Merge remote-tracking branch 'origin/dev' into nf-core-template-merge…

…-2.11.1

.github/workflows/awsfulltest.yml

@@ -12,12 +12,12 @@ jobs:
     name: Run AWS full tests
     if: github.repository == 'nf-core/scrnaseq'
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        aligner: ["alevin", "kallisto", "star", "cellranger", "universc"]
     steps:
       - name: Launch workflow via tower
         uses: seqeralabs/action-tower-launch@v2
-        # 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
         with:
           workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }}
           access_token: ${{ secrets.TOWER_ACCESS_TOKEN }}

.github/workflows/awstest.yml

@@ -9,6 +9,9 @@ jobs:
     name: Run AWS tests
     if: github.repository == 'nf-core/scrnaseq'
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        aligner: ["alevin", "kallisto", "star", "cellranger", "universc"]
     steps:
       # Launch workflow using Tower CLI tool action
       - name: Launch workflow via tower
@@ -21,10 +24,10 @@ jobs:
           workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/scrnaseq/work-${{ github.sha }}
           parameters: |
             {
-              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/scrnaseq/results-test-${{ github.sha }}"
+              "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/scrnaseq/results-test-${{ github.sha }}/aligner_${{ matrix.aligner }}",
+              "aligner": "${{ matrix.aligner }}"
             }
           profiles: test
-
       - uses: actions/upload-artifact@v3
         with:
           name: Tower debug log file

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ env:
   NXF_ANSI_LOG: false
 
 concurrency:
-  group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
 jobs:
@@ -26,7 +26,21 @@ jobs:
         NXF_VER:
           - "23.04.0"
           - "latest-everything"
+        profile:
+          [
+            "test,docker --aligner alevin",
+            "test,docker --aligner kallisto",
+            "test,docker --aligner star",
+            "test,docker --aligner cellranger -stub",
+            "test,docker --aligner universc -stub",
+          ]
     steps:
+      - name: Free some space
+        run: |
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /opt/ghc
+          sudo rm -rf "/usr/local/share/boost"
+          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
       - name: Check out pipeline code
         uses: actions/checkout@v4
 
@@ -36,8 +50,7 @@ jobs:
           version: "${{ matrix.NXF_VER }}"
 
       - name: Run pipeline with test data
-        # TODO nf-core: You can customise CI pipeline run tests as required
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.profile }} --outdir ./results

.gitignore

@@ -6,3 +6,6 @@ results/
 testing/
 testing*
 *.pyc
+log/
+reports/
+testme.sh

.nf-core.yml

@@ -1 +1,5 @@
 repository_type: pipeline
+lint:
+  template_strings: False
+  files_unchanged:
+    - .github/ISSUE_TEMPLATE/bug_report.yml

CHANGELOG.md

@@ -3,14 +3,102 @@
 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).
 
-## v2.5.0dev - [date]
+## [Unreleased]
 
-Initial release of nf-core/scrnaseq, created with the [nf-core](https://nf-co.re/) template.
+- Better support for custom protocols ([#273](https://github.com/nf-core/scrnaseq/pull/273)).
+  - The universc protocol is now specified via the `--protocol` flag
+  - Any protocol specified is now passed to the respective aligner
+  - Added a section to the documentation
 
-### `Added`
+## v2.4.1 - 2023-09-28
 
-### `Fixed`
+- Fix whitelist logic for dropseq ([#267](https://github.com/nf-core/scrnaseq/pull/267))
+- Fix false-positive filename check in cellranger module ([#261](https://github.com/nf-core/scrnaseq/pull/261))
+- Template update to v2.10 ([#269](https://github.com/nf-core/scrnaseq/pull/269))
 
-### `Dependencies`
+## v2.4.0 - 2023-08-16 Lime Platinum Crab
 
-### `Deprecated`
+- Fix typo causing empty version imformation for mtx_conversion subworkflow ([#254](https://github.com/nf-core/scrnaseq/pull/254))
+- Add `singularity.registry = 'quay.io'` and bump NF version to 23.04.0 ([#237](https://github.com/nf-core/scrnaseq/pull/237))
+- Fixed issue with file collisions while using cellranger ([#232](https://github.com/nf-core/scrnaseq/pull/232))
+- Fix issue where multiqc inputs tried to access objects that did not exist ([#239](https://github.com/nf-core/scrnaseq/pull/239))
+- Removed `public_aws_ecr` profile ([#242](https://github.com/nf-core/scrnaseq/pull/242))
+- Include cellranger in MultiQC report ([#244](https://github.com/nf-core/scrnaseq/pull/244))
+- Nf-core template update to v2.9 ([#245](https://github.com/nf-core/scrnaseq/pull/245))
+- Update cellranger and fastqc module ([#246](https://github.com/nf-core/scrnaseq/pull/246)).
+  The [updated cellranger module](https://github.com/nf-core/modules/pull/3537) now automatically renames input FASTQ
+  files to match the expected naming conventions.
+
+## v2.3.2 - 2023-06-07 Sepia Samarium Salmon
+
+- Move containers for pipeline to quay.io ([#233](https://github.com/nf-core/scrnaseq/pull/233))
+
+## v2.3.1 - 2023-06-02 Yellow Strontium Pinscher
+
+- Add `public_aws_ecr` config for using the AWS mirror of containers where possible ([#225](https://github.com/nf-core/scrnaseq/pull/225))
+
+## v2.3.0 Steelblue Waspaloy Dachshund
+
+- Fix problem on samplesheet check related to amount of columns ([[#211](https://github.com/nf-core/scrnaseq/issues/211)])
+- Fixed bug in starsolo output cardinality.
+
+## v2.2.0
+
+- Added support to output 10x count files in text format.
+- Add gene symbols to count matrices
+- Added UniverSC aligner to implement open-source version of Cell Ranger with wrapper for 40 technologies
+- Update cellranger to v7.1.0 ([#205](https://github.com/nf-core/scrnaseq/pull/205)).
+
+### Fixes
+
+- Autocanceling previous CI runs when new changes are pushed.
+- Fixed [#193](https://github.com/nf-core/scrnaseq/issues/177) by updating the Seurat container directive
+- Fixed [#177](https://github.com/nf-core/scrnaseq/issues/177) by adjusting the channels generation and usage when skipping fastqc
+- Fixed [#173](https://github.com/nf-core/scrnaseq/issues/173) by adjusting parameter type and adding them to modules.config
+- Fixed [#170](https://github.com/nf-core/scrnaseq/issues/170) by adding UniverSC subworkflow using new module
+- Fixed [#196](https://github.com/nf-core/scrnaseq/issues/196) by adjusting runtime requirements for AlevinQC
+- Fixed [#191](https://github.com/nf-core/scrnaseq/issues/191) by updating simpleAF containers to latest version
+
+## v2.1.0 - 2022-10-06 "Green Mercury Siberian Husky"
+
+- Alevin workflow updated to use Alevin-Fry via simpleaf - thanks to @rob-p for supporting this and @fmalmeida implementing the support
+
+### Fixes
+
+- Fixed Kallistobustools workflow [#123](https://github.com/nf-core/scrnaseq/issues/123) by upgrading to nf-core/modules module
+- Fixed matrix conversion error when running STAR with --soloFeatures GeneFull [#135](https://github.com/nf-core/scrnaseq/pull/135)
+- Fixed seurat matrix conversion error when running with conda profile [#136](https://github.com/nf-core/scrnaseq/pull/136)
+- Fixed Kallistobustools module [#116](https://github.com/nf-core/scrnaseq/issues/116). By updating nf-core module and making sure conversion modules take into account the different outputs produced by kallisto standard and non-standard workflows.
+- Updated pipeline template to [nf-core/tools 2.6](https://github.com/nf-core/tools/releases/tag/2.6)
+
+## v2.0.0 - 2022-06-17 "Gray Nickel Beagle"
+
+- Pipeline ported to dsl2
+- Template update with latest nf-core/tools v2.1
+- Added cellranger v.7.0.0 subworkflow
+- Added full size tests
+
+### Fixes
+
+- Make sure pipeline runs on multiple samples [#77](https://github.com/nf-core/scrnaseq/pull/77)
+- Fix issue where STARsolo always uses 10XV2 chemistry [#60](https://github.com/nf-core/scrnaseq/issues/60)
+
+## v1.1.0 - 2021-03-24 "Olive Mercury Corgi"
+
+- Template update with latest nf-core/tools v1.13.2
+- Parameters JSON Schema added [#42](https://github.com/nf-core/scrnaseq/issues/42)
+- [25](https://github.com/nf-core/scrnaseq/issues/25) Fix small documentation error with wrong parameter for txp2gene
+
+### Fixes
+
+- [#20](https://github.com/nf-core/scrnaseq/issues/20) Fix Transcriptome Fasta argument not detected well
+- [#21](https://github.com/nf-core/scrnaseq/issues/21) Fix `--kallisto_index` being ignored
+
+## v1.0.0 - 2019-11-28 "Tiny Aluminium Crab"
+
+Initial release of nf-core/scrnaseq, created with the [nf-core](http://nf-co.re/) template.
+This includes the following workflow options:
+
+- Salmon Alevin + AlevinQC
+- STARSolo
+- Kallisto / BUStools

