d..62e38c4d 100644 --- a/tests/config/test_data.config +++ b/tests/config/test_data.config @@ -14,6 +14,7 @@ params { genome_paf = "${test_data_dir}/genomics/sarscov2/genome/genome.paf" genome_sizes = "${test_data_dir}/genomics/sarscov2/genome/genome.sizes" transcriptome_fasta = "${test_data_dir}/genomics/sarscov2/genome/transcriptome.fasta" + proteome_fasta = "${test_data_dir}/genomics/sarscov2/genome/proteome.fasta" transcriptome_paf = "${test_data_dir}/genomics/sarscov2/genome/transcriptome.paf" test_bed = "${test_data_dir}/genomics/sarscov2/genome/bed/test.bed" @@ -109,6 +110,9 @@ params { test_sequencing_summary = "${test_data_dir}/genomics/sarscov2/nanopore/sequencing_summary/test.sequencing_summary.txt" } + 'metagenome' { + kraken_report = "${test_data_dir}/genomics/sarscov2/metagenome/test_1.kraken2.report.txt" + } } 'homo_sapiens' { 'genome' { @@ -245,8 +249,8 @@ params { test2_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2_2.fastq.gz" test2_umi_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_1.fastq.gz" test2_umi_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test2.umi_2.fastq.gz" - test_rnaseq_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_1.fastq.gz" - test_rnaseq_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test.rnaseq_2.fastq.gz" + test_rnaseq_1_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz" + test_rnaseq_2_fastq_gz = "${test_data_dir}/genomics/homo_sapiens/illumina/fastq/test_rnaseq_2.fastq.gz" test_baserecalibrator_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.baserecalibrator.table" test2_baserecalibrator_table = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table" diff --git a/tests/modules/antismash/antismashlitedownloaddatabases/test.yml b/tests/modules/antismash/antismashlitedownloaddatabases/test.yml index 3493bb4b..1079363c 100644 --- a/tests/modules/antismash/antismashlitedownloaddatabases/test.yml +++ b/tests/modules/antismash/antismashlitedownloaddatabases/test.yml @@ -1,14 +1,17 @@ - name: antismash antismashlitedownloaddatabases test_antismash_antismashlitedownloaddatabases command: nextflow run tests/modules/antismash/antismashlitedownloaddatabases -entry test_antismash_antismashlitedownloaddatabases -c tests/config/nextflow.config tags: - - antismash/antismashlitedownloaddatabases - antismash + - antismash/antismashlitedownloaddatabases files: - path: output/antismash/versions.yml - md5sum: e2656c8d2bcc7469eba40eb1ee5c91b3 + md5sum: 24859c67023abab99de295d3675a24b6 - path: output/antismash/antismash_db - path: output/antismash/antismash_db/clusterblast - path: output/antismash/antismash_db/clustercompare - path: output/antismash/antismash_db/pfam - path: output/antismash/antismash_db/resfam - path: output/antismash/antismash_db/tigrfam + - path: output/antismash/css + - path: output/antismash/detection + - path: output/antismash/modules diff --git a/tests/modules/bamtools/split/main.nf b/tests/modules/bamtools/split/main.nf index eb0bed01..e5c15c32 100644 --- a/tests/modules/bamtools/split/main.nf +++ b/tests/modules/bamtools/split/main.nf @@ -2,13 +2,29 @@ nextflow.enable.dsl = 2 -include { BAMTOOLS_SPLIT } from '../../../../modules/bamtools/split/main.nf' +include { BAMTOOLS_SPLIT as BAMTOOLS_SPLIT_SINGLE } from '../../../../modules/bamtools/split/main.nf' +include { BAMTOOLS_SPLIT as BAMTOOLS_SPLIT_MULTIPLE } from '../../../../modules/bamtools/split/main.nf' -workflow test_bamtools_split { +workflow test_bamtools_split_single_input { input = [ [ id:'test', single_end:false ], // meta map - file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) ] + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] - BAMTOOLS_SPLIT ( input ) + BAMTOOLS_SPLIT_SINGLE ( input ) } + +workflow test_bamtools_split_multiple { + + input = [ + [ id:'test', single_end:false ], // meta map + [ + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true), + file(params.test_data['homo_sapiens']['illumina']['test2_paired_end_sorted_bam'], checkIfExists: true) + ] + ] + + BAMTOOLS_SPLIT_MULTIPLE ( input ) +} + diff --git a/tests/modules/bamtools/split/test.yml b/tests/modules/bamtools/split/test.yml index 4f52e9ce..af639b43 100644 --- a/tests/modules/bamtools/split/test.yml +++ b/tests/modules/bamtools/split/test.yml @@ -1,10 +1,23 @@ -- name: bamtools split test_bamtools_split - command: nextflow run ./tests/modules/bamtools/split -entry test_bamtools_split -c ./tests/config/nextflow.config -c ./tests/modules/bamtools/split/nextflow.config +- name: bamtools split test_bamtools_split_single_input + command: nextflow run ./tests/modules/bamtools/split -entry test_bamtools_split_single_input -c ./tests/config/nextflow.config -c ./tests/modules/bamtools/split/nextflow.config tags: - - bamtools/split - bamtools + - bamtools/split files: - - path: output/bamtools/test.paired_end.sorted.REF_chr22.bam + - path: output/bamtools/test.REF_chr22.bam md5sum: b7dc50e0edf9c6bfc2e3b0e6d074dc07 - - path: output/bamtools/test.paired_end.sorted.REF_unmapped.bam + - path: output/bamtools/test.REF_unmapped.bam md5sum: e0754bf72c51543b2d745d96537035fb + - path: output/bamtools/versions.yml + +- name: bamtools split test_bamtools_split_multiple + command: nextflow run ./tests/modules/bamtools/split -entry test_bamtools_split_multiple -c ./tests/config/nextflow.config -c ./tests/modules/bamtools/split/nextflow.config + tags: + - bamtools + - bamtools/split + files: + - path: output/bamtools/test.REF_chr22.bam + md5sum: 585675bea34c48ebe9db06a561d4b4fa + - path: output/bamtools/test.REF_unmapped.bam + md5sum: 16ad644c87b9471f3026bc87c98b4963 + - path: output/bamtools/versions.yml diff --git a/tests/modules/diamond/blastp/main.nf b/tests/modules/diamond/blastp/main.nf index 87d05bf9..ff669233 100644 --- a/tests/modules/diamond/blastp/main.nf +++ b/tests/modules/diamond/blastp/main.nf @@ -7,9 +7,22 @@ include { DIAMOND_BLASTP } from '../../../../modules/diamond/blastp/main.nf' workflow test_diamond_blastp { - db = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ] - fasta = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ] + db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] + fasta = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] + out_ext = 'txt' + blast_columns = 'qseqid qlen' DIAMOND_MAKEDB ( db ) - DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db ) + DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, out_ext, blast_columns ) +} + +workflow test_diamond_blastp_daa { + + db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] + fasta = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] + out_ext = 'daa' + blast_columns = [] + + DIAMOND_MAKEDB ( db ) + DIAMOND_BLASTP ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, out_ext, blast_columns ) } diff --git a/tests/modules/diamond/blastp/test.yml b/tests/modules/diamond/blastp/test.yml index 32dfacaa..aff4e1c5 100644 --- a/tests/modules/diamond/blastp/test.yml +++ b/tests/modules/diamond/blastp/test.yml @@ -1,8 +1,17 @@ -- name: diamond blastp - command: nextflow run ./tests/modules/diamond/blastp -entry test_diamond_blastp -c ./tests/config/nextflow.config -c ./tests/modules/diamond/blastp/nextflow.config +- name: diamond blastp test_diamond_blastp + command: nextflow run tests/modules/diamond/blastp -entry test_diamond_blastp -c tests/config/nextflow.config tags: - - diamond - diamond/blastp + - diamond files: - - path: ./output/diamond/test.diamond_blastp.txt - md5sum: 3ca7f6290c1d8741c573370e6f8b4db0 + - path: output/diamond/test.diamond_blastp.txt + - path: output/diamond/versions.yml + +- name: diamond blastp test_diamond_blastp_daa + command: nextflow run tests/modules/diamond/blastp -entry test_diamond_blastp_daa -c tests/config/nextflow.config + tags: + - diamond/blastp + - diamond + files: + - path: output/diamond/test.diamond_blastp.daa + - path: output/diamond/versions.yml diff --git a/tests/modules/diamond/blastx/main.nf b/tests/modules/diamond/blastx/main.nf index 77eb08ea..8316aa91 100644 --- a/tests/modules/diamond/blastx/main.nf +++ b/tests/modules/diamond/blastx/main.nf @@ -7,9 +7,22 @@ include { DIAMOND_BLASTX } from '../../../../modules/diamond/blastx/main.nf' workflow test_diamond_blastx { - db = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ] + db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] fasta = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ] + out_ext = 'tfdfdt' // Nonsense file extension to check default case. + blast_columns = 'qseqid qlen' DIAMOND_MAKEDB ( db ) - DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db ) + DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, out_ext, blast_columns ) +} + +workflow test_diamond_blastx_daa { + + db = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] + fasta = [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ] + out_ext = 'daa' + blast_columns = [] + + DIAMOND_MAKEDB ( db ) + DIAMOND_BLASTX ( [ [id:'test'], fasta ], DIAMOND_MAKEDB.out.db, out_ext, blast_columns ) } diff --git a/tests/modules/diamond/blastx/test.yml b/tests/modules/diamond/blastx/test.yml index fe7c6938..b2b6149f 100644 --- a/tests/modules/diamond/blastx/test.yml +++ b/tests/modules/diamond/blastx/test.yml @@ -1,8 +1,18 @@ -- name: diamond blastx - command: nextflow run ./tests/modules/diamond/blastx -entry test_diamond_blastx -c ./tests/config/nextflow.config -c ./tests/modules/diamond/blastx/nextflow.config +- name: diamond blastx test_diamond_blastx + command: nextflow run tests/modules/diamond/blastx -entry test_diamond_blastx -c tests/config/nextflow.config tags: - diamond - diamond/blastx files: - - path: ./output/diamond/test.diamond_blastx.txt - md5sum: d41d8cd98f00b204e9800998ecf8427e + - path: output/diamond/test.diamond_blastx.txt + - path: output/diamond/versions.yml + +- name: diamond blastx test_diamond_blastx_daa + command: nextflow run tests/modules/diamond/blastx -entry test_diamond_blastx_daa -c tests/config/nextflow.config + tags: + - diamond + - diamond/blastx + files: + - path: output/diamond/test.diamond_blastx.daa + md5sum: 0df4a833408416f32981415873facc11 + - path: output/diamond/versions.yml diff --git a/tests/modules/diamond/makedb/main.nf b/tests/modules/diamond/makedb/main.nf index 70982ae9..d309de6d 100644 --- a/tests/modules/diamond/makedb/main.nf +++ b/tests/modules/diamond/makedb/main.nf @@ -6,7 +6,7 @@ include { DIAMOND_MAKEDB } from '../../../../modules/diamond/makedb/main.nf' workflow test_diamond_makedb { - input = [ file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) ] + input = [ file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true) ] DIAMOND_MAKEDB ( input ) } diff --git a/tests/modules/diamond/makedb/test.yml b/tests/modules/diamond/makedb/test.yml index c8f2d79e..cdddf735 100644 --- a/tests/modules/diamond/makedb/test.yml +++ b/tests/modules/diamond/makedb/test.yml @@ -1,8 +1,9 @@ - name: diamond makedb test_diamond_makedb - command: nextflow run ./tests/modules/diamond/makedb -entry test_diamond_makedb -c ./tests/config/nextflow.config -c ./tests/modules/diamond/makedb/nextflow.config + command: nextflow run tests/modules/diamond/makedb -entry test_diamond_makedb -c tests/config/nextflow.config tags: - - diamond - diamond/makedb + - diamond files: - - path: output/diamond/genome.fasta.dmnd - md5sum: 2447fb376394c20d43ea3aad2aa5d15d + - path: output/diamond/proteome.fasta.dmnd + md5sum: fc28c50b202dd7a7c5451cddff2ba1f4 + - path: output/diamond/versions.yml diff --git a/tests/modules/elprep/merge/main.nf b/tests/modules/elprep/merge/main.nf new file mode 100644 index 00000000..b4a40ce3 --- /dev/null +++ b/tests/modules/elprep/merge/main.nf @@ -0,0 +1,17 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { ELPREP_SPLIT } from '../../../../modules/elprep/split/main.nf' +include { ELPREP_MERGE } from '../../../../modules/elprep/merge/main.nf' + +workflow test_elprep_merge { + + input = [ + [ id:'test', single_end:false ], // meta map + file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] + + ELPREP_SPLIT ( input ) + ELPREP_MERGE ( ELPREP_SPLIT.out.bam ) +} diff --git a/tests/modules/elprep/merge/nextflow.config b/tests/modules/elprep/merge/nextflow.config new file mode 100644 index 00000000..4e4570f4 --- /dev/null +++ b/tests/modules/elprep/merge/nextflow.config @@ -0,0 +1,5 @@ +process { + withName : ELPREP_MERGE { + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + } +} diff --git a/tests/modules/elprep/merge/test.yml b/tests/modules/elprep/merge/test.yml new file mode 100644 index 00000000..ad2ecfef --- /dev/null +++ b/tests/modules/elprep/merge/test.yml @@ -0,0 +1,8 @@ +- name: elprep merge test_elprep_merge + command: nextflow run tests/modules/elprep/merge -entry test_elprep_merge -c tests/config/nextflow.config + tags: + - elprep + - elprep/merge + files: + - path: output/elprep/output/test.bam + - path: output/elprep/versions.yml diff --git a/tests/modules/gatk4/splitncigarreads/main.nf b/tests/modules/gatk4/splitncigarreads/main.nf index 7e5b7c9a..31e45cec 100644 --- a/tests/modules/gatk4/splitncigarreads/main.nf +++ b/tests/modules/gatk4/splitncigarreads/main.nf @@ -6,7 +6,23 @@ include { GATK4_SPLITNCIGARREADS } from '../../../../modules/gatk4/splitncigarre workflow test_gatk4_splitncigarreads { input = [ [ id:'test' ], // meta map - [ file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true) ] + file(params.test_data['sarscov2']['illumina']['test_paired_end_bam'], checkIfExists: true), + [], + [] + ] + + fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) + dict = file(params.test_data['sarscov2']['genome']['genome_dict'], checkIfExists: true) + + GATK4_SPLITNCIGARREADS ( input, fasta, fai, dict ) +} + +workflow test_gatk4_splitncigarreads_intervals { + input = [ [ id:'test' ], // meta map + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true), + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true), + file(params.test_data['sarscov2']['genome']['test_bed'], checkIfExists: true) ] fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) diff --git a/tests/modules/gatk4/splitncigarreads/test.yml b/tests/modules/gatk4/splitncigarreads/test.yml index c38064e2..d9a58901 100644 --- a/tests/modules/gatk4/splitncigarreads/test.yml +++ b/tests/modules/gatk4/splitncigarreads/test.yml @@ -5,5 +5,14 @@ - gatk4/splitncigarreads files: - path: output/gatk4/test.bam - md5sum: ceed15c0bd64ff5c38d3816905933b0b + md5sum: 436d8e31285c6b588bdd1c7f1d07f6f2 + - path: output/gatk4/versions.yml +- name: gatk4 splitncigarreads test_gatk4_splitncigarreads_intervals + command: nextflow run tests/modules/gatk4/splitncigarreads -entry test_gatk4_splitncigarreads_intervals -c tests/config/nextflow.config + tags: + - gatk4 + - gatk4/splitncigarreads + files: + - path: output/gatk4/test.bam + md5sum: cd56e3225950f519fd47164cca60a0bb - path: output/gatk4/versions.yml diff --git a/tests/modules/krona/ktimporttext/main.nf b/tests/modules/krona/ktimporttext/main.nf new file mode 100644 index 00000000..3d288b7b --- /dev/null +++ b/tests/modules/krona/ktimporttext/main.nf @@ -0,0 +1,31 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { KRONA_KTIMPORTTEXT } from '../../../../modules/krona/ktimporttext/main.nf' + +workflow test_krona_ktimporttext_multi { + + input = [ + [ id:'test', single_end:false ], // meta map + [ + file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/krona/ktimporttext.txt', checkIfExists: true), // krona default test file + file(params.test_data['sarscov2']['metagenome']['kraken_report'], checkIfExists: true), //Kraken2 report file + file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/krona/kaiju_out4krona.txt', checkIfExists: true) // Kaiju output 4 krona + ] + ] + + KRONA_KTIMPORTTEXT ( input ) +} + +workflow test_krona_ktimporttext_single { + + input = [ + [ id:'test', single_end:false ], // meta map + [ + file('http://krona.sourceforge.net/examples/text.txt', checkIfExists: true) // krona default test file + ] + ] + + KRONA_KTIMPORTTEXT ( input ) +} diff --git a/tests/modules/krona/ktimporttext/nextflow.config