1.1 release

.github/workflows/ci.yml

@@ -1,7 +1,12 @@
 name: nf-core CI
 # This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
 on:
-  workflow_dispatch:
+  push:
+    branches:
+      - dev
+  pull_request:
+  release:
+    types: [published]
 
 env:
   NXF_ANSI_LOG: false
@@ -19,7 +24,7 @@ jobs:
     strategy:
       matrix:
         NXF_VER:
-          - "23.04.0"
+          - "22.10.1"
           - "latest-everything"
     steps:
       - name: Check out pipeline code

.github/workflows/fix-linting.yml

@@ -8,21 +8,21 @@ jobs:
     # Only run if comment is on a PR with the main repo, and if it contains the magic keywords
     if: >
       contains(github.event.comment.html_url, '/pull/') &&
-      contains(github.event.comment.body, '@nf-core-bot fix linting') &&
+      contains(github.event.comment.body, '@sanger-tolsoft fix linting') &&
       github.repository == 'sanger-tol/genomenote'
     runs-on: ubuntu-latest
     steps:
-      # Use the @nf-core-bot token to check out so we can push later
+      # Use the @sanger-tolsoft token to check out so we can push later
       - uses: actions/checkout@v3
         with:
-          token: ${{ secrets.nf_core_bot_auth_token }}
+          token: ${{ secrets.sangertolsoft_access_token }}
 
       # Action runs on the issue comment, so we don't get the PR by default
       # Use the gh cli to check out the PR
       - name: Checkout Pull Request
         run: gh pr checkout ${{ github.event.issue.number }}
         env:
-          GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }}
+          GITHUB_TOKEN: ${{ secrets.sangertolsoft_access_token }}
 
       - uses: actions/setup-node@v3
 
@@ -46,8 +46,8 @@ jobs:
       - name: Commit & push changes
         if: steps.prettier_status.outputs.result == 'fail'
         run: |
-          git config user.email "core@nf-co.re"
-          git config user.name "nf-core-bot"
+          git config user.email "105875386+sanger-tolsoft@users.noreply.github.com"
+          git config user.name "sanger-tolsoft"
           git config push.default upstream
           git add .
           git status

.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
@@ -84,7 +84,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install nf-core
+          pip install nf-core==2.8
 
       - name: Run nf-core lint
         env:

.github/workflows/sanger_test.yml

@@ -0,0 +1,29 @@
+name: sanger-tol LSF tests
+
+on:
+  workflow_dispatch:
+jobs:
+  run-tower:
+    name: Run LSF tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Launch workflow via tower
+        uses: seqeralabs/action-tower-launch@v2
+        with:
+          workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
+          access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
+          compute_env: ${{ secrets.TOWER_COMPUTE_ENV }}
+          revision: ${{ github.sha }}
+          workdir: ${{ secrets.TOWER_WORKDIR_PARENT }}/work/${{ github.repository }}/work-${{ github.sha }}
+          parameters: |
+            {
+              "outdir": "${{ secrets.TOWER_WORKDIR_PARENT }}/results/${{ github.repository }}/results-${{ github.sha }}",
+            }
+          profiles: test,sanger,singularity,cleanup
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: Tower debug log file
+          path: |
+            tower_action_*.log
+            tower_action_*.json

.github/workflows/sanger_test_full.yml

@@ -0,0 +1,43 @@
+name: sanger-tol LSF full size tests
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+  workflow_dispatch:
+jobs:
+  run-tower:
+    name: Run LSF full size tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Sets env vars for push
+        run: |
+          echo "REVISION=${{ github.sha }}" >> $GITHUB_ENV
+        if: github.event_name == 'push'
+
+      - name: Sets env vars for workflow_dispatch
+        run: |
+          echo "REVISION=${{ github.sha }}" >> $GITHUB_ENV
+        if: github.event_name == 'workflow_dispatch'
+
+      - name: Launch workflow via tower
+        uses: seqeralabs/action-tower-launch@v2
+        with:
+          workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
+          access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
+          compute_env: ${{ secrets.TOWER_COMPUTE_ENV }}
+          revision: ${{ env.REVISION }}
+          workdir: ${{ secrets.TOWER_WORKDIR_PARENT }}/work/${{ github.repository }}/work-${{ env.REVISION }}
+          parameters: |
+            {
+              "outdir": "${{ secrets.TOWER_WORKDIR_PARENT }}/results/${{ github.repository }}/results-${{ env.REVISION }}",
+            }
+          profiles: test_full,sanger,singularity,cleanup
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: Tower debug log file
+          path: |
+            tower_action_*.log
+            tower_action_*.json