CITATIONS.md

@@ -18,6 +18,21 @@
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+* [Alevin](https://doi.org/10.1186/s13059-019-1670-y)
+
+  > Srivastava, A., Malik, L., Smith, T. et al. Alevin efficiently estimates accurate gene abundances from dscRNA-seq data. Genome Biol 20, 65 (2019).
+
+* [Salmon](https://www.nature.com/articles/nmeth.4197)
+
+  > Patro, R., Duggal, G., Love, M. et al. Salmon provides fast and bias-aware quantification of transcript expression. Nat Methods 14, 417–419 (2017).
+
+* [Kallisto/Bustools](https://www.nature.com/articles/s41587-021-00870-2)
+
+  > Melsted, P., Booeshaghi, A.S., Liu, L. et al. Modular, efficient and constant-memory single-cell RNA-seq preprocessing. Nat Biotechnol 39, 813–818 (2021).
+
+* [StarSolo](https://www.biorxiv.org/content/10.1101/2021.05.05.442755v1)
+  > Benjamin Kaminow, Dinar Yunusov, Alexander Dobin. STARsolo: accurate, fast and versatile mapping/quantification of single-cell and single-nucleus RNA-seq data. BioRxiv 2021.05.05.442755 (2021).
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -1,7 +1,7 @@
 # ![nf-core/scrnaseq](docs/images/nf-core-scrnaseq_logo_light.png#gh-light-mode-only) ![nf-core/scrnaseq](docs/images/nf-core-scrnaseq_logo_dark.png#gh-dark-mode-only)
 
 [![GitHub Actions CI Status](https://github.com/nf-core/scrnaseq/workflows/nf-core%20CI/badge.svg)](https://github.com/nf-core/scrnaseq/actions?query=workflow%3A%22nf-core+CI%22)
-[![GitHub Actions Linting Status](https://github.com/nf-core/scrnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/scrnaseq/actions?query=workflow%3A%22nf-core+linting%22)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/scrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
+[![GitHub Actions Linting Status](https://github.com/nf-core/scrnaseq/workflows/nf-core%20linting/badge.svg)](https://github.com/nf-core/scrnaseq/actions?query=workflow%3A%22nf-core+linting%22)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/scrnaseq/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.3568187-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.3568187)
 
 [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
@@ -13,50 +13,49 @@
 
 ## Introduction
 
-**nf-core/scrnaseq** is a bioinformatics pipeline that ...
+**nf-core/scrnaseq** is a bioinformatics best-practice analysis pipeline for processing 10x Genomics single-cell RNA-seq data.
 
-<!-- TODO nf-core:
-   Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the
-   major pipeline sections and the types of output it produces. You're giving an overview to someone new
-   to nf-core here, in 15-20 seconds. For an example, see https://github.com/nf-core/rnaseq/blob/master/README.md#introduction
--->
+This is a community effort in building a pipeline capable to support:
 
-<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
-     workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
-<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
+- Alevin-Fry + AlevinQC
+- STARSolo
+- Kallisto + BUStools
+- Cellranger
+- UniverSC
 
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+## Documentation
+
+The nf-core/scrnaseq pipeline comes with documentation about the pipeline [usage](https://nf-co.re/scrnaseq/usage), [parameters](https://nf-co.re/scrnaseq/parameters) and [output](https://nf-co.re/scrnaseq/output).
+
+![scrnaseq workflow](docs/images/scrnaseq_pipeline_v1.0_metro_clean.png)
 
 ## 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.
 
-<!-- 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):
-
 First, prepare a samplesheet with your input data that looks as follows:
 
 `samplesheet.csv`:
 
 ```csv
-sample,fastq_1,fastq_2
-CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz
+sample,fastq_1,fastq_2,expected_cells
+pbmc8k,pbmc8k_S1_L007_R1_001.fastq.gz,pbmc8k_S1_L007_R2_001.fastq.gz,"10000"
+pbmc8k,pbmc8k_S1_L008_R1_001.fastq.gz,pbmc8k_S1_L008_R2_001.fastq.gz,"10000"
 ```
 
 Each row represents a fastq file (single-end) or a pair of fastq files (paired end).
 
