From 6bf6638cc7c027e6569fd97eb55e20d91c8c1689 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 4 Jun 2026 12:16:40 +0200
Subject: [PATCH 01/34] Add snpclustering subworkflow

---
 subworkflows/nf-core/snpclustering/main.nf    | 156 +++++++++++++++
 subworkflows/nf-core/snpclustering/meta.yml   | 180 +++++++++++++++++
 .../nf-core/snpclustering/tests/main.nf.test  | 162 +++++++++++++++
 .../snpclustering/tests/main.nf.test.snap     | 186 ++++++++++++++++++
 .../snpclustering/tests/nextflow.config       |  44 +++++
 5 files changed, 728 insertions(+)
 create mode 100644 subworkflows/nf-core/snpclustering/main.nf
 create mode 100644 subworkflows/nf-core/snpclustering/meta.yml
 create mode 100644 subworkflows/nf-core/snpclustering/tests/main.nf.test
 create mode 100644 subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
 create mode 100644 subworkflows/nf-core/snpclustering/tests/nextflow.config

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
new file mode 100644
index 000000000000..221553311025
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -0,0 +1,156 @@
+include { BEAGLE5_BEAGLE } from '../../../modules/nf-core/beagle5/beagle/main'
+include { PLINK2_VCF } from '../../../modules/nf-core/plink2/vcf/main'
+include { PLINK2_PCA } from '../../../modules/nf-core/plink2/pca/main'
+include { CUSTOM_PCACLUSTERING } from '../../../modules/nf-core/custom/pcaclustering/main'
+include { CUSTOM_CLUSTERMETRICS } from '../../../modules/nf-core/custom/clustermetrics/main'
+include { CUSTOM_CLUSTERVISUALIZATION } from '../../../modules/nf-core/custom/clustervisualization/main'
+
+workflow SNPCLUSTERING {
+
+    take:
+    vcf_ch
+    refpanel_ch
+    genmap_ch
+    region
+    npcs
+    use_approx
+    algorithm
+    n_clusters
+    dbscan_eps
+    dbscan_min_samples
+
+    main:
+    ch_versions = Channel.empty()
+
+    /*
+     * Build BEAGLE input tuple:
+     * tuple val(meta), path(vcf), path(vcf_index), path(refpanel), path(refpanel_index),
+     *       path(genmap), path(exclsamples), path(exclmarkers), val(region)
+     *
+     * For now, refpanel/genmap/exclusion files are optional and passed as empty lists
+     * when not provided by the caller.
+     */
+    ch_beagle_input = vcf_ch.map { meta, vcf, vcf_index ->
+        tuple(
+            meta,
+            vcf,
+            vcf_index,
+            [],
+            [],
+            [],
+            [],
+            [],
+            region
+        )
+    }
+
+    BEAGLE5_BEAGLE(ch_beagle_input)
+    ch_versions = ch_versions.mix(BEAGLE5_BEAGLE.out.versions_beagle)
+
+    /*
+     * Convert imputed VCF to PLINK2 pfiles
+     */
+    PLINK2_VCF(BEAGLE5_BEAGLE.out.vcf)
+    ch_versions = ch_versions.mix(PLINK2_VCF.out.versions)
+
+    /*
+     * PLINK2_PCA expects:
+     * tuple val(meta), val(npcs), val(use_approx), path(pgen), path(psam), path(pvar)
+     */
+    ch_plink_pca_input = PLINK2_VCF.out.pgen
+        .join(PLINK2_VCF.out.pvar)
+        .join(PLINK2_VCF.out.psam)
+        .map { meta, pgen, pvar, psam ->
+            tuple(meta, npcs, use_approx, pgen, psam, pvar)
+        }
+
+    PLINK2_PCA(ch_plink_pca_input)
+    ch_versions = ch_versions.mix(PLINK2_PCA.out.versions)
+
+    /*
+     * Convert .eigenvec to TSV for downstream clustering modules
+     */
+    EIGENVEC_TO_TSV(PLINK2_PCA.out.evecfile)
+
+    /*
+     * PCA clustering
+     * Signature inferred from your successful wiring so far:
+     * CUSTOM_PCACLUSTERING(tsv, algorithm, n_clusters, dbscan_eps, dbscan_min_samples)
+     */
+    CUSTOM_PCACLUSTERING(
+        EIGENVEC_TO_TSV.out.tsv,
+        algorithm,
+        n_clusters,
+        dbscan_eps,
+        dbscan_min_samples
+    )
+    ch_versions = ch_versions.mix(CUSTOM_PCACLUSTERING.out.versions)
+
+    /*
+     * Metrics and visualization both expect one tuple input channel
+     * built from: meta + tsv + cluster assignments
+     */
+    ch_cluster_analysis_input = EIGENVEC_TO_TSV.out.tsv
+        .join(CUSTOM_PCACLUSTERING.out.clusters)
+        .map { meta, tsv, clusters ->
+            tuple(meta, tsv, clusters)
+        }
+
+    CUSTOM_CLUSTERMETRICS(ch_cluster_analysis_input)
+    ch_versions = ch_versions.mix(CUSTOM_CLUSTERMETRICS.out.versions)
+
+    CUSTOM_CLUSTERVISUALIZATION(ch_cluster_analysis_input)
+    ch_versions = ch_versions.mix(CUSTOM_CLUSTERVISUALIZATION.out.versions)
+
+    emit:
+    imputed_vcf   = BEAGLE5_BEAGLE.out.vcf
+    beagle_log    = BEAGLE5_BEAGLE.out.log
+
+    pgen          = PLINK2_VCF.out.pgen
+    pvar          = PLINK2_VCF.out.pvar
+    psam          = PLINK2_VCF.out.psam
+
+    evecfile      = PLINK2_PCA.out.evecfile
+    evfile        = PLINK2_PCA.out.evfile
+    pca_log       = PLINK2_PCA.out.logfile
+
+    tsv           = EIGENVEC_TO_TSV.out.tsv
+
+    clusters      = CUSTOM_PCACLUSTERING.out.clusters
+    cluster_info  = CUSTOM_PCACLUSTERING.out.info
+
+    metrics       = CUSTOM_CLUSTERMETRICS.out.metrics
+    k_sweep       = CUSTOM_CLUSTERMETRICS.out.k_sweep
+    selected      = CUSTOM_CLUSTERMETRICS.out.selected
+    metric_plots  = CUSTOM_CLUSTERMETRICS.out.plots
+
+    umap_tsv      = CUSTOM_CLUSTERVISUALIZATION.out.umap_tsv
+    tsne_tsv      = CUSTOM_CLUSTERVISUALIZATION.out.tsne_tsv
+    umap_png      = CUSTOM_CLUSTERVISUALIZATION.out.umap_png
+    tsne_png      = CUSTOM_CLUSTERVISUALIZATION.out.tsne_png
+
+    versions      = ch_versions
+}
+
+process EIGENVEC_TO_TSV {
+    tag "${meta.id}"
+    label 'process_single'
+
+    input:
+    tuple val(meta), path(eigenvec)
+
+    output:
+    tuple val(meta), path("${meta.id}.tsv"), emit: tsv
+    path "versions.yml", emit: versions
+
+    script:
+    """
+    awk 'NR==1 { sub(/^#/, ""); \$1 = ""; sub(/^\\t/, ""); sub(/^IID\\t/, "sample_id\\t"); print; next }
+    { \$1 = ""; sub(/^\\t/, ""); print }' OFS='\\t' ${eigenvec} > ${meta.id}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gawk: \$(awk --version | head -1 | sed 's/GNU Awk //;s/,.*//')
+    END_VERSIONS
+    """
+}
diff --git a/subworkflows/nf-core/snpclustering/meta.yml b/subworkflows/nf-core/snpclustering/meta.yml
new file mode 100644
index 000000000000..cdf6d7c6e00b
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/meta.yml
@@ -0,0 +1,180 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json
+name: "snpclustering"
+description: >
+  Subworkflow for SNP clustering. Takes genotyped VCF files, imputes missing
+  genotypes with BEAGLE5, converts to PLINK2 pgen format, performs PCA,
+  converts eigenvec to TSV with awk, then runs PCA-based clustering,
+  cluster metrics, and cluster visualization.
+keywords:
+  - snp
+  - clustering
+  - pca
+  - plink2
+  - beagle
+  - imputation
+  - population genetics
+
+components:
+  - beagle5/beagle
+  - plink2/vcf
+  - plink2/pca
+  - custom/pcaclustering
+  - custom/clustermetrics
+  - custom/clustervisualization
+
+input:
+  - - meta:
+        type: map
+        description: Groovy map containing sample metadata.
+    - vcf:
+        type: file
+        description: Genotyped VCF file.
+        pattern: "*.{vcf,vcf.gz}"
+    - vcf_index:
+        type: file
+        description: Index for the VCF file.
+        pattern: "*.{tbi,csi}"
+
+  - - meta:
+        type: map
+        description: Groovy map for the optional reference panel.
+    - refpanel:
+        type: file
+        description: Optional BEAGLE reference panel VCF.
+        pattern: "*.{vcf,vcf.gz}"
+    - refpanel_index:
+        type: file
+        description: Optional index for the reference panel.
+        pattern: "*.{tbi,csi}"
+
+  - - meta:
+        type: map
+        description: Groovy map for the optional genetic map.
+    - genmap:
+        type: file
+        description: Optional genetic map file for BEAGLE.
+        pattern: "*.map"
+
+  - - region:
+        type: val
+        description: Optional genomic region passed to BEAGLE.
+
+  - - npcs:
+        type: val
+        description: Number of principal components to compute.
+
+  - - use_approx:
+        type: val
+        description: Whether to use approximate PCA.
+
+  - - algorithm:
+        type: val
+        description: Clustering algorithm to use.
+
+  - - n_clusters:
+        type: val
+        description: Number of clusters for kmeans or similar methods.
+
+  - - dbscan_eps:
+        type: val
+        description: DBSCAN eps parameter.
+
+  - - dbscan_min_samples:
+        type: val
+        description: DBSCAN minimum samples parameter.
+
+output:
+  - imputed_vcf:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - vcf:
+          type: file
+          description: Imputed VCF from BEAGLE5.
+          pattern: "*.{vcf,vcf.gz}"
+
+  - pfiles:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - pgen:
+          type: file
+          description: PLINK2 pgen file.
+          pattern: "*.pgen"
+      - psam:
+          type: file
+          description: PLINK2 psam file.
+          pattern: "*.psam"
+      - pvar:
+          type: file
+          description: PLINK2 pvar file.
+          pattern: "*.pvar"
+
+  - pca:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - eigenvec:
+          type: file
+          description: PCA eigenvectors from PLINK2.
+          pattern: "*.eigenvec"
+      - eigenval:
+          type: file
+          description: PCA eigenvalues from PLINK2.
+          pattern: "*.eigenval"
+
+  - tsv:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - tsv:
+          type: file
+          description: Tidy TSV converted from eigenvec by awk.
+          pattern: "*.tsv"
+
+  - cluster_labels:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - clusters:
+          type: file
+          description: Cluster labels output from PCA clustering.
+          pattern: "*.tsv"
+
+  - cluster_info:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - info:
+          type: file
+          description: Additional cluster info output.
+          pattern: "*.tsv"
+
+  - metrics:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - metrics:
+          type: file
+          description: Cluster quality metrics output.
+          pattern: "*.tsv"
+
+  - plots:
+      - meta:
+          type: map
+          description: Groovy map of sample metadata.
+      - plots:
+          type: file
+          description: Cluster visualization outputs.
+          pattern: "*.{png,pdf,html}"
+
+  - versions:
+      - versions:
+          type: file
+          description: Software versions collected from the subworkflow.
+          pattern: "versions.yml"
+
+authors:
+  - "@dbaku42"
+maintainers:
+  - "@dbaku42"
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
new file mode 100644
index 000000000000..8a2af307932e
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -0,0 +1,162 @@
+nextflow_workflow {
+
+    name "Test Subworkflow SNPCLUSTERING"
+    script "../main.nf"
+    workflow "SNPCLUSTERING"
+
+    tag "subworkflows"
+    tag "subworkflows_nfcore"
+    tag "subworkflows/snpclustering"
+    tag "snpclustering"
+    tag "plink2"
+    tag "plink2/vcf"
+    tag "plink2/pca"
+    tag "beagle5/beagle"
+    tag "custom/pcaclustering"
+    tag "custom/clustermetrics"
+    tag "custom/clustervisualization"
+
+    config "./nextflow.config"
+
+    test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
+        when {
+            workflow {
+                """
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz.csi', checkIfExists: true)
+                ])
+                input[1] = Channel.empty()
+                input[2] = Channel.empty()
+                input[3] = ""
+                input[4] = params.npcs
+                input[5] = params.use_approx
+                input[6] = "kmeans"
+                input[7] = 3
+                input[8] = params.dbscan_eps
+                input[9] = params.dbscan_min_samples
+                """
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert snapshot(
+                workflow.out.clusters.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.cluster_info.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.metrics.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.versions
+            ).match()
+        }
+    }
+
+    test("homo_sapiens - 1000GP.chr22.vcf.gz - dbscan") {
+        when {
+            workflow {
+                """
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz.csi', checkIfExists: true)
+                ])
+                input[1] = Channel.empty()
+                input[2] = Channel.empty()
+                input[3] = ""
+                input[4] = params.npcs
+                input[5] = params.use_approx
+                input[6] = "dbscan"
+                input[7] = params.n_clusters
+                input[8] = params.dbscan_eps
+                input[9] = params.dbscan_min_samples
+                """
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert snapshot(
+                workflow.out.clusters.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.cluster_info.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.metrics.collect { [
+                    it[0],
+                    path(it[1]).getFileName().toString()
+                ]},
+                workflow.out.versions
+            ).match()
+        }
+    }
+
+    test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans - stub") {
+        options "-stub"
+        when {
+            workflow {
+                """
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz.csi', checkIfExists: true)
+                ])
+                input[1] = Channel.empty()
+                input[2] = Channel.empty()
+                input[3] = ""
+                input[4] = params.npcs
+                input[5] = params.use_approx
+                input[6] = "kmeans"
+                input[7] = 3
+                input[8] = params.dbscan_eps
+                input[9] = params.dbscan_min_samples
+                """
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert snapshot(sanitizeOutput(workflow.out)).match()
+        }
+    }
+
+    test("homo_sapiens - 1000GP.chr22.vcf.gz - dbscan - stub") {
+        options "-stub"
+        when {
+            workflow {
+                """
+                input[0] = Channel.of([
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz', checkIfExists: true),
+                    file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/1000GP.chr22.vcf.gz.csi', checkIfExists: true)
+                ])
+                input[1] = Channel.empty()
+                input[2] = Channel.empty()
+                input[3] = ""
+                input[4] = params.npcs
+                input[5] = params.use_approx
+                input[6] = "dbscan"
+                input[7] = params.n_clusters
+                input[8] = params.dbscan_eps
+                input[9] = params.dbscan_min_samples
+                """
+            }
+        }
+
+        then {
+            assert workflow.success
+            assert snapshot(sanitizeOutput(workflow.out)).match()
+        }
+    }
+}
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
new file mode 100644
index 000000000000..f4d7988e57d5
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -0,0 +1,186 @@
+{
+    "homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters": {
+        "content": [
+            [
+                
+            ],
+            [
+                
+            ],
+            [
+                
+            ],
+            [
+                
+            ]
+        ],
+        "timestamp": "2026-06-04T01:16:07.326033555",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    },
+    "homo_sapiens - 1000GP.chr22.vcf.gz - dbscan": {
+        "content": [
+            [
+                
+            ],
+            [
+                
+            ],
+            [
+                
+            ],
+            [
+                
+            ]
+        ],
+        "timestamp": "2026-06-04T01:16:13.695098223",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    },
+    "homo_sapiens - 1000GP.chr22.vcf.gz - dbscan - stub": {
+        "content": [
+            {
+                "beagle_log": [
+                    
+                ],
+                "cluster_info": [
+                    
+                ],
+                "clusters": [
+                    
+                ],
+                "evecfile": [
+                    
+                ],
+                "evfile": [
+                    
+                ],
+                "imputed_vcf": [
+                    
+                ],
+                "k_sweep": [
+                    
+                ],
+                "metric_plots": [
+                    
+                ],
+                "metrics": [
+                    
+                ],
+                "pca_log": [
+                    
+                ],
+                "pgen": [
+                    
+                ],
+                "psam": [
+                    
+                ],
+                "pvar": [
+                    
+                ],
+                "selected": [
+                    
+                ],
+                "tsne_png": [
+                    
+                ],
+                "tsne_tsv": [
+                    
+                ],
+                "tsv": [
+                    
+                ],
+                "umap_png": [
+                    
+                ],
+                "umap_tsv": [
+                    
+                ],
+                "versions": [
+                    
+                ]
+            }
+        ],
+        "timestamp": "2026-06-04T01:16:30.853529288",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    },
+    "homo_sapiens - 1000GP.chr22.vcf.gz - kmeans - stub": {
+        "content": [
+            {
+                "beagle_log": [
+                    
+                ],
+                "cluster_info": [
+                    
+                ],
+                "clusters": [
+                    
+                ],
+                "evecfile": [
+                    
+                ],
+                "evfile": [
+                    
+                ],
+                "imputed_vcf": [
+                    
+                ],
+                "k_sweep": [
+                    
+                ],
+                "metric_plots": [
+                    
+                ],
+                "metrics": [
+                    
+                ],
+                "pca_log": [
+                    
+                ],
+                "pgen": [
+                    
+                ],
+                "psam": [
+                    
+                ],
+                "pvar": [
+                    
+                ],
+                "selected": [
+                    
+                ],
+                "tsne_png": [
+                    
+                ],
+                "tsne_tsv": [
+                    
+                ],
+                "tsv": [
+                    
+                ],
+                "umap_png": [
+                    
+                ],
+                "umap_tsv": [
+                    
+                ],
+                "versions": [
+                    
+                ]
+            }
+        ],
+        "timestamp": "2026-06-04T01:16:16.700560685",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    }
+}
\ No newline at end of file
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
new file mode 100644
index 000000000000..99eba676d04a
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -0,0 +1,44 @@
+params {
+    npcs = 8
+    use_approx = true
+    algorithm = "kmeans"
+    n_clusters = 3
+    dbscan_eps = 0.5
+    dbscan_min_samples = 5
+}
+
+process {
+    withName: 'BEAGLE5_BEAGLE' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+
+    withName: 'PLINK2_VCF' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+
+    withName: 'PLINK2_PCA' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+
+    withName: 'EIGENVEC_TO_TSV' {
+        ext.prefix = { "${meta.id}" }
+    }
+
+    withName: 'CUSTOM_PCACLUSTERING' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+
+    withName: 'CUSTOM_CLUSTERMETRICS' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+
+    withName: 'CUSTOM_CLUSTERVISUALIZATION' {
+        ext.prefix = { "${meta.id}" }
+        ext.when = false
+    }
+}

