Merge remote-tracking branch 'upstream/dev' into topic-channel

Signed-off-by: Ben Sherman <bentshermann@gmail.com>
nf-core · Dec 12, 2023 · 8f7e5bd · 8f7e5bd
2 parents ed5cf57 + e4c8d67
commit 8f7e5bd
Show file tree

Hide file tree

Showing 202 changed files with 5,362 additions and 901 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -232,16 +232,19 @@ jobs:
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner hisat2 ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
 
-  salmon:
-    name: Test Salmon with workflow parameters
+  pseudo:
+    name: Test Pseudoaligners with workflow parameters
     if: ${{ (github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'nf-core/rnaseq')) && !contains(github.event.head_commit.message, '[ci fast]') }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
         parameters:
-          - "--skip_qc"
-          - "--skip_alignment --skip_pseudo_alignment"
-          - "--salmon_index false --transcript_fasta false"
+          - "--pseudo_aligner salmon --skip_qc"
+          - "--pseudo_aligner salmon --skip_alignment --skip_pseudo_alignment"
+          - "--pseudo_aligner salmon --salmon_index false --transcript_fasta false"
+          - "--pseudo_aligner kallisto --skip_qc"
+          - "--pseudo_aligner kallisto --skip_alignment --skip_pseudo_alignment"
+          - "--pseudo_aligner kallisto --kallisto_index false --transcript_fasta false"
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
@@ -280,6 +283,6 @@ jobs:
           wget -qO- get.nextflow.io | bash
           sudo mv nextflow /usr/local/bin/
 
-      - name: Run pipeline with Salmon and various parameters
+      - name: Run pipeline with Salmon or Kallisto and various parameters
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --pseudo_aligner salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
diff --git a/.github/workflows/cloud_tests_full.yml b/.github/workflows/cloud_tests_full.yml
@@ -23,8 +23,9 @@ jobs:
       matrix:
         aligner: ["star_salmon", "star_rsem"]
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
+          revision: ${{ github.sha }}
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
           compute_env: ${{ secrets.TOWER_CE_AWS_CPU }}
@@ -35,21 +36,23 @@ jobs:
             {
                 "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
                 "aligner": "${{ matrix.aligner }}",
-                "outdir": "${{ secrets.TOWER_BUCKET_AWS }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}"
+                "outdir": "${{ secrets.TOWER_BUCKET_AWS }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}/"
             }
       - uses: actions/upload-artifact@v3
         with:
           name: Tower debug log file
           path: tower_action_*.log
+
   run-full-tests-on-gcp:
     if: ${{ github.event.inputs.platform == 'all' || github.event.inputs.platform == 'gcp' || !github.event.inputs }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
         aligner: ["star_salmon", "star_rsem"]
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
+          revision: ${{ github.sha }}
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
           compute_env: ${{ secrets.TOWER_CE_GCP_CPU }}
@@ -60,21 +63,23 @@ jobs:
             {
                 "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
                 "aligner": "${{ matrix.aligner }}",
-                "outdir": "${{ secrets.TOWER_BUCKET_GCP }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}"
+                "outdir": "${{ secrets.TOWER_BUCKET_GCP }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}/"
             }
       - uses: actions/upload-artifact@v3
         with:
           name: Tower debug log file
           path: tower_action_*.log
+
   run-full-tests-on-azure:
     if: ${{ github.event.inputs.platform == 'all' || github.event.inputs.platform == 'azure' || !github.event.inputs }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
         aligner: ["star_salmon", "star_rsem"]
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
+          revision: ${{ github.sha }}
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
           compute_env: ${{ secrets.TOWER_CE_AZURE_CPU }}
@@ -85,7 +90,7 @@ jobs:
             {
                 "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",
                 "aligner": "${{ matrix.aligner }}",
-                "outdir": "${{ secrets.TOWER_BUCKET_AZURE }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}",
+                "outdir": "${{ secrets.TOWER_BUCKET_AZURE }}/rnaseq/results-${{ github.sha }}/aligner_${{ matrix.aligner }}/",
                 "igenomes_base": "${{ secrets.TOWER_IGENOMES_BASE_AZURE }}"
             }
       - uses: actions/upload-artifact@v3

