Dev -> Master for 3.12.0 release

.editorconfig

@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml,html,css,scss,js,cff}]
+[*.{md,yml,yaml,html,css,scss,js}]
 indent_size = 2
 
 # These files are edited and tested upstream in nf-core/modules

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -45,6 +45,6 @@ body:
         * Nextflow version _(eg. 22.10.1)_
         * Hardware _(eg. HPC, Desktop, Cloud)_
         * Executor _(eg. slurm, local, awsbatch)_
-        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter or Charliecloud)_
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud, or Apptainer)_
         * OS _(eg. CentOS Linux, macOS, Linux Mint)_
         * Version of nf-core/rnaseq _(eg. 1.1, 1.5, 1.8.2)_

.github/PULL_REQUEST_TEMPLATE.md

@@ -15,7 +15,8 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/rnas
 
 - [ ] This comment contains a description of changes (with reason).
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
-- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/rnaseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/rnaseq _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/rnaseq/tree/master/.github/CONTRIBUTING.md)
+- [ ] If necessary, also make a PR on the nf-core/rnaseq _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 (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.

.github/workflows/branch.yml

@@ -13,7 +13,7 @@ jobs:
       - name: Check PRs
         if: github.repository == 'nf-core/rnaseq'
         run: |
-          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnaseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnaseq ]] && [[ $GITHUB_HEAD_REF == "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
 
       # If the above check failed, post a comment on the PR explaining the failure
       # NOTE - this doesn't currently work if the PR is coming from a fork, due to limitations in GitHub actions secrets

.github/workflows/ci.yml

@@ -66,7 +66,7 @@ jobs:
 
       - name: Run pipeline with test data
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
 
   star_salmon:
     name: Test STAR Salmon with workflow parameters
@@ -128,7 +128,7 @@ jobs:
 
       - name: Run pipeline with STAR and various parameters
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner star_salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner star_salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
 
   star_rsem:
     name: Test STAR RSEM with workflow parameters
@@ -179,7 +179,7 @@ jobs:
 
       - name: Run pipeline with RSEM STAR and various parameters
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner star_rsem ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --aligner star_rsem ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
 
   hisat2:
     name: Test HISAT2 with workflow parameters
@@ -230,7 +230,7 @@ jobs:
 
       - name: Run pipeline with HISAT2 and various parameters
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --aligner hisat2 ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          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
@@ -239,7 +239,8 @@ jobs:
     strategy:
       matrix:
         parameters:
-          - "--skip_qc --skip_alignment"
+          - "--skip_qc"
+          - "--skip_alignment --skip_pseudo_alignment"
           - "--salmon_index false --transcript_fasta false"
     steps:
       - name: Check out pipeline code
@@ -281,4 +282,4 @@ jobs:
 
       - name: Run pipeline with Salmon and various parameters
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --pseudo_aligner salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/
+          nextflow run ${GITHUB_WORKSPACE} -profile test_cache,docker --pseudo_aligner salmon ${{ matrix.parameters }} --outdir ./results --test_data_base ${{ github.workspace }}/test-datasets/

.github/workflows/clean-up.yml

@@ -0,0 +1,24 @@
+name: "Close user-tagged issues and PRs"
+on:
+  schedule:
+    - cron: "0 0 * * 0" # Once a week
+
+jobs:
+  clean-up:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v7
+        with:
+          stale-issue-message: "This issue has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment otherwise this issue will be closed in 20 days."
+          stale-pr-message: "This PR has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor. Remove stale label or add a comment if it is still useful."
+          close-issue-message: "This issue was closed because it has been tagged as awaiting-changes or awaiting-feedback by an nf-core contributor and then staled for 20 days with no activity."
+          days-before-stale: 30
+          days-before-close: 20
+          days-before-pr-close: -1
+          any-of-labels: "awaiting-changes,awaiting-feedback"
+          exempt-issue-labels: "WIP"
+          exempt-pr-labels: "WIP"
+          repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/cloud_tests_full.yml

@@ -30,7 +30,7 @@ jobs:
           compute_env: ${{ secrets.TOWER_CE_AWS_CPU }}
           workdir: "${{ secrets.TOWER_BUCKET_AWS }}/work/rnaseq/work-${{ github.sha }}"
           run_name: "aws_rnaseq_full_${{ matrix.aligner }}"
-          profiles: test_full_aws
+          profiles: test_full_aws,public_aws_ecr
           parameters: |
             {
                 "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}",

.github/workflows/cloud_tests_small.yml

@@ -25,7 +25,7 @@ jobs:
           compute_env: ${{ secrets.TOWER_CE_AWS_CPU }}
           workdir: "${{ secrets.TOWER_BUCKET_AWS }}/work/rnaseq/work-${{ github.sha }}"
           run_name: "aws_rnaseq_small"
-          profiles: test
+          profiles: test,public_aws_ecr
           parameters: |
             {
                 "outdir": "${{ secrets.TOWER_BUCKET_AWS }}/rnaseq/results-test-${{ github.sha }}"

.github/workflows/linting.yml

@@ -78,7 +78,7 @@ jobs:
 
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.7"
+          python-version: "3.8"
           architecture: "x64"
 
       - name: Install dependencies

.pre-commit-config.yaml

@@ -0,0 +1,5 @@
+repos:
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v2.7.1"
+    hooks:
+      - id: prettier

CHANGELOG.md

@@ -3,6 +3,53 @@
 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).
 
