Merge pull request #28 from sanger-tol/dev

Pre-v1 merge

.github/workflows/ci.yml

@@ -10,6 +10,8 @@ on:
 
 env:
   NXF_ANSI_LOG: false
+  NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/.singularity
+  NXF_SINGULARITY_LIBRARYDIR: ${{ github.workspace }}/.singularity
 
 concurrency:
   group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
@@ -19,14 +21,20 @@ jobs:
   test:
     name: Run pipeline with test data
     # Only run on push if this is the nf-core dev branch (merged PRs)
-    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/curationpretextt') }}"
+    if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/curationpretext') }}"
     runs-on: ubuntu-latest
     strategy:
       matrix:
         NXF_VER:
           - "22.10.1"
           - "latest-everything"
     steps:
+      - name: Get branch names
+        # Pulls the names of current branches in repo
+        # steps.branch-names.outputs.current_branch is used later and returns the name of the branch the PR is made FROM not to
+        id: branch-names
+        uses: tj-actions/branch-names@v8
+
       - name: Check out pipeline code
         uses: actions/checkout@v3
 
@@ -35,17 +43,36 @@ jobs:
         with:
           version: "${{ matrix.NXF_VER }}"
 
+      - name: Setup apptainer
+        uses: eWaterCycle/setup-apptainer@main
+
+      - name: Set up Singularity
+        run: |
+          mkdir -p $NXF_SINGULARITY_CACHEDIR
+          mkdir -p $NXF_SINGULARITY_LIBRARYDIR
+
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install nf-core
+        run: |
+          pip install nf-core
+
+      - name: NF-Core Download - download singularity containers
+        # Forcibly download repo on active branch and download SINGULARITY containers into the CACHE dir if not found
+        # Must occur after singularity install or will crash trying to dl containers
+        # Zip up this fresh download and run the checked out version
+        run: |
+          nf-core download sanger-tol/curationpretext --revision ${{ steps.branch-names.outputs.current_branch }} --compress none -d --force --outdir sanger-curationpretext --container-cache-utilisation amend --container-system singularity
+
       - name: Download test data
         # Download A fungal test data set that is full enough to show some real output.
         run: |
           curl https://tolit.cog.sanger.ac.uk/test-data/resources/treeval/TreeValTinyData.tar.gz | tar xzf -
 
-      - name: Run MAPS_ONLY pipeline with test data
-        # Remember that you can parallelise this by using strategy.matrix
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results -entry MAPS_ONLY
-
-      - name: Run ALL_FILES pipeline with test data
+      - name: Singularity - Run ALL_FILES pipeline with test data
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ./sanger-curationpretext/${{ steps.branch-names.outputs.current_branch }}/main.nf -profile test,singularity --outdir ./Sing-res

.github/workflows/linting.yml

@@ -22,7 +22,7 @@ jobs:
         run: npm install -g editorconfig-checker
 
       - name: Run ECLint check
-        run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile')
+        run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|cff\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile')
 
   Prettier:
     runs-on: ubuntu-latest

.nf-core.yml

@@ -2,6 +2,9 @@ repository_type: pipeline
 lint:
   files_exist:
     - assets/multiqc_config.yml
+    - assets/nf-core-curationpretext_logo_light.png
+    - docs/images/nf-core-curationpretext_logo_light.png
+    - docs/images/nf-core-curationpretext_logo_dark.png
   files_unchanged:
     - .github/workflows/linting.yml
     - LICENSE

CHANGELOG.md

@@ -3,7 +3,60 @@
 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).
 