From 87af5c5a1d43051bb0fd9dcd0c0b6e614853635b Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 4 Jun 2026 13:05:55 +0200
Subject: [PATCH 02/34] fix meta.yml

---
 subworkflows/nf-core/snpclustering/meta.yml | 265 ++++++++++----------
 1 file changed, 128 insertions(+), 137 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/meta.yml b/subworkflows/nf-core/snpclustering/meta.yml
index cdf6d7c6e00b..25098093fb72 100644
--- a/subworkflows/nf-core/snpclustering/meta.yml
+++ b/subworkflows/nf-core/snpclustering/meta.yml
@@ -23,156 +23,147 @@ components:
   - custom/clustervisualization
 
 input:
-  - - meta:
-        type: map
-        description: Groovy map containing sample metadata.
-    - vcf:
-        type: file
-        description: Genotyped VCF file.
-        pattern: "*.{vcf,vcf.gz}"
-    - vcf_index:
-        type: file
-        description: Index for the VCF file.
-        pattern: "*.{tbi,csi}"
-
-  - - meta:
-        type: map
-        description: Groovy map for the optional reference panel.
-    - refpanel:
-        type: file
-        description: Optional BEAGLE reference panel VCF.
-        pattern: "*.{vcf,vcf.gz}"
-    - refpanel_index:
-        type: file
-        description: Optional index for the reference panel.
-        pattern: "*.{tbi,csi}"
-
-  - - meta:
-        type: map
-        description: Groovy map for the optional genetic map.
-    - genmap:
-        type: file
-        description: Optional genetic map file for BEAGLE.
-        pattern: "*.map"
-
-  - - region:
-        type: val
-        description: Optional genomic region passed to BEAGLE.
-
-  - - npcs:
-        type: val
-        description: Number of principal components to compute.
-
-  - - use_approx:
-        type: val
-        description: Whether to use approximate PCA.
-
-  - - algorithm:
-        type: val
-        description: Clustering algorithm to use.
-
-  - - n_clusters:
-        type: val
-        description: Number of clusters for kmeans or similar methods.
-
-  - - dbscan_eps:
-        type: val
-        description: DBSCAN eps parameter.
-
-  - - dbscan_min_samples:
-        type: val
-        description: DBSCAN minimum samples parameter.
+  - meta:
+      type: map
+      description: Groovy map containing sample metadata.
+    vcf:
+      type: file
+      description: Genotyped VCF file.
+      pattern: "*.{vcf,vcf.gz}"
+    vcf_index:
+      type: file
+      description: Index for the VCF file.
+      pattern: "*.{tbi,csi}"
+
+  - meta:
+      type: map
+      description: Groovy map for the optional reference panel.
+    refpanel:
+      type: file
+      description: Optional BEAGLE reference panel VCF.
+      pattern: "*.{vcf,vcf.gz}"
+    refpanel_index:
+      type: file
+      description: Optional index for the reference panel.
+      pattern: "*.{tbi,csi}"
+
+  - meta:
+      type: map
+      description: Groovy map for the optional genetic map.
+    genmap:
+      type: file
+      description: Optional genetic map file for BEAGLE.
+      pattern: "*.map"
+
+  - region:
+      type: val
+      description: Optional genomic region passed to BEAGLE.
+
+  - npcs:
+      type: val
+      description: Number of principal components to compute.
+
+  - use_approx:
+      type: val
+      description: Whether to use approximate PCA.
+
+  - algorithm:
+      type: val
+      description: Clustering algorithm to use.
+
+  - n_clusters:
+      type: val
+      description: Number of clusters for kmeans or similar methods.
+
+  - dbscan_eps:
+      type: val
+      description: DBSCAN eps parameter.
+
+  - dbscan_min_samples:
+      type: val
+      description: DBSCAN minimum samples parameter.
 
 output:
   - imputed_vcf:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - vcf:
-          type: file
-          description: Imputed VCF from BEAGLE5.
-          pattern: "*.{vcf,vcf.gz}"
+      type: map
+      description: Groovy map of sample metadata.
+    vcf:
+      type: file
+      description: Imputed VCF from BEAGLE5.
+      pattern: "*.{vcf,vcf.gz}"
 
   - pfiles:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - pgen:
-          type: file
-          description: PLINK2 pgen file.
-          pattern: "*.pgen"
-      - psam:
-          type: file
-          description: PLINK2 psam file.
-          pattern: "*.psam"
-      - pvar:
-          type: file
-          description: PLINK2 pvar file.
-          pattern: "*.pvar"
+      type: map
+      description: Groovy map of sample metadata.
+    pgen:
+      type: file
+      description: PLINK2 pgen file.
+      pattern: "*.pgen"
+    psam:
+      type: file
+      description: PLINK2 psam file.
+      pattern: "*.psam"
+    pvar:
+      type: file
+      description: PLINK2 pvar file.
+      pattern: "*.pvar"
 
   - pca:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - eigenvec:
-          type: file
-          description: PCA eigenvectors from PLINK2.
-          pattern: "*.eigenvec"
-      - eigenval:
-          type: file
-          description: PCA eigenvalues from PLINK2.
-          pattern: "*.eigenval"
-
-  - tsv:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - tsv:
-          type: file
-          description: Tidy TSV converted from eigenvec by awk.
-          pattern: "*.tsv"
+      type: map
+      description: Groovy map of sample metadata.
+    eigenvec:
+      type: file
+      description: PCA eigenvectors from PLINK2.
+      pattern: "*.eigenvec"
+    eigenval:
+      type: file
+      description: PCA eigenvalues from PLINK2.
+      pattern: "*.eigenval"
+
+  - eigenvec_tsv:
+      type: map
+      description: Groovy map of sample metadata.
+    tsv:
+      type: file
+      description: Tidy TSV converted from eigenvec by awk.
+      pattern: "*.tsv"
 
   - cluster_labels:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - clusters:
-          type: file
-          description: Cluster labels output from PCA clustering.
-          pattern: "*.tsv"
+      type: map
+      description: Groovy map of sample metadata.
+    clusters:
+      type: file
+      description: Cluster labels output from PCA clustering.
+      pattern: "*.tsv"
 
   - cluster_info:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - info:
-          type: file
-          description: Additional cluster info output.
-          pattern: "*.tsv"
-
-  - metrics:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - metrics:
-          type: file
-          description: Cluster quality metrics output.
-          pattern: "*.tsv"
-
-  - plots:
-      - meta:
-          type: map
-          description: Groovy map of sample metadata.
-      - plots:
-          type: file
-          description: Cluster visualization outputs.
-          pattern: "*.{png,pdf,html}"
+      type: map
+      description: Groovy map of sample metadata.
+    info:
+      type: file
+      description: Additional cluster info output.
+      pattern: "*.tsv"
+
+  - cluster_metrics:
+      type: map
+      description: Groovy map of sample metadata.
+    metrics:
+      type: file
+      description: Cluster quality metrics output.
+      pattern: "*.tsv"
+
+  - cluster_plots:
+      type: map
+      description: Groovy map of sample metadata.
+    plots:
+      type: file
+      description: Cluster visualization outputs.
+      pattern: "*.{png,pdf,html}"
 
   - versions:
-      - versions:
-          type: file
-          description: Software versions collected from the subworkflow.
-          pattern: "versions.yml"
+      type: file
+      description: Software versions collected from the subworkflow.
+      pattern: "versions.yml"
 
 authors:
   - "@dbaku42"

From 8bbe838af36e3efdcc9adae8591044137f8c7372 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Mon, 6 Jul 2026 14:06:48 +0200
Subject: [PATCH 03/34] Update subworkflows/nf-core/snpclustering/main.nf
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: Famke Bäuerle <45968370+famosab@users.noreply.github.com>
---
 subworkflows/nf-core/snpclustering/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 221553311025..b84372caf897 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,4 +1,4 @@
-include { BEAGLE5_BEAGLE } from '../../../modules/nf-core/beagle5/beagle/main'
+include { BEAGLE5_BEAGLE } from '../../../modules/nf-core/beagle5/beagle'
 include { PLINK2_VCF } from '../../../modules/nf-core/plink2/vcf/main'
 include { PLINK2_PCA } from '../../../modules/nf-core/plink2/pca/main'
 include { CUSTOM_PCACLUSTERING } from '../../../modules/nf-core/custom/pcaclustering/main'

From e1862fc685bb5bd8c313ec261732153933408524 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Mon, 6 Jul 2026 15:42:45 +0200
Subject: [PATCH 04/34] Remove ext.prefix assignments from processes

