Merge branch 'bouncy-basenji' into add_db_type

nf-core · Jun 13, 2024 · 547a0aa · 547a0aa
2 parents 1f5d5ea + 6b47739
commit 547a0aa
Show file tree

Hide file tree

Showing 62 changed files with 3,605 additions and 600 deletions.
diff --git a/.editorconfig b/.editorconfig
@@ -28,10 +28,6 @@ indent_style = unset
 [/assets/email*]
 indent_size = unset
 
-# ignore Readme
-[README.md]
-indent_style = unset
-
-# ignore python
+# ignore python and markdown
 [*.{py,md}]
 indent_style = unset
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -18,7 +18,7 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/taxp
 - [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md)
 - [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core lint`).
-- [ ] Ensure the test suite passes (`nf-test test main.nf.test -profile test,docker`).
+- [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Check for unexpected warnings in debug mode (`nextflow run . -profile debug,test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.
 - [ ] Output Documentation in `docs/output.md` is updated.

diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
@@ -8,12 +8,12 @@ on:
     types: [published]
   workflow_dispatch:
 jobs:
-  run-tower:
+  run-platform:
     name: Run AWS full tests
     if: github.repository == 'nf-core/taxprofiler'
     runs-on: ubuntu-latest
     steps:
-      - name: Launch workflow via tower
+      - name: Launch workflow via Seqera Platform
         uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
@@ -30,7 +30,7 @@ jobs:
 
       - uses: actions/upload-artifact@v4
         with:
-          name: Tower debug log file
+          name: Seqera Platform debug log file
           path: |
-            tower_action_*.log
-            tower_action_*.json
+            seqera_platform_action_*.log
+            seqera_platform_action_*.json
diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
@@ -5,13 +5,13 @@ name: nf-core AWS test
 on:
   workflow_dispatch:
 jobs:
-  run-tower:
+  run-platform:
     name: Run AWS tests
     if: github.repository == 'nf-core/taxprofiler'
     runs-on: ubuntu-latest
     steps:
-      # Launch workflow using Tower CLI tool action
-      - name: Launch workflow via tower
+      # Launch workflow using Seqera Platform CLI tool action
+      - name: Launch workflow via Seqera Platform
         uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
@@ -27,7 +27,7 @@ jobs:
 
       - uses: actions/upload-artifact@v4
         with:
-          name: Tower debug log file
+          name: Seqera Platform debug log file
           path: |
-            tower_action_*.log
-            tower_action_*.json
+            seqera_platform_action_*.log
+            seqera_platform_action_*.json
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -42,10 +42,10 @@ jobs:
 
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
         with:
           version: "${{ matrix.NXF_VER }}"
 

diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml
@@ -14,6 +14,8 @@ on:
   pull_request:
     types:
       - opened
+      - edited
+      - synchronize
     branches:
       - master
   pull_request_target:
@@ -28,11 +30,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - name: Disk space cleanup
+        uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
+
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
           architecture: "x64"
       - uses: eWaterCycle/setup-singularity@931d4e31109e875b13309ae1d07c70ca8fbc8537 # v7
         with:
@@ -72,11 +77,10 @@ jobs:
           NXF_SINGULARITY_CACHEDIR: ./
           NXF_SINGULARITY_HOME_MOUNT: true
         run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results
-
       - name: Run the downloaded pipeline (stub run not supported)
         id: run_pipeline
         if: ${{ job.steps.stub_run_pipeline.status == failure() }}
         env:
           NXF_SINGULARITY_CACHEDIR: ./
           NXF_SINGULARITY_HOME_MOUNT: true
-        run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -profile test,singularity --outdir ./results{% endraw %}
+        run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -profile test,singularity --outdir ./results
diff --git a/.github/workflows/fix-linting.yml b/.github/workflows/fix-linting.yml
@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # Use the @nf-core-bot token to check out so we can push later
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
         with:
           token: ${{ secrets.nf_core_bot_auth_token }}
 
@@ -32,9 +32,9 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.nf_core_bot_auth_token }}
 
       # Install and run pre-commit
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: 3.11
+          python-version: "3.12"
 
       - name: Install pre-commit
         run: pip install pre-commit

diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
@@ -14,13 +14,12 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+      - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
-      - name: Set up Python 3.11
-        uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - name: Set up Python 3.12
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: 3.11
-          cache: "pip"
+          python-version: "3.12"
 