b/tests/modules/krona/ktimporttext/nextflow.config new file mode 100644 index 00000000..50f50a7a --- /dev/null +++ b/tests/modules/krona/ktimporttext/nextflow.config @@ -0,0 +1,5 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} \ No newline at end of file diff --git a/tests/modules/krona/ktimporttext/test.yml b/tests/modules/krona/ktimporttext/test.yml new file mode 100644 index 00000000..93ae12da --- /dev/null +++ b/tests/modules/krona/ktimporttext/test.yml @@ -0,0 +1,19 @@ +- name: krona ktimporttext test_krona_ktimporttext_multi + command: nextflow run tests/modules/krona/ktimporttext -entry test_krona_ktimporttext_multi -c tests/config/nextflow.config + tags: + - krona + - krona/ktimporttext + files: + - path: output/krona/test.html + contains: + - "DOCTYPE html PUBLIC" + +- name: krona ktimporttext test_krona_ktimporttext_single + command: nextflow run tests/modules/krona/ktimporttext -entry test_krona_ktimporttext_single -c tests/config/nextflow.config + tags: + - krona + - krona/ktimporttext + files: + - path: output/krona/test.html + contains: + - "DOCTYPE html PUBLIC" diff --git a/tests/modules/minimap2/align/main.nf b/tests/modules/minimap2/align/main.nf index e507d3e5..ee6c0838 100644 --- a/tests/modules/minimap2/align/main.nf +++ b/tests/modules/minimap2/align/main.nf @@ -9,8 +9,11 @@ workflow test_minimap2_align_single_end { [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)] ] fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + bam_format = true + cigar_paf_format = false + cigar_bam = false - MINIMAP2_ALIGN ( input, fasta ) + MINIMAP2_ALIGN ( input, fasta, bam_format, cigar_paf_format, cigar_bam) } workflow test_minimap2_align_paired_end { @@ -19,6 +22,9 @@ workflow test_minimap2_align_paired_end { file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ] ] fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + bam_format = true + cigar_paf_format = false + cigar_bam = false - MINIMAP2_ALIGN ( input, fasta ) + MINIMAP2_ALIGN ( input, fasta, bam_format, cigar_paf_format, cigar_bam ) } diff --git a/tests/modules/minimap2/align/test.yml b/tests/modules/minimap2/align/test.yml index 73dd73e2..c392e313 100644 --- a/tests/modules/minimap2/align/test.yml +++ b/tests/modules/minimap2/align/test.yml @@ -1,17 +1,17 @@ -- name: minimap2 align single-end - command: nextflow run ./tests/modules/minimap2/align -entry test_minimap2_align_single_end -c ./tests/config/nextflow.config -c ./tests/modules/minimap2/align/nextflow.config +- name: minimap2 align test_minimap2_align_single_end + command: nextflow run tests/modules/minimap2/align -entry test_minimap2_align_single_end -c tests/config/nextflow.config tags: - minimap2 - minimap2/align files: - - path: ./output/minimap2/test.paf - md5sum: 70e8cf299ee3ecd33e629d10c1f588ce + - path: output/minimap2/test.bam + - path: output/minimap2/versions.yml -- name: minimap2 align paired-end - command: nextflow run ./tests/modules/minimap2/align -entry test_minimap2_align_paired_end -c ./tests/config/nextflow.config -c ./tests/modules/minimap2/align/nextflow.config +- name: minimap2 align test_minimap2_align_paired_end + command: nextflow run tests/modules/minimap2/align -entry test_minimap2_align_paired_end -c tests/config/nextflow.config tags: - minimap2 - minimap2/align files: - - path: ./output/minimap2/test.paf - md5sum: 5e7b55a26bf0ea3a2843423d3e0b9a28 + - path: output/minimap2/test.bam + - path: output/minimap2/versions.yml diff --git a/tests/modules/picard/addorreplacereadgroups/test.yml b/tests/modules/picard/addorreplacereadgroups/test.yml index aa1536bb..6ee81737 100644 --- a/tests/modules/picard/addorreplacereadgroups/test.yml +++ b/tests/modules/picard/addorreplacereadgroups/test.yml @@ -7,4 +7,3 @@ - path: output/picard/test.bam md5sum: 7b82f3461c2d80fc6a10385e78c9427f - path: output/picard/versions.yml - md5sum: 8a2d176295e1343146ea433c79bb517f diff --git a/tests/modules/picard/cleansam/test.yml b/tests/modules/picard/cleansam/test.yml index 