---
 .../nf-core/snpclustering/tests/nextflow.config  | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 99eba676d04a..9fa98d971a85 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -9,36 +9,32 @@ params {
 
 process {
     withName: 'BEAGLE5_BEAGLE' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 
     withName: 'PLINK2_VCF' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 
     withName: 'PLINK2_PCA' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 
-    withName: 'EIGENVEC_TO_TSV' {
-        ext.prefix = { "${meta.id}" }
-    }
-
     withName: 'CUSTOM_PCACLUSTERING' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 
     withName: 'CUSTOM_CLUSTERMETRICS' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 
     withName: 'CUSTOM_CLUSTERVISUALIZATION' {
-        ext.prefix = { "${meta.id}" }
+        
         ext.when = false
     }
 }

From fc8ef720a506186a791c0ec7b2639b79a457fb44 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Thu, 9 Jul 2026 14:45:17 +0200
Subject: [PATCH 05/34] Align include statements for consistency

---
 subworkflows/nf-core/snpclustering/main.nf | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index b84372caf897..c2cf741b69de 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,8 +1,8 @@
-include { BEAGLE5_BEAGLE } from '../../../modules/nf-core/beagle5/beagle'
-include { PLINK2_VCF } from '../../../modules/nf-core/plink2/vcf/main'
-include { PLINK2_PCA } from '../../../modules/nf-core/plink2/pca/main'
-include { CUSTOM_PCACLUSTERING } from '../../../modules/nf-core/custom/pcaclustering/main'
-include { CUSTOM_CLUSTERMETRICS } from '../../../modules/nf-core/custom/clustermetrics/main'
+include { BEAGLE5_BEAGLE              } from '../../../modules/nf-core/beagle5/beagle'
+include { PLINK2_VCF                  } from '../../../modules/nf-core/plink2/vcf/main'
+include { PLINK2_PCA                  } from '../../../modules/nf-core/plink2/pca/main'
+include { CUSTOM_PCACLUSTERING        } from '../../../modules/nf-core/custom/pcaclustering/main'
+include { CUSTOM_CLUSTERMETRICS       } from '../../../modules/nf-core/custom/clustermetrics/main'
 include { CUSTOM_CLUSTERVISUALIZATION } from '../../../modules/nf-core/custom/clustervisualization/main'
 
 workflow SNPCLUSTERING {

From 6dd867d821e71744fba49fb64c6f5365a2f70a38 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Thu, 9 Jul 2026 14:57:32 +0200
Subject: [PATCH 06/34] Refactor process definitions in nextflow.config

---
 .../snpclustering/tests/nextflow.config        | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 9fa98d971a85..a3e8e398d109 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -8,33 +8,27 @@ params {
 }
 
 process {
-    withName: 'BEAGLE5_BEAGLE' {
-        
+    withName: 'BEAGLE5_BEAGLE' {        
         ext.when = false
     }
 
-    withName: 'PLINK2_VCF' {
-        
+    withName: 'PLINK2_VCF' {        
         ext.when = false
     }
 
-    withName: 'PLINK2_PCA' {
-        
+    withName: 'PLINK2_PCA' {        
         ext.when = false
     }
 
-    withName: 'CUSTOM_PCACLUSTERING' {
-        
+    withName: 'CUSTOM_PCACLUSTERING' {        
         ext.when = false
     }
 
-    withName: 'CUSTOM_CLUSTERMETRICS' {
-        
+    withName: 'CUSTOM_CLUSTERMETRICS' {        
         ext.when = false
     }
 
-    withName: 'CUSTOM_CLUSTERVISUALIZATION' {
-        
+    withName: 'CUSTOM_CLUSTERVISUALIZATION' {        
         ext.when = false
     }
 }

From 22e4b021ad1c71f1529e2cc2f120460aa5352b09 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Tue, 21 Jul 2026 14:15:36 +0200
Subject: [PATCH 07/34] Clean up comments in main.nf

Removed comments about optional files and signature inference.
---
 subworkflows/nf-core/snpclustering/main.nf | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index c2cf741b69de..e8d12f37a23c 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -26,9 +26,6 @@ workflow SNPCLUSTERING {
      * Build BEAGLE input tuple:
      * tuple val(meta), path(vcf), path(vcf_index), path(refpanel), path(refpanel_index),
      *       path(genmap), path(exclsamples), path(exclmarkers), val(region)
-     *
-     * For now, refpanel/genmap/exclusion files are optional and passed as empty lists
-     * when not provided by the caller.
      */
     ch_beagle_input = vcf_ch.map { meta, vcf, vcf_index ->
         tuple(
@@ -74,7 +71,6 @@ workflow SNPCLUSTERING {
 
     /*
      * PCA clustering
-     * Signature inferred from your successful wiring so far:
      * CUSTOM_PCACLUSTERING(tsv, algorithm, n_clusters, dbscan_eps, dbscan_min_samples)
      */
     CUSTOM_PCACLUSTERING(

From bb78b2283dc99f2a099b9a947675e96f84845caf Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Mon, 17 Aug 2026 19:12:03 +0200
Subject: [PATCH 08/34] WIP: fix versions emit in custom modules

---
 .../custom/clustermetrics/environment.yml     |  12 ++
 modules/nf-core/custom/clustermetrics/main.nf |  46 ++++++
 .../nf-core/custom/clustermetrics/meta.yml    |  96 ++++++++++++
 .../templates/cluster_metrics.py              | 143 ++++++++++++++++++
 .../custom/clustermetrics/tests/main.nf.test  |  70 +++++++++
 .../clustermetrics/tests/main.nf.test.snap    | 104 +++++++++++++
 .../clustervisualization/environment.yml      |  14 ++
 .../custom/clustervisualization/main.nf       |  45 ++++++
 .../custom/clustervisualization/meta.yml      | 101 +++++++++++++
 .../templates/cluster_viz.py                  | 129 ++++++++++++++++
 .../clustervisualization/tests/main.nf.test   |  60 ++++++++
 .../tests/main.nf.test.snap                   |  95 ++++++++++++
 .../custom/pcaclustering/environment.yml      |  11 ++
 modules/nf-core/custom/pcaclustering/main.nf  |  42 +++++
 modules/nf-core/custom/pcaclustering/meta.yml |  81 ++++++++++
 .../pcaclustering/templates/clustering.py     |  81 ++++++++++
 .../custom/pcaclustering/tests/main.nf.test   |  85 +++++++++++
 .../pcaclustering/tests/main.nf.test.snap     | 106 +++++++++++++
 subworkflows/nf-core/snpclustering/main.nf    |  30 ++--
 .../snpclustering/tests/nextflow.config       |  22 +--
 20 files changed, 1346 insertions(+), 27 deletions(-)
 create mode 100644 modules/nf-core/custom/clustermetrics/environment.yml
 create mode 100644 modules/nf-core/custom/clustermetrics/main.nf
 create mode 100644 modules/nf-core/custom/clustermetrics/meta.yml
 create mode 100644 modules/nf-core/custom/clustermetrics/templates/cluster_metrics.py
 create mode 100644 modules/nf-core/custom/clustermetrics/tests/main.nf.test
 create mode 100644 modules/nf-core/custom/clustermetrics/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/custom/clustervisualization/environment.yml
 create mode 100644 modules/nf-core/custom/clustervisualization/main.nf
 create mode 100644 modules/nf-core/custom/clustervisualization/meta.yml
 create mode 100644 modules/nf-core/custom/clustervisualization/templates/cluster_viz.py
 create mode 100644 modules/nf-core/custom/clustervisualization/tests/main.nf.test
 create mode 100644 modules/nf-core/custom/clustervisualization/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/custom/pcaclustering/environment.yml
 create mode 100644 modules/nf-core/custom/pcaclustering/main.nf
 create mode 100644 modules/nf-core/custom/pcaclustering/meta.yml
 create mode 100644 modules/nf-core/custom/pcaclustering/templates/clustering.py
 create mode 100644 modules/nf-core/custom/pcaclustering/tests/main.nf.test
 create mode 100644 modules/nf-core/custom/pcaclustering/tests/main.nf.test.snap

