BBsplit unmapped - enhancement

modules/nf-core/bbmap/bbsplit/main.nf

@@ -18,6 +18,7 @@ process BBMAP_BBSPLIT {
     output:
     path "bbsplit_index"                      , optional:true, emit: index
     tuple val(meta), path('*primary*fastq.gz'), optional:true, emit: primary_fastq
+    tuple val(meta), path('*unmapped*fastq.gz'), optional:true, emit: unmapped_fastq
     tuple val(meta), path('*fastq.gz')        , optional:true, emit: all_fastq
     tuple val(meta), path('*txt')             , optional:true, emit: stats
     tuple val(meta), path('*.log')            , optional:true, emit: log
@@ -46,6 +47,7 @@ process BBMAP_BBSPLIT {
     def fastq_out=''
     def index_files=''
     def refstats_cmd=''
+    def fastq_unmapped=''
     def use_index = index ? true : false
 
     if (only_build_index) {
@@ -64,6 +66,7 @@ process BBMAP_BBSPLIT {
         }
         fastq_in  = meta.single_end ? "in=${reads}" : "in=${reads[0]} in2=${reads[1]}"
         fastq_out = meta.single_end ? "basename=${prefix}_%.fastq.gz" : "basename=${prefix}_%_#.fastq.gz"
+        fastq_unmapped = meta.single_end ? "outu=${prefix}_unmapped.fastq.gz" : "outu=${prefix}_unmapped_#.fastq.gz"
         refstats_cmd = 'refstats=' + prefix + '.stats.txt'
     }
     """
@@ -93,6 +96,7 @@ process BBMAP_BBSPLIT {
         $fastq_in \\
         $fastq_out \\
         $refstats_cmd \\
+        $fastq_unmapped \\
         $args 2>| >(tee ${prefix}.log >&2)
 
     # Summary files will have an absolute path that will make the index
@@ -123,6 +127,7 @@ process BBMAP_BBSPLIT {
         echo '' | gzip >  ${prefix}_primary.fastq.gz
         ${other_refs}
         touch ${prefix}.stats.txt
+        touch ${prefix}_unmapped.fastq.gz
     fi
 
     touch ${prefix}.log

modules/nf-core/bbmap/bbsplit/meta.yml

@@ -1,5 +1,6 @@
 name: bbmap_bbsplit
-description: Split sequencing reads by mapping them to multiple references simultaneously
+description: Split sequencing reads by mapping them to multiple references
+  simultaneously
 keywords:
   - align
   - map
@@ -8,8 +9,8 @@ keywords:
   - reference
 tools:
   - bbmap:
-      description: BBMap is a short read aligner, as well as various other bioinformatic
-        tools.
+      description: BBMap is a short read aligner, as well as various other
+        bioinformatic tools.
       homepage: https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/
       documentation: https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/
       licence: ["UC-LBL license (see package)"]
@@ -40,7 +41,8 @@ input:
         description: List of other reference ids apart from the primary
     - other_ref_paths:
         type: list
-        description: Path to other references paths corresponding to "other_ref_names"
+        description: Path to other references paths corresponding to
+          "other_ref_names"
   - only_build_index:
       type: string
       description: true = only build index; false = mapping
@@ -62,6 +64,18 @@ output:
           pattern: "*primary*fastq.gz"
           ontologies:
             - edam: http://edamontology.org/format_3989 # GZIP format
+  unmapped_fastq:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test', single_end:false ]
+      - "*unmapped*fastq.gz":
+          type: file
+          description: Unmapped FASTQ file
+          pattern: "*unmapped*fastq.gz"
+          ontologies:
+            - edam: http://edamontology.org/format_3989 # GZIP format
   all_fastq:
     - - meta:
           type: map

modules/nf-core/bbmap/bbsplit/tests/main.nf.test

@@ -87,7 +87,7 @@ nextflow_process {
                     """
                     input[0] = Channel.of([
                         [ id:'test', single_end:true ], // meta map
-                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true)
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/sarscov2_mus-musculus.fastq.gz', checkIfExists: true)
                     ])
                     input[1] = BBMAP_BBSPLIT_INDEX.out.index
                     input[2] = []
@@ -103,6 +103,7 @@ nextflow_process {
                 { assert path(process.out.log[0][1]).text.contains("If you wish to regenerate the index") },
                 { assert snapshot(
                     process.out.primary_fastq,
+                    process.out.unmapped_fastq,
                     process.out.stats,
                     process.out.findAll { key, val -> key.startsWith("versions") }
                 ).match()}

