Merge branch 'viash-hub:main' into umi_tools_extract

emmarousseau · Jul 1, 2024 · fa76a0f · fa76a0f
2 parents c947810 + 3e08b59
commit fa76a0f
Show file tree

Hide file tree

Showing 27 changed files with 2,655 additions and 326 deletions.
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
@@ -3,114 +3,7 @@ name: Component Testing
 on:
   pull_request:
   push:
-    branches: [ '**' ]
 
 jobs:
-  run_ci_check_job:
-    runs-on: ubuntu-latest
-    outputs:
-      run_ci: ${{ steps.github_cli.outputs.check }}
-    steps:
-      - name: 'Check if branch has an existing pull request and the trigger was a push'
-        id: github_cli
-        run: |
-          pull_request=$(gh pr list -R ${{ github.repository }} -H ${{ github.ref_name }} --json url --state open --limit 1 | jq '.[0].url')
-          # If the branch has a PR and this run was triggered by a push event, do not run
-          if [[ "$pull_request" != "null" && "$GITHUB_REF_NAME" != "main" && "${{ github.event_name == 'push' }}" == "true" && "${{ !contains(github.event.head_commit.message, 'ci force') }}" == "true" ]]; then
-            echo "check=false" >> $GITHUB_OUTPUT
-          else
-            echo "check=true" >> $GITHUB_OUTPUT
-          fi
-        env:
-           GH_TOKEN: ${{ github.token }}
-
-  # phase 1
-  list:
-    needs: run_ci_check_job
-    runs-on: ubuntu-latest
-    if: ${{ needs.run_ci_check_job.outputs.run_ci == 'true' }}
-
-    outputs:
-      matrix: ${{ steps.set_matrix.outputs.matrix }}
-
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-
-    - name: Get head git commit message
-      id: get_head_commit_message
-      run: echo "HEAD_COMMIT_MESSAGE=$(git show -s --format=%s ${{ github.event.pull_request.head.sha || github.sha }})" >> "$GITHUB_OUTPUT"
-
-    - uses: viash-io/viash-actions/setup@v5
-
-    - name: Check if all config can be parsed if there is no unicode support
-      run: |
-        LANG=C viash ns list > /dev/null
-
-    # see https://github.com/viash-io/viash/issues/654
-    # and https://github.com/viash-io/viash-actions/pull/27
-    # - name: Get changed files
-    #   id: changed-files
-    #   uses: tj-actions/changed-files@v42
-    #   with:
-    #     separator: ";"
-    #     diff_relative: true
-    # - id: ns_list
-    #   uses: viash-io/viash-actions/ns-list@v5
-    #   with:
-    #     platform: docker
-    #     format: json
-    #     query: ^(?!workflows)
-    # - id: ns_list_filtered
-    #   uses: viash-io/viash-actions/project/detect-changed-components@v5
-    #   with:
-    #     input_file: "${{ steps.ns_list.outputs.output_file }}"
-    # - id: set_matrix
-    #   run: |
-    #     echo "matrix=$(jq -c '[ .[] | 
-    #       { 
-    #         "name": (.functionality.namespace + "/" + .functionality.name),
-    #         "config": .info.config,
-    #         "dir": .info.config | capture("^(?<dir>.*\/)").dir
-    #       }
-    #     ]' ${{ contains(steps.get_head_commit_message.outputs.HEAD_COMMIT_MESSAGE, 'ci force') && steps.ns_list.outputs.output_file || steps.ns_list_filtered.outputs.output_file }} )" >> $GITHUB_OUTPUT
-
-
-    - id: set_matrix
-      run: |
-        viash ns list --format json > ns_list.json
-        echo "matrix=$(jq -c '[ .[] | 
-          { 
-            "name": (.namespace + "/" + .name),
-            "config": .build_info.config,
-            "dir": .build_info.config | capture("^(?<dir>.*\/)").dir
-          }
-        ]' ns_list.json )" >> $GITHUB_OUTPUT
-
-  # phase 2
-  viash_test:
-    needs: list
-    if: ${{ needs.list.outputs.matrix != '[]' && needs.list.outputs.matrix != '' }}
-    runs-on: ubuntu-latest
-
-    strategy:
-      fail-fast: false
-      matrix:
-        component: ${{ fromJson(needs.list.outputs.matrix) }}
-
-    steps:
-    # Remove unnecessary files to free up space. Otherwise, we get 'no space left on device.'
-    - uses: data-intuitive/reclaim-the-bytes@v2
-
-    - uses: actions/checkout@v4
-
-    - uses: viash-io/viash-actions/setup@v5
-
-    - name: Run test
-      timeout-minutes: 30
-      run: |
-        viash test \
-          "${{ matrix.component.config }}" \
-          --cpus 2 \
-          --memory "6gb"
+  test:
+    uses: viash-hub/toolbox/.github/workflows/test.yaml@main
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,10 @@
-# base unreleased
+# biobox x.x.x
+
+## BUG FIXES
+
+* `pear`: fix component not exiting with the correct exitcode when PEAR fails.
+
+# biobox 0.1.0
 