diff --git a/modules/nf-core/custom/clustermetrics/environment.yml b/modules/nf-core/custom/clustermetrics/environment.yml
new file mode 100644
index 000000000000..8d7b4bbbb690
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/environment.yml
@@ -0,0 +1,12 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::matplotlib=3.10.9
+  - conda-forge::numpy=2.4.4
+  - conda-forge::pandas=3.0.3
+  - conda-forge::python=3.12.13
+  - conda-forge::pyyaml=6.0.3
+  - conda-forge::scikit-learn=1.8.0
diff --git a/modules/nf-core/custom/clustermetrics/main.nf b/modules/nf-core/custom/clustermetrics/main.nf
new file mode 100644
index 000000000000..de01489438ad
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/main.nf
@@ -0,0 +1,46 @@
+process CUSTOM_CLUSTERMETRICS {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/25/25129a5258522a434c386b800d3e2e3e6dc72d8a1171b7b10f21df3488526795/data' :
+        'community.wave.seqera.io/library/matplotlib_numpy_pandas_python_pruned:169e228afc7d3686' }"
+
+    input:
+    tuple val(meta), path(features), path(clusters)
+
+    output:
+    tuple val(meta), path("*.metrics.tsv")  , emit: metrics
+    tuple val(meta), path("*.k_sweep.csv")  , emit: k_sweep
+    tuple val(meta), path("*.selected.json"), emit: selected
+    tuple val(meta), path("*.png")          , emit: plots, optional: true
+    path "versions.yml"                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'cluster_metrics.py'
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.metrics.tsv
+    touch ${prefix}.k_sweep.csv
+    touch ${prefix}.selected.json
+    touch ${prefix}.elbow.png
+    touch ${prefix}.silhouette.png
+    touch ${prefix}.davies_bouldin.png
+    touch ${prefix}.calinski_harabasz.png
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python3 --version | sed 's/Python //')
+        matplotlib: \$(python3 -c "from importlib.metadata import version; print(version('matplotlib'))")
+        numpy: \$(python3 -c "from importlib.metadata import version; print(version('numpy'))")
+        pandas: \$(python3 -c "from importlib.metadata import version; print(version('pandas'))")
+        scikit-learn: \$(python3 -c "from importlib.metadata import version; print(version('scikit-learn'))")
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/custom/clustermetrics/meta.yml b/modules/nf-core/custom/clustermetrics/meta.yml
new file mode 100644
index 000000000000..e364f55b6f75
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/meta.yml
@@ -0,0 +1,96 @@
+name: "CUSTOM_CLUSTERMETRICS"
+description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz,
+  Davies-Bouldin) and performs k-sweep analysis"
+keywords:
+  - clustering
+  - metrics
+  - silhouette
+  - calinski-harabasz
+  - davies-bouldin
+  - evaluation
+tools:
+  - "scikit-learn":
+      description: "Machine learning library for clustering metrics"
+      homepage: "https://scikit-learn.org/"
+      documentation: "https://scikit-learn.org/stable/modules/clustering.html"
+      licence:
+        - "BSD-3-Clause"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - features:
+        type: file
+        description: |
+          Tab-separated feature matrix with a `sample_id` column and one
+          column per numeric feature (e.g. PCA scores).
+        pattern: "*.tsv"
+        ontologies:
+          - edam: http://edamontology.org/format_3475
+    - clusters:
+        type: file
+        description: |
+          Comma-separated cluster assignments with `sample_id` and integer
+          `cluster` columns. Label -1 is treated as DBSCAN noise.
+        pattern: "*.csv"
+        ontologies:
+          - edam: http://edamontology.org/format_3752
+output:
+  metrics:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.metrics.tsv":
+          type: file
+          description: TSV with selected cluster quality metrics
+          pattern: "*.metrics.tsv"
+          ontologies:
+            - edam: http://edamontology.org/format_3475
+  k_sweep:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.k_sweep.csv":
+          type: file
+          description: CSV with metrics for different values of k
+          pattern: "*.k_sweep.csv"
+          ontologies:
+            - edam: http://edamontology.org/format_3752
+  selected:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.selected.json":
+          type: file
+          description: JSON with the selected/best metrics
+          pattern: "*.selected.json"
+          ontologies:
+            - edam: http://edamontology.org/format_3464
+  plots:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.png":
+          type: file
+          description: Optional PNG plots (elbow, silhouette, etc.)
+          pattern: "*.png"
+          ontologies: []
+  versions:
+    - "versions.yml":
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750
+topics:
+  versions:
+    - versions.yml:
+        type: string
+        description: The name of the process
+authors:
+  - "@dbaku42"
+maintainers:
+  - "@dbaku42"
diff --git a/modules/nf-core/custom/clustermetrics/templates/cluster_metrics.py b/modules/nf-core/custom/clustermetrics/templates/cluster_metrics.py
new file mode 100644
index 000000000000..fd8856fd41cf
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/templates/cluster_metrics.py
@@ -0,0 +1,143 @@
+#!/usr/bin/env python3
+
+# Copyright (c) nf-core
+# This software is licensed under the MIT License.
+# SPDX-License-Identifier: MIT
+
+import argparse
+import json
+import platform
+import shlex
+
+import matplotlib
+
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import pandas as pd
+import sklearn
+import yaml
+from sklearn.cluster import KMeans
+from sklearn.metrics import (
+    calinski_harabasz_score,
+    davies_bouldin_score,
+    silhouette_score,
+)
+
+
+def load_features(path):
+    """Read a TSV of `sample_id` + numeric feature columns, indexed by sample_id."""
+    df = pd.read_csv(path, sep="\\t")
+    if "sample_id" not in df.columns:
+        raise ValueError(f"features file must have a 'sample_id' column. Found: {list(df.columns)}")
+    df["sample_id"] = df["sample_id"].astype(str)
+    return df.set_index("sample_id").apply(pd.to_numeric, errors="coerce").fillna(0.0)
+
+
+def load_clusters(path):
+    """Read a CSV of `sample_id` + `cluster`, returning a Series of int labels."""
+    df = pd.read_csv(path)
+    if "sample_id" not in df.columns or "cluster" not in df.columns:
+        raise ValueError(f"clusters file must have 'sample_id' and 'cluster' columns. Found: {list(df.columns)}")
+    df["sample_id"] = df["sample_id"].astype(str)
+    return df.set_index("sample_id")["cluster"].astype(int)
+
+
+def cluster_quality(x, labels):
+    """Silhouette / Calinski-Harabasz / Davies-Bouldin for given (x, labels).
+
+    Treats label -1 as DBSCAN noise and excludes those points. Returns None
+    for each score when fewer than 2 clusters of more than one point remain.
+    """
+    mask = labels != -1
+    x, labels = x[mask], labels[mask]
+    n = len(set(labels))
+    valid = 2 <= n < len(x)
+    return {
+        "silhouette": float(silhouette_score(x, labels)) if valid else None,
+        "calinski_harabasz": float(calinski_harabasz_score(x, labels)) if valid else None,
+        "davies_bouldin": float(davies_bouldin_score(x, labels)) if valid else None,
+    }
+
+
+def plot_curve(sweep_df, metric, title, ylabel, out_png):
+    plt.figure(figsize=(7, 4.5))
+    vals = sweep_df[metric].dropna()
+    ks = sweep_df.loc[vals.index, "k"]
+    plt.plot(ks, vals, marker="o")
+    plt.xticks(sweep_df["k"].tolist())
+    plt.title(title)
+    plt.xlabel("k")
+    plt.ylabel(ylabel)
+    plt.tight_layout()
+    plt.savefig(out_png, dpi=200)
+    plt.close()
+
+
+def main():
+    features = "$features"
+    clusters_path = "$clusters"
+    prefix = "${task.ext.prefix ?: meta.id}"
+
+    # Optional configuration via task.ext.args (nf-core convention).
+    raw_args = "$task.ext.args"
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--k-min", type=int, default=2)
+    parser.add_argument("--k-max", type=int, default=12)
+    opts = parser.parse_args(shlex.split(raw_args) if raw_args and raw_args != "null" else [])
+
+    joined = load_features(features).join(load_clusters(clusters_path), how="inner")
+    if len(joined) < 2:
+        raise ValueError(f"Need at least 2 samples with matching sample_id in both inputs. Got {len(joined)}.")
+
+    labels = joined["cluster"].values
+    x = joined.drop(columns=["cluster"]).to_numpy(dtype=float)
+
+    # Quality metrics on the supplied labels.
+    selected = {"n_clusters": len(set(labels) - {-1}), **cluster_quality(x, labels)}
+    pd.DataFrame([selected]).to_csv(f"{prefix}.metrics.tsv", sep="\\t", index=False)
+    with open(f"{prefix}.selected.json", "w") as fh:
+        json.dump(selected, fh, indent=2)
+
+    # KMeans k-sweep for downstream comparison.
+    rows = []
+    for k in range(opts.k_min, min(opts.k_max, len(x)) + 1):
+        model = KMeans(n_clusters=k, n_init=10, random_state=42).fit(x)
+        rows.append({"k": k, "inertia": float(model.inertia_), **cluster_quality(x, model.labels_)})
+
+    sweep_df = pd.DataFrame(rows)
+    sweep_df.to_csv(f"{prefix}.k_sweep.csv", index=False, float_format="%.10g")
+
+    if not sweep_df.empty:
+        plot_curve(sweep_df, "inertia", "Elbow method (KMeans inertia)", "inertia", f"{prefix}.elbow.png")
+        plot_curve(
+            sweep_df, "silhouette", "Silhouette score (higher is better)", "silhouette", f"{prefix}.silhouette.png"
+        )
+        plot_curve(
+            sweep_df,
+            "davies_bouldin",
+            "Davies-Bouldin index (lower is better)",
+            "davies_bouldin",
+            f"{prefix}.davies_bouldin.png",
+        )
+        plot_curve(
+            sweep_df,
+            "calinski_harabasz",
+            "Calinski-Harabasz index (higher is better)",
+            "calinski_harabasz",
+            f"{prefix}.calinski_harabasz.png",
+        )
+
+    versions = {
+        "${task.process}": {
+            "python": platform.python_version(),
+            "pandas": pd.__version__,
+            "scikit-learn": sklearn.__version__,
+            "matplotlib": matplotlib.__version__,
+        }
+    }
+    with open("versions.yml", "w") as fh:
+        yaml.dump(versions, fh, default_flow_style=False, sort_keys=False)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/modules/nf-core/custom/clustermetrics/tests/main.nf.test b/modules/nf-core/custom/clustermetrics/tests/main.nf.test
new file mode 100644
index 000000000000..d5a42e682198
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/tests/main.nf.test
@@ -0,0 +1,70 @@
+nextflow_process {
+
+    name "Test Process CUSTOM_CLUSTERMETRICS"
+    script "../main.nf"
+    process "CUSTOM_CLUSTERMETRICS"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "custom"
+    tag "custom/clustermetrics"
+
+    test("clustermetrics - features and clusters") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_clusters.csv", checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.metrics,
+                    process.out.k_sweep,
+                    process.out.selected,
+                    process.out.versions,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+    }
+
+    test("clustermetrics - features and clusters - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_clusters.csv", checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.metrics,
+                    process.out.k_sweep,
+                    process.out.selected,
+                    process.out.plots,
+                    process.out.versions,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/custom/clustermetrics/tests/main.nf.test.snap b/modules/nf-core/custom/clustermetrics/tests/main.nf.test.snap
new file mode 100644
index 000000000000..0ec0df908bc5
--- /dev/null
+++ b/modules/nf-core/custom/clustermetrics/tests/main.nf.test.snap
@@ -0,0 +1,104 @@
+{
+    "clustermetrics - features and clusters": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.metrics.tsv:md5,15c36eab43e480e0311c4bcc3d511477"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.k_sweep.csv:md5,98635ea739c5e136ced833916ae5d931"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.selected.json:md5,d1d1b3788b7a111f38bf3b27d4bb1ab4"
+                ]
+            ],
+            [
+                "versions.yml:md5,602aa5dfe6c0b807d758c4f5cf3fc5e4"
+            ],
+            {
+                "CUSTOM_CLUSTERMETRICS": {
+                    "python": "3.12.13",
+                    "pandas": "3.0.3",
+                    "scikit-learn": "1.8.0",
+                    "matplotlib": "3.10.9"
+                }
+            }
+        ],
+        "timestamp": "2026-05-19T14:11:28.630001071",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    },
+    "clustermetrics - features and clusters - stub": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.metrics.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.k_sweep.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.selected.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    [
+                        "test.calinski_harabasz.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "test.davies_bouldin.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "test.elbow.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                        "test.silhouette.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ]
+            ],
+            [
+                "versions.yml:md5,90240f0a22302d1727455b6be6e96abb"
+            ],
+            {
+                "CUSTOM_CLUSTERMETRICS": {
+                    "python": "3.12.13",
+                    "matplotlib": "3.10.9",
+                    "numpy": "2.4.4",
+                    "pandas": "3.0.3",
+                    "scikit-learn": "1.8.0"
+                }
+            }
+        ],
+        "timestamp": "2026-05-19T14:11:36.600888057",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/custom/clustervisualization/environment.yml b/modules/nf-core/custom/clustervisualization/environment.yml
new file mode 100644
index 000000000000..befadae8f312
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/environment.yml
@@ -0,0 +1,14 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::matplotlib=3.10.9
+  - conda-forge::numpy=2.4.4
+  - conda-forge::pandas=3.0.3
+  - conda-forge::python=3.12.13
+  - conda-forge::pyyaml=6.0.3
+  - conda-forge::scikit-learn=1.8.0
+  - conda-forge::seaborn=0.13.2
+  - conda-forge::umap-learn=0.5.12
diff --git a/modules/nf-core/custom/clustervisualization/main.nf b/modules/nf-core/custom/clustervisualization/main.nf
new file mode 100644
index 000000000000..0b1346f20de4
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/main.nf
@@ -0,0 +1,45 @@
+process CUSTOM_CLUSTERVISUALIZATION {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/64/64297e13d9d4f05ce543656e943a023735e7cb252d7534ccc9134d8b40423083/data' :
+        'community.wave.seqera.io/library/matplotlib_numpy_pandas_python_pruned:826e4ab1361ff931' }"
+
+    input:
+    tuple val(meta), path(features), path(clusters)
+
+    output:
+    tuple val(meta), path("*.umap.tsv"), emit: umap_tsv
+    tuple val(meta), path("*.tsne.tsv"), emit: tsne_tsv
+    tuple val(meta), path("*.umap.png"), emit: umap_png, optional: true
+    tuple val(meta), path("*.tsne.png"), emit: tsne_png, optional: true
+    path "versions.yml"                , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'cluster_viz.py'
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.umap.tsv
+    touch ${prefix}.tsne.tsv
+    touch ${prefix}.umap.png
+    touch ${prefix}.tsne.png
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python3 --version | sed 's/Python //')
+        matplotlib: \$(python3 -c "from importlib.metadata import version; print(version('matplotlib'))")
+        numpy: \$(python3 -c "from importlib.metadata import version; print(version('numpy'))")
+        pandas: \$(python3 -c "from importlib.metadata import version; print(version('pandas'))")
+        scikit-learn: \$(python3 -c "from importlib.metadata import version; print(version('scikit-learn'))")
+        seaborn: \$(python3 -c "from importlib.metadata import version; print(version('seaborn'))")
+        umap-learn: \$(python3 -c "from importlib.metadata import version; print(version('umap-learn'))")
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/custom/clustervisualization/meta.yml b/modules/nf-core/custom/clustervisualization/meta.yml
new file mode 100644
index 000000000000..62bed07814e5
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/meta.yml
@@ -0,0 +1,101 @@
+name: "CUSTOM_CLUSTERVISUALIZATION"
+description: "Generates UMAP and t-SNE visualizations colored by cluster"
+keywords:
+  - clustering
+  - visualization
+  - pca
+  - umap
+  - tsne
+  - dimension-reduction
+tools:
+  - scikit-learn:
+      description: "Machine learning library for dimension reduction (PCA, t-SNE)"
+      homepage: "https://scikit-learn.org/"
+      documentation: "https://scikit-learn.org/stable/modules/clustering.html"
+      licence:
+        - "BSD-3-Clause"
+      identifier: ""
+  - umap-learn:
+      description: "Uniform Manifold Approximation and Projection for dimension reduction"
+      homepage: "https://umap-learn.readthedocs.io/"
+      documentation: "https://umap-learn.readthedocs.io/en/latest/"
+      licence:
+        - "BSD-3-Clause"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: "Groovy Map containing sample information"
+    - features:
+        type: file
+        description: |
+          Tab-separated feature matrix with a `sample_id` column and one
+          column per numeric feature (e.g. PCA scores).
+        pattern: "*.tsv"
+        ontologies:
+          - edam: http://edamontology.org/format_3475
+    - clusters:
+        type: file
+        description: |
+          Comma-separated cluster assignments with `sample_id` and integer
+          `cluster` columns. Label -1 is treated as DBSCAN noise.
+        pattern: "*.csv"
+        ontologies:
+          - edam: http://edamontology.org/format_3752
+output:
+  umap_tsv:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample information"
+      - "*.umap.tsv":
+          type: file
+          description: "UMAP coordinates per sample"
+          pattern: "*.umap.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/operation_2432"
+            - edam: http://edamontology.org/format_3475
+  tsne_tsv:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample information"
+      - "*.tsne.tsv":
+          type: file
+          description: "t-SNE coordinates per sample"
+          pattern: "*.tsne.tsv"
+          ontologies:
+            - edam: "http://edamontology.org/operation_2432"
+            - edam: http://edamontology.org/format_3475
+  umap_png:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample information"
+      - "*.umap.png":
+          type: file
+          description: "UMAP visualization coloured by cluster"
+          pattern: "*.umap.png"
+          ontologies: []
+  tsne_png:
+    - - meta:
+          type: map
+          description: "Groovy Map containing sample information"
+      - "*.tsne.png":
+          type: file
+          description: "t-SNE visualization coloured by cluster"
+          pattern: "*.tsne.png"
+          ontologies: []
+  versions:
+    - versions.yml:
+        type: file
+        description: "Software versions used in the module"
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750
+topics:
+  versions:
+    - versions.yml:
+        type: string
+        description: The name of the process
+authors:
+  - "@dbaku42"
+maintainers:
+  - "@dbaku42"
diff --git a/modules/nf-core/custom/clustervisualization/templates/cluster_viz.py b/modules/nf-core/custom/clustervisualization/templates/cluster_viz.py
new file mode 100644
index 000000000000..6f6a60d5ac37
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/templates/cluster_viz.py
@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+
+# Copyright (c) nf-core
+# This software is licensed under the MIT License.
+# SPDX-License-Identifier: MIT
+
+import argparse
+import os
+import shlex
+
+# numba (UMAP) and matplotlib write caches; redirect to /tmp so the script works
+# inside read-only container filesystems.
+os.environ.setdefault("NUMBA_CACHE_DIR", "/tmp")
+os.environ.setdefault("MPLCONFIGDIR", "/tmp")
+
+import platform
+
+import matplotlib
+
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import sklearn
+import umap
+import yaml
+from sklearn.manifold import TSNE
