diff --git a/.nf-core.yml b/.nf-core.yml index 474e44e..09fed42 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1,33 +1,33 @@ lint: files_exist: - - CODE_OF_CONDUCT.md - - assets/nf-core-vcftomat_logo_light.png - - docs/images/nf-core-vcftomat_logo_light.png - - docs/images/nf-core-vcftomat_logo_dark.png - - .github/ISSUE_TEMPLATE/config.yml - - .github/workflows/awstest.yml - - .github/workflows/awsfulltest.yml + - CODE_OF_CONDUCT.md + - assets/nf-core-vcftomat_logo_light.png + - docs/images/nf-core-vcftomat_logo_light.png + - docs/images/nf-core-vcftomat_logo_dark.png + - .github/ISSUE_TEMPLATE/config.yml + - .github/workflows/awstest.yml + - .github/workflows/awsfulltest.yml files_unchanged: - - .github/CONTRIBUTING.md - - .prettierignore - - .github/CONTRIBUTING.md - - .prettierignore - - CODE_OF_CONDUCT.md - - assets/nf-core-vcftomat_logo_light.png - - docs/images/nf-core-vcftomat_logo_light.png - - docs/images/nf-core-vcftomat_logo_dark.png - - .github/ISSUE_TEMPLATE/bug_report.yml + - .github/CONTRIBUTING.md + - .prettierignore + - .github/CONTRIBUTING.md + - .prettierignore + - CODE_OF_CONDUCT.md + - assets/nf-core-vcftomat_logo_light.png + - docs/images/nf-core-vcftomat_logo_light.png + - docs/images/nf-core-vcftomat_logo_dark.png + - .github/ISSUE_TEMPLATE/bug_report.yml included_configs: false actions_ci: false multiqc_config: - - report_comment + - report_comment nextflow_config: - - manifest.name - - manifest.homePage - - validation.help.beforeText - - validation.help.afterText - - validation.summary.beforeText - - validation.summary.afterText + - manifest.name + - manifest.homePage + - validation.help.beforeText + - validation.help.afterText + - validation.summary.beforeText + - validation.summary.afterText nf_core_version: 3.1.0 repository_type: pipeline template: @@ -40,8 +40,8 @@ template: org: qbic-pipelines outdir: . skip_features: - - gitpod - - codespaces - - fastqc - - adaptivecard - version: 1.1.0 + - gitpod + - codespaces + - fastqc + - adaptivecard + version: 1.2.0dev diff --git a/CHANGELOG.md b/CHANGELOG.md index a21bb96..bffbcca 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## v1.2.0dev + +### Added + +### Fixed + ## v1.1.0 - Newton Puccoon - 08.01.2025 ### Added diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index b1d5749..e83ee9d 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,5 +1,5 @@ report_comment: > - This report has been generated by the qbic-pipelines/vcftomat analysis pipeline. report_section_order: "qbic-pipelines-vcftomat-methods-description": diff --git a/nextflow.config b/nextflow.config index 16515b3..79ae5b9 100644 --- a/nextflow.config +++ b/nextflow.config @@ -234,7 +234,7 @@ manifest { mainScript = 'main.nf' defaultBranch = 'master' nextflowVersion = '!>=24.04.2' - version = '1.1.0' + version = '1.2.0dev' doi = '' } diff --git a/ro-crate-metadata.json b/ro-crate-metadata.json index d73a10f..478308c 100644 --- a/ro-crate-metadata.json +++ b/ro-crate-metadata.json @@ -21,9 +21,9 @@ { "@id": "./", "@type": "Dataset", - "creativeWorkStatus": "Stable", - "datePublished": "2025-01-08T12:21:55+00:00", - "description": "# qbic-pipelines/vcftomat\n\n[![GitHub Actions CI Status](https://github.com/qbic-pipelines/vcftomat/actions/workflows/ci.yml/badge.svg)](https://github.com/qbic-pipelines/vcftomat/actions/workflows/ci.yml)\n[![GitHub Actions Linting Status](https://github.com/qbic-pipelines/vcftomat/actions/workflows/linting.yml/badge.svg)](https://github.com/qbic-pipelines/vcftomat/actions/workflows/linting.yml)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)\n\n[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)\n\n[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.svg)](https://www.nextflow.io/)\n[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)\n[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)\n[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)\n[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/qbic-pipelines/vcftomat)\n\n## Introduction\n\n**qbic-pipelines/vcftomat** is a bioinformatics pipeline that processes g.vcf files to a matrix suitable for downstream analysis. The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:\n\n1. Indexes (g.)vcf files ([`tabix`](http://www.htslib.org/doc/tabix.html))\n2. Converts g.vcf files to vcf with `genotypegvcf` ([`GATK`](https://gatk.broadinstitute.org/hc/en-us))\n3. Concatenates all vcfs that have the same id and the same label with `bcftools/concat` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))\n4. Changes the sample name in the vcf file to the filename with `bcftools/reheader` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html)) - This can be turned off by adding `--rename false` to the `nextflow run` command.