 ## BREAKING CHANGES
 
@@ -17,6 +23,8 @@
     - `busco/busco_list_datasets`: Lists available busco datasets (PR #18).
     - `busco/busco_download_datasets`: Download busco datasets (PR #19).
 
+* `cutadapt`: Remove adapter sequences from high-throughput sequencing reads (PR #7).
+
 * `featurecounts`: Assign sequence reads to genomic features (PR #11).
 
 * `bgzip`: Add bgzip functionality to compress and decompress files (PR #13).
@@ -29,7 +37,9 @@
 
 * `multiqc`: Aggregate results from bioinformatics analyses across many samples into a single report (PR #42).
 
-* `star/star_align_reads`: Align reads to a reference genome (PR #22).
+* `star`:
+    - `star/star_align_reads`: Align reads to a reference genome (PR #22).
+    - `star/star_genome_generate`: Generate a genome index for STAR alignment (PR #58).
 
 * `gffread`: Validate, filter, convert and perform other operations on GFF files (PR #29).  
 
@@ -53,8 +63,9 @@
 
 * `falco`: A C++ drop-in replacement of FastQC to assess the quality of sequence read data (PR #43).
 
-
-## MAJOR CHANGES
+* `bedtools`:
+    - `bedtools_getfasta`: extract sequences from a FASTA file for each of the
+                           intervals defined in a BED/GFF/VCF file (PR #59).
 
 ## MINOR CHANGES
 
@@ -64,8 +75,16 @@
 
 * Update to Viash 0.9.0-RC3 (PR #51).
 
+* Update to Viash 0.9.0-RC6 (PR #63).
+
+* Switch to viash-hub/toolbox actions (PR #64).
+
 ## DOCUMENTATION
 
+* Update README (PR #64).
+
 ## BUG FIXES
 
-* Add escaping character before leading hashtag in the description field of the config file (PR #50).
+* Add escaping character before leading hashtag in the description field of the config file (PR #50).
+
+* Format URL in biobase/bcl_convert description (PR #55).
diff --git a/README.md b/README.md
@@ -1,15 +1,24 @@
-# Base repository for reusable Viash components
 
 
-This repository is a collection of reproducible and reusable Viash
-components.
+# 🌱📦 biobox
+
+[![ViashHub](https://img.shields.io/badge/ViashHub-biobox-7a4baa.png)](https://web.viash-hub.com/packages/biobox)
+[![GitHub](https://img.shields.io/badge/GitHub-viash--hub%2Fbiobox-blue.png)](https://github.com/viash-hub/biobox)
+[![GitHub
+License](https://img.shields.io/github/license/viash-hub/biobox.png)](https://github.com/viash-hub/biobox/blob/main/LICENSE)
+[![GitHub
+Issues](https://img.shields.io/github/issues/viash-hub/biobox.png)](https://github.com/viash-hub/biobox/issues)
+[![Viash
+version](https://img.shields.io/badge/Viash-v0.9.0--RC6-blue)](https://viash.io)
+
+A collection of bioinformatics tools for working with sequence data.
 
 ## Objectives
 
 - **Reusability**: Facilitating the use of components across various
   projects and contexts.
-- **Reproducibility**: Guaranteeing that bioinformatics analyses can be
-  reliably replicated.
+- **Reproducibility**: Ensuring that components are reproducible and can
+  be easily shared.
 - **Best Practices**: Adhering to established standards in software
   development and bioinformatics.
 
@@ -43,18 +52,21 @@ contribute a component to this repository.
 12. Create test script
 13. Create a `/var/software_versions.txt` file
 
-See the [CONTRIBUTING](CONTRIBUTING.md) file for more details.
+See the
+[CONTRIBUTING](https://github.com/viash-hub/biobox/blob/main/CONTRIBUTING.md)
+file for more details.
 
 ## Support and Community
 
 For support, questions, or to join our community:
 
 - **Issues**: Submit questions or issues via the [GitHub issue
-  tracker](https://github.com/viash-hub/base/issues).
+  tracker](https://github.com/viash-hub/biobox/issues).
 - **Discussions**: Join our discussions via [GitHub
-  Discussions](https://github.com/viash-hub/base/discussions).
+  Discussions](https://github.com/viash-hub/biobox/discussions).
 