+
+
+def load_features(path):
+    """Read a TSV of `sample_id` + numeric feature columns, indexed by sample_id."""
+    df = pd.read_csv(path, sep="\\t")
+    if "sample_id" not in df.columns:
+        raise ValueError(f"features file must have a 'sample_id' column. Found: {list(df.columns)}")
+    df["sample_id"] = df["sample_id"].astype(str)
+    return df.set_index("sample_id").apply(pd.to_numeric, errors="coerce").fillna(0.0)
+
+
+def load_clusters(path):
+    """Read a CSV of `sample_id` + `cluster`, returning a Series of int labels."""
+    df = pd.read_csv(path)
+    if "sample_id" not in df.columns or "cluster" not in df.columns:
+        raise ValueError(f"clusters file must have 'sample_id' and 'cluster' columns. Found: {list(df.columns)}")
+    df["sample_id"] = df["sample_id"].astype(str)
+    return df.set_index("sample_id")["cluster"].astype(int)
+
+
+def embed(x, method, umap_neighbors, tsne_perplexity):
+    """Project x to 2D using UMAP or t-SNE.
+
+    n_neighbors / perplexity are clamped against sample count so tiny test
+    inputs (where the user-specified defaults exceed n_samples) still run.
+    """
+    n = len(x)
+    if method == "umap":
+        reducer = umap.UMAP(n_components=2, n_neighbors=min(umap_neighbors, max(2, n - 1)), random_state=42)
+    elif method == "tsne":
+        reducer = TSNE(n_components=2, perplexity=min(tsne_perplexity, max(2, n - 1)), random_state=42)
+    else:
+        raise ValueError(f"Unknown method '{method}' (expected 'umap' or 'tsne')")
+    return reducer.fit_transform(x)
+
+
+def plot_embedding(emb, labels, method, out_png):
+    plt.figure(figsize=(8, 6))
+    palette = sns.color_palette("tab10", n_colors=max(1, len(np.unique(labels))))
+    sns.scatterplot(
+        x=emb[:, 0],
+        y=emb[:, 1],
+        hue=labels.astype(str),
+        palette=palette,
+        alpha=0.8,
+        s=60,
+        edgecolor="k",
+        linewidth=0.3,
+    )
+    plt.title(f"{method.upper()} projection colored by cluster")
+    plt.xlabel(f"{method.upper()} 1")
+    plt.ylabel(f"{method.upper()} 2")
+    plt.legend(title="Cluster", bbox_to_anchor=(1.05, 1), loc="upper left")
+    plt.tight_layout()
+    plt.savefig(out_png, dpi=200, bbox_inches="tight")
+    plt.close()
+
+
+def main():
+    features = "$features"
+    clusters_path = "$clusters"
+    prefix = "${task.ext.prefix ?: meta.id}"
+
+    # Optional configuration via task.ext.args (nf-core convention).
+    raw_args = "$task.ext.args"
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--umap-neighbors", type=int, default=15)
+    parser.add_argument("--tsne-perplexity", type=int, default=30)
+    opts = parser.parse_args(shlex.split(raw_args) if raw_args and raw_args != "null" else [])
+
+    joined = load_features(features).join(load_clusters(clusters_path), how="inner")
+    if len(joined) < 2:
+        raise ValueError(f"Need at least 2 samples with matching sample_id in both inputs. Got {len(joined)}.")
+
+    labels = joined["cluster"].values
+    x = joined.drop(columns=["cluster"]).to_numpy(dtype=float)
+    sample_ids = joined.index.to_numpy()
+
+    for method in ("umap", "tsne"):
+        emb = embed(x, method, opts.umap_neighbors, opts.tsne_perplexity)
+        pd.DataFrame({"sample_id": sample_ids, "Dim1": emb[:, 0], "Dim2": emb[:, 1], "cluster": labels}).to_csv(
+            f"{prefix}.{method}.tsv", sep="\\t", index=False
+        )
+        plot_embedding(emb, labels, method, f"{prefix}.{method}.png")
+
+    versions = {
+        "${task.process}": {
+            "python": platform.python_version(),
+            "pandas": pd.__version__,
+            "matplotlib": matplotlib.__version__,
+            "seaborn": sns.__version__,
+            "umap-learn": umap.__version__,
+            "scikit-learn": sklearn.__version__,
+        }
+    }
+    with open("versions.yml", "w") as fh:
+        yaml.dump(versions, fh, default_flow_style=False, sort_keys=False)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/modules/nf-core/custom/clustervisualization/tests/main.nf.test b/modules/nf-core/custom/clustervisualization/tests/main.nf.test
new file mode 100644
index 000000000000..0334f0d09434
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/tests/main.nf.test
@@ -0,0 +1,60 @@
+nextflow_process {
+    name "Test Process CUSTOM_CLUSTERVISUALIZATION"
+    script "../main.nf"
+    process "CUSTOM_CLUSTERVISUALIZATION"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "custom"
+    tag "custom/clustervisualization"
+    test("clustervisualization - features and clusters") {
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_clusters.csv", checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.umap_tsv,
+                    process.out.tsne_tsv,
+                    process.out.versions,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+    }
+    test("clustervisualization - features and clusters - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true),
+                    file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_clusters.csv", checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.umap_tsv,
+                    process.out.tsne_tsv,
+                    process.out.umap_png,
+                    process.out.tsne_png,
+                    process.out.versions,
+                    path(process.out.versions[0]).yaml
+                ).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/custom/clustervisualization/tests/main.nf.test.snap b/modules/nf-core/custom/clustervisualization/tests/main.nf.test.snap
new file mode 100644
index 000000000000..f180dfa8b993
--- /dev/null
+++ b/modules/nf-core/custom/clustervisualization/tests/main.nf.test.snap
@@ -0,0 +1,95 @@
+{
+    "clustervisualization - features and clusters - stub": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.umap.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.tsne.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.umap.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.tsne.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                "versions.yml:md5,76a5042b303be74c24dee681187d6a1f"
+            ],
+            {
+                "CUSTOM_CLUSTERVISUALIZATION": {
+                    "python": "3.12.13",
+                    "matplotlib": "3.10.9",
+                    "numpy": "2.4.4",
+                    "pandas": "3.0.3",
+                    "scikit-learn": "1.8.0",
+                    "seaborn": "0.13.2",
+                    "umap-learn": "0.5.12"
+                }
+            }
+        ],
+        "timestamp": "2026-05-19T16:36:24.854839682",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.09.0"
+        }
+    },
+    "clustervisualization - features and clusters": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.umap.tsv:md5,d338c1ef0e979dbf653e21c3417e975e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.tsne.tsv:md5,eb00f27d82530f665552b158e8e3c8ff"
+                ]
+            ],
+            [
+                "versions.yml:md5,a00bfbb9b1b4145177ec0e8a7406caf9"
+            ],
+            {
+                "CUSTOM_CLUSTERVISUALIZATION": {
+                    "python": "3.12.13",
+                    "pandas": "3.0.3",
+                    "matplotlib": "3.10.9",
+                    "seaborn": "0.13.2",
+                    "umap-learn": "0.5.12",
+                    "scikit-learn": "1.8.0"
+                }
+            }
+        ],
+        "timestamp": "2026-05-19T17:08:32.73077357",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.10.2"
+        }
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/custom/pcaclustering/environment.yml b/modules/nf-core/custom/pcaclustering/environment.yml
new file mode 100644
index 000000000000..1fda7f0e4c10
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/environment.yml
@@ -0,0 +1,11 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - conda-forge::numpy=2.4.4
+  - conda-forge::pandas=3.0.3
+  - conda-forge::python=3.12.13
+  - conda-forge::pyyaml=6.0.3
+  - conda-forge::scikit-learn=1.8.0
diff --git a/modules/nf-core/custom/pcaclustering/main.nf b/modules/nf-core/custom/pcaclustering/main.nf
new file mode 100644
index 000000000000..4a4be41f876b
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/main.nf
@@ -0,0 +1,42 @@
+process CUSTOM_PCACLUSTERING {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine in ['singularity', 'apptainer'] && !task.ext.singularity_pull_docker_container ?
+        'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/a3/a37807bdaf3edad30a2b212962b6af381bc10381a80c40efb2bb07f6ee43032f/data' :
+        'community.wave.seqera.io/library/numpy_pandas_python_pyyaml_scikit-learn:c500ceb82d3d7606' }"
+
+    input:
+    tuple val(meta), path(features)
+    val algorithm
+    val n_clusters
+    val dbscan_eps
+    val dbscan_min_samples
+
+    output:
+    tuple val(meta), path("*.clusters.csv")        , emit: clusters
+    tuple val(meta), path("*.clustering_info.json"), emit: info
+    path "versions.yml"                            , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'clustering.py'
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.clusters.csv
+    touch ${prefix}.clustering_info.json
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python3 --version | sed 's/Python //')
+        numpy: \$(python3 -c "from importlib.metadata import version; print(version('numpy'))")
+        pandas: \$(python3 -c "from importlib.metadata import version; print(version('pandas'))")
+        scikit-learn: \$(python3 -c "from importlib.metadata import version; print(version('scikit-learn'))")
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/custom/pcaclustering/meta.yml b/modules/nf-core/custom/pcaclustering/meta.yml
new file mode 100644
index 000000000000..72a1cefbaa11
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/meta.yml
@@ -0,0 +1,81 @@
+name: "CUSTOM_PCACLUSTERING"
+description: "Performs KMeans or DBSCAN clustering on a sample-by-feature numeric
+  matrix (e.g. principal components, embeddings)"
+keywords:
+  - clustering
+  - kmeans
+  - dbscan
+  - pca
+  - embeddings
+tools:
+  - "scikit-learn":
+      description: "Machine learning library for clustering"
+      homepage: "https://scikit-learn.org/"
+      documentation: "https://scikit-learn.org/stable/modules/clustering.html"
+      licence:
+        - "BSD-3-Clause"
+      identifier: ""
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - features:
+        type: file
+        description: |
+          Tab-separated file whose first column is sample IDs (any column
+          name) and remaining columns are numeric features (e.g. PLINK2 PCA
+          components with `FID` dropped, scikit-learn embeddings, etc.).
+        pattern: "*.{tsv,txt}"
+        ontologies:
+          - edam: http://edamontology.org/format_3475
+  - algorithm:
+      type: string
+      description: Clustering algorithm to use (kmeans or dbscan)
+  - n_clusters:
+      type: integer
+      description: Number of clusters for KMeans
+  - dbscan_eps:
+      type: float
+      description: Epsilon parameter for DBSCAN
+  - dbscan_min_samples:
+      type: integer
+      description: Minimum samples parameter for DBSCAN
+output:
+  clusters:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.clusters.csv":
+          type: file
+          description: CSV file with sample_id and assigned cluster
+          pattern: "*.clusters.csv"
+          ontologies:
+            - edam: http://edamontology.org/format_3752
+  info:
+    - - meta:
+          type: map
+          description: Groovy Map containing sample information
+      - "*.clustering_info.json":
+          type: file
+          description: JSON file with clustering parameters and statistics
+          pattern: "*.clustering_info.json"
+          ontologies:
+            - edam: http://edamontology.org/format_3464
+  versions:
+    - "versions.yml":
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750
+topics:
+  versions:
+    - versions.yml:
+        type: string
+        description: The name of the process
+authors:
+  - "@dbaku42"
+maintainers:
+  - "@dbaku42"
diff --git a/modules/nf-core/custom/pcaclustering/templates/clustering.py b/modules/nf-core/custom/pcaclustering/templates/clustering.py
new file mode 100644
index 000000000000..0a133a21557d
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/templates/clustering.py
@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+
+# Copyright (c) nf-core
+# This software is licensed under the MIT License.
+# SPDX-License-Identifier: MIT
+
+import json
+import platform
+
+import numpy as np
+import pandas as pd
+import sklearn
+import yaml
+from sklearn.cluster import DBSCAN, KMeans
+
+
+def load_features(path):
+    """Read a TSV where the first column is sample IDs and the remaining
+    columns are numeric features.
+
+    Returns (sample_ids: pd.Series, features: np.ndarray).
+    """
+    df = pd.read_csv(path, sep="\\t", dtype={0: str})
+    if df.shape[1] < 2:
+        raise ValueError(f"features file must have at least one feature column. Found columns: {list(df.columns)}")
+    sample_ids = df.iloc[:, 0]
+    features = df.iloc[:, 1:].to_numpy(dtype=float)
+    return sample_ids, features
+
+
+def main():
+    features_path = "$features"
+    algorithm = "$algorithm"
+    n_clusters = int("$n_clusters")
+    dbscan_eps = float("$dbscan_eps")
+    dbscan_min_samples = int("$dbscan_min_samples")
+    prefix = "${task.ext.prefix ?: meta.id}"
+
+    sample_ids, x = load_features(features_path)
+
+    if algorithm == "kmeans":
+        model = KMeans(n_clusters=n_clusters, init="random", n_init=100, random_state=42)
+        labels = model.fit_predict(x)
+        info = {
+            "algorithm": "kmeans",
+            "k": n_clusters,
+            "inertia": float(model.inertia_),
+        }
+    elif algorithm == "dbscan":
+        model = DBSCAN(eps=dbscan_eps, min_samples=dbscan_min_samples)
+        labels = model.fit_predict(x)
+        info = {
+            "algorithm": "dbscan",
+            "eps": dbscan_eps,
+            "min_samples": dbscan_min_samples,
+            "n_clusters_found": len(set(labels) - {-1}),
+            "n_noise": int(np.sum(labels == -1)),
+        }
+    else:
+        raise ValueError(f"Unknown algorithm '{algorithm}' (expected 'kmeans' or 'dbscan')")
+
+    info |= {"n_samples": int(x.shape[0]), "n_features": int(x.shape[1])}
+
+    pd.DataFrame({"sample_id": sample_ids, "cluster": labels}).to_csv(f"{prefix}.clusters.csv", index=False)
+    with open(f"{prefix}.clustering_info.json", "w") as fh:
+        json.dump(info, fh, indent=2)
+
+    versions = {
+        "${task.process}": {
+            "python": platform.python_version(),
+            "pandas": pd.__version__,
+            "numpy": np.__version__,
+            "scikit-learn": sklearn.__version__,
+        }
+    }
+    with open("versions.yml", "w") as fh:
+        yaml.dump(versions, fh, default_flow_style=False, sort_keys=False)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/modules/nf-core/custom/pcaclustering/tests/main.nf.test b/modules/nf-core/custom/pcaclustering/tests/main.nf.test
new file mode 100644
index 000000000000..2df4745f7679
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/tests/main.nf.test
@@ -0,0 +1,85 @@
+nextflow_process {
+    name "Test Process CUSTOM_PCACLUSTERING"
+    script "../main.nf"
+    process "CUSTOM_PCACLUSTERING"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "custom"
+    tag "custom/pcaclustering"
+
+    test("clustering - eigenvec") {
+        when {
+            process {
+                """
+                input[0] = [ [id:'test'], file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true) ]
+                input[1] = 'kmeans'
+                input[2] = 3
+                input[3] = 0.5
+                input[4] = 5
+                """
+            }
+        }
+        then {
+            // KMeans inertia varies by a few ULPs across CPU instruction sets
+            // (BLAS reduction order), so parse the JSON and round it for the
+            // snapshot. Production output keeps full precision.
+            def info_data = new groovy.json.JsonSlurper().parse(file(process.out.info[0][1]))
+            info_data.inertia = (info_data.inertia as Double).round(4)
+
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.clusters,
+                    info_data,
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+    test("clustering - eigenvec - dbscan") {
+        when {
+            process {
+                """
+                input[0] = [ [id:'test'], file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true) ]
+                input[1] = 'dbscan'
+                input[2] = 3
+                input[3] = 0.5
+                input[4] = 2
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.clusters,
+                    process.out.info,
+                    process.out.versions
+                ).match() }
+            )
+        }
+    }
+
+    test("clustering - eigenvec - stub") {
+        options "-stub"
+        when {
+            process {
+                """
+                input[0] = [ [id:'test'], file(params.modules_testdata_base_path + "genomics/homo_sapiens/popgen/clustering/test_features.tsv", checkIfExists: true) ]
+                input[1] = 'kmeans'
+                input[2] = 3
+                input[3] = 0.5
+                input[4] = 5
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/custom/pcaclustering/tests/main.nf.test.snap b/modules/nf-core/custom/pcaclustering/tests/main.nf.test.snap
new file mode 100644
index 000000000000..7e08b009bf70
--- /dev/null
+++ b/modules/nf-core/custom/pcaclustering/tests/main.nf.test.snap
@@ -0,0 +1,106 @@
+{
+    "clustering - eigenvec - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "2": [
+                    "versions.yml:md5,0464456de4c7d72da565bc36330bb1a8"
+                ],
+                "clusters": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "info": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,0464456de4c7d72da565bc36330bb1a8"
+                ]
+            }
+        ],
+        "timestamp": "2026-05-19T17:25:31.986165338",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.10.2"
+        }
+    },
+    "clustering - eigenvec": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clusters.csv:md5,cd4fbcba75a4ec9f809eb0f1c58d2f72"
+                ]
+            ],
+            {
+                "algorithm": "kmeans",
+                "k": 3,
+                "inertia": 8.6821,
+                "n_samples": 200,
+                "n_features": 10
+            },
+            [
+                "versions.yml:md5,18e52941377b816e6e2b9e1a6b971fe6"
+            ]
+        ],
+        "timestamp": "2026-05-19T17:25:21.968960876",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.10.2"
+        }
+    },
+    "clustering - eigenvec - dbscan": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clusters.csv:md5,92f56a552d32dce29af32327ab926a25"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clustering_info.json:md5,9e45308fc57961f23e547a1149ad0c26"
+                ]
+            ],
+            [
+                "versions.yml:md5,18e52941377b816e6e2b9e1a6b971fe6"
+            ]
+        ],
+        "timestamp": "2026-05-19T17:25:27.683788344",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "25.10.2"
+        }
+    }
+}
\ No newline at end of file
diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 221553311025..f23d4443365a 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,8 +1,8 @@
-include { BEAGLE5_BEAGLE } from '../../../modules/nf-core/beagle5/beagle/main'
-include { PLINK2_VCF } from '../../../modules/nf-core/plink2/vcf/main'
-include { PLINK2_PCA } from '../../../modules/nf-core/plink2/pca/main'
-include { CUSTOM_PCACLUSTERING } from '../../../modules/nf-core/custom/pcaclustering/main'
-include { CUSTOM_CLUSTERMETRICS } from '../../../modules/nf-core/custom/clustermetrics/main'
+include { BEAGLE5_BEAGLE              } from '../../../modules/nf-core/beagle5/beagle'
+include { PLINK2_VCF                  } from '../../../modules/nf-core/plink2/vcf/main'
+include { PLINK2_PCA                  } from '../../../modules/nf-core/plink2/pca/main'
+include { CUSTOM_PCACLUSTERING        } from '../../../modules/nf-core/custom/pcaclustering/main'
+include { CUSTOM_CLUSTERMETRICS       } from '../../../modules/nf-core/custom/clustermetrics/main'
 include { CUSTOM_CLUSTERVISUALIZATION } from '../../../modules/nf-core/custom/clustervisualization/main'
 
