Merge pull request #241 from nf-core/dev

Release 2.2.1

.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/smrnaseq _(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/smrn
 
 - [ ] 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/smrnaseq/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/smrnaseq _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/smrnaseq/tree/master/.github/CONTRIBUTING.md)
+- [ ] If necessary, also make a PR on the nf-core/smrnaseq _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/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
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}
@@ -24,7 +24,7 @@ jobs:
             {
               "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/smrnaseq/results-${{ github.sha }}"
             }
-          profiles: test_full,aws_tower
+          profiles: test_full,public_aws_ecr
       - uses: actions/upload-artifact@v3
         with:
           name: Tower debug log file

.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: ${{ secrets.TOWER_ACCESS_TOKEN }}
@@ -22,7 +22,7 @@ jobs:
             {
               "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/smrnaseq/results-test-${{ github.sha }}"
             }
-          profiles: test,aws_tower
+          profiles: test,public_aws_ecr
       - uses: actions/upload-artifact@v3
         with:
           name: Tower debug log file

.github/workflows/branch.yml

@@ -13,7 +13,7 @@ jobs:
       - name: Check PRs
         if: github.repository == 'nf-core/smrnaseq'
         run: |
-          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/smrnaseq ]] && [[ $GITHUB_HEAD_REF = "dev" ]]; } || [[ $GITHUB_HEAD_REF == "patch" ]]
+          { [[ ${{github.event.pull_request.head.repo.full_name }} == nf-core/smrnaseq ]] && [[ $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/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/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 +3,13 @@
 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).
 
+## [v2.2.1](https://github.com/nf-core/smrnaseq/releases/tag/2.2.1) - 2023-05-08
+
+### Enhancements & fixes
+
+- [[#238](https://github.com/nf-core/smrnaseq/issues/238)] - Restored the missing mirtop outputs
+- [[#242](https://github.com/nf-core/smrnaseq/issues/242)] - Fixed mirtrace using wrong input fastq files (untrimmed)
+
 ## [v2.2.0](https://github.com/nf-core/smrnaseq/releases/tag/2.2.0) - 2023-04-26
 
 - [[#220](https://github.com/nf-core/smrnaseq/issues/220)] - Fixed an issue where miRTrace reports fastq basename instead of sample ID

README.md

@@ -8,11 +8,11 @@
 [![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/smrnaseq)
 
-[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23smrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/smrnaseq)[![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%23smrnaseq-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/smrnaseq)[![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/smrnaseq** is a bioinformatics best-practice analysis pipeline for Small RNA-Seq Best Practice Analysis Pipeline.
+**nf-core/smrnaseq** is a bioinformatics best-practice analysis pipeline for Small RNA-Seq.
 
 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!
 
@@ -50,38 +50,61 @@ You can find numerous talks on the nf-core events page from various topics inclu
 9. miRNA quality control ([`mirtrace`](https://github.com/friedlanderlab/mirtrace))
 10. Present QC for raw read, alignment, and expression results ([`MultiQC`](http://multiqc.info/))
 
-## Quick Start
+## Usage
 
-1. Install [`Nextflow`](https://www.nextflow.io/docs/latest/getstarted.html#installation) (`>=22.10.1`)
+> **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.
 
-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))_.
+<!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.
+     Explain what rows and columns represent. For instance (please edit as appropriate):
 
-3. Download the pipeline and test it on a minimal dataset with a single command:
+First, prepare a samplesheet with your input data that looks as follows:
 
-   ```bash
-   nextflow run nf-core/smrnaseq -profile test,YOURPROFILE --outdir <OUTDIR>
-   ```
+`samplesheet.csv`:
 
-   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.
+```csv
+sample,fastq_1
+CONTROL_REP1,AEG588A1_S1_L002_001.fastq.gz
+```
 
-   > - 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.
+Each row represents a fastq file (single-end).
 
-4. Start running your own analysis!
+-->
 
-   ```bash
-   nextflow run nf-core/smrnaseq --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
-   ```
+Now, you can run the pipeline using:
 
-## Documentation
+<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
 
-The nf-core/smrnaseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/smrnaseq/usage), [parameters](https://nf-co.re/smrnaseq/parameters) and [output](https://nf-co.re/smrnaseq/output).
+```bash
+nextflow run nf-core/smrnaseq \
+   -profile <docker/singularity/.../institute> \
+   --input samplesheet.csv \
+    --genome 'GRCh37' \
+    --mirtrace_species 'hsa' \
+    --protocol 'illumina' \
+    --outdir <OUTDIR>
+```
+
+> **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).
+
+For more details, please refer to the [usage documentation](https://nf-co.re/smrnaseq/usage) and the [parameter documentation](https://nf-co.re/smrnaseq/parameters).
+
+## Pipeline output
+
+To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/smrnaseq/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/smrnaseq/output).
 
 ## Credits
 
-nf-core/smrnaseq was originally written for use at the [National Genomics Infrastructure](https://portal.scilifelab.se/genomics/) at [SciLifeLab](http://www.scilifelab.se/) in Stockholm, Sweden, by Phil Ewels ([@ewels](https://github.com/ewels)), Chuan Wang ([@chuan-wang](https://github.com/chuan-wang)) and Rickard Hammarén ([@Hammarn](https://github.com/hammarn)).
+nf-core/smrnaseq was originally written by P. Ewels, C. Wang, R. Hammarén, L. Pantano, A. Peltzer.
+
+We thank the following people for their extensive assistance in the development of this pipeline:
 
 Lorena Pantano ([@lpantano](https://github.com/lpantano)) from MIT updated the pipeline to Nextflow DSL2.
 

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'
 

conf/igenomes.config

@@ -38,6 +38,14 @@ params {
             blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
             mirtrace_species = "hsa"
         }
+        'CHM13' {
+            fasta       = "${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/public_aws_ecr.config

@@ -0,0 +1,30 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    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: '.*:SAMPLESHEET_CHECK' {
+        container = "quay.io/biocontainers/python:3.8.3"
+    }
+    withName: '.*:BOWTIE_MAP.*' {
+        container = 'quay.io/biocontainers/mulled-v2-ffbf83a6b0ab6ec567a336cf349b80637135bca3:40128b496751b037e2bd85f6789e83d4ff8a4837-0'
+    }
+    withName: '.*:EDGER_QC' {
+        container = 'quay.io/biocontainers/mulled-v2-419bd7f10b2b902489ac63bbaafc7db76f8e0ae1:709335c37934db1b481054cbec637c6e5b5971cb-0'
+    }
+    withName: '.*:MIRTOP_QUANT' {
+        container = 'quay.io/biocontainers/mulled-v2-0c13ef770dd7cc5c76c2ce23ba6669234cf03385:63be019f50581cc5dfe4fc0f73ae50f2d4d661f7-0'
+    }
+    withName: '.*:TABLE_MERGE' {
+        container = 'quay.io/biocontainers/r-data.table:1.12.2'
+    }
+}