+## [[3.12.0](https://github.com/nf-core/rnaseq/releases/tag/3.12.0)] - 2023-06-02
+
+### Credits
+
+Special thanks to the following for their contributions to the release:
+
+- [Adam Talbot](https://github.com/adamrtalbot)
+- [Esha Joshi](https://github.com/ejseqera)
+- [Ghepardo](https://github.com/Ghepardo)
+- [Matthias Zepper](https://github.com/MatthiasZepper)
+- [Maxime Garcia](https://github.com/maxulysse)
+- [Rob Syme](https://github.com/robsyme)
+
+Thank you to everyone else that has contributed by reporting bugs, enhancements or in any other way, shape or form.
+
+### 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.
+- [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`
+- [PR #1042](https://github.com/nf-core/rnaseq/pull/1042) - revert samtools_sort modules to no memory assignement
+
+### Parameters
+
+| Old parameter | New parameter             |
+| ------------- | ------------------------- |
+|               | `--skip_pseudo_alignment` |
+
+> **NB:** Parameter has been **updated** if both old and new parameter information is present.
+> **NB:** Parameter has been **added** if just the new parameter information is present.
+> **NB:** Parameter has been **removed** if new parameter information isn't present.
+
+### Software dependencies
+
+| Dependency | Old version | New version |
+| ---------- | ----------- | ----------- |
+| `fastp`    | 0.23.2      | 0.23.4      |
+| `samtools` | 1.16.1      | 1.17        |
+
+> **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.
+
 ## [[3.11.2](https://github.com/nf-core/rnaseq/releases/tag/3.11.2)] - 2023-04-25
 
 ### Credits

README.md

@@ -8,7 +8,7 @@
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)
 [![Launch on Nextflow Tower](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Nextflow%20Tower-%234256e7)](https://tower.nf/launch?pipeline=https://github.com/nf-core/rnaseq)
 
-[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnaseq)[![Follow on Twitter](http://img.shields.io/badge/twitter-%40nf__core-1DA1F2?labelColor=000000&logo=twitter)](https://twitter.com/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)
+[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnaseq)[![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)
 
 ## Introduction
 
@@ -50,9 +50,11 @@
 ## Usage
 
 > **Note**
-> If you are new to nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.
+> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how
+> to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline)
+> with `-profile test` before running the workflow on actual data.
 
-First, you need to prepare a samplesheet with your input data that looks as follows:
+First, prepare a samplesheet with your input data that looks as follows:
 
 **samplesheet.csv**:
 
@@ -65,8 +67,10 @@ CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz,a
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end). Rows with the same sample identifier are considered technical replicates and merged automatically. The strandedness refers to the library preparation and will be automatically inferred if set to `auto`.
 
-> **Warning**
-> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration **except for parameters**; see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
+> **Warning:**
+> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those
+> provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_;
+> see [docs](https://nf-co.re/usage/configuration#custom-configuration-files).
 
 Now, you can run the pipeline using:
 
@@ -82,8 +86,9 @@ For more details, please refer to the [usage documentation](https://nf-co.re/rna
 
 ## Pipeline output
 
-The output of the pipeline applied to a [full-sized example dataset](https://github.com/nf-core/test-datasets/tree/rnaseq#full-test-dataset-origin) can be found [here](https://nf-co.re/rnaseq/results).
-For more details, please refer to the [output documentation](https://nf-co.re/rnaseq/output).
+To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/rnaseq/results) tab on the nf-core website pipeline page.
+For more details about the output files and reports, please refer to the
+[output documentation](https://nf-co.re/rnaseq/output).
 