modules/nf-core/bbmap/bbsplit/tests/main.nf.test.snap

@@ -16,7 +16,16 @@
                         "id": "test",
                         "single_end": true
                     },
-                    "test.stats.txt:md5,2cbf69b72e5f4f8508306b54e8fe2861"
+                    "test_unmapped.fastq.gz:md5,c513990406ea4296dfd81073adcdb6e1"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": true
+                    },
+                    "test.stats.txt:md5,dfdb1be5d832dfecca787ced0bdf6d2a"
                 ]
             ],
             {
@@ -33,7 +42,7 @@
             "nf-test": "0.9.3",
             "nextflow": "25.10.2"
         },
-        "timestamp": "2026-01-19T14:51:21.775776"
+        "timestamp": "2026-01-28T17:04:15.937554023"
     },
     "sarscov2_se_fastq_fasta_chr22_fasta - build index": {
         "content": [

subworkflows/nf-core/fastq_qc_trim_filter_setstrandedness/meta.yml

@@ -1,5 +1,7 @@
 name: "fastq_qc_trim_filter_setstrandedness"
-description: Performs linting, quality control, trimming, filtering, and strandedness determination on RNA-seq FASTQ files, preparing them for downstream analysis.
+description: Performs linting, quality control, trimming, filtering, and
+  strandedness determination on RNA-seq FASTQ files, preparing them for
+  downstream analysis.
 keywords:
   - fastq
   - rnaseq
@@ -94,7 +96,8 @@ input:
             description: BBSplit index directory or tar.gz archive
             pattern: "{*,*.tar.gz}"
   - ch_rrna_fastas:
-      description: Channel containing one or more FASTA files containing rRNA sequences for use with SortMeRNA or Bowtie2
+      description: Channel containing one or more FASTA files containing rRNA
+        sequences for use with SortMeRNA or Bowtie2
       structure:
         - meta:
             type: map
@@ -105,7 +108,8 @@ input:
             pattern: "*.{fa,fasta}"
   - skip_bbsplit:
       type: boolean
-      description: Whether to skip BBSplit for removal of non-reference genome reads
+      description: Whether to skip BBSplit for removal of non-reference genome
+        reads
   - skip_fastqc:
       type: boolean
       description: Whether to skip FastQC
@@ -114,7 +118,8 @@ input:
       description: Whether to skip trimming
   - skip_umi_extract:
       type: boolean
-      description: Skip the UMI extraction from the read in case the UMIs have been moved to the headers in advance of the pipeline run
+      description: Skip the UMI extraction from the read in case the UMIs have
+        been moved to the headers in advance of the pipeline run
   - skip_linting:
       type: boolean
       description: Whether to skip linting of FastQ files
@@ -126,14 +131,16 @@ input:
       description: Whether to create sortmerna index before running sortmerna
   - make_bowtie2_index:
       type: boolean
-      description: Whether to create bowtie2 index before running bowtie2 for rRNA removal
+      description: Whether to create bowtie2 index before running bowtie2 for rRNA
+        removal
   - trimmer:
       type: string
       description: Specifies the trimming tool to use
       enum: ["trimgalore", "fastp"]
   - min_trimmed_reads:
       type: integer
-      description: Minimum number of trimmed reads below which samples are removed from further processing
+      description: Minimum number of trimmed reads below which samples are removed
+        from further processing
   - save_trimmed:
       type: boolean
       description: Save the trimmed FastQ files in the results directory?
@@ -153,14 +160,18 @@ input:
       description: Enable UMI-based read deduplication
   - umi_discard_read:
       type: integer
-      description: After UMI barcode extraction discard either R1 or R2 by setting this parameter to 1 or 2, respectively
+      description: After UMI barcode extraction discard either R1 or R2 by setting
+        this parameter to 1 or 2, respectively
   - stranded_threshold:
       type: float
       min: 0.5
-      description: The fraction of stranded reads that must be assigned to a strandedness for confident assignment. Must be at least 0.5.
+      description: The fraction of stranded reads that must be assigned to a
+        strandedness for confident assignment. Must be at least 0.5.
   - unstranded_threshold:
       type: float
-      description: The difference in fraction of stranded reads assigned to 'forward' and 'reverse' below which a sample is classified as 'unstranded'.
+      description: The difference in fraction of stranded reads assigned to
+        'forward' and 'reverse' below which a sample is classified as
+        'unstranded'.
 
 output:
   - reads:
@@ -174,7 +185,8 @@ output:
             description: Preprocessed FastQ files
             pattern: "*.{fq,fastq},{,.gz}"
   - multiqc_files:
-      description: MultiQC-compatible output files from tools used in preprocessing
+      description: MultiQC-compatible output files from tools used in
+        preprocessing
       structure:
         - meta:
             type: map
@@ -192,13 +204,6 @@ output:
         - count:
             type: integer
             description: Number of reads after trimming
-  - versions:
-      description: File containing software versions
-      structure:
-        - versions:
-            type: file
-            description: File containing software versions
-            pattern: "versions.yml"
   - lint_log:
       description: Log files from FastQ linting
       structure: