nf-core · jma1991 · May 19, 2023 · Apr 28, 2023 · May 19, 2023 · May 19, 2023
diff --git a/.editorconfig b/.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

diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.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/rnasplice _(eg. 1.1, 1.5, 1.8.2)_
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.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/rnasplice/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/rnasplice _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/rnasplice/tree/master/.github/CONTRIBUTING.md)
+- [ ] If necessary, also make a PR on the nf-core/rnasplice _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.

diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml
@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Launch workflow via tower
-        uses: nf-core/tower-action@v3
+        uses: seqeralabs/action-tower-launch@v1
         # TODO nf-core: You can customise AWS full pipeline tests as required
         # Add full size test data (but still relatively small datasets for few samples)
         # on the `test_full.config` test runs with only one set of parameters

diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml
@@ -12,7 +12,7 @@ jobs:
     steps:
       # Launch workflow using Tower CLI tool action
       - name: Launch workflow via tower
-        uses: nf-core/tower-action@v3
+        uses: seqeralabs/action-tower-launch@v1
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}

diff --git a/.github/workflows/branch.yml b/.github/workflows/branch.yml
@@ -13,7 +13,7 @@ jobs:
       - name: Check PRs
         if: github.repository == 'nf-core/rnasplice'
         run: |
-          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnasplice ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/rnasplice ]] && [[ $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

diff --git a/.github/workflows/clean-up.yml b/.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 }}"
diff --git a/.github/workflows/linting.yml b/.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

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,5 @@
+repos:
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: "v2.7.1"
+    hooks:
+      - id: prettier
diff --git a/README.md b/README.md
@@ -8,24 +8,12 @@
 [![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/rnasplice)
 
-[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23rnasplice-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnasplice)[![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%23rnasplice-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/rnasplice)[![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
 
 **nf-core/rnasplice** is a bioinformatics pipeline for alternative splicing analysis of RNA sequencing data obtained from organisms with a reference genome and annotation.
 
-The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It uses Docker/Singularity containers making installation trivial and results highly reproducible. The [Nextflow DSL2](https://www.nextflow.io/docs/latest/dsl2.html) implementation of this pipeline uses one container per process which makes it much easier to maintain and update software dependencies. Where possible, these processes have been submitted to and installed from [nf-core/modules](https://github.com/nf-core/modules) in order to make them available to all nf-core pipelines, and to everyone within the Nextflow community!
-
-<!-- TODO nf-core: Add full-sized test dataset and amend the paragraph below if applicable -->
-
-On release, automated continuous integration tests run the pipeline on a full-sized dataset on the AWS cloud infrastructure. This ensures that the pipeline runs on AWS, has sensible resource allocation defaults set to run on real-world datasets, and permits the persistent storage of results to benchmark between pipeline releases and other analysis sources. The results obtained from the full-sized test can be viewed on the [nf-core website](https://nf-co.re/rnasplice/results).
-
-## Online videos
-
-You can find numerous talks on the [nf-core events page](https://nf-co.re/events) from various topics including writing pipelines/modules in Nextflow DSL2, using nf-core tooling, running nf-core pipelines as well as more generic content like contributing to Github. Please check them out!
-
-## Pipeline summary
-
 ![nf-core/rnasplice metro map](assets/rnasplice_map.png)
 
 1. Merge re-sequenced FastQ files ([`cat`](http://www.linfo.org/cat.html))
@@ -53,38 +41,64 @@ You can find numerous talks on the [nf-core events page](https://nf-co.re/events
     1. [`STAR`](https://github.com/alexdobin/STAR) -> [`rMATS`](https://github.com/Xinglab/rmats-turbo)
     2. [`Salmon`](https://combine-lab.github.io/salmon/) -> [`SUPPA2`](https://github.com/comprna/SUPPA)
 
-## Quick Start
+## 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.
 
-1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`)
+First, prepare a samplesheet with your input data that looks as follows:
 
-2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/) (you can follow [this tutorial](https://singularity-tutorial.github.io/01-installation/)), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(you can use [`Conda`](https://conda.io/miniconda.html) both to install Nextflow itself and also to manage software within pipelines. Please only use it within pipelines as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_.
+`samplesheet.csv`:
 
-3. Download the pipeline and test it on a minimal dataset with a single command:
+```csv
+sample,fastq_1,fastq_2,strandedness,condition
+CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz,forward,CONTROL
+CONTROL_REP1,AEG588A1_S1_L003_R1_001.fastq.gz,AEG588A1_S1_L003_R2_001.fastq.gz,forward,CONTROL
+CONTROL_REP1,AEG588A1_S1_L004_R1_001.fastq.gz,AEG588A1_S1_L004_R2_001.fastq.gz,forward,CONTROL
+```
 
-   ```bash
-   nextflow run nf-core/rnasplice -profile test,YOURPROFILE --outdir <OUTDIR>
-   ```
+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 should be specified by the user.
 