 ## License
 
 This repository is licensed under an MIT license. See the
-[LICENSE](LICENSE) file for details.
+[LICENSE](https://github.com/viash-hub/biobox/blob/main/LICENSE) file
+for details.
diff --git a/README.qmd b/README.qmd
@@ -1,14 +1,25 @@
 ---
-title: Base repository for reusable Viash components
 format: gfm
 ---
+```{r setup, include=FALSE}
+project <- yaml::read_yaml("_viash.yaml")
+license <- paste0(project$links$repository, "/blob/main/LICENSE")
+contributing <- paste0(project$links$repository, "/blob/main/CONTRIBUTING.md")
+```
+# 🌱📦 `r project$name`
+
+[![ViashHub](https://img.shields.io/badge/ViashHub-`r project$name`-7a4baa)](https://web.viash-hub.com/packages/`r project$name`) 
+[![GitHub](https://img.shields.io/badge/GitHub-viash--hub%2F`r project$name`-blue)](`r project$links$repository`) 
+[![GitHub License](https://img.shields.io/github/license/viash-hub/`r project$name`)](`r license`) 
+[![GitHub Issues](https://img.shields.io/github/issues/viash-hub/`r project$name`)](`r project$links$issue_tracker`) 
+[![Viash version](https://img.shields.io/badge/Viash-v`r gsub("-", "--", project$viash_version)`-blue)](https://viash.io)
 
-This repository is a collection of reproducible and reusable Viash components.
+`r project$description`
 
 ## Objectives
 
 - **Reusability**: Facilitating the use of components across various projects and contexts.
-- **Reproducibility**: Guaranteeing that bioinformatics analyses can be reliably replicated.
+- **Reproducibility**: Ensuring that components are reproducible and can be easily shared.
 - **Best Practices**: Adhering to established standards in software development and bioinformatics.
 
 ## Contributing
@@ -37,15 +48,15 @@ knitr::asis_output(
 )
 ```
 
-See the [CONTRIBUTING](CONTRIBUTING.md) file for more details.
+See the [CONTRIBUTING](`r contributing`) file for more details.
 
 
 ## Support and Community
 
 For support, questions, or to join our community:
 
-- **Issues**: Submit questions or issues via the [GitHub issue tracker](https://github.com/viash-hub/base/issues).
-- **Discussions**: Join our discussions via [GitHub Discussions](https://github.com/viash-hub/base/discussions).
+- **Issues**: Submit questions or issues via the [GitHub issue tracker](`r project$links$issue_tracker`).
+- **Discussions**: Join our discussions via [GitHub Discussions](`r project$links$repository`/discussions).
 
 ## License
-This repository is licensed under an MIT license. See the [LICENSE](LICENSE) file for details.
+This repository is licensed under an MIT license. See the [LICENSE](`r license`) file for details.
diff --git a/_viash.yaml b/_viash.yaml
@@ -1,13 +1,13 @@
-name: biobase
+name: biobox
 description: |
   A collection of bioinformatics tools for working with sequence data.
 license: MIT
-keywords: [bioinformatics, sequence, alignment, variant calling]
+keywords: [bioinformatics, modules, sequencing]
 links:
-  issue_tracker: https://github.com/viash-hub/biobase/issues
-  repository: https://github.com/viash-hub/biobase
+  issue_tracker: https://github.com/viash-hub/biobox/issues
+  repository: https://github.com/viash-hub/biobox
 
-viash_version: 0.9.0-RC3
+viash_version: 0.9.0-RC6
 
 config_mods: |
   .requirements.commands := ['ps']
diff --git a/src/bcl_convert/config.vsh.yaml b/src/bcl_convert/config.vsh.yaml
@@ -2,8 +2,8 @@ name: bcl_convert
 description: |
   Convert bcl files to fastq files using bcl-convert.
   Information about upgrading from bcl2fastq via
-  https://emea.support.illumina.com/bulletins/2020/10/upgrading-from-bcl2fastq-to-bcl-convert.html
-  and https://support.illumina.com/sequencing/sequencing_software/bcl-convert/compatibility.html
+  [Upgrading from bcl2fastq to BCL Convert](https://emea.support.illumina.com/bulletins/2020/10/upgrading-from-bcl2fastq-to-bcl-convert.html)
+  and [BCL Convert Compatible Products](https://support.illumina.com/sequencing/sequencing_software/bcl-convert/compatibility.html)
 argument_groups:
   - name: Input arguments
     arguments: