diff --git a/CHANGELOG.md b/CHANGELOG.md index 98ebac94bc..2b58295908 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -199,6 +199,7 @@ Akkatjåkkå is another glacier. ### Added - [1759](https://github.com/nf-core/sarek/pull/1759) - Back to dev +- [1760](https://github.com/nf-core/sarek/pull/1760) - Add linting of FASTQ with FQ/LINT ### Changed diff --git a/modules.json b/modules.json index fbd23a8885..00e94441c8 100644 --- a/modules.json +++ b/modules.json @@ -181,6 +181,11 @@ "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d", "installed_by": ["modules"] }, + "fq/lint": { + "branch": "master", + "git_sha": "2c0260ed80daeca9c6dfa477a4daf04ff336dc37", + "installed_by": ["modules"] + }, "freebayes": { "branch": "master", "git_sha": "d04951ee68e3e8b875ebf5ddb7ba6e05233624c1", diff --git a/modules/nf-core/fq/lint/environment.yml b/modules/nf-core/fq/lint/environment.yml new file mode 100644 index 0000000000..74b146083b --- /dev/null +++ b/modules/nf-core/fq/lint/environment.yml @@ -0,0 +1,5 @@ +channels: + - conda-forge + - bioconda +dependencies: + - bioconda::fq=0.12.0 diff --git a/modules/nf-core/fq/lint/main.nf b/modules/nf-core/fq/lint/main.nf new file mode 100644 index 0000000000..27107b4657 --- /dev/null +++ b/modules/nf-core/fq/lint/main.nf @@ -0,0 +1,44 @@ +process FQ_LINT { + tag "$meta.id" + label 'process_low' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/fq:0.12.0--h9ee0642_0': + 'biocontainers/fq:0.12.0--h9ee0642_0' }" + + input: + tuple val(meta), path(fastq) + + output: + tuple val(meta), path("*.fq_lint.txt"), emit: lint + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + def prefix = task.ext.prefix ?: "${meta.id}" + """ + fq lint \\ + $args \\ + $fastq > ${prefix}.fq_lint.txt + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + fq: \$(echo \$(fq lint --version | sed 's/fq-lint //g')) + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + touch ${prefix}.fq_lint.txt + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + fq: \$(echo \$(fq lint --version | sed 's/fq-lint //g')) + END_VERSIONS + """ +} diff --git a/modules/nf-core/fq/lint/meta.yml b/modules/nf-core/fq/lint/meta.yml new file mode 100644 index 0000000000..7240fb5796 --- /dev/null +++ b/modules/nf-core/fq/lint/meta.yml @@ -0,0 +1,43 @@ +name: "fq_lint" +description: fq lint is a FASTQ file pair validator. +keywords: + - lint + - fastq + - validate +tools: + - "fq": + description: "fq is a library to generate and validate FASTQ file pairs." + homepage: "https://github.com/stjude-rust-labs/fq" + documentation: "https://github.com/stjude-rust-labs/fq" + tool_dev_url: "https://github.com/stjude-rust-labs/fq" + licence: ["MIT"] + identifier: "" +input: + - - meta: + type: map + description: | + Groovy Map containing sample information + e.g. [ id:'test', single_end:false ] + - fastq: + type: file + description: FASTQ file list + pattern: "*.fastq{,.gz}" +output: + - lint: + - meta: + type: file + description: Lint output + pattern: "*.fq_lint.txt" + - "*.fq_lint.txt": + type: file + description: Lint output + pattern: "*.fq_lint.txt" + - versions: + - versions.yml: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@adamrtalbot" +maintainers: + - "@adamrtalbot" diff --git a/modules/nf-core/fq/lint/tests/main.nf.test b/modules/nf-core/fq/lint/tests/main.nf.test new file mode 100644 index 0000000000..ec2eaf8bc0 --- /dev/null +++ b/modules/nf-core/fq/lint/tests/main.nf.test @@ -0,0 +1,63 @@ +nextflow_process { + + name "Test Process FQ_LINT" + script "../main.nf" + process "FQ_LINT" + + tag "modules" + tag "modules_nfcore" + tag "fq" + tag "fq/lint" + + test("test_fq_lint_success") { + when { + params { + outdir = "$outputDir" + } + process { + """ + input[0] = [ [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ] + ] + """ + } + } + + then { + assertAll ( + { assert process.success }, + { assert process.out.lint.get(0).get(1) ==~ ".*/test.fq_lint.txt" }, + { assert path(process.out.lint.get(0).get(1)).getText().contains("fq-lint start") }, + { assert path(process.out.lint.get(0).get(1)).getText().contains("read 100 records") }, + { assert path(process.out.lint.get(0).get(1)).getText().contains("fq-lint end") }, + ) + } + + } + + test("test_fq_lint_fail") { + when { + params { + outdir = "$outputDir" + } + process { + """ + input[0] = [ [ id:'test', single_end:false ], // meta map + [ file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true), + file(params.modules_testdata_base_path + 'genomics/prokaryotes/candidatus_portiera_aleyrodidarum/illumina/fastq/test_2.fastq.gz', checkIfExists: true) ] + ] + """ + } + } + + then { + assertAll ( + { assert !process.success }, + { assert snapshot(process.out).match() }, + ) + } + + } + +} diff --git a/modules/nf-core/fq/lint/tests/main.nf.test.snap b/modules/nf-core/fq/lint/tests/main.nf.test.snap new file mode 100644 index 0000000000..fec8e5243b --- /dev/null +++ b/modules/nf-core/fq/lint/tests/main.nf.test.snap @@ -0,0 +1,25 @@ +{ + "test_fq_lint_fail": { + "content": [ + { + "0": [ + + ], + "1": [ + + ], + "lint": [ + + ], + "versions": [ + + ] + } + ], + "meta": { + "nf-test": "0.9.0", + "nextflow": "24.04.4" + }, + "timestamp": "2024-10-19T16:37:02.133847389" + } +} \ No newline at end of file diff --git a/modules/nf-core/fq/lint/tests/tags.yml b/modules/nf-core/fq/lint/tests/tags.yml new file mode 100644 index 0000000000..9c9c323f88 --- /dev/null +++ b/modules/nf-core/fq/lint/tests/tags.yml @@ -0,0 +1,2 @@ +fq/lint: + - modules/nf-core/fq/lint/** diff --git a/nextflow_schema.json b/nextflow_schema.json index 1fe0895003..37336dd9ef 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -118,7 +118,7 @@ "fa_icon": "fas fa-forward", "description": "Disable specified tools.", "help_text": "Multiple tools can be specified, separated by commas.\n\n> **NB** `--skip_tools baserecalibrator_report` is actually just not saving the reports.\n> **NB** `--skip_tools markduplicates_report` does not skip `MarkDuplicates` but prevent the collection of duplicate metrics that slows down performance.", - "pattern": "^((baserecalibrator|baserecalibrator_report|bcftools|dnascope_filter|documentation|fastqc|haplotypecaller_filter|haplotyper_filter|markduplicates|markduplicates_report|mosdepth|multiqc|samtools|vcftools|versions)?,?)*(?