-   Note that some form of configuration will be needed so that Nextflow knows how to fetch the required software. This is usually done in the form of a config profile (`YOURPROFILE` in the example command above). You can chain multiple config profiles in a comma-separated string.
+> **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).
 
-   > - The pipeline comes with config profiles called `docker`, `singularity`, `podman`, `shifter`, `charliecloud` and `conda` which instruct the pipeline to use the named tool for software management. For example, `-profile test,docker`.
-   > - Please check [nf-core/configs](https://github.com/nf-core/configs#documentation) to see if a custom config file to run nf-core pipelines already exists for your Institute. If so, you can simply use `-profile <institute>` in your command. This will enable either `docker` or `singularity` and set the appropriate execution settings for your local compute environment.
-   > - If you are using `singularity`, please use the [`nf-core download`](https://nf-co.re/tools/#downloading-pipelines-for-offline-use) command to download images first, before running the pipeline. Setting the [`NXF_SINGULARITY_CACHEDIR` or `singularity.cacheDir`](https://www.nextflow.io/docs/latest/singularity.html?#singularity-docker-hub) Nextflow options enables you to store and re-use the images from a central location for future pipeline runs.
-   > - If you are using `conda`, it is highly recommended to use the [`NXF_CONDA_CACHEDIR` or `conda.cacheDir`](https://www.nextflow.io/docs/latest/conda.html) settings to store the environments in a central location for future pipeline runs.
+Now, you can run the pipeline using:
 
-4. Start running your own analysis!
+```bash
+nextflow run nf-core/rnasplice \
+   --input samplesheet.csv \
+   --contrasts contrastsheet.csv \
+   --genome GRCh37 \
+   --outdir <OUTDIR> \
+   -profile <docker/singularity/.../institute>
+```
 
-   ```bash
-   nextflow run nf-core/rnasplice --input samplesheet.csv --contrasts contrastsheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
-   ```
+For more details, please refer to the [usage documentation](https://nf-co.re/rnasplice/usage) and the [parameter documentation](https://nf-co.re/rnasplice/parameters).
 
-## Documentation
+## Pipeline output
 
-The nf-core/rnasplice pipeline comes with documentation about the pipeline [usage](https://github.com/zifornd/rnasplice/blob/dev/docs/usage.md) and [output](https://github.com/zifornd/rnasplice/blob/dev/docs/output.md).
+To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/rnasplice/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/rnasplice/output).
+
+## Online videos
+
+You can find numerous talks on the [nf-core events page](https://nf-co.re/events) from various topics including writing pipelines/modules in Nextflow DSL2, using nf-core tooling, running nf-core pipelines as well as more generic content like contributing to Github. Please check them out!
 
 ## Credits
 
-nf-core/rnasplice was originally written by Benjamin Southgate ([@Ben-Southgate](https://github.com/bensouthgate)), James Ashmore ([@James-Ashmore](https://github.com/jma1991)), Asma Ali ([@Asma-Ali](https://github.com/asmaali98)), Keerthana Bhaskaran ([@Keerthana-Bhaskaran](https://github.com/Keerthana-Bhaskaran-TG)), and Lathika Madhan Mohan ([@Lathika-Madhan-Mohan](https://github.com/lathikaa)) from [Zifo RnD Solutions](https://www.zifornd.com/).
+nf-core/rnasplice was originally written by the bioinformatics team from [Zifo RnD Solutions](https://www.zifornd.com/):
+
+- [Benjamin Southgate](https://github.com/bensouthgate)
+- [James Ashmore](https://github.com/jma1991)
+- [Valentino Ruggieri](https://github.com/valentinoruggieri))
+- [Claire Prince](https://github.com/claire-prince)
+- [Keerthana Bhaskaran](https://github.com/Keerthana-Bhaskaran-TG))
+- [Asma Ali](https://github.com/asmaali98))
+- [Lathika Madhan Mohan](https://github.com/lathikaa))
 
 We thank Harshil Patel ([@drpatelh](https://github.com/drpatelh)) and Seqera Labs ([seqeralabs](https://github.com/seqeralabs)) for their assistance in the development of this pipeline.
 

diff --git a/bin/check_samplesheet_fastq.py b/bin/check_samplesheet_fastq.py
@@ -190,9 +190,6 @@ def sniff_format(handle):
     peek = read_head(handle)
     handle.seek(0)
     sniffer = csv.Sniffer()
-    if not sniffer.has_header(peek):
-        logger.critical("The given sample sheet does not appear to contain a header.")
-        sys.exit(1)
     dialect = sniffer.sniff(peek)
     return dialect
 

diff --git a/conf/base.config b/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 [143,137,104,134,139] ? 'retry' : 'finish' }
+    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
     maxRetries    = 1
     maxErrors     = '-1'
 

diff --git a/conf/igenomes.config b/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/"