--->
-
 Now, you can run the pipeline using:
 
-<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->
-
 ```bash
 nextflow run nf-core/scrnaseq \
    -profile <docker/singularity/.../institute> \
    --input samplesheet.csv \
+   --genome_fasta GRCm38.p6.genome.chr19.fa \
+   --gtf gencode.vM19.annotation.chr19.gtf \
+   --protocol 10XV2 \
+   --aligner <alevin/kallisto/star/cellranger/universc> \
    --outdir <OUTDIR>
 ```
 
@@ -66,6 +65,21 @@ nextflow run nf-core/scrnaseq \
 
 For more details and further functionality, please refer to the [usage documentation](https://nf-co.re/scrnaseq/usage) and the [parameter documentation](https://nf-co.re/scrnaseq/parameters).
 
+## Decision Tree for users
+
+The nf-core/scrnaseq pipeline features several paths to analyze your single cell data. Future additions will also be done soon, e.g. the addition of multi-ome analysis types. To aid users in analyzing their data, we have added a decision tree to help people decide on what type of analysis they want to run and how to choose appropriate parameters for that.
+
+```mermaid
+graph TD
+    A[sc RNA] -->|alevin-fry| B(h5ad/seurat/mtx matrices)
+    A[sc RNA] -->|CellRanger| B(h5ad/seurat/mtx matrices)
+    A[sc RNA] -->|kbpython| B(h5ad/seurat/mtx matrices)
+    A[sc RNA] -->|STARsolo| B(h5ad/seurat/mtx matrices)
+    A[sc RNA] -->|Universc| B(h5ad/seurat/mtx matrices)
+```
+
+Options for the respective alignment method can be found [here](https://github.com/nf-core/scrnaseq/blob/dev/docs/usage.md#aligning-options) to choose between methods.
+
 ## Pipeline output
 
 To see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/scrnaseq/results) tab on the nf-core website pipeline page.
@@ -74,11 +88,14 @@ For more details about the output files and reports, please refer to the
 
 ## Credits
 
-nf-core/scrnaseq was originally written by Bailey PJ, Botvinnik O, Marques de Almeida F, Peltzer A, Sturm G.
+nf-core/scrnaseq was originally written by Bailey PJ, Botvinnik O, Marques de Almeida F, Gabernet G, Peltzer A, Sturm G.
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+- @heylf
+- @KevinMenden
+- @FloWuenne
+- @rob-p
 
 ## Contributions and Support
 
@@ -88,17 +105,10 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
-<!-- If you use nf-core/scrnaseq for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
+If you use nf-core/scrnaseq for your analysis, please cite it using the following doi: [10.5281/zenodo.3568187](https://doi.org/10.5281/zenodo.3568187)
 
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+The basic benchmarks that were used as motivation for incorporating the three available modular workflows can be found in [this publication](https://www.biorxiv.org/content/10.1101/673285v2).
 
-An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
-
-You can cite the `nf-core` publication as follows:
+We offer all three paths for the processing of scRNAseq data so it remains up to the user to decide which pipeline workflow is chosen for a particular analysis question.
 
-> **The nf-core framework for community-curated bioinformatics pipelines.**
->
-> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.
->
-> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).
+An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.

assets/methods_description_template.yml

@@ -3,7 +3,6 @@ description: "Suggested text and references to use when describing pipeline usag
 section_name: "nf-core/scrnaseq Methods Description"
 section_href: "https://github.com/nf-core/scrnaseq"
 plot_type: "html"
-## TODO nf-core: Update the HTML below to your preferred methods description, e.g. add publication citation for this pipeline
 ## You inject any metadata in the Nextflow '${workflow}' object
 data: |
   <h4>Methods</h4>