 workflow SNPCLUSTERING {
@@ -26,9 +26,6 @@ workflow SNPCLUSTERING {
      * Build BEAGLE input tuple:
      * tuple val(meta), path(vcf), path(vcf_index), path(refpanel), path(refpanel_index),
      *       path(genmap), path(exclsamples), path(exclmarkers), val(region)
-     *
-     * For now, refpanel/genmap/exclusion files are optional and passed as empty lists
-     * when not provided by the caller.
      */
     ch_beagle_input = vcf_ch.map { meta, vcf, vcf_index ->
         tuple(
@@ -74,7 +71,6 @@ workflow SNPCLUSTERING {
 
     /*
      * PCA clustering
-     * Signature inferred from your successful wiring so far:
      * CUSTOM_PCACLUSTERING(tsv, algorithm, n_clusters, dbscan_eps, dbscan_min_samples)
      */
     CUSTOM_PCACLUSTERING(
@@ -133,6 +129,7 @@ workflow SNPCLUSTERING {
 }
 
 process EIGENVEC_TO_TSV {
+
     tag "${meta.id}"
     label 'process_single'
 
@@ -145,8 +142,18 @@ process EIGENVEC_TO_TSV {
 
     script:
     """
-    awk 'NR==1 { sub(/^#/, ""); \$1 = ""; sub(/^\\t/, ""); sub(/^IID\\t/, "sample_id\\t"); print; next }
-    { \$1 = ""; sub(/^\\t/, ""); print }' OFS='\\t' ${eigenvec} > ${meta.id}.tsv
+    awk '
+    NR==1 {
+        sub(/^#/, "")
+        if (\$1 == "IID") {
+            \$1="sample_id"
+        }
+        print
+        next
+    }
+    {
+        print
+    }' OFS='\\t' ${eigenvec} > ${meta.id}.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -154,3 +161,4 @@ process EIGENVEC_TO_TSV {
     END_VERSIONS
     """
 }
+
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 99eba676d04a..a3e8e398d109 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -8,37 +8,27 @@ params {
 }
 
 process {
-    withName: 'BEAGLE5_BEAGLE' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'BEAGLE5_BEAGLE' {        
         ext.when = false
     }
 
-    withName: 'PLINK2_VCF' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'PLINK2_VCF' {        
         ext.when = false
     }
 
-    withName: 'PLINK2_PCA' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'PLINK2_PCA' {        
         ext.when = false
     }
 
-    withName: 'EIGENVEC_TO_TSV' {
-        ext.prefix = { "${meta.id}" }
-    }
-
-    withName: 'CUSTOM_PCACLUSTERING' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'CUSTOM_PCACLUSTERING' {        
         ext.when = false
     }
 
-    withName: 'CUSTOM_CLUSTERMETRICS' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'CUSTOM_CLUSTERMETRICS' {        
         ext.when = false
     }
 
-    withName: 'CUSTOM_CLUSTERVISUALIZATION' {
-        ext.prefix = { "${meta.id}" }
+    withName: 'CUSTOM_CLUSTERVISUALIZATION' {        
         ext.when = false
     }
 }

From a84585e425c3cd292a0cd4df03571fe38822afbe Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 19 Aug 2026 09:27:43 +0200
Subject: [PATCH 09/34] fix: adapt ch_versions.mix() to migrated topic-based
 emit names (plink2)

---
 subworkflows/nf-core/snpclustering/main.nf | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index f23d4443365a..62eabbf5c7f9 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -48,7 +48,7 @@ workflow SNPCLUSTERING {
      * Convert imputed VCF to PLINK2 pfiles
      */
     PLINK2_VCF(BEAGLE5_BEAGLE.out.vcf)
-    ch_versions = ch_versions.mix(PLINK2_VCF.out.versions)
+    ch_versions = ch_versions.mix(PLINK2_VCF.out.versions_plink2)
 
     /*
      * PLINK2_PCA expects:
@@ -62,7 +62,7 @@ workflow SNPCLUSTERING {
         }
 
     PLINK2_PCA(ch_plink_pca_input)
-    ch_versions = ch_versions.mix(PLINK2_PCA.out.versions)
+    ch_versions = ch_versions.mix(PLINK2_PCA.out.versions_plink2)
 
     /*
      * Convert .eigenvec to TSV for downstream clustering modules

From 4e37881c6b43ae44c24c0bd30f7293276743ae52 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 20 Aug 2026 16:23:44 +0200
Subject: [PATCH 10/34] test: regenerate snpclustering snapshots with real
 content, Root cause of empty snapshots: tests/nextflow.config had
 ext.when=false set on all main processes, skipping their execution entirely
 while workflow.success remained true. Removed that block and regenerated
 snapshots using --profile docker.

