Fix bugs in qc_bam and prepare_genome subworkflows and add tests

CHANGELOG.md

@@ -32,6 +32,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#151](https://github.com/nf-core/seqinspector/pull/151) Added a prepare_genome subworkflow to handle bwamem2 indexing
 - [#159](https://github.com/nf-core/seqinspector/pull/159) Added a subworkflow QC_BAM including picard_collecthsmetrics for alignment QC of hybrid-selection data
 - [#158](https://github.com/nf-core/seqinspector/pull/158) Moved picard_collectmultiplemetrics to the subworkflow QC_BAM
+- [#162](https://github.com/nf-core/seqinspector/pull/162) Add tests for prepare_genome subworkflow
 
 ### `Fixed`
 
@@ -40,6 +41,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#107](https://github.com/nf-core/seqinspector/pull/107) Put SeqFU-stats section reports together
 - [#112](https://github.com/nf-core/seqinspector/pull/112) Making fastq_screen_references value to use parentDir
 - [#94] (https://github.com/nf-core/seqinspector/issues/94) Go through and validate test data
+- [#162](https://github.com/nf-core/seqinspector/pull/162) Fix bugs in qc_bam and prepare_genome subworkflows and add tests
 - [#163](https://github.com/nf-core/seqinspector/pull/163) Run fastqscreen with subsampled data if available
 
 ### `Dependencies`

conf/modules.config

@@ -43,6 +43,14 @@ process {
         ]
     }
 
+        withName: 'PICARD_CREATESEQUENCEDICTIONARY' {
+        publishDir = [
+            path: { "${params.outdir}/picard_createsequencedictionary" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'BWAMEM2_MEM' {
         publishDir = [
             path: { "${params.outdir}/bwamem2_mem" },

subworkflows/local/prepare_genome/main.nf

@@ -1,8 +1,8 @@
 //
 // Prepare reference genome files
 
-include { BWAMEM2_INDEX                 } from '../../../modules/nf-core/bwamem2/index'
-include { SAMTOOLS_FAIDX                } from '../../../modules/nf-core/samtools/faidx'
+include { BWAMEM2_INDEX                   } from '../../../modules/nf-core/bwamem2/index'
+include { SAMTOOLS_FAIDX                  } from '../../../modules/nf-core/samtools/faidx'
 include { PICARD_CREATESEQUENCEDICTIONARY } from '../../../modules/nf-core/picard/createsequencedictionary/main'
 
 workflow PREPARE_GENOME {
@@ -18,7 +18,6 @@ workflow PREPARE_GENOME {
     // Initialize all channels that might be used later
     ch_bwamem2_index      = channel.empty()
     ch_reference_fai      = channel.empty()
-    ch_reference_fasta    = channel.empty()
     ch_ref_dict           = channel.empty()
     ch_versions           = channel.empty()
 