 ## Online videos
 
@@ -104,7 +109,7 @@ Many thanks to other who have helped out along the way too, including (but not l
 - [Alex Peltzer](https://github.com/apeltzer)
 - [Colin Davenport](https://github.com/colindaven)
 - [Denis Moreno](https://github.com/Galithil)
-- [Edumnd Miller](https://github.com/Emiller88)
+- [Edmund Miller](https://github.com/Emiller88)
 - [Gregor Sturm](https://github.com/grst)
 - [Jacki Buros Novik](https://github.com/jburos)
 - [Lorena Pantano](https://github.com/lpantano)

conf/base.config

@@ -14,7 +14,7 @@ process {
     memory = { check_max( 6.GB * task.attempt, 'memory' ) }
     time   = { check_max( 4.h  * task.attempt, 'time'   ) }
 
-    errorStrategy = { task.exitStatus in [140,143,137,104,134,139] ? 'retry' : 'finish' }
+    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
     maxRetries    = 1
     maxErrors     = '-1'
 

conf/igenomes.config

@@ -36,6 +36,14 @@ params {
             macs_gsize  = "2.7e9"
             blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
         }
+        'CHM13' {
+            fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa"
+            bwa         = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/"
+            bwamem2     = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/"
+            gtf         = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf"
+            gff         = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz"
+            mito_name   = "chrM"
+        }
         'GRCm38' {
             fasta       = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa"
             bwa         = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/"

conf/modules.config

@@ -1137,7 +1137,7 @@ if (!params.skip_multiqc) {
 // Salmon pseudo-alignment options
 //
 
-if (params.pseudo_aligner == 'salmon') {
+if (!params.skip_pseudo_alignment && params.pseudo_aligner == 'salmon') {
     process {
         withName: '.*:QUANTIFY_SALMON:SALMON_QUANT' {
             ext.args   = params.extra_salmon_quant_args ?: ''

conf/public_aws_ecr.config

@@ -0,0 +1,72 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    AWS ECR Config
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config to set public AWS ECR images wherever possible
+    This improves speed when running on AWS infrastructure.
+    Use this as an example template when using your own private registry.
+----------------------------------------------------------------------------------------
+*/
+
+docker.registry = 'public.ecr.aws'
+podman.registry = 'public.ecr.aws'
+
+process {
+    withName: 'CAT_ADDITIONAL_FASTA' {
+        container = 'quay.io/biocontainers/python:3.9--1'
+    }
+    withName: 'CAT_FASTQ' {
+        container = 'quay.io/nf-core/ubuntu:20.04'
+    }
+    withName: 'DESEQ2_QC' {
+        container = 'quay.io/biocontainers/mulled-v2-8849acf39a43cdd6c839a369a74c0adc823e2f91:ab110436faf952a33575c64dd74615a84011450b-0'
+    }
+    withName: 'GTF2BED' {
+        container = 'quay.io/biocontainers/perl:5.26.2'
+    }
+    withName: 'GTF_GENE_FILTER' {
+        container = 'quay.io/biocontainers/python:3.9--1'
+    }
+    withName: 'GUNZIP' {
+        container = 'quay.io/nf-core/ubuntu:20.04'
+    }
+    withName: 'HISAT2_ALIGN' {
+        container = 'quay.io/biocontainers/mulled-v2-a97e90b3b802d1da3d6958e0867610c718cb5eb1:2cdf6bf1e92acbeb9b2834b1c58754167173a410-0'
+    }
+    withName: 'MULTIQC_CUSTOM_BIOTYPE' {
+        container = 'quay.io/biocontainers/python:3.9--1'
+    }
+    withName: 'PREPROCESS_TRANSCRIPTS_FASTA_GENCODE' {
+        container = 'quay.io/nf-core/ubuntu:20.04'
+    }
+    withName: 'RSEM_CALCULATEEXPRESSION' {
+        container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0'
+    }
+    withName: 'RSEM_MERGE_COUNTS' {
+        container = 'quay.io/nf-core/ubuntu:20.04'
+    }
+    withName: 'RSEM_PREPAREREFERENCE' {
+        container = 'quay.io/biocontainers/mulled-v2-cf0123ef83b3c38c13e3b0696a3f285d3f20f15b:64aad4a4e144878400649e71f42105311be7ed87-0'
+    }
+    withName: 'SALMON_TX2GENE' {
+        container = 'quay.io/biocontainers/python:3.9--1'
+    }
+    withName: 'SAMPLESHEET_CHECK' {
+        container = 'quay.io/biocontainers/python:3.9--1'
+    }
+    withName: 'STAR_ALIGN' {
+        container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0'
+    }
+    withName: 'STAR_ALIGN_IGENOMES' {
+        container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0'
+    }
+    withName: 'STAR_GENOMEGENERATE' {
+        container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:1df389393721fc66f3fd8778ad938ac711951107-0'
+    }
+    withName: 'STAR_GENOMEGENERATE_IGENOMES' {
+        container = 'quay.io/biocontainers/mulled-v2-1fa26d1ce03c295fe2fdcf85831a92fbcbd7e8c2:59cdd445419f14abac76b31dd0d71217994cbcc9-0'
+    }
+    withName: 'UNTAR' {
+        container = 'quay.io/nf-core/ubuntu:20.04'
+    }
+}