Fix/featurecounts mixed se pe on448

bin/featurecounts_merge.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+# Merge multiple featureCounts count tables into a single matrix.
+#
+# The consensus-peak quantification runs featureCounts once per library type
+# (single-end / paired-end), so each input table shares an identical annotation
+# block (Geneid, Chr, Start, End, Strand, Length) computed from the same SAF, and
+# differs only in its per-sample count columns. This column-binds those sample
+# columns back together, keyed on Geneid, and reproduces the featureCounts output
+# layout expected downstream by deseq2_qc.r:
+#
+#   line 1        : a "# Program:featureCounts" comment (skipped via read.delim skip=1)
+#   line 2        : header  Geneid  Chr  Start  End  Strand  Length  <sample cols...>
+#   remaining rows: annotation columns 1-6 followed by one count per sample
+#
+# With a single input table this is an order-preserving pass-through.
+#
+# Usage: featurecounts_merge.sh OUTFILE INPUT1 [INPUT2 ...]
+set -euo pipefail
+
+if [ "$#" -lt 2 ]; then
+    echo "Usage: $(basename "$0") OUTFILE INPUT1 [INPUT2 ...]" >&2
+    exit 1
+fi
+
+out=$1
+shift
+
+awk '
+    BEGIN { FS = OFS = "\t" }
+
+    # Skip the leading "# Program:featureCounts ..." comment of every input file.
+    FNR == 1 { fidx++; next }
+
+    # Header row: keep the 6 annotation columns from the first file only,
+    # then append every input file`s sample columns (7..NF) in argument order.
+    FNR == 2 {
+        if (fidx == 1) { hdr = $1; for (i = 2; i <= 6; i++) hdr = hdr OFS $i }
+        for (i = 7; i <= NF; i++) hdr = hdr OFS $i
+        next
+    }
+
+    # Data rows: index on Geneid (column 1). Preserve the first file`s row order
+    # and annotation; append sample counts from each file for the matching Geneid.
+    {
+        key = $1
+        if (fidx == 1) {
+            order[++n] = key
+            a = $1; for (i = 2; i <= 6; i++) a = a OFS $i; ann[key] = a
+            v = "";  for (i = 7; i <= NF; i++) v = v OFS $i; val[key] = v
+        } else {
+            for (i = 7; i <= NF; i++) val[key] = val[key] OFS $i
+        }
+    }
+
+    END {
+        print "# Program:featureCounts (merged single-end and paired-end libraries)"
+        print hdr
+        for (j = 1; j <= n; j++) print ann[order[j]] val[order[j]]
+    }
+' "$@" > "$out"

conf/modules.config

@@ -705,6 +705,15 @@ process {
 
         withName: '.*:MERGED_LIBRARY_CONSENSUS_PEAKS:SUBREAD_FEATURECOUNTS'  {
             ext.args   = '-F SAF -O --fracOverlap 0.2'
+            ext.prefix = { "consensus_peaks.mLb.clN.${meta.single_end ? 'SE' : 'PE'}" }
+            publishDir = [
+                path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus" },
+                mode: params.publish_dir_mode,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            ]
+        }
+
+        withName: '.*:MERGED_LIBRARY_CONSENSUS_PEAKS:FEATURECOUNTS_MERGE'  {
             ext.prefix = "consensus_peaks.mLb.clN"
             publishDir = [
                 path: { "${params.outdir}/${params.aligner}/merged_library/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus" },
@@ -946,6 +955,15 @@ process {
 
             withName: '.*:MERGED_REPLICATE_CONSENSUS_PEAKS:SUBREAD_FEATURECOUNTS'  {
                 ext.args   = '-F SAF -O --fracOverlap 0.2'
+                ext.prefix = { "consensus_peaks.mRp.clN.${meta.single_end ? 'SE' : 'PE'}" }
+                publishDir = [
+                    path: { "${params.outdir}/${params.aligner}/merged_replicate/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus" },
+                    mode: params.publish_dir_mode,
+                    saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+                ]
+            }
+
+            withName: '.*:MERGED_REPLICATE_CONSENSUS_PEAKS:FEATURECOUNTS_MERGE'  {
                 ext.prefix = "consensus_peaks.mRp.clN"
                 publishDir = [
                     path: { "${params.outdir}/${params.aligner}/merged_replicate/macs3/${params.narrow_peak ? 'narrow_peak' : 'broad_peak'}/consensus" },

modules.json

@@ -164,8 +164,7 @@
                     "subread/featurecounts": {
                         "branch": "master",
                         "git_sha": "6d46786420b4d7bc88eba026eb389c0c5535d120",
-                        "installed_by": ["modules"],
-                        "patch": "modules/nf-core/subread/featurecounts/subread-featurecounts.diff"
+                        "installed_by": ["modules"]
                     },
                     "trimgalore": {
                         "branch": "master",

modules/local/featurecounts_merge.nf

@@ -0,0 +1,33 @@
+process FEATURECOUNTS_MERGE {
+    tag "${meta.id}"
+    label 'process_single'
+
+    conda "conda-forge::sed=4.7"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'nf-core/ubuntu:20.04' }"
+
+    input:
+    tuple val(meta), path('featurecounts/*')
+
+    output:
+    tuple val(meta), path("*.featureCounts.tsv"), emit: counts
+    tuple val("${task.process}"), val('sed'), eval("sed --version | sed '1!d;s/.*GNU sed) //'"), topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    featurecounts_merge.sh \\
+        ${prefix}.featureCounts.tsv \\
+        \$(ls featurecounts/*.featureCounts.tsv | sort)
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.featureCounts.tsv
+    """
+}