       - name: Install pre-commit
         run: pip install pre-commit
@@ -32,14 +31,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4
+        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v1
+        uses: nf-core/setup-nextflow@v2
 
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
-          python-version: "3.11"
+          python-version: "3.12"
           architecture: "x64"
 
       - name: Install dependencies
@@ -60,7 +59,7 @@ jobs:
 
       - name: Upload linting log file artifact
         if: ${{ always() }}
-        uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4
+        uses: actions/upload-artifact@65462800fd760344b1a7b4382951275a0abb4808 # v4
         with:
           name: linting-logs
           path: |

diff --git a/.github/workflows/linting_comment.yml b/.github/workflows/linting_comment.yml
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Download lint results
-        uses: dawidd6/action-download-artifact@f6b0bace624032e30a85a8fd9c1a7f8f611f5737 # v3
+        uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3
         with:
           workflow: linting.yml
           workflow_conclusion: completed

diff --git a/.github/workflows/release-announcements.yml b/.github/workflows/release-announcements.yml
@@ -12,7 +12,7 @@ jobs:
       - name: get topics and convert to hashtags
         id: get_topics
         run: |
-          curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ' >> $GITHUB_OUTPUT
+          echo "topics=$(curl -s https://nf-co.re/pipelines.json | jq -r '.remote_workflows[] | select(.full_name == "${{ github.repository }}") | .topics[]' | awk '{print "#"$0}' | tr '\n' ' ')"  >> $GITHUB_OUTPUT
 
       - uses: rzr/fediverse-action@master
         with:
@@ -25,13 +25,13 @@ jobs:
 
             Please see the changelog: ${{ github.event.release.html_url }}
 
-            ${{ steps.get_topics.outputs.GITHUB_OUTPUT }} #nfcore #openscience #nextflow #bioinformatics
+            ${{ steps.get_topics.outputs.topics }} #nfcore #openscience #nextflow #bioinformatics
 
   send-tweet:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/setup-python@0a5c61591373683505ea898e09a3ea4f39ef2b9c # v5
+      - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:
           python-version: "3.10"
       - name: Install dependencies

diff --git a/.nf-core.yml b/.nf-core.yml
@@ -1 +1,2 @@
 repository_type: pipeline
+nf_core_version: "2.14.1"
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -3,6 +3,9 @@ repos:
     rev: "v3.1.0"
     hooks:
       - id: prettier
+        additional_dependencies:
+          - [email protected]
+
   - repo: https://github.com/editorconfig-checker/editorconfig-checker.python
     rev: "2.7.3"
     hooks:

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,15 +10,51 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133)
 - [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases
 
-## v1.1.6dev - [unreleased]
+## v1.1.8dev - Augmented Akita Patch []
+
+### `Added`
+
+- [#487](https://github.com/nf-core/taxprofiler/pull/487) Updated to nf-core pipeline template v2.14.1 (added by jfy133)
+
+### `Fixed`
+
+- [#484](https://github.com/nf-core/taxprofiler/pull/484) Improved input validation to immediately fail if run accession IDs within a given sample ID are not unique (❤️ to @sofstam for reporting, fixed by @jfy133)
+- [#491](https://github.com/nf-core/taxprofiler/pull/491) Added flag to publish intermediate bracken files (❤️ to @ewissel for reporting, fixed by @sofstam and @jfy133)
+- [489](https://github.com/nf-core/taxprofiler/pull/489) Fix KrakenUniq classified reads output format mismatch (❤️ to @SannaAb for reporting, fixed by @jfy133)
+
+### `Dependencies`
+
+| Tool | Previous version | New version |
+| ---- | ---------------- | ----------- |
+| KMCP | 0.9.1            | 0.9.4       |
+
+### `Deprecated`
+
+- [#492](https://github.com/nf-core/taxprofiler/pull/492) Removed `--kmcp_mode` parameter from KMCP to allow per database specification by setting in db_params in database sheet (fixed by @jfy133)
+
+## v1.1.7 - Augmented Akita Patch [2024-04-25]
+
+### `Added`
+
+- [#477](https://github.com/nf-core/taxprofiler/pull/477) Provide more emphasis and links to tutorials on how to retrieve and supply reference databases (❤️ to @vmkalbskopf for reporting, added by @jfy133)
+
+### `Fixed`
+
+- [#476](https://github.com/nf-core/taxprofiler/pull/476/) Fixed bug in validating Bracken/Kraken/KMCP split database parameters (fixed by @LilyAnderssonLee)
+
+### `Dependencies`
+
+### `Deprecated`
+
+## v1.1.6 - Augmented Akita Patch [2024-04-16]
 