---
 .../snpclustering/tests/main.nf.test.snap     | 410 +++++++++++++++---
 .../snpclustering/tests/nextflow.config       |  36 +-
 2 files changed, 359 insertions(+), 87 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index f4d7988e57d5..7bb0440847d8 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -2,185 +2,483 @@
     "homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters": {
         "content": [
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clusters.csv"
+                ]
             ],
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clustering_info.json"
+                ]
             ],
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.metrics.tsv"
+                ]
             ],
             [
-                
+                [
+                    "SNPCLUSTERING:BEAGLE5_BEAGLE",
+                    "beagle",
+                    "5.5"
+                ],
+                [
+                    "SNPCLUSTERING:PLINK2_PCA",
+                    "plink2",
+                    "2.00a5.10LM"
+                ],
+                [
+                    "SNPCLUSTERING:PLINK2_VCF",
+                    "plink2",
+                    "2.00a2.3LM"
+                ],
+                "versions.yml:md5,088adb486c0aa9f234effd310576eaf7",
+                "versions.yml:md5,5e7ab136010cdcda51f91b12562b28c7",
+                "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
             ]
         ],
-        "timestamp": "2026-06-04T01:16:07.326033555",
+        "timestamp": "2026-08-20T16:08:17.636962775",
         "meta": {
             "nf-test": "0.9.5",
-            "nextflow": "25.09.0"
+            "nextflow": "26.04.6"
         }
     },
     "homo_sapiens - 1000GP.chr22.vcf.gz - dbscan": {
         "content": [
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clusters.csv"
+                ]
             ],
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.clustering_info.json"
+                ]
             ],
             [
-                
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test.metrics.tsv"
+                ]
             ],
             [
-                
+                [
+                    "SNPCLUSTERING:BEAGLE5_BEAGLE",
+                    "beagle",
+                    "5.5"
+                ],
+                [
+                    "SNPCLUSTERING:PLINK2_PCA",
+                    "plink2",
+                    "2.00a5.10LM"
+                ],
+                [
+                    "SNPCLUSTERING:PLINK2_VCF",
+                    "plink2",
+                    "2.00a2.3LM"
+                ],
+                "versions.yml:md5,088adb486c0aa9f234effd310576eaf7",
+                "versions.yml:md5,5e7ab136010cdcda51f91b12562b28c7",
+                "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
             ]
         ],
-        "timestamp": "2026-06-04T01:16:13.695098223",
+        "timestamp": "2026-08-20T16:08:55.94750336",
         "meta": {
             "nf-test": "0.9.5",
-            "nextflow": "25.09.0"
+            "nextflow": "26.04.6"
         }
     },
     "homo_sapiens - 1000GP.chr22.vcf.gz - dbscan - stub": {
         "content": [
             {
                 "beagle_log": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "cluster_info": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "clusters": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "evecfile": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenvec:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "evfile": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenval:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "imputed_vcf": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
                 ],
                 "k_sweep": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.k_sweep.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "metric_plots": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.calinski_harabasz.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.davies_bouldin.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.elbow.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.silhouette.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
                 ],
                 "metrics": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.metrics.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pca_log": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pgen": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pgen:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "psam": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.psam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pvar": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pvar:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "selected": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.selected.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsne_png": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsne_tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "umap_png": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "umap_tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "versions": [
-                    
+                    [
+                        "SNPCLUSTERING:BEAGLE5_BEAGLE",
+                        "beagle",
+                        "5.5"
+                    ],
+                    [
+                        "SNPCLUSTERING:PLINK2_PCA",
+                        "plink2",
+                        "2.00a5.10LM"
+                    ],
+                    [
+                        "SNPCLUSTERING:PLINK2_VCF",
+                        "plink2",
+                        "2.00a2.3LM"
+                    ],
+                    "versions.yml:md5,a5331a41c30b50872e8f9dc902b1fbdb",
+                    "versions.yml:md5,c3f41cb637b4e448e41a2451ac6ea796",
+                    "versions.yml:md5,c9f69ed90f9787ff5d98fda995824a89"
                 ]
             }
         ],
-        "timestamp": "2026-06-04T01:16:30.853529288",
+        "timestamp": "2026-08-20T16:09:17.538676351",
         "meta": {
             "nf-test": "0.9.5",
-            "nextflow": "25.09.0"
+            "nextflow": "26.04.6"
         }
     },
     "homo_sapiens - 1000GP.chr22.vcf.gz - kmeans - stub": {
         "content": [
             {
                 "beagle_log": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "cluster_info": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "clusters": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "evecfile": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenvec:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "evfile": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenval:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "imputed_vcf": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.vcf.gz:md5,68b329da9893e34099c7d8ad5cb9c940"
+                    ]
                 ],
                 "k_sweep": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.k_sweep.csv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "metric_plots": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.calinski_harabasz.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.davies_bouldin.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.elbow.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.silhouette.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        ]
+                    ]
                 ],
                 "metrics": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.metrics.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pca_log": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pgen": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pgen:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "psam": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.psam:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "pvar": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pvar:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "selected": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.selected.json:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsne_png": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsne_tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "umap_png": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "umap_tsv": [
-                    
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
                 ],
                 "versions": [
-                    
+                    [
+                        "SNPCLUSTERING:BEAGLE5_BEAGLE",
+                        "beagle",
+                        "5.5"
+                    ],
+                    [
+                        "SNPCLUSTERING:PLINK2_PCA",
+                        "plink2",
+                        "2.00a5.10LM"
+                    ],
+                    [
+                        "SNPCLUSTERING:PLINK2_VCF",
+                        "plink2",
+                        "2.00a2.3LM"
+                    ],
+                    "versions.yml:md5,a5331a41c30b50872e8f9dc902b1fbdb",
+                    "versions.yml:md5,c3f41cb637b4e448e41a2451ac6ea796",
+                    "versions.yml:md5,c9f69ed90f9787ff5d98fda995824a89"
                 ]
             }
         ],
-        "timestamp": "2026-06-04T01:16:16.700560685",
+        "timestamp": "2026-08-20T16:09:07.718191139",
         "meta": {
             "nf-test": "0.9.5",
-            "nextflow": "25.09.0"
+            "nextflow": "26.04.6"
         }
     }
 }
\ No newline at end of file
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index a3e8e398d109..9a0e1b2279b2 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -1,34 +1,8 @@
 params {
-    npcs = 8
-    use_approx = true
-    algorithm = "kmeans"
-    n_clusters = 3
-    dbscan_eps = 0.5
+    npcs               = 8
+    use_approx         = true
+    algorithm          = "kmeans"
+    n_clusters         = 3
+    dbscan_eps         = 0.5
     dbscan_min_samples = 5
 }
-
-process {
-    withName: 'BEAGLE5_BEAGLE' {        
-        ext.when = false
-    }
-
-    withName: 'PLINK2_VCF' {        
-        ext.when = false
-    }
-
-    withName: 'PLINK2_PCA' {        
-        ext.when = false
-    }
-
-    withName: 'CUSTOM_PCACLUSTERING' {        
-        ext.when = false
-    }
-
-    withName: 'CUSTOM_CLUSTERMETRICS' {        
-        ext.when = false
-    }
-
-    withName: 'CUSTOM_CLUSTERVISUALIZATION' {        
-        ext.when = false
-    }
-}

From 6400b7bbf8451e4f41010463ae874fd6de1c45df Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 20 Aug 2026 16:57:42 +0200
Subject: [PATCH 11/34] fix: update versions emit pattern in custom clustering
 modules

---
 modules/nf-core/custom/clustermetrics/main.nf     |  2 +-
 modules/nf-core/custom/clustermetrics/meta.yml    | 15 +++++++--------
 .../nf-core/custom/clustervisualization/main.nf   |  2 +-
 .../nf-core/custom/clustervisualization/meta.yml  | 10 +++++-----
 modules/nf-core/custom/pcaclustering/main.nf      |  2 +-
 modules/nf-core/custom/pcaclustering/meta.yml     | 11 +++++------
 6 files changed, 20 insertions(+), 22 deletions(-)

diff --git a/modules/nf-core/custom/clustermetrics/main.nf b/modules/nf-core/custom/clustermetrics/main.nf
index de01489438ad..2eb096b08f40 100644
--- a/modules/nf-core/custom/clustermetrics/main.nf
+++ b/modules/nf-core/custom/clustermetrics/main.nf
@@ -15,7 +15,7 @@ process CUSTOM_CLUSTERMETRICS {
     tuple val(meta), path("*.k_sweep.csv")  , emit: k_sweep
     tuple val(meta), path("*.selected.json"), emit: selected
     tuple val(meta), path("*.png")          , emit: plots, optional: true
-    path "versions.yml"                     , emit: versions
+    path "versions.yml"                     , emit: versions, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/nf-core/custom/clustermetrics/meta.yml b/modules/nf-core/custom/clustermetrics/meta.yml
index e364f55b6f75..92a1bea0d37b 100644
--- a/modules/nf-core/custom/clustermetrics/meta.yml
+++ b/modules/nf-core/custom/clustermetrics/meta.yml
@@ -1,6 +1,5 @@
 name: "CUSTOM_CLUSTERMETRICS"
-description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz,
-  Davies-Bouldin) and performs k-sweep analysis"
+description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz, Davies-Bouldin) and performs k-sweep analysis"
 keywords:
   - clustering
   - metrics
@@ -29,7 +28,7 @@ input:
           column per numeric feature (e.g. PCA scores).
         pattern: "*.tsv"
         ontologies:
-          - edam: http://edamontology.org/format_3475
+          - edam: http://edamontology.org/format_3475 # TSV
     - clusters:
         type: file
         description: |
@@ -37,7 +36,7 @@ input:
           `cluster` columns. Label -1 is treated as DBSCAN noise.
         pattern: "*.csv"
         ontologies:
-          - edam: http://edamontology.org/format_3752
+          - edam: http://edamontology.org/format_3752 # CSV
 output:
   metrics:
     - - meta:
@@ -48,7 +47,7 @@ output:
           description: TSV with selected cluster quality metrics
           pattern: "*.metrics.tsv"
           ontologies:
-            - edam: http://edamontology.org/format_3475
+            - edam: http://edamontology.org/format_3475 # TSV
   k_sweep:
     - - meta:
           type: map
@@ -58,7 +57,7 @@ output:
           description: CSV with metrics for different values of k
           pattern: "*.k_sweep.csv"
           ontologies:
-            - edam: http://edamontology.org/format_3752
+            - edam: http://edamontology.org/format_3752 # CSV
   selected:
     - - meta:
           type: map
@@ -68,7 +67,7 @@ output:
           description: JSON with the selected/best metrics
           pattern: "*.selected.json"
           ontologies:
-            - edam: http://edamontology.org/format_3464
+            - edam: http://edamontology.org/format_3464 # JSON
   plots:
     - - meta:
           type: map
@@ -84,7 +83,7 @@ output:
         description: File containing software versions
         pattern: "versions.yml"
         ontologies:
-          - edam: http://edamontology.org/format_3750
+          - edam: http://edamontology.org/format_3750 # YAML
 topics:
   versions:
     - versions.yml:
diff --git a/modules/nf-core/custom/clustervisualization/main.nf b/modules/nf-core/custom/clustervisualization/main.nf
index 0b1346f20de4..393c5345c636 100644
--- a/modules/nf-core/custom/clustervisualization/main.nf
+++ b/modules/nf-core/custom/clustervisualization/main.nf
@@ -15,7 +15,7 @@ process CUSTOM_CLUSTERVISUALIZATION {
     tuple val(meta), path("*.tsne.tsv"), emit: tsne_tsv
     tuple val(meta), path("*.umap.png"), emit: umap_png, optional: true
     tuple val(meta), path("*.tsne.png"), emit: tsne_png, optional: true
-    path "versions.yml"                , emit: versions
+    path "versions.yml"                , emit: versions, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/nf-core/custom/clustervisualization/meta.yml b/modules/nf-core/custom/clustervisualization/meta.yml
index 62bed07814e5..2465d4be4fe1 100644
--- a/modules/nf-core/custom/clustervisualization/meta.yml
+++ b/modules/nf-core/custom/clustervisualization/meta.yml
@@ -33,7 +33,7 @@ input:
           column per numeric feature (e.g. PCA scores).
         pattern: "*.tsv"
         ontologies:
-          - edam: http://edamontology.org/format_3475
+          - edam: http://edamontology.org/format_3475 # TSV
     - clusters:
         type: file
         description: |
@@ -41,7 +41,7 @@ input:
           `cluster` columns. Label -1 is treated as DBSCAN noise.
         pattern: "*.csv"
         ontologies:
-          - edam: http://edamontology.org/format_3752
+          - edam: http://edamontology.org/format_3752 # CSV
 output:
   umap_tsv:
     - - meta:
@@ -53,7 +53,7 @@ output:
           pattern: "*.umap.tsv"
           ontologies:
             - edam: "http://edamontology.org/operation_2432"
-            - edam: http://edamontology.org/format_3475
+            - edam: http://edamontology.org/format_3475 # TSV
   tsne_tsv:
     - - meta:
           type: map
@@ -64,7 +64,7 @@ output:
           pattern: "*.tsne.tsv"
           ontologies:
             - edam: "http://edamontology.org/operation_2432"
-            - edam: http://edamontology.org/format_3475
+            - edam: http://edamontology.org/format_3475 # TSV
   umap_png:
     - - meta:
           type: map
@@ -89,7 +89,7 @@ output:
         description: "Software versions used in the module"
         pattern: "versions.yml"
         ontologies:
-          - edam: http://edamontology.org/format_3750
+          - edam: http://edamontology.org/format_3750 # YAML
 topics:
   versions:
     - versions.yml:
diff --git a/modules/nf-core/custom/pcaclustering/main.nf b/modules/nf-core/custom/pcaclustering/main.nf
index 4a4be41f876b..b14414f28f75 100644
--- a/modules/nf-core/custom/pcaclustering/main.nf
+++ b/modules/nf-core/custom/pcaclustering/main.nf
@@ -17,7 +17,7 @@ process CUSTOM_PCACLUSTERING {
     output:
     tuple val(meta), path("*.clusters.csv")        , emit: clusters
     tuple val(meta), path("*.clustering_info.json"), emit: info
-    path "versions.yml"                            , emit: versions
+    path "versions.yml"                            , emit: versions, topic: versions
 
     when:
     task.ext.when == null || task.ext.when
diff --git a/modules/nf-core/custom/pcaclustering/meta.yml b/modules/nf-core/custom/pcaclustering/meta.yml
index 72a1cefbaa11..13f612c8eb9e 100644
--- a/modules/nf-core/custom/pcaclustering/meta.yml
+++ b/modules/nf-core/custom/pcaclustering/meta.yml
@@ -1,6 +1,5 @@
 name: "CUSTOM_PCACLUSTERING"
-description: "Performs KMeans or DBSCAN clustering on a sample-by-feature numeric
-  matrix (e.g. principal components, embeddings)"
+description: "Performs KMeans or DBSCAN clustering on a sample-by-feature numeric matrix (e.g. principal components, embeddings)"
 keywords:
   - clustering
   - kmeans
@@ -29,7 +28,7 @@ input:
           components with `FID` dropped, scikit-learn embeddings, etc.).
         pattern: "*.{tsv,txt}"
         ontologies:
-          - edam: http://edamontology.org/format_3475
+          - edam: http://edamontology.org/format_3475 # TSV
   - algorithm:
       type: string
       description: Clustering algorithm to use (kmeans or dbscan)
@@ -52,7 +51,7 @@ output:
           description: CSV file with sample_id and assigned cluster
           pattern: "*.clusters.csv"
           ontologies:
-            - edam: http://edamontology.org/format_3752
+            - edam: http://edamontology.org/format_3752 # CSV
   info:
     - - meta:
           type: map
@@ -62,14 +61,14 @@ output:
           description: JSON file with clustering parameters and statistics
           pattern: "*.clustering_info.json"
           ontologies:
-            - edam: http://edamontology.org/format_3464
+            - edam: http://edamontology.org/format_3464 # JSON
   versions:
     - "versions.yml":
         type: file
         description: File containing software versions
         pattern: "versions.yml"
         ontologies:
-          - edam: http://edamontology.org/format_3750
+          - edam: http://edamontology.org/format_3750 # YAML
 topics:
   versions:
     - versions.yml:

From 1fba4a3457120ffdf6d1b36d0d9d6f9237ff4851 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 20 Aug 2026 17:16:02 +0200
Subject: [PATCH 12/34] fix: ensure main.nf ends with single newline

---
 subworkflows/nf-core/snpclustering/main.nf | 1 -
 1 file changed, 1 deletion(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 62eabbf5c7f9..0640bfaf386e 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -161,4 +161,3 @@ process EIGENVEC_TO_TSV {
     END_VERSIONS
     """
 }
-

From 1f98f397512ff6d54b1acf71a21eb017b9030d54 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Tue, 25 Aug 2026 11:56:38 +0200
Subject: [PATCH 13/34] Replace inline EIGENVEC_TO_TSV process with GAWK module
 in snpclustering