-## [[1.0.0](https://github.com/sanger-tol/curationpretext/releases/tag/1.0.0)] - UNSC Infinity - [2023-10-02]
+## [[1.0.0](https://github.com/sanger-tol/curationpretext/releases/tag/1.0.0)] - UNSC Cradle - [2024-02-22]
+
+### Added
+
+- Subworkflows for both minimap2 and bwamem2 mapping.
+- Subworkflow for Pretext accessory file ingestion.
+- Considerations for other longread datatypes
+
+### Paramters
+
+| Old Version | New Versions    |
+| ----------- | --------------- |
+|             | --aligner       |
+|             | --longread_type |
+| --pacbio    | --longread      |
+
+### Software Dependencies
+
+Note, since the pipeline is using Nextflow DSL2, each process will be run with its own Biocontainer. This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference.
+
+| Module                                                              | Old Version    | New Versions   |
+| ------------------------------------------------------------------- | -------------- | -------------- |
+| bamtobed_sort ( bedtools + samtools )                               | -              | 2.31.0 + 1.17  |
+| bedtools ( genomecov, bamtobed, intersect, map, merge, makewindows) | 2.31.0         | 2.31.1         |
+| bwamem2 index                                                       | -              | 2.2.1          |
+| cram_filter_align_bwamem2_fixmate_sort                              | -              |                |
+| ^ ( samtools + bwamem2 ) ^                                          | 1.16.1 + 2.2.1 | 1.17 + 2.2.1   |
+| cram_filter_minimap2_filter5end_fixmate_sort                        | -              |                |
+| ^ ( samtools + minimap2 ) ^                                         | -              | 1.17 + 2.24    |
+| extract_cov_id ( coreutils )                                        | -              | 9.1            |
+| extract_repeat ( perl )                                             | -              | 5.26.2         |
+| extract_telo ( coreutils )                                          | -              | 9.1            |
+| find_telomere_regions ( gcc )                                       | -              | 7.1.0          |
+| find_telomere_windows ( java-jdk )                                  | -              | 8.0.112        |
+| gap_length ( coreutils )                                            | -              | 9.1            |
+| generate_cram_csv ( samtools )                                      | -              | 1.17           |
+| get_largest_scaff ( coreutils )                                     | -              | 9.1            |
+| gnu-sort                                                            | -              | 8.25           |
+| pretextmap + samtools                                               | 0.1.9 + 1.17   | 0.1.9\* + 1.18 |
+| pretextgraph                                                        |                | 0.0.4          |
+| pretextsnapshot + UCSC                                              | 0.0.6 + 447    | 0.0.6b + 447   |
+| seqtk                                                               | -              | 1.4            |
+| samtools (faidx,merge,sort,view)                                    | 1.17           | 1.18           |
+| tabix                                                               | -              | 1.11           |
+| ucsc                                                                | 377            | 445            |
+| windowmasker (blast)                                                | -              | 2.14.0         |
+
+- This version has been modified by @yumisims inorder to expose the texture buffer variable
+
+### Dependencies
+
+### Deprecated
+
+## [[0.1.0](https://github.com/sanger-tol/curationpretext/releases/tag/0.1.0)] - UNSC Infinity - [2023-10-02]
 
 Initial release of sanger-tol/curationpretext, created with the [sager-tol](https://nf-co.re/) template.
 

CITATION.cff

@@ -0,0 +1,34 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
+cff-version: 1.2.0
+title: sanger-tol/curationpretext v1.0.0
+message: >-
+    If you use this software, please cite it using the
+    metadata from this file.
+type: software
+authors:
+    - given-names: Damon-Lee Bernard
+      family-names: Pointon
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0003-2949-6719"
+    - given-names: Matthieu
+      family-names: Muffato
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0002-7860-3560"
+    - given-names: Ying
+      family-names: Sims
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0003-4765-4872"
+    - given-names: William
+      family-names: Eagles
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0009-0006-9956-0404"
+identifiers:
+    - type: doi
+      value: 10.5281/zenodo.XXXXXXX
+repository-code: "https://github.com/sanger-tol/curationpretext"
+license: MIT
+commit: TODO
+version: 1.0.0
+date-released: "2024-07-18"

LICENSE

@@ -19,3 +19,8 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+
+The filter_five_end.ph script has been taken from the Arima Mapping Pipeline, has not been modified and is subject to the below license:
+
+Copyright (c) 2017 Arima Genomics, Inc.