3b235d07..08dcd84d 100644 --- a/tests/modules/picard/cleansam/test.yml +++ b/tests/modules/picard/cleansam/test.yml @@ -7,4 +7,3 @@ - path: output/picard/test.bam md5sum: a48f8e77a1480445efc57570c3a38a68 - path: output/picard/versions.yml - md5sum: e6457d7c6de51bf6f4b577eda65e57ac diff --git a/tests/modules/picard/collectwgsmetrics/main.nf b/tests/modules/picard/collectwgsmetrics/main.nf index 1d75a2bd..eddf5603 100644 --- a/tests/modules/picard/collectwgsmetrics/main.nf +++ b/tests/modules/picard/collectwgsmetrics/main.nf @@ -6,8 +6,7 @@ include { PICARD_COLLECTWGSMETRICS } from '../../../../modules/picard/collectwgs workflow test_picard_collectwgsmetrics { input = [ [ id:'test', single_end:false ], // meta map - file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true), - file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true) + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true), ] fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) diff --git a/tests/modules/picard/createsequencedictionary/test.yml b/tests/modules/picard/createsequencedictionary/test.yml index 2a43be41..59f2dd44 100644 --- a/tests/modules/picard/createsequencedictionary/test.yml +++ b/tests/modules/picard/createsequencedictionary/test.yml @@ -7,4 +7,3 @@ - path: output/picard/test.dict contains: ["SN:MT192765.1"] - path: output/picard/versions.yml - md5sum: b3d8c7ea65b8a6d3237b153d13fe2014 diff --git a/tests/modules/picard/fixmateinformation/test.yml b/tests/modules/picard/fixmateinformation/test.yml index f12f823b..f2f9c491 100644 --- a/tests/modules/picard/fixmateinformation/test.yml +++ b/tests/modules/picard/fixmateinformation/test.yml @@ -7,4 +7,3 @@ - path: output/picard/test.bam md5sum: 746102e8c242c0ef42e045c49d320030 - path: output/picard/versions.yml - md5sum: 4329ba7cdca8f4f6018dfd5c019ba2eb diff --git a/tests/modules/picard/liftovervcf/nextflow.config b/tests/modules/picard/liftovervcf/nextflow.config index e1581bb9..f69fc351 100644 --- a/tests/modules/picard/liftovervcf/nextflow.config +++ b/tests/modules/picard/liftovervcf/nextflow.config @@ -1,5 +1,5 @@ process { - ext.args = "WARN_ON_MISSING_CONTIG=true" + ext.args = "--WARN_ON_MISSING_CONTIG true" publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } } diff --git a/tests/modules/picard/markduplicates/nextflow.config b/tests/modules/picard/markduplicates/nextflow.config index 9178c5b1..40d46110 100644 --- a/tests/modules/picard/markduplicates/nextflow.config +++ b/tests/modules/picard/markduplicates/nextflow.config @@ -3,7 +3,7 @@ process { publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } withName: PICARD_MARKDUPLICATES_UNSORTED { - ext.args = 'ASSUME_SORT_ORDER=queryname' + ext.args = '--ASSUME_SORT_ORDER queryname' } } diff --git a/tests/modules/rsem/calculateexpression/test.yml b/tests/modules/rsem/calculateexpression/test.yml index f19c3398..b0251de9 100644 --- a/tests/modules/rsem/calculateexpression/test.yml +++ b/tests/modules/rsem/calculateexpression/test.yml @@ -42,7 +42,7 @@ - path: output/rsem/rsem/genome.transcripts.fa md5sum: 050c521a2719c2ae48267c1e65218f29 - path: output/rsem/rsem/genomeParameters.txt - md5sum: 2fe3a030e1706c3e8cd4df3818e6dd2f + md5sum: df5a456e3242520cc36e0083a6a7d9dd - path: output/rsem/rsem/sjdbInfo.txt md5sum: 5690ea9d9f09f7ff85b7fd47bd234903 - path: output/rsem/rsem/sjdbList.fromGTF.out.tab @@ -63,4 +63,4 @@ - path: output/rsem/test.stat/test.theta md5sum: de2e4490c98cc5383a86ae8225fd0a28 - path: output/rsem/test.transcript.bam - md5sum: 7846491086c478858419667d60f18edd + md5sum: ed681d39f5700ffc74d6321525330d93 diff --git a/tests/modules/samtools/bamtocram/main.nf b/tests/modules/samtools/bamtocram/main.nf new file mode 100644 index 00000000..b1743310 --- /dev/null +++ b/tests/modules/samtools/bamtocram/main.nf @@ -0,0 +1,17 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { SAMTOOLS_BAMTOCRAM } from '../../../../modules/samtools/bamtocram/main.nf' + +workflow test_samtools_bamtocram { + + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true), + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)] + + fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) + + SAMTOOLS_BAMTOCRAM ( input, fasta, fai ) +} \ No newline at end of file diff --git a/tests/modules/samtools/bamtocram/nextflow.config b/tests/modules/samtools/bamtocram/nextflow.config new file mode 100644 index 00000000..8730f1c4 --- /dev/null +++ b/tests/modules/samtools/bamtocram/nextflow.config @@ -0,0 +1,5 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} diff --git a/tests/modules/samtools/bamtocram/test.yml b/tests/modules/samtools/bamtocram/test.yml new file mode 100644 index 00000000..3cb82902 --- /dev/null +++ b/tests/modules/samtools/bamtocram/test.yml @@ -0,0 +1,9 @@ +- name: samtools bamtocram test_samtools_bamtocram + command: nextflow run ./tests/modules/samtools/bamtocram -entry test_samtools_bamtocram -c ./tests/config/nextflow.config -c ./tests/modules/samtools/bamtocram/nextflow.config + tags: + - samtools/bamtocram + - samtools + files: + - path: output/samtools/test.cram + - path: output/samtools/test.cram.crai + - path: output/samtools/versions.yml diff --git a/tests/modules/tabix/tabix/main.nf b/tests/modules/tabix/tabix/main.nf index 993ee812..da26f4d7 100644 --- a/tests/modules/tabix/tabix/main.nf +++ b/tests/modules/tabix/tabix/main.nf @@ -2,9 +2,10 @@ nextflow.enable.dsl = 2 -include { TABIX_TABIX as TABIX_BED } from '../../../../modules/tabix/tabix/main.nf' -include { TABIX_TABIX as TABIX_GFF } from '../../../../modules/tabix/tabix/main.nf' -include { TABIX_TABIX as TABIX_VCF } from '../../../../modules/tabix/tabix/main.nf' +include { TABIX_TABIX as TABIX_BED } from '../../../../modules/tabix/tabix/main.nf' +include { TABIX_TABIX as TABIX_GFF } from '../../../../modules/tabix/tabix/main.nf' +include { TABIX_TABIX as TABIX_VCF_TBI } from '../../../../modules/tabix/tabix/main.nf' +include { TABIX_TABIX as TABIX_VCF_CSI } from '../../../../modules/tabix/tabix/main.nf' workflow test_tabix_tabix_bed { input = [ [ id:'B.bed' ], // meta map @@ -22,10 +23,18 @@ workflow test_tabix_tabix_gff { TABIX_GFF ( input ) } -workflow test_tabix_tabix_vcf { +workflow test_tabix_tabix_vcf_tbi { input = [ [ id:'test.vcf' ], // meta map [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ] ] - TABIX_VCF ( input ) + TABIX_VCF_TBI ( input ) +} + +workflow test_tabix_tabix_vcf_csi { + input = [ [ id:'test.vcf' ], // meta map + [ file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true) ] + ] + + TABIX_VCF_CSI ( input ) } diff --git a/tests/modules/tabix/tabix/nextflow.config b/tests/modules/tabix/tabix/nextflow.config index aa97a873..139e0865 100644 --- a/tests/modules/tabix/tabix/nextflow.config +++ b/tests/modules/tabix/tabix/nextflow.config @@ -10,8 +10,12 @@ process { ext.args = '-p gff' } - withName: TABIX_VCF { + withName: TABIX_VCF_TBI { ext.args = '-p vcf' } + withName: TABIX_VCF_CSI { + ext.args = '-p vcf --csi' + } + } diff --git a/tests/modules/tabix/tabix/test.yml b/tests/modules/tabix/tabix/test.yml index 46be28dd..6d168ef5 100644 --- a/tests/modules/tabix/tabix/test.yml +++ b/tests/modules/tabix/tabix/test.yml @@ -15,10 +15,18 @@ - path: ./output/tabix/genome.gff3.gz.tbi md5sum: f79a67d95a98076e04fbe0455d825926 - name: tabix tabix vcf - command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config + command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf_tbi -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config tags: - tabix - tabix/tabix files: - path: output/tabix/test.vcf.gz.tbi md5sum: 36e11bf96ed0af4a92caa91a68612d64 +- name: tabix tabix vcf csi + command: nextflow run ./tests/modules/tabix/tabix -entry test_tabix_tabix_vcf_csi -c ./tests/config/nextflow.config -c ./tests/modules/tabix/tabix/nextflow.config + tags: + - tabix + - tabix/tabix + files: + - path: output/tabix/test.vcf.gz.csi + md5sum: 5f930522d2b9dcdba2807b7da4dfa3fd diff --git a/tests/modules/tiddit/sv/test.yml b/tests/modules/tiddit/sv/test.yml index 168d21c5..40ea5b4d 100644 --- a/tests/modules/tiddit/sv/test.yml +++ b/tests/modules/tiddit/sv/test.yml @@ -9,6 +9,7 @@ - path: output/tiddit/test.signals.tab md5sum: dab4b2fec4ddf8eb1c23005b0770150e - path: output/tiddit/test.vcf + md5sum: bdce14ae8292bf3deb81f6f255baf859 - name: tiddit sv no ref command: nextflow run ./tests/modules/tiddit/sv -entry test_tiddit_sv_no_ref -c ./tests/config/nextflow.config -c ./tests/modules/tiddit/sv/nextflow.config @@ -21,3 +22,4 @@ - path: output/tiddit/test.signals.tab md5sum: dab4b2fec4ddf8eb1c23005b0770150e - path: output/tiddit/test.vcf + md5sum: 3d0e83a8199b2bdb81cfe3e6b12bf64b diff --git a/tests/subworkflows/nf-core/bam_qc_picard/main.nf b/tests/subworkflows/nf-core/bam_qc_picard/main.nf new file mode 100644 index 00000000..a3e2ed62 --- /dev/null +++ b/tests/subworkflows/nf-core/bam_qc_picard/main.nf @@ -0,0 +1,27 @@ +#!/usr/bin/env nextflow + +nextflow.enable.dsl = 2 + +include { BAM_QC_PICARD } from '../../../../subworkflows/nf-core/bam_qc_picard/main' addParams([:]) + +workflow test_bam_qc_picard_wgs { + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] + fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + fasta_fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) + + BAM_QC_PICARD ( input, fasta, fasta_fai, [], [] ) +} + +workflow test_bam_qc_picard_targetted { + input = [ [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) + ] + fasta = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + fasta_fai = file(params.test_data['sarscov2']['genome']['genome_fasta_fai'], checkIfExists: true) + bait = file(params.test_data['sarscov2']['genome']['baits_interval_list'], checkIfExists: true) + target = file(params.test_data['sarscov2']['genome']['targets_interval_list'], checkIfExists: true) + + BAM_QC_PICARD ( input, fasta, fasta_fai, bait, target ) +} diff --git a/tests/subworkflows/nf-core/bam_qc_picard/nextflow.config b/tests/subworkflows/nf-core/bam_qc_picard/nextflow.config new file mode 100644 index 00000000..8730f1c4 --- /dev/null +++ b/tests/subworkflows/nf-core/bam_qc_picard/nextflow.config @@ -0,0 +1,5 @@ +process { + + publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" } + +} diff --git a/tests/subworkflows/nf-core/bam_qc_picard/test.yml b/tests/subworkflows/nf-core/bam_qc_picard/test.yml new file mode 100644 index 00000000..7b0a6c2b --- /dev/null +++ b/tests/subworkflows/nf-core/bam_qc_picard/test.yml @@ -0,0 +1,33 @@ +- name: bam qc picard wgs + command: nextflow run ./tests/subworkflows/nf-core/bam_qc_picard -entry test_bam_qc_picard_wgs -c tests/config/nextflow.config + tags: + - subworkflows + # - subworkflows/bam_qc_picard + # Modules + # - picard + # - picard/collectmultiplemetrics + # - picard/collectwgsmetrics + files: + - path: ./output/picard/test.CollectMultipleMetrics.alignment_summary_metrics + - path: ./output/picard/test.CollectMultipleMetrics.insert_size_metrics + - path: ./output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle_metrics + - path: ./output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics + - path: ./output/picard/test.CollectMultipleMetrics.quality_distribution_metrics + - path: ./output/picard/test.CollectWgsMetrics.coverage_metrics + +- name: bam qc picard targetted + command: nextflow run ./tests/subworkflows/nf-core/bam_qc_picard -entry test_bam_qc_picard_targetted -c tests/config/nextflow.config + tags: + - subworkflows + # - subworkflows/bam_qc_picard + # Modules + # - picard + # - picard/collectmultiplemetrics + # - picard/collecthsmetrics + files: + - path: ./output/picard/test.CollectMultipleMetrics.alignment_summary_metrics + - path: ./output/picard/test.CollectMultipleMetrics.insert_size_metrics + - path: ./output/picard/test.CollectMultipleMetrics.base_distribution_by_cycle_metrics + - path: ./output/picard/test.CollectMultipleMetrics.quality_by_cycle_metrics + - path: ./output/picard/test.CollectMultipleMetrics.quality_distribution_metrics + - path: ./output/picard/test.CollectHsMetrics.coverage_metrics