Draft: Add feature for sample demultiplexing followed by immune profiling

.gitignore

@@ -11,3 +11,4 @@ reports/
 testme.sh
 .nf-test*
 .vscode
+null/

CHANGELOG.md

@@ -3,6 +3,8 @@
 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).
 
+## [Unreleased]
+
 ## v2.7.1 - 2024-08-13
 
 - Fix that tests have not been executed with nf-test v0.9 ([#359](https://github.com/nf-core/scrnaseq/pull/359))

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/scrnaseq/releases/tag/2.7.1" target="_blank">nf-core/scrnaseq</a>
+  This report has been generated by the <a href="https://github.com/nf-core/scrnaseq/tree/dev" target="_blank">nf-core/scrnaseq</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/scrnaseq/2.7.1/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/scrnaseq/dev/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-scrnaseq-methods-description":
     order: -1000

conf/modules.config

@@ -218,7 +218,7 @@ if (params.aligner == 'kallisto') {
 if (params.aligner == 'cellrangermulti') {
     process {
         withName: FASTQC { ext.prefix = { "${meta.id}_${meta.feature_type}" } } // allow distinguishment of data types after renaming
-        withName: 'NFCORE_SCRNASEQ:SCRNASEQ:CELLRANGER_MULTI_ALIGN:CELLRANGER_MULTI' {
+        withName: 'NFCORE_SCRNASEQ:SCRNASEQ:CELLRANGER_MULTI_ALIGN:CELLRANGER_MULTI|NFCORE_SCRNASEQ:SCRNASEQ:CELLRANGER_MULTI_ALIGN_VDJ:CELLRANGER_MULTI_DEMUX|NFCORE_SCRNASEQ:SCRNASEQ:CELLRANGER_MULTI_ALIGN_VDJ:CELLRANGER_MULTI_IMMUNE' {
             ext.prefix = null // force it null, for some reason it was being wrongly read in the module
             publishDir = [
                 path: "${params.outdir}/${params.aligner}/count",
@@ -250,5 +250,12 @@ if (params.aligner == 'cellrangermulti') {
                 mode: params.publish_dir_mode
             ]
         }
+        withName: BAMTOFASTQ10X {
+            publishDir = [
+                path: "${params.outdir}/${params.aligner}/bam2fastq",
+                mode: params.publish_dir_mode
+            ]
+            ext.args = "--reads-per-fastq=2200000000"
+        }
     }
 }

docs/output.md

@@ -122,6 +122,8 @@ for the corresponding documentation.
 
 - Overall same output structure as cellranger. In case of multiplexed samples there will be one ouput folder for
   each demultiplexed sample, and one containing all (non-demultiplexed) cells.
+- In case sample demultiplexing is to be followed by immune profiling, an extra output is added containing .fastq files
+  converted from the standard .bam file output.
 
 ## UniverSC
 

modules.json

@@ -5,6 +5,11 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "bamtofastq10x": {
+                        "branch": "master",
+                        "git_sha": "63d6994f4f85c0628b7f2ac1e7097136c1b4be34",
+                        "installed_by": ["modules"]
+                    },
                     "cellranger/count": {
                         "branch": "master",
                         "git_sha": "90dad5491658049282ceb287a3d7732c1ce39837",

nextflow.config

@@ -305,7 +305,7 @@ manifest {
     description     = """Pipeline for processing 10x Genomics single cell rnaseq data"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '2.7.1'
+    version         = '2.8.0dev'
     doi             = '10.5281/zenodo.3568187'
 }
 

subworkflows/local/align_cellrangermulti.nf

@@ -1,20 +1,15 @@
 //
 // Include modules
 //
-include { CELLRANGER_MKGTF                  } from "../../modules/nf-core/cellranger/mkgtf/main.nf"
-include { CELLRANGER_MKREF                  } from "../../modules/nf-core/cellranger/mkref/main.nf"
-include { CELLRANGER_MKVDJREF               } from "../../modules/nf-core/cellranger/mkvdjref/main.nf"
 include { CELLRANGER_MULTI                  } from "../../modules/nf-core/cellranger/multi/main.nf"
 include { PARSE_CELLRANGERMULTI_SAMPLESHEET } from "../../modules/local/parse_cellrangermulti_samplesheet.nf"
 
 // Define workflow to subset and index a genome region fasta file
 workflow CELLRANGER_MULTI_ALIGN {
     take:
-        ch_fasta
-        ch_gtf
         ch_fastq
-        cellranger_gex_index
-        cellranger_vdj_index
+        ch_cellranger_gex_index
+        ch_cellranger_vdj_index
         ch_multi_samplesheet
 
     main:
@@ -109,58 +104,6 @@ workflow CELLRANGER_MULTI_ALIGN {
             ch_frna_sample_csv = []
         }
 
-        //
-        // Prepare GTF
-        //
-        if ( !cellranger_gex_index || (!cellranger_vdj_index && !params.skip_cellrangermulti_vdjref) ) {
-
-            // Filter GTF based on gene biotypes passed in params.modules
-            CELLRANGER_MKGTF ( ch_gtf )
-            ch_versions = ch_versions.mix(CELLRANGER_MKGTF.out.versions)
-
-        }
-
-        //
-        // Prepare gex reference (Normal Ref)
-        //
-        if ( !cellranger_gex_index ) {
-
-            // Make reference genome
-            CELLRANGER_MKREF(
-                ch_fasta,
-                CELLRANGER_MKGTF.out.gtf,
-                "gex_reference"
-            )
-            ch_versions = ch_versions.mix(CELLRANGER_MKREF.out.versions)
-            ch_cellranger_gex_index = CELLRANGER_MKREF.out.reference.ifEmpty { [] }
-
-        } else {
-            ch_cellranger_gex_index = cellranger_gex_index
-        }
-
-        //
-        // Prepare vdj reference (Special)
-        //
-        if ( !cellranger_vdj_index ) {
-
-            if ( !params.skip_cellrangermulti_vdjref  ) { // if user uses cellranger multi but does not have VDJ data
-                // Make reference genome
-                CELLRANGER_MKVDJREF(
-                    ch_fasta,
-                    CELLRANGER_MKGTF.out.gtf,
-                    [], // currently ignoring the 'seqs' option
-                    "vdj_reference"
-                )
-                ch_versions = ch_versions.mix(CELLRANGER_MKVDJREF.out.versions)
-                ch_cellranger_vdj_index = CELLRANGER_MKVDJREF.out.reference.ifEmpty { [] }
-            } else {
-                ch_cellranger_vdj_index = []
-            }
-
-        } else {
-            ch_cellranger_vdj_index = cellranger_vdj_index
-        }
-
         //
         // MODULE: cellranger multi
         //