\n5. Merges all vcfs from the same sample with `bcftools/merge` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))\n6. Converts the (merged) vcfs to a matrix using a custom R script written by @ellisdoro ([`R`](https://www.r-project.org/))\n7. Collects all reports into a MultiQC report ([`MultiQC`](http://multiqc.info/))\n\n![](./docs/images/vcftomat.excalidraw.png)\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.\n\nFirst, prepare a samplesheet with your input data that looks as follows:\n\n`samplesheet.csv`:\n\n```csv\nsample,label,gvcf,vcf_path,vcf_index_path\nSAMPLE-1,pipelineA-callerA,false,path/to/vcf.gz,path/to/.vcf.gz.tbi\nSAMPLE-1,pipelineB-callerA,false,path/to/vcf.gz,path/to/.vcf.gz.tbi\nSAMPLE-2,pipelineB-callerB,true,path/to/g.vcf.gz,path/to/g.vcf.gz.tbi\nSAMPLE-2,pipelineB-callerB,true,path/to/g.vcf.gz,path/to/g.vcf.gz.tbi\n```\n\nEach row represents a VCF file coming from a sample. The `label` column enables concatenation of vcfs (for example when the pipeline produces different vcfs for chrM and chrY). The `gvcf` column indicates whether the file is a g.vcf file or not. The `vcf_path` and `vcf_index_path` columns contain the path to the VCF file and its index, respectively.\n\nNow, you can run the pipeline using:\n\n```bash\nnextflow run qbic-pipelines/vcftomat \\\n -profile \\\n --input samplesheet.csv \\\n --genome GATK.GRCh38 \\\n --outdir \n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\n## Credits\n\nqbic-pipelines/vcftomat was originally written by Famke B\u00e4uerle, Dorothy Ellis.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\n## Citations\n\n\n\n\n\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nThis pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/main/LICENSE).\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n", + "creativeWorkStatus": "InProgress", + "datePublished": "2025-01-08T14:48:05+00:00", + "description": "# qbic-pipelines/vcftomat\n\n[![GitHub Actions CI Status](https://github.com/qbic-pipelines/vcftomat/actions/workflows/ci.yml/badge.svg)](https://github.com/qbic-pipelines/vcftomat/actions/workflows/ci.yml)\n[![GitHub Actions Linting Status](https://github.com/qbic-pipelines/vcftomat/actions/workflows/linting.yml/badge.svg)](https://github.com/qbic-pipelines/vcftomat/actions/workflows/linting.yml)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.14616650-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.14616650)\n[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)\n\n[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A524.04.2-23aa62.svg)](https://www.nextflow.io/)\n[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)\n[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)\n[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)\n[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/qbic-pipelines/vcftomat)\n\n## Introduction\n\n**qbic-pipelines/vcftomat** is a bioinformatics pipeline that processes g.vcf files to a matrix suitable for downstream analysis. The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes data using the following steps:\n\n1. Indexes (g.)vcf files ([`tabix`](http://www.htslib.org/doc/tabix.html))\n2. Converts g.vcf files to vcf with `genotypegvcf` ([`GATK`](https://gatk.broadinstitute.org/hc/en-us))\n3. Concatenates all vcfs that have the same id and the same label with `bcftools/concat` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))\n4. Changes the sample name in the vcf file to the filename with `bcftools/reheader` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html)) - This can be turned off by adding `--rename false` to the `nextflow run` command.