diff --git a/.github/workflows/cloud_tests_small.yml b/.github/workflows/cloud_tests_small.yml
@@ -18,7 +18,7 @@ jobs:
     if: ${{ github.event.inputs.platform == 'all' || github.event.inputs.platform == 'aws' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
@@ -38,7 +38,7 @@ jobs:
     if: ${{ github.event.inputs.platform == 'all' || github.event.inputs.platform == 'gcp' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
@@ -58,7 +58,7 @@ jobs:
     if: ${{ github.event.inputs.platform == 'all' || github.event.inputs.platform == 'azure' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: seqeralabs/action-tower-launch@v1
+      - uses: seqeralabs/action-tower-launch@v2
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,16 +3,69 @@
 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).
 
-## v3.13.0dev - [date]
+## v3.14.0dev - [date]
+
+### Credits
+
+### Enhancements & fixes
+
+- [PR #1135](https://github.com/nf-core/rnaseq/pull/1135) - Update [action-tower-launch](https://github.com/marketplace/actions/action-tower-launch) to v2 which supports more variable handling.
+- [PR #1138](https://github.com/nf-core/rnaseq/pull/1138) - Updates FASTQC and UMITOOLS modules and their dependencies which have had their version string extraction commands updated ([#1103](https://github.com/nf-core/rnaseq/issues/1103))
+- Update Rseqc and Fastp modules to print STDERR to screen and file.
+
+### Software dependencies
+
+| Dependency | Old version | New version |
+| ---------- | ----------- | ----------- |
+| `picard`   | 3.0.0       | 3.1.1       |
+| `samtools` | 1.17        | 1.18        |
+
+> **NB:** Dependency has been **updated** if both old and new version information is present.
+>
+> **NB:** Dependency has been **added** if just the new version information is present.
+>
+> **NB:** Dependency has been **removed** if new version information isn't present.
+
+### Modules / Subworkflows
+
+- BAM_RSEQC subworkflow updated with new channel names.
+
+## [[3.13.2](https://github.com/nf-core/rnaseq/releases/tag/3.13.2)] - 2023-11-21
+
+### Credits
+
+Special thanks to the following for their contributions to the release:
+
+- [Jonathan Manning](https://github.com/pinin4fjords)
+- [Regina Hertfelder Reynolds](https://github.com/RHReynolds)
+- [Matthias Zepper](https://github.com/MatthiasZepper)
+
+### Enhancements & fixes
+
+- [PR #1123](https://github.com/nf-core/rnaseq/pull/1123) - Overhaul tximport.r, output length tables
+- [PR #1124](https://github.com/nf-core/rnaseq/pull/1124) - Ensure pseudoaligner is set if pseudoalignment is not skipped
+- [PR #1126](https://github.com/nf-core/rnaseq/pull/1126) - Pipeline fails if transcript_fasta not provided and `skip_gtf_filter = true`.
+- [PR #1127](https://github.com/nf-core/rnaseq/pull/1127) - Enlarge sampling to determine the number of columns in `filter_gtf.py` script.
+
+## [[3.13.1](https://github.com/nf-core/rnaseq/releases/tag/3.13.1)] - 2023-11-17
+
+### Enhancements and fixes
+
+- [PR #1121](https://github.com/nf-core/rnaseq/pull/1121) - Changes for 3.13.1 patch release incl. igenomes star fix
+
+## [[3.13.0](https://github.com/nf-core/rnaseq/releases/tag/3.13.0)] - 2023-11-17
 
 ### Credits
 
 Special thanks to the following for their contributions to the release:
 
 - [Adam Talbot](https://github.com/adamrtalbot)
+- [hmehlan](https://github.com/hmehlan)
+- [Jonathan Manning](https://github.com/pinin4fjords)
 - [Júlia Mir Pedrol](https://github.com/mirpedrol)
 - [Matthias Zepper](https://github.com/MatthiasZepper)
 - [Maxime Garcia](https://github.com/maxulysse)
+- [Steffen Möller](https://github.com/smoe)
 
 Thank you to everyone else that has contributed by reporting bugs, enhancements or in any other way, shape or form.
 