.nf-core.yml

@@ -13,6 +13,7 @@ lint:
     - .github/ISSUE_TEMPLATE/bug_report.yml
     - lib/NfcoreTemplate.groovy
     - .github/CONTRIBUTING.md
+    - .github/workflows/linting.yml
   nextflow_config:
     - manifest.name
     - manifest.homePage

CHANGELOG.md

@@ -3,6 +3,59 @@
 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).
 
+## [[1.1.0](https://github.com/sanger-tol/genomenote/releases/tag/1.1.0)] - Golden Retriever - [2024-01-04]
+
+### Enhancements & fixes
+
+- The pipeline now queries the NCBI Taxonomy API rather than
+  [GoaT](https://goat.genomehubs.org/api) to establish the list of lineages on
+  which to run BUSCO. The possible lineages are now defined [in the pipeline
+  configuration](assets/mapping_taxids-busco_dataset_name.eukaryota_odb10.2019-12-16.txt)
+  but can be overridden with the `--lineage_tax_ids` parameter.
+- The pipeline will now immediately fail if the assembly can't be retrieve by
+  the [datasets](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/download-and-install/)
+  command-line tool.
+- Pipeline information is now outputted in `pipeline_info/genomenote/` instead
+  of `genomenote_info/`.
+- `maxRetries` increased to 5 to cope with large datasets.
+- BUSCO now runs in "scratch" mode, i.e. off a temporary directory, as the
+  number of files it creates could otherwise overwhelm a network filesystem.
+- `SORT`, `FASTK`, and `MERQURYFK`, can now put their temporary files in the
+  work directory rather than `/tmp`. Turn that on with the `--use_work_dir_as_temp`
+  flag.
+- The memory requirement of `SORT` is adjusted to account for some overheads
+  and avoid the job to be killed.
+- All resource requirements (memory, time, CPUs) now fit the actual usage. This
+  is achieved by automatically adjusting to the size of the input whenever
+  possible.
+- Genomes with sequences longer than 2 Gbp are now supported thanks to
+  upgrading FastK and MerquryFK.
+- Fixed a bug that was causing the Completeness to be reported as 0 in the
+  statistics CSV file, when the k-mer database was constructed from BAM files.
+- QV/Completeness can now be computed off 10X sequencing data.
+- Minimal version of Nextflow downgraded to 23.04 to 22.10. 22.10 is tested as
+  part of our continuous integration (CI) pipeline.
+- The "test" profile now runs faster, thanks to tuning some Busco/Metaeuk
+  parameters.
+- The "test_full" profile is now tested automatically when updating the `dev`
+  and `main` branches.
+- The pipelines now support Hi-C alignment files in the BAM format.
+
+### Parameters
+
+| Old parameter | New parameter          |
+| ------------- | ---------------------- |
+|               | --lineage_tax_ids      |
+|               | --use_work_dir_as_temp |
+
+### Software dependencies
+
+| Dependency  | Old version                                | New version                                |
+| ----------- | ------------------------------------------ | ------------------------------------------ |
+| `datasets`  | 14.2                                       | 15.12                                      |
+| `FastK`     | `f18a4e6d2207539f7b84461daebc54530a9559b0` | `427104ea91c78c3b8b8b49f1a7d6bbeaa869ba1c` |
+| `MerquryFK` | `8ae344092df5dcaf83cfb7f90f662597a9b1fc61` | `d00d98157618f4e8d1a9190026b19b471055b22e` |
+
 ## [[1.0.0](https://github.com/sanger-tol/genomenote/releases/tag/1.0.0)] - Czechoslovakian Wolfdog - [2023-05-18]
 
 Initial release of sanger-tol/genomenote, created with the [nf-core](https://nf-co.re/) template.

CITATION.cff

@@ -0,0 +1,38 @@
+# 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/genomenote v1.1.0
+message: >-
+    If you use this software, please cite it using the
+    metadata from this file.
+type: software
+authors:
+    - given-names: Cibin
+      family-names: Sadasivan Baby
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0002-8538-276X"
+    - given-names: Matthieu
+      family-names: Muffato
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0002-7860-3560"
+    - given-names: Guoying
+      family-names: Qi
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0003-1262-8973"
+    - given-names: Priyanka
+      family-names: Surana
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0002-7167-0875"
+    - given-names: Yates
+      family-names: Bethan
+      affiliation: Wellcome Sanger Institute
+      orcid: "https://orcid.org/0000-0003-1658-1762"
+identifiers:
+    - type: doi
+      value: 10.5281/zenodo.7949384
+repository-code: "https://github.com/sanger-tol/genomenote"
+license: MIT
+commit: TODO
+version: 1.1.0
+date-released: "2022-10-07"

CITATIONS.md

@@ -24,6 +24,10 @@
 
   > Abdennur, Nezar, and Leonid A Mirny. “Cooler: Scalable Storage for Hi-C Data and Other Genomically Labeled Arrays.” Bioinformatics, vol. 36, no. 1, 2019, pp. 311–316., https://doi.org/10.1093/bioinformatics/btz540.
 
+- [Crumble](https://github.com/jkbonfield/crumble)
+
+  > James K Bonfield, Shane A McCarthy, and Richard Durbin. "Crumble: reference free lossy compression of sequence quality values" Bioinformatics, Volume 35, Issue 2, January 2019, Pages 337–339, https://doi.org/10.1093/bioinformatics/bty608
+
 - [FastK](https://github.com/thegenemyers/FASTK)
 
 - [MerquryFK](https://github.com/thegenemyers/MERQURY.FK)

README.md

@@ -3,7 +3,7 @@
 [![GitHub Actions Linting Status](https://github.com/sanger-tol/genomenote/workflows/nf-core%20linting/badge.svg)](https://github.com/sanger-tol/genomenote/actions?query=workflow%3A%22nf-core+linting%22)
 [![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.7949384-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7949384)
 
-[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.10.1-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
@@ -22,9 +22,9 @@
 3. Filter BED ([`GNU sort`](https://www.gnu.org/software/coreutils/manual/html_node/sort-invocation.html), [`filter bed`](https://raw.githubusercontent.com/sanger-tol/genomenote/main/bin/filter_bed.sh))
 4. Contact maps ([`Cooler cload`](https://cooler.readthedocs.io/en/latest/cli.html#cooler-cload-pairs), [`Cooler zoomify`](https://cooler.readthedocs.io/en/latest/cli.html#cooler-zoomify), [`Cooler dump`](https://cooler.readthedocs.io/en/latest/cli.html#cooler-dump))
 5. Summary statistics ([`NCBI datasets summary genome accession`](https://www.ncbi.nlm.nih.gov/datasets/docs/v2/reference-docs/command-line/datasets/summary/genome/datasets_summary_genome_accession/))
-6. Genome completeness ([`GoaT API`](https://goat.genomehubs.org/api-docs/), [`BUSCO`](https://busco.ezlab.org))
+6. Genome completeness ([`NCBI API`](https://www.ncbi.nlm.nih.gov/datasets/docs/v1/reference-docs/rest-api/), [`BUSCO`](https://busco.ezlab.org))
 7. Consensus quality and k-mer completeness ([`FASTK`](https://github.com/thegenemyers/FASTK), [`MERQURY.FK`](https://github.com/thegenemyers/MERQURY.FK))
-8. Collated summary table ([`createtable`](https://raw.githubusercontent.com/sanger-tol/genomenote/main/bin/create_table.py))
+8. Collated summary table ([`createtable`](bin/create_table.py))
 9. Present results and visualisations ([`MultiQC`](http://multiqc.info/), [`R`](https://www.r-project.org/))
 
 ## Usage
@@ -44,7 +44,7 @@ mMelMel3,hic,/analysis/mMelMel3.2_paternal_haplotype/read_mapping/hic/GCA_922984
 mMelMel3,pacbio,/genomic_data/mMelMel3/pacbio/kmer/k31
 ```
 
-Each row represents an aligned HiC reads file or an unaligned PacBio reads file or a PacBio k-mer database.
+Each row represents an aligned HiC reads file, an unaligned PacBio/10X reads file, or a PacBio/10X k-mer database.
 
 Now, you can run the pipeline using:
 
@@ -75,13 +75,13 @@ We thank the following people for their assistance in the development of this pi
 
 ## Contributions and Support
 
-If you would like to contribute to this pipeline, please see the [contributing guidelines](https://raw.githubusercontent.com/sanger-tol/genomenote/main/.github/CONTRIBUTING.md).
+If you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).
 
 ## Citations
 
 If you use sanger-tol/genomenote for your analysis, please cite it using the following doi: [10.5281/zenodo.7949384](https://doi.org/10.5281/zenodo.7949384)
 
-An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](https://raw.githubusercontent.com/sanger-tol/genomenote/main/CITATIONS.md) file.
+An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 
 This 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/master/LICENSE).
 

assets/mapping_taxids-busco_dataset_name.eukaryota_odb10.2019-12-16.txt

@@ -0,0 +1,67 @@
+422676	aconoidasida
+7898	actinopterygii
+5338	agaricales
+155619	agaricomycetes
+33630	alveolata
+5794	apicomplexa
+6854	arachnida
+6656	arthropoda
+4890	ascomycota
+8782	aves
+5204	basidiomycota
+68889	boletales
+3699	brassicales
+134362	capnodiales
+33554	carnivora
+91561	cetartiodactyla
+34395	chaetothyriales
+3041	chlorophyta
+5796	coccidia
+28738	cyprinodontiformes
+7147	diptera
+147541	dothideomycetes
+3193	embryophyta
+33392	endopterygota
+314146	euarchontoglires
+33682	euglenozoa
+2759	eukaryota
+5042	eurotiales
+147545	eurotiomycetes
+9347	eutheria
+72025	fabales
+4751	fungi
+314147	glires
+1028384	glomerellales
+5178	helotiales
+7524	hemiptera
+7399	hymenoptera
+5125	hypocreales
+50557	insecta
+314145	laurasiatheria
+147548	leotiomycetes
+7088	lepidoptera
+4447	liliopsida
+40674	mammalia
+33208	metazoa
+6029	microsporidia
+6447	mollusca
+4827	mucorales
+1913637	mucoromycota
+6231	nematoda
+33183	onygenales
+9126	passeriformes
+5820	plasmodium
+92860	pleosporales
+38820	poales
+5303	polyporales
+9443	primates
+4891	saccharomycetes
+8457	sauropsida
+4069	solanales
+147550	sordariomycetes
+33634	stramenopiles
+32523	tetrapoda
+155616	tremellomycetes
+7742	vertebrata
+33090	viridiplantae
+71240	eudicots

assets/samplesheet.csv

@@ -1,4 +1,4 @@
 sample,datatype,datafile
-uoEpiScrs1,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Epithemia_sp._CRS-2021b/genomic_data/uoEpiScrs1/pacbio/m64228e_220617_134154.ccs.bc1015_BAK8B_OA--bc1015_BAK8B_OA.rmdup.bam
-uoEpiScrs1,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Epithemia_sp._CRS-2021b/genomic_data/uoEpiScrs1/pacbio/m64016e_220621_193126.ccs.bc1008_BAK8A_OA--bc1008_BAK8A_OA.rmdup.bam
+uoEpiScrs1,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Epithemia_sp._CRS-2021b/genomic_data/uoEpiScrs1/pacbio/m64228e_220617_134154.ccs.bc1015_BAK8B_OA--bc1015_BAK8B_OA.rmdup.subset.bam
+uoEpiScrs1,pacbio,https://tolit.cog.sanger.ac.uk/test-data/Epithemia_sp._CRS-2021b/genomic_data/uoEpiScrs1/pacbio/m64016e_220621_193126.ccs.bc1008_BAK8A_OA--bc1008_BAK8A_OA.rmdup.subset.bam
 uoEpiScrs1,hic,https://tolit.cog.sanger.ac.uk/test-data/Epithemia_sp._CRS-2021b/analysis/uoEpiScrs1.1/read_mapping/hic/GCA_946965045.1.unmasked.hic.uoEpiScrs1.subsampled.cram

assets/slackreport.json

@@ -3,7 +3,7 @@
         {
             "fallback": "Plain-text summary of the attachment.",
             "color": "<% if (success) { %>good<% } else { %>danger<%} %>",
-            "author_name": "sanger-tol/readmapping v${version} - ${runName}",
+            "author_name": "sanger-tol/genomenote v${version} - ${runName}",
             "author_icon": "https://www.nextflow.io/docs/latest/_static/favicon.ico",
             "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors<% } %>",
             "fields": [