 ### `Added`
 
-- [#417](https://github.com/nf-core/taxprofiler/pull/417) - Added reference-free metagenome estimation with Nonpareil (added by @jfy133)
 - [#454](https://github.com/nf-core/taxprofiler/pull/454) Updated to nf-core pipeline template v2.13.1 (added by @LilyAnderssonLee & @sofstam)
 - [#461](https://github.com/nf-core/taxprofiler/pull/461) Turned on 'strict' Nextflow evaluation runs (added by @jfy133)
 - [#461](https://github.com/nf-core/taxprofiler/pull/461) Optimised database compression so each compressed input database is untarred once, and shared amongst each run with different parameters (added by @jfy133)
 - [#461](https://github.com/nf-core/taxprofiler/pull/461) Added new parameter to optionally save uncompressed databases (added by @jfy133)
+- [#471](https://github.com/nf-core/taxprofiler/pull/471) Remove `-stub` run in the `download_pipeline.yml` because the pipeline does not support stub runs on dev (fixed by @LilyAnderssonLee)
 
 ### `Fixed`
 

diff --git a/README.md b/README.md
@@ -13,7 +13,7 @@
 [![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/)
-[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/taxprofiler)
+[![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/nf-core/taxprofiler)
 
 [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23taxprofiler-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/taxprofiler)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/nf_core)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)
 

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,4 +1,5 @@
 report_comment: >
+
   This report has been generated by the <a href="https://github.com/nf-core/taxprofiler/tree/dev" target="_blank">nf-core/taxprofiler</a>
   analysis pipeline. For information about how to interpret these results, please see the
   <a href="https://nf-co.re/taxprofiler/dev/docs/output" target="_blank">documentation</a>.

diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -14,6 +14,7 @@
             },
             "run_accession": {
                 "type": "string",
+                "unique": ["sample"],
                 "errorMessage": "Run accession must be provided and cannot contain spaces."
             },
             "instrument_platform": {

diff --git a/conf/modules.config b/conf/modules.config
@@ -495,7 +495,8 @@ process {
         publishDir = [
             path: { "${params.outdir}/kraken2/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt,fastq.gz}'
+            pattern: '*.{txt,fastq.gz}',
+            saveAs: {  !params.bracken_save_intermediatekraken2 && meta.tool == "bracken" ? null : it  }
         ]
     }
 
@@ -545,7 +546,7 @@ process {
         publishDir = [
             path: { "${params.outdir}/krakenuniq/${meta.db_name}/" },
             mode: params.publish_dir_mode,
-            pattern: '*.{txt,fasta.gz}'
+            pattern: '*.{txt,fastq.gz,fasta.gz}'
         ]
     }
 

diff --git a/conf/test.config b/conf/test.config
@@ -20,17 +20,17 @@ params {
     max_time   = '6.h'
 
     // Input data
-    input                                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/samplesheet.csv'
-    databases                              = 'https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/database_v1.2.csv'
+    input                                  = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet.csv'
+    databases                              = params.pipelines_testdata_base_path + 'taxprofiler/database_v1.1.csv'
     perform_shortread_qc                   = true
+    perform_shortread_redundancyestimation = true
     perform_longread_qc                    = true
     shortread_qc_mergepairs                = true
-    perform_shortread_redundancyestimation = true
     perform_shortread_complexityfilter     = true
     perform_shortread_hostremoval          = true
     perform_longread_hostremoval           = true
     perform_runmerging                     = true
-    hostremoval_reference                  = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    hostremoval_reference                  = params.pipelines_testdata_base_path + 'modules/data/genomics/homo_sapiens/genome/genome.fasta'
     run_kaiju                              = true
     run_kraken2                            = true
     run_bracken                            = true
@@ -43,8 +43,7 @@ params {
     run_ganon                              = true
     run_krona                              = true
     run_kmcp                               = true
-    kmcp_mode                              = 0
-    krona_taxonomy_directory               = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
+    krona_taxonomy_directory               = params.pipelines_testdata_base_path + 'modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab'
     malt_save_reads                        = true
     kraken2_save_reads                     = true
     centrifuge_save_reads                  = true