@@ -28,13 +81,20 @@ Thank you to everyone else that has contributed by reporting bugs, enhancements
 - [PR #1083](https://github.com/nf-core/rnaseq/pull/1083) - Move local modules and subworkflows to subfolders
 - [PR #1088](https://github.com/nf-core/rnaseq/pull/1088) - Updates contributing and code of conduct documents with nf-core template 2.10
 - [PR #1091](https://github.com/nf-core/rnaseq/pull/1091) - Reorganise parameters in schema for better usability
+- [PR #1106](https://github.com/nf-core/rnaseq/pull/1106) - Kallisto quantification
+- [PR #1107](https://github.com/nf-core/rnaseq/pull/1107) - Expand GTF filtering to remove rows with empty transcript ID when required, fix STAR GTF usage
+- [#976](https://github.com/nf-core/rnaseq/issues/976) - Add author and licenses for all custom scripts
+- [#1050](https://github.com/nf-core/rnaseq/issues/1050) - Provide custom prefix/suffix for summary files to avoid overwriting
+- [#1074](https://github.com/nf-core/rnaseq/issues/1074) - Enable quantification using StringTie AND a custom
+- [#1082](https://github.com/nf-core/rnaseq/issues/1082) - More informative error message for `filter_gtf_for_genes_in_genome.py`
+- [#1102](https://github.com/nf-core/rnaseq/issues/1102) - gene entries with empty transcript_id fields
 
 ### Software dependencies
 
 | Dependency              | Old version | New version |
 | ----------------------- | ----------- | ----------- |
 | `fastqc`                | 0.11.9      | 0.12.1      |
-| `multiqc`               | 1.14        | 1.15        |
+| `multiqc`               | 1.14        | 1.17        |
 | `ucsc-bedgraphtobigwig` | 377         | 445         |
 
 > **NB:** Dependency has been **updated** if both old and new version information is present.
@@ -43,6 +103,17 @@ Thank you to everyone else that has contributed by reporting bugs, enhancements
 >
 > **NB:** Dependency has been **removed** if new version information isn't present.
 
+### Modules / Subworkflows
+
+| Script                   | Old name          | New name                    |
+| ------------------------ | ----------------- | --------------------------- |
+| `local/gtf_filter`       | `GTF_GENE_FILTER` | `GTF_FILTER`                |
+| `local/tx2gene`          | `SALMON_TX2GENE`  | `TX2GENE`                   |
+| `local/tximport`         | `SALMON_TXIMPORT` | `TXIMPORT`                  |
+| `local/quantify_salmon`  | `QUANTIFY_SALMON` | `QUANTIFY_PSEUDO_ALIGNMENT` |
+| `nf-core/kallisto_index` |                   | `KALLISTO_INDEX`            |
+| `nf-core/kallisto_quant` |                   | `KALLISTO_QUANT`            |
+
 ## [[3.12.0](https://github.com/nf-core/rnaseq/releases/tag/3.12.0)] - 2023-06-02
 
 ### Credits
@@ -61,7 +132,7 @@ Thank you to everyone else that has contributed by reporting bugs, enhancements
 ### Enhancements & fixes
 
 - [[#1011](https://github.com/nf-core/rnaseq/issues/1011)] - FastQ files from UMI-tools not being passed to fastp
-- [[#1018](https://github.com/nf-core/rnaseq/issues/1018)] - Ability to skip both alignment and pseudo-alignment to only run pre-processing QC steps.
+- [[#1018](https://github.com/nf-core/rnaseq/issues/1018)] - Ability to skip both alignment and pseudoalignment to only run pre-processing QC steps.
 - [PR #1016](https://github.com/nf-core/rnaseq/pull/1016) - Updated pipeline template to [nf-core/tools 2.8](https://github.com/nf-core/tools/releases/tag/2.8)
 - [PR #1025](https://github.com/nf-core/fetchngs/pull/1025) - Add `public_aws_ecr.config` to source mulled containers when using `public.ecr.aws` Docker Biocontainer registry
 - [PR #1038](https://github.com/nf-core/rnaseq/pull/1038) - Updated error log for count values when supplying `--additional_fasta`
@@ -809,7 +880,7 @@ Major novel changes include:
 - Added options to skip several steps
   - Skip trimming using `--skipTrimming`
   - Skip BiotypeQC using `--skipBiotypeQC`
-  - Skip Alignment using `--skipAlignment` to only use pseudo-alignment using Salmon
+  - Skip Alignment using `--skipAlignment` to only use pseudoalignment using Salmon
 