modules/local/tests/featurecounts_merge.nf.test

@@ -0,0 +1,102 @@
+nextflow_process {
+
+    name "Test Process FEATURECOUNTS_MERGE"
+    script "../featurecounts_merge.nf"
+    process "FEATURECOUNTS_MERGE"
+
+    tag "modules"
+    tag "modules_local"
+    tag "featurecounts_merge"
+
+    test("merge single-end and paired-end count tables") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'consensus_peaks' ],
+                    [
+                        file("\${projectDir}/modules/local/tests/fixtures/se.featureCounts.tsv", checkIfExists: true),
+                        file("\${projectDir}/modules/local/tests/fixtures/pe.featureCounts.tsv", checkIfExists: true)
+                    ]
+                ]
+                """
+            }
+        }
+
+        then {
+            def merged = path(process.out.counts.get(0).get(1)).readLines()
+            def header = merged.find { it.startsWith('Geneid') }.split('\t')
+            def sampleCols = header[6..-1]
+            assertAll(
+                { assert process.success },
+                // one merged table emitted
+                { assert process.out.counts.size() == 1 },
+                // The module merges its inputs in `ls | sort` filename order, so the
+                // column order is deterministic. Here 'pe.featureCounts.tsv' sorts
+                // before 'se.featureCounts.tsv' (in the pipeline the files are
+                // '...PE.featureCounts.tsv' / '...SE.featureCounts.tsv', so PE-first).
+                // Every SE and PE sample column appears exactly once.
+                { assert sampleCols == ['T0_PE.bam', 'T15_PE.bam', 'T100_SE.bam', 'T150_SE.bam'] },
+                { assert sampleCols.toUnique().size() == sampleCols.size() },
+                // Annotation + row order preserved from the first-sorted (PE) table;
+                // SE counts matched to rows by Geneid despite the different row order.
+                { assert merged.contains('peak_3\tIII\t9\t309\t+\t301\t131\t132\t31\t32') },
+                { assert merged.contains('peak_1\tI\t1\t100\t+\t100\t111\t112\t11\t12') },
+                { assert merged.contains('peak_2\tII\t5\t205\t+\t201\t121\t122\t21\t22') },
+                { assert snapshot(process.out.versions).match("versions") }
+            )
+        }
+    }
+
+    test("single-file pass-through (homogeneous cohort)") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'consensus_peaks' ],
+                    [ file("\${projectDir}/modules/local/tests/fixtures/se.featureCounts.tsv", checkIfExists: true) ]
+                ]
+                """
+            }
+        }
+
+        then {
+            def merged = path(process.out.counts.get(0).get(1)).readLines()
+            def header = merged.find { it.startsWith('Geneid') }.split('\t')
+            assertAll(
+                { assert process.success },
+                { assert (header[6..-1]) == ['T100_SE.bam', 'T150_SE.bam'] },
+                { assert merged.contains('peak_1\tI\t1\t100\t+\t100\t11\t12') },
+                { assert merged.contains('peak_3\tIII\t9\t309\t+\t301\t31\t32') }
+            )
+        }
+    }
+
+    test("stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'consensus_peaks' ],
+                    [
+                        file("\${projectDir}/modules/local/tests/fixtures/se.featureCounts.tsv", checkIfExists: true),
+                        file("\${projectDir}/modules/local/tests/fixtures/pe.featureCounts.tsv", checkIfExists: true)
+                    ]
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}

modules/local/tests/featurecounts_merge.nf.test.snap

@@ -0,0 +1,44 @@
+{
+    "versions": {
+        "content": null,
+        "timestamp": "2026-07-23T03:28:47.894742",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "26.04.4"
+        }
+    },
+    "stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "consensus_peaks"
+                        },
+                        "consensus_peaks.featureCounts.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        "FEATURECOUNTS_MERGE",
+                        "sed",
+                        ""
+                    ]
+                ],
+                "counts": [
+                    [
+                        {
+                            "id": "consensus_peaks"
+                        },
+                        "consensus_peaks.featureCounts.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            }
+        ],
+        "timestamp": "2026-07-23T03:28:54.791169",
+        "meta": {
+            "nf-test": "0.9.4",
+            "nextflow": "26.04.4"
+        }
+    }
+}

modules/local/tests/fixtures/pe.featureCounts.tsv

@@ -0,0 +1,5 @@
+# Program:featureCounts v2.1.1; Command:"featureCounts" "-F" "SAF" "-p"
+Geneid	Chr	Start	End	Strand	Length	T0_PE.bam	T15_PE.bam
+peak_3	III	9	309	+	301	131	132
+peak_1	I	1	100	+	100	111	112
+peak_2	II	5	205	+	201	121	122

modules/local/tests/fixtures/se.featureCounts.tsv

@@ -0,0 +1,5 @@
+# Program:featureCounts v2.1.1; Command:"featureCounts" "-F" "SAF"
+Geneid	Chr	Start	End	Strand	Length	T100_SE.bam	T150_SE.bam
+peak_1	I	1	100	+	100	11	12
+peak_2	II	5	205	+	201	21	22
+peak_3	III	9	309	+	301	31	32