subworkflows/local/prepare_genome/tests/main.nf.test

@@ -0,0 +1,146 @@
+nextflow_workflow {
+
+    name "Test Workflow PREPARE_GENOME"
+    script "subworkflows/local/prepare_genome/main.nf"
+    workflow "PREPARE_GENOME"
+    tag 'subworkflows'
+    tag 'prepare_genome'
+
+    test("Test without bwamem2 index file path and with run_picard_collecthsmetrics=false") {
+
+        when {
+            config "./nextflow.config"
+            params {
+                outdir = "$outputDir"
+                run_picard_collecthsmetrics = true
+
+            }
+            workflow {
+                """
+                input[0]  = channel.of([id:'genome'], file(params.pipelines_testdata_base_path + '/reference/reference.fasta', checkIfExists: true)).collect()
+                input[1]  = null
+                input[2]  = ''
+                input[3]  = false
+                input[4]  = null
+                """
+            }
+        }
+
+        then {
+            // All files + folders produced by BWAMEM2_INDEX
+            def bwamem2_index_files = getAllFilesFromDir(
+                params.outdir + '/bwamem2_index',
+                relative: true, includeDir: true
+            )
+            // All files + folders produced by SAMTOOLS_FAIDX
+            def samtools_faidx_files = getAllFilesFromDir(
+                params.outdir + '/samtools_faidx',
+                relative: true, includeDir: true
+            )
+
+            assert workflow.success
+
+            assert snapshot(
+                    bwamem2_index_files,
+                    samtools_faidx_files
+                ).match()
+
+            // BWAMEM2_INDEX and SAMTOOLS_FAIDX should run
+            assert workflow.out.versions.size() == 2
+        }
+
+    }
+
+    test("Test without bwamem2 index file path, with run_picard_collecthsmetrics=true and with ref_dict") {
+
+        when {
+            config "./nextflow.config"
+            params {
+                outdir = "$outputDir"
+                run_picard_collecthsmetrics = true
+
+            }
+            workflow {
+                """
+                input[0]  = channel.of([id:'genome'], file(params.pipelines_testdata_base_path + '/reference/reference.fasta', checkIfExists: true)).collect()
+                input[1]  = null
+                input[2]  = ''
+                input[3]  = true
+                input[4]  = params.pipelines_testdata_base_path + '/reference/reference.dict'
+                """
+            }
+        }
+
+        then {
+            // All files + folders produced by BWAMEM2_INDEX
+            def bwamem2_index_files = getAllFilesFromDir(
+                params.outdir + '/bwamem2_index',
+                relative: true, includeDir: true
+            )
+            // All files + folders produced by SAMTOOLS_FAIDX
+            def samtools_faidx_files = getAllFilesFromDir(
+                params.outdir + '/samtools_faidx',
+                relative: true, includeDir: true
+            )
+
+            assert workflow.success
+            assert snapshot(
+                    bwamem2_index_files,
+                    samtools_faidx_files
+                ).match()
+            // BWAMEM2_INDEX and SAMTOOLS_FAIDX should run
+            assert workflow.out.versions.size() == 2
+        }
+
+    }
+
+    test("Test without bwamem2 index file path, with run_picard_collecthsmetrics=true and without ref_dict") {
+
+        when {
+            config "./nextflow.config"
+            params {
+                outdir = "$outputDir"
+                run_picard_collecthsmetrics = true
+
+            }
+            workflow {
+                """
+                input[0]  = channel.of([id:'genome'], file(params.pipelines_testdata_base_path + '/reference/reference.fasta', checkIfExists: true)).collect()
+                input[1]  = null
+                input[2]  = ''
+                input[3]  = true
+                input[4]  = null
+                """
+            }
+        }
+
+        then {
+            // All files + folders produced by BWAMEM2_INDEX
+            def bwamem2_index_files = getAllFilesFromDir(
+                params.outdir + '/bwamem2_index',
+                relative: true, includeDir: true
+            )
+            // All files + folders produced by SAMTOOLS_FAIDX
+            def samtools_faidx_files = getAllFilesFromDir(
+                params.outdir + '/samtools_faidx',
+                relative: true, includeDir: true
+            )
+            // All files + folders produced by PICARD_CREATESEQUENCEDICTIONARY
+            def picard_createsequencedictionary_files = getAllFilesFromDir(
+                params.outdir + '/picard_createsequencedictionary',
+                relative: true, includeDir: true
+            )
+
+            assert workflow.success
+            assert snapshot(
+                    bwamem2_index_files,
+                    samtools_faidx_files,
+                    picard_createsequencedictionary_files
+                ).match()
+            // BWAMEM2_INDEX, SAMTOOLS_FAIDX and PICARD_CREATESEQUENCEDICTIONARY should run
+            assert workflow.out.versions.size() == 3
+        }
+
+    }
+
+}

subworkflows/local/prepare_genome/tests/main.nf.test.snap

@@ -0,0 +1,75 @@
+{
+    "Test without bwamem2 index file path, with run_picard_collecthsmetrics=true and without ref_dict": {
+        "content": [
+            [
+                "",
+                "bwamem2",
+                "bwamem2/reference.fasta.0123",
+                "bwamem2/reference.fasta.amb",
+                "bwamem2/reference.fasta.ann",
+                "bwamem2/reference.fasta.bwt.2bit.64",
+                "bwamem2/reference.fasta.pac"
+            ],
+            [
+                "",
+                "reference.fasta.fai",
+                "reference.fasta.sizes"
+            ],
+            [
+                "",
+                "genome.dict"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.2"
+        },
+        "timestamp": "2025-12-02T11:58:24.141721"
+    },
+    "Test without bwamem2 index file path, with run_picard_collecthsmetrics=true and with ref_dict": {
+        "content": [
+            [
+                "",
+                "bwamem2",
+                "bwamem2/reference.fasta.0123",
+                "bwamem2/reference.fasta.amb",
+                "bwamem2/reference.fasta.ann",
+                "bwamem2/reference.fasta.bwt.2bit.64",
+                "bwamem2/reference.fasta.pac"
+            ],
+            [
+                "",
+                "reference.fasta.fai",
+                "reference.fasta.sizes"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.2"
+        },
+        "timestamp": "2025-12-02T11:57:18.592897"
+    },
+    "Test without bwamem2 index file path and with run_picard_collecthsmetrics=false": {
+        "content": [
+            [
+                "",
+                "bwamem2",
+                "bwamem2/reference.fasta.0123",
+                "bwamem2/reference.fasta.amb",
+                "bwamem2/reference.fasta.ann",
+                "bwamem2/reference.fasta.bwt.2bit.64",
+                "bwamem2/reference.fasta.pac"
+            ],
+            [
+                "",
+                "reference.fasta.fai",
+                "reference.fasta.sizes"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.3",
+            "nextflow": "25.10.2"
+        },
+        "timestamp": "2025-12-02T11:56:19.206085"
+    }
+}

subworkflows/local/prepare_genome/tests/nextflow.config

@@ -0,0 +1,7 @@
+// Load the basic test config
+includeConfig '../../../../tests/nextflow.config'
+
+
+params {
+    pipelines_testdata_base_path = params.pipelines_testdata_base_path + 'raredisease/'
+}