 ### Documentation updates
 

diff --git a/README.md b/README.md
@@ -39,7 +39,7 @@
     3. [`dupRadar`](https://bioconductor.org/packages/release/bioc/html/dupRadar.html)
     4. [`Preseq`](http://smithlabresearch.org/software/preseq/)
     5. [`DESeq2`](https://bioconductor.org/packages/release/bioc/html/DESeq2.html)
-15. Pseudo-alignment and quantification ([`Salmon`](https://combine-lab.github.io/salmon/); _optional_)
+15. Pseudoalignment and quantification ([`Salmon`](https://combine-lab.github.io/salmon/) or ['Kallisto'](https://pachterlab.github.io/kallisto/); _optional_)
 16. Present QC for raw read, alignment, gene biotype, sample similarity, and strand-specificity checks ([`MultiQC`](http://multiqc.info/), [`R`](https://www.r-project.org/))
 
 > **Note**

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/rnaseq/releases/tag/dev" target="_blank">nf-core/rnaseq</a>
+  This report has been generated by the <a href="https://github.com/nf-core/rnaseq/releases/tag/3.13.0" target="_blank">nf-core/rnaseq</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/rnaseq/dev/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/rnaseq/3.13.0/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-rnaseq-methods-description":
     order: -1000
@@ -23,6 +23,7 @@ run_modules:
   - hisat2
   - rsem
   - salmon
+  - kallisto
   - samtools
   - picard
   - preseq
@@ -66,6 +67,7 @@ extra_fn_clean_exts:
   - ".umi_dedup"
   - "_val"
   - ".markdup"
+  - "_primary"
 
 # Customise the module search patterns to speed up execution time
 #  - Skip module sub-tools that we are not interested in

diff --git a/assets/slackreport.json b/assets/slackreport.json
@@ -3,7 +3,7 @@
         {
             "fallback": "Plain-text summary of the attachment.",
             "color": "<% if (success) { %>good<% } else { %>danger<%} %>",
-            "author_name": "nf-core/rnaseq v${version} - ${runName}",
+            "author_name": "nf-core/rnaseq ${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": [

diff --git a/bin/deseq2_qc.r b/bin/deseq2_qc.r
@@ -1,5 +1,7 @@
 #!/usr/bin/env Rscript
 
+# Written by Harshil Patel and Gavin Kelly and released under the MIT license.
+
 ################################################
 ################################################
 ## REQUIREMENTS                               ##

diff --git a/bin/dupradar.r b/bin/dupradar.r
@@ -1,5 +1,7 @@
 #!/usr/bin/env Rscript
 
+# Written by Phil Ewels and released under the MIT license.
+
 # Command line argument processing
 args = commandArgs(trailingOnly=TRUE)
 if (length(args) < 5) {
@@ -91,6 +93,7 @@ curve_y <- curve_y[seq(1, length(curve_y), 10)]
 curve_x = 10^curve_x
 # Write to file
 line="#id: dupradar
+#plot_type: 'linegraph'
 #section_name: 'DupRadar'
 #section_href: 'bioconductor.org/packages/release/bioc/html/dupRadar.html'
 #description: \"provides duplication rate quality control for RNA-Seq datasets. Highly expressed genes can be expected to have a lot of duplicate reads, but high numbers of duplicates at low read counts can indicate low library complexity with technical duplication.

diff --git a/bin/fasta2gtf.py b/bin/fasta2gtf.py
@@ -1,4 +1,7 @@
 #!/usr/bin/env python3
+
+# Written by Pranathi Vemuri and released under the MIT license.
+
 """
 Read a custom fasta file and create a custom GTF containing each entry
 """

diff --git a/bin/fastq_dir_to_samplesheet.py b/bin/fastq_dir_to_samplesheet.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python3
 
+# Written by Harshil Patel and released under the MIT license.
+
 import os
 import sys
 import glob