\n5. Merges all vcfs from the same sample with `bcftools/merge` ([`bcftools`](https://samtools.github.io/bcftools/bcftools.html))\n6. Converts the (merged) vcfs to a matrix using a custom R script written by @ellisdoro ([`R`](https://www.r-project.org/))\n7. Collects all reports into a MultiQC report ([`MultiQC`](http://multiqc.info/))\n\n![](./docs/images/vcftomat.excalidraw.png)\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.\n\nFirst, prepare a samplesheet with your input data that looks as follows:\n\n`samplesheet.csv`:\n\n```csv\nsample,label,gvcf,vcf_path,vcf_index_path\nSAMPLE-1,pipelineA-callerA,false,path/to/vcf.gz,path/to/.vcf.gz.tbi\nSAMPLE-1,pipelineB-callerA,false,path/to/vcf.gz,path/to/.vcf.gz.tbi\nSAMPLE-2,pipelineB-callerB,true,path/to/g.vcf.gz,path/to/g.vcf.gz.tbi\nSAMPLE-2,pipelineB-callerB,true,path/to/g.vcf.gz,path/to/g.vcf.gz.tbi\n```\n\nEach row represents a VCF file coming from a sample. The `label` column enables concatenation of vcfs (for example when the pipeline produces different vcfs for chrM and chrY). The `gvcf` column indicates whether the file is a g.vcf file or not. The `vcf_path` and `vcf_index_path` columns contain the path to the VCF file and its index, respectively.\n\nNow, you can run the pipeline using:\n\n```bash\nnextflow run qbic-pipelines/vcftomat \\\n -profile \\\n --input samplesheet.csv \\\n --genome GATK.GRCh38 \\\n --outdir \n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\n## Credits\n\nqbic-pipelines/vcftomat was originally written by Famke B\u00e4uerle, Dorothy Ellis.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\n## Citations\n\nIf you use qbic-pipelines/vcftomat for your analysis, please cite it using the following doi: [10.5281/zenodo.14616650](https://doi.org/10.5281/zenodo.14616650)\n\n\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nThis pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/main/LICENSE).\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n", "hasPart": [ { "@id": "main.nf" @@ -102,7 +102,7 @@ }, "mentions": [ { - "@id": "#52a401c6-dec9-4dfe-92eb-d33149004223" + "@id": "#a331573e-ab8a-4ef8-b58b-fce079a0219d" } ], "name": "qbic-pipelines/vcftomat" @@ -124,7 +124,11 @@ }, { "@id": "main.nf", - "@type": ["File", "SoftwareSourceCode", "ComputationalWorkflow"], + "@type": [ + "File", + "SoftwareSourceCode", + "ComputationalWorkflow" + ], "creator": [ { "@id": "https://orcid.org/0000-0003-1387-0251" @@ -134,24 +138,36 @@ } ], "dateCreated": "", - "dateModified": "2025-01-08T13:21:55Z", + "dateModified": "2025-01-08T15:48:05Z", "dct:conformsTo": "https://bioschemas.org/profiles/ComputationalWorkflow/1.0-RELEASE/", - "keywords": ["nf-core", "nextflow"], - "license": ["MIT"], + "keywords": [ + "nf-core", + "nextflow" + ], + "license": [ + "MIT" + ], "maintainer": [ { "@id": "https://orcid.org/0000-0003-1387-0251" } ], - "name": ["qbic-pipelines/vcftomat"], + "name": [ + "qbic-pipelines/vcftomat" + ], "programmingLanguage": { "@id": "https://w3id.org/workflowhub/workflow-ro-crate#nextflow" }, "sdPublisher": { "@id": "https://nf-co.re/" }, - "url": ["https://github.com/qbic-pipelines/vcftomat", "https://nf-co.re/qbic-pipelines/vcftomat/1.1.0/"], - "version": ["1.1.0"] + "url": [ + "https://github.com/qbic-pipelines/vcftomat", + "https://nf-co.re/qbic-pipelines/vcftomat/dev/" + ], + "version": [ + "1.2.0dev" + ] }, { "@id": "https://w3id.org/workflowhub/workflow-ro-crate#nextflow", @@ -166,11 +182,11 @@ "version": "!>=24.04.2" }, { - "@id": "#52a401c6-dec9-4dfe-92eb-d33149004223", + "@id": "#a331573e-ab8a-4ef8-b58b-fce079a0219d", "@type": "TestSuite", "instance": [ { - "@id": "#2a6b4982-255a-44b9-9ff1-e0690f6c6e9d" + "@id": "#f9045bea-c5d1-4ad4-9246-ae0340086aaa" } ], "mainEntity": { @@ -179,7 +195,7 @@ "name": "Test suite for qbic-pipelines/vcftomat" }, { - "@id": "#2a6b4982-255a-44b9-9ff1-e0690f6c6e9d", + "@id": "#f9045bea-c5d1-4ad4-9246-ae0340086aaa", "@type": "TestInstance", "name": "GitHub Actions workflow for testing qbic-pipelines/vcftomat", "resource": "repos/qbic-pipelines/vcftomat/actions/workflows/ci.yml", @@ -325,4 +341,4 @@ "name": "Famke Ba\u0308uerle" } ] -} +} \ No newline at end of file