Add demultiplexing subworkflow 10x

.github/workflows/ci.yml

@@ -40,8 +40,7 @@ jobs:
       fail-fast: false
       matrix:
         NXF_VER: ${{ fromJson(needs.define_nxf_versions.outputs.matrix) }}
-        profile:
-          - docker
+        profile: ["bases2fastq", "bcl2fastq", "bclconvert", "fqtk", "sgdemux", "skip_tools"]
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
@@ -60,7 +59,7 @@ jobs:
 
       # Run nf-test
       - name: Run nf-test
-        run: nf-test test tests/pipeline/ --profile=test,${{ matrix.profile }} --junitxml=test.xml
+        run: nf-test test tests/pipeline/${{ matrix.profile }}.nf.test --profile=test,docker --junitxml=test.xml
 
       # If the test fails, output the software_versions.yml using the 'batcat' utility
       - name: Output log on failure

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#202](https://github.com/nf-core/demultiplex/pull/202) Added cellranger mkfastq subworkflow for demultiplexing 10x samples.
 - [#206](https://github.com/nf-core/demultiplex/pull/206) Add test with uncompressed data.
 - [#208](https://github.com/nf-core/demultiplex/pull/208) Added parameter for removing adapter information from samplesheets.
 

README.md

@@ -25,6 +25,7 @@
 2. Element Biosciences (via `bases2fastq`)
 3. Singular Genomics (via [`sgdemux`](https://github.com/Singular-Genomics/singular-demux))
 4. FASTQ files with user supplied read structures (via [`fqtk`](https://github.com/fulcrumgenomics/fqtk))
+5. 10x Genomics (via [`mkfastq`](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq))
 
 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!
 
@@ -39,6 +40,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
 - [bcl2fastq](#bcl2fastq) - converting bcl files to fastq, and demultiplexing (CONDITIONAL)
 - [sgdemux](#sgdemux) - demultiplexing bgzipped fastq files produced by Singular Genomics (CONDITIONAL)
 - [fqtk](#fqtk) - a toolkit for working with FASTQ files, written in Rust (CONDITIONAL)
+- [mkfastq](#mkfastq) - converting bcl files to fastq, and demultiplexing for single-cell sequencing data (CONDITIONAL)
 
 2. [fastp](#fastp) - Adapter and quality trimming
 3. [Falco](#falco) - Raw read QC

conf/modules.config

@@ -170,6 +170,35 @@ process {
         ]
     }
 
+    withName: CELLRANGER_MKFASTQ {
+        ext.args = {[
+            meta.lane ? "--lanes ${meta.lane}" : "",
+        ].join(" ").trim()}
+        publishDir = [
+            [
+                // Gather and write InterOp files
+                path: { "${params.outdir}/${meta.id}/InterOp" },
+                mode: params.publish_dir_mode,
+                pattern: "**/outs/interop_path/**.bin",
+                saveAs: {filename -> filename.split("/")[-1] }
+            ],
+            [
+                // Gather and write Reports and Stats
+                path: { meta.lane ? "${params.outdir}/${meta.id}/L00${meta.lane}" : "${params.outdir}/${meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "**/outs/fastq_path/{Reports,Stats}",
+                saveAs: {filename -> filename.split("/")[-1] }
+            ],
+            [
+                //Gather fastqs
+                path: { "${params.outdir}/${meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "**/outs/fastq_path/**.fastq.gz",
+                saveAs: {filename -> filename.split("/")[-1] }
+            ]
+        ]
+    }
+
     withName: 'MULTIQC' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

conf/test_mkfastq.config

@@ -0,0 +1,25 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/demultiplex -profile test_mkfastq,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test mkfastq profile'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '1.h'
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/demultiplex/samplesheet/1.3.0/mkfastq-samplesheet.csv'
+    demultiplexer = 'mkfastq'
+}

docs/output.md

@@ -15,6 +15,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [bcl2fastq](#bcl2fastq) - converting bcl files to fastq, and demultiplexing (CONDITIONAL)
 - [sgdemux](#sgdemux) - demultiplexing bgzipped fastq files produced by Singular Genomics (CONDITIONAL)
 - [fqtk](#fqtk) - demultiplexing fastq files (CONDITIONAL)
+- [mkfastq](#mkfastq) - converting bcl files to fastq, and demultiplexing for single-cell sequencing data (CONDITIONAL)
 - [fastp](#fastp) - Adapter and quality trimming
 - [Falco](#falco) - Raw read QC
 - [md5sum](#md5sum) - Creates an MD5 (128-bit) checksum of every fastq.
@@ -101,6 +102,25 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 </details>
 
+### mkfastq
+
+[mkfastq](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq) A tool for converting BCL files to FASTQ and demultiplexing for single-cell sequencing data.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+| File                 | Directory                          | Description                                                 |
+| :------------------- | :--------------------------------- | :---------------------------------------------------------- |
+| FASTQ                | <OUTDIR>/<id>                      | Demultiplexed fastq.gz files                                |
+| `*.fastp.html`       | <OUTDIR>/<id>                      | HTML report for fastp                                       |
+| `*.fastp.json`       | <OUTDIR>/<id>                      | JSON report for fastp                                       |
+| `*_summary.txt`      | <OUTDIR>/<id>                      | Summary statistics for the sequencing run                   |
+| Fastqc summary stats | <OUTDIR>/<id>/\*fastqc_data.txt    | Per base quality summary, for each demultiplexed FASTQ file |
+| Fastqc summary html  | <OUTDIR>/<id>/\*fastqc_report.html | Interactive html link for fastqc summary stats              |
+| Md5Sum               | <OUTDIR>/<id>/\*.md5               | Md5Sums for each demultiplexed FASTQ file                   |
+
+</details>
+
 ### fastp
 
 <details markdown="1">

modules.json

@@ -20,6 +20,11 @@
                         "git_sha": "e1e42c1312400df268a0c92e14bd33552e782448",
                         "installed_by": ["bcl_demultiplex"]
                     },
+                    "cellranger/mkfastq": {
+                        "branch": "master",
+                        "git_sha": "2bb941b6d3a01006c9f5bb49ca7eb8bb395dda9f",
+                        "installed_by": ["modules"]
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "de45447d060b8c8b98575bc637a4a575fd0638e1",