---
 .../snpclustering/awk/eigenvec_to_tsv.awk     |  9 +++
 subworkflows/nf-core/snpclustering/main.nf    | 71 +++++++------------
 .../snpclustering/tests/main.nf.test.snap     | 28 ++++++--
 .../snpclustering/tests/nextflow.config       |  7 ++
 4 files changed, 66 insertions(+), 49 deletions(-)
 create mode 100644 subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk

diff --git a/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk b/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
new file mode 100644
index 000000000000..c84a0c3e9160
--- /dev/null
+++ b/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
@@ -0,0 +1,9 @@
+NR==1 {
+    sub(/^#/, "")
+    if ($1 == "IID") {
+        $1 = "sample_id"
+    }
+    print
+    next
+}
+{ print }
diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 0640bfaf386e..ae7c89b321b7 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,9 +1,10 @@
-include { BEAGLE5_BEAGLE              } from '../../../modules/nf-core/beagle5/beagle'
-include { PLINK2_VCF                  } from '../../../modules/nf-core/plink2/vcf/main'
-include { PLINK2_PCA                  } from '../../../modules/nf-core/plink2/pca/main'
-include { CUSTOM_PCACLUSTERING        } from '../../../modules/nf-core/custom/pcaclustering/main'
-include { CUSTOM_CLUSTERMETRICS       } from '../../../modules/nf-core/custom/clustermetrics/main'
-include { CUSTOM_CLUSTERVISUALIZATION } from '../../../modules/nf-core/custom/clustervisualization/main'
+include { BEAGLE5_BEAGLE                } from '../../../modules/nf-core/beagle5/beagle'
+include { PLINK2_VCF                    } from '../../../modules/nf-core/plink2/vcf/main'
+include { PLINK2_PCA                    } from '../../../modules/nf-core/plink2/pca/main'
+include { GAWK as GAWK_EIGENVEC_TO_TSV  } from '../../../modules/nf-core/gawk/main'
+include { CUSTOM_PCACLUSTERING          } from '../../../modules/nf-core/custom/pcaclustering/main'
+include { CUSTOM_CLUSTERMETRICS         } from '../../../modules/nf-core/custom/clustermetrics/main'
+include { CUSTOM_CLUSTERVISUALIZATION   } from '../../../modules/nf-core/custom/clustervisualization/main'
 
 workflow SNPCLUSTERING {
 
@@ -22,6 +23,12 @@ workflow SNPCLUSTERING {
     main:
     ch_versions = Channel.empty()
 
+    // Bundled awk program (see ./awk/eigenvec_to_tsv.awk); shipped alongside
+    // the subworkflow and passed to GAWK_EIGENVEC_TO_TSV as `program_file` so
+    // the awk source stays readable as awk rather than as an escaped Groovy
+    // string.
+    ch_eigenvec_to_tsv_awk = file("${moduleDir}/awk/eigenvec_to_tsv.awk", checkIfExists: true)
+
     /*
      * Build BEAGLE input tuple:
      * tuple val(meta), path(vcf), path(vcf_index), path(refpanel), path(refpanel_index),
@@ -65,16 +72,24 @@ workflow SNPCLUSTERING {
     ch_versions = ch_versions.mix(PLINK2_PCA.out.versions_plink2)
 
     /*
-     * Convert .eigenvec to TSV for downstream clustering modules
+     * Convert .eigenvec to a tab-separated file for downstream clustering
+     * modules: strips the leading '#' from the header and renames the IID
+     * column to sample_id. Output keeps its default naming (<meta.id>.eigenvec)
+     * — only the tab-separated content matters downstream, not the extension.
      */
-    EIGENVEC_TO_TSV(PLINK2_PCA.out.evecfile)
+    GAWK_EIGENVEC_TO_TSV(
+        PLINK2_PCA.out.evecfile,
+        ch_eigenvec_to_tsv_awk,
+        false
+    )
+    ch_versions = ch_versions.mix(GAWK_EIGENVEC_TO_TSV.out.versions_gawk)
 
     /*
      * PCA clustering
      * CUSTOM_PCACLUSTERING(tsv, algorithm, n_clusters, dbscan_eps, dbscan_min_samples)
      */
     CUSTOM_PCACLUSTERING(
-        EIGENVEC_TO_TSV.out.tsv,
+        GAWK_EIGENVEC_TO_TSV.out.output,
         algorithm,
         n_clusters,
         dbscan_eps,
@@ -86,7 +101,7 @@ workflow SNPCLUSTERING {
      * Metrics and visualization both expect one tuple input channel
      * built from: meta + tsv + cluster assignments
      */
-    ch_cluster_analysis_input = EIGENVEC_TO_TSV.out.tsv
+    ch_cluster_analysis_input = GAWK_EIGENVEC_TO_TSV.out.output
         .join(CUSTOM_PCACLUSTERING.out.clusters)
         .map { meta, tsv, clusters ->
             tuple(meta, tsv, clusters)
@@ -110,7 +125,7 @@ workflow SNPCLUSTERING {
     evfile        = PLINK2_PCA.out.evfile
     pca_log       = PLINK2_PCA.out.logfile
 
-    tsv           = EIGENVEC_TO_TSV.out.tsv
+    tsv           = GAWK_EIGENVEC_TO_TSV.out.output
 
     clusters      = CUSTOM_PCACLUSTERING.out.clusters
     cluster_info  = CUSTOM_PCACLUSTERING.out.info
@@ -127,37 +142,3 @@ workflow SNPCLUSTERING {
 
     versions      = ch_versions
 }
-
-process EIGENVEC_TO_TSV {
-
-    tag "${meta.id}"
-    label 'process_single'
-
-    input:
-    tuple val(meta), path(eigenvec)
-
-    output:
-    tuple val(meta), path("${meta.id}.tsv"), emit: tsv
-    path "versions.yml", emit: versions
-
-    script:
-    """
-    awk '
-    NR==1 {
-        sub(/^#/, "")
-        if (\$1 == "IID") {
-            \$1="sample_id"
-        }
-        print
-        next
-    }
-    {
-        print
-    }' OFS='\\t' ${eigenvec} > ${meta.id}.tsv
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        gawk: \$(awk --version | head -1 | sed 's/GNU Awk //;s/,.*//')
-    END_VERSIONS
-    """
-}
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 7bb0440847d8..4bd2b72cd485 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -31,6 +31,11 @@
                     "beagle",
                     "5.5"
                 ],
+                [
+                    "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
+                    "gawk",
+                    "5.3.1"
+                ],
                 [
                     "SNPCLUSTERING:PLINK2_PCA",
                     "plink2",
@@ -46,7 +51,7 @@
                 "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
             ]
         ],
-        "timestamp": "2026-08-20T16:08:17.636962775",
+        "timestamp": "2026-08-25T11:53:17.934676935",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -84,6 +89,11 @@
                     "beagle",
                     "5.5"
                 ],
+                [
+                    "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
+                    "gawk",
+                    "5.3.1"
+                ],
                 [
                     "SNPCLUSTERING:PLINK2_PCA",
                     "plink2",
@@ -99,7 +109,7 @@
                 "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
             ]
         ],
-        "timestamp": "2026-08-20T16:08:55.94750336",
+        "timestamp": "2026-08-25T11:53:57.926394897",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -271,6 +281,11 @@
                         "beagle",
                         "5.5"
                     ],
+                    [
+                        "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
+                        "gawk",
+                        "5.3.1"
+                    ],
                     [
                         "SNPCLUSTERING:PLINK2_PCA",
                         "plink2",
@@ -287,7 +302,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-20T16:09:17.538676351",
+        "timestamp": "2026-08-25T11:54:24.140132513",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -459,6 +474,11 @@
                         "beagle",
                         "5.5"
                     ],
+                    [
+                        "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
+                        "gawk",
+                        "5.3.1"
+                    ],
                     [
                         "SNPCLUSTERING:PLINK2_PCA",
                         "plink2",
@@ -475,7 +495,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-20T16:09:07.718191139",
+        "timestamp": "2026-08-25T11:54:10.985447937",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 9a0e1b2279b2..93f8ed077be8 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -6,3 +6,10 @@ params {
     dbscan_eps         = 0.5
     dbscan_min_samples = 5
 }
+
+process {
+    withName: GAWK_EIGENVEC_TO_TSV {
+        ext.args   = "-v OFS='\\t'"
+        ext.suffix = "tsv"
+    }
+}

From 6a7677fcb50a4bd5005451af856b4aab88575ba9 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 15:33:08 +0200
Subject: [PATCH 14/34] fix(snpclustering): use topic versions and snapshot
 stable md5s

---
 subworkflows/nf-core/snpclustering/main.nf    |  19 -
 subworkflows/nf-core/snpclustering/meta.yml   | 321 +++++++-----
 .../nf-core/snpclustering/tests/main.nf.test  |  71 ++-
 .../snpclustering/tests/main.nf.test.snap     | 470 ++++++++++++------
 4 files changed, 540 insertions(+), 341 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index ae7c89b321b7..3b8fb56bf670 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -7,7 +7,6 @@ include { CUSTOM_CLUSTERMETRICS         } from '../../../modules/nf-core/custom/
 include { CUSTOM_CLUSTERVISUALIZATION   } from '../../../modules/nf-core/custom/clustervisualization/main'
 
 workflow SNPCLUSTERING {
-
     take:
     vcf_ch
     refpanel_ch
@@ -21,8 +20,6 @@ workflow SNPCLUSTERING {
     dbscan_min_samples
 
     main:
-    ch_versions = Channel.empty()
-
     // Bundled awk program (see ./awk/eigenvec_to_tsv.awk); shipped alongside
     // the subworkflow and passed to GAWK_EIGENVEC_TO_TSV as `program_file` so
     // the awk source stays readable as awk rather than as an escaped Groovy
@@ -49,13 +46,11 @@ workflow SNPCLUSTERING {
     }
 
     BEAGLE5_BEAGLE(ch_beagle_input)
-    ch_versions = ch_versions.mix(BEAGLE5_BEAGLE.out.versions_beagle)
 
     /*
      * Convert imputed VCF to PLINK2 pfiles
      */
     PLINK2_VCF(BEAGLE5_BEAGLE.out.vcf)
-    ch_versions = ch_versions.mix(PLINK2_VCF.out.versions_plink2)
 
     /*
      * PLINK2_PCA expects:
@@ -69,7 +64,6 @@ workflow SNPCLUSTERING {
         }
 
     PLINK2_PCA(ch_plink_pca_input)
-    ch_versions = ch_versions.mix(PLINK2_PCA.out.versions_plink2)
 
     /*
      * Convert .eigenvec to a tab-separated file for downstream clustering
@@ -82,7 +76,6 @@ workflow SNPCLUSTERING {
         ch_eigenvec_to_tsv_awk,
         false
     )
-    ch_versions = ch_versions.mix(GAWK_EIGENVEC_TO_TSV.out.versions_gawk)
 
     /*
      * PCA clustering
@@ -95,7 +88,6 @@ workflow SNPCLUSTERING {
         dbscan_eps,
         dbscan_min_samples
     )
-    ch_versions = ch_versions.mix(CUSTOM_PCACLUSTERING.out.versions)
 
     /*
      * Metrics and visualization both expect one tuple input channel
@@ -108,37 +100,26 @@ workflow SNPCLUSTERING {
         }
 
     CUSTOM_CLUSTERMETRICS(ch_cluster_analysis_input)
-    ch_versions = ch_versions.mix(CUSTOM_CLUSTERMETRICS.out.versions)
-
     CUSTOM_CLUSTERVISUALIZATION(ch_cluster_analysis_input)
-    ch_versions = ch_versions.mix(CUSTOM_CLUSTERVISUALIZATION.out.versions)
 
     emit:
     imputed_vcf   = BEAGLE5_BEAGLE.out.vcf
     beagle_log    = BEAGLE5_BEAGLE.out.log
-
     pgen          = PLINK2_VCF.out.pgen
     pvar          = PLINK2_VCF.out.pvar
     psam          = PLINK2_VCF.out.psam
-
     evecfile      = PLINK2_PCA.out.evecfile
     evfile        = PLINK2_PCA.out.evfile
     pca_log       = PLINK2_PCA.out.logfile
-
     tsv           = GAWK_EIGENVEC_TO_TSV.out.output
-
     clusters      = CUSTOM_PCACLUSTERING.out.clusters
     cluster_info  = CUSTOM_PCACLUSTERING.out.info
-
     metrics       = CUSTOM_CLUSTERMETRICS.out.metrics
     k_sweep       = CUSTOM_CLUSTERMETRICS.out.k_sweep
     selected      = CUSTOM_CLUSTERMETRICS.out.selected
     metric_plots  = CUSTOM_CLUSTERMETRICS.out.plots
-
     umap_tsv      = CUSTOM_CLUSTERVISUALIZATION.out.umap_tsv
     tsne_tsv      = CUSTOM_CLUSTERVISUALIZATION.out.tsne_tsv
     umap_png      = CUSTOM_CLUSTERVISUALIZATION.out.umap_png
     tsne_png      = CUSTOM_CLUSTERVISUALIZATION.out.tsne_png
-
-    versions      = ch_versions
 }
diff --git a/subworkflows/nf-core/snpclustering/meta.yml b/subworkflows/nf-core/snpclustering/meta.yml
index 25098093fb72..171a9f1e6e12 100644
--- a/subworkflows/nf-core/snpclustering/meta.yml
+++ b/subworkflows/nf-core/snpclustering/meta.yml
@@ -13,158 +13,207 @@ keywords:
   - beagle
   - imputation
   - population genetics
-
 components:
   - beagle5/beagle
   - plink2/vcf
   - plink2/pca
+  - gawk
   - custom/pcaclustering
   - custom/clustermetrics
   - custom/clustervisualization
-
 input:
-  - meta:
-      type: map
-      description: Groovy map containing sample metadata.
-    vcf:
-      type: file
-      description: Genotyped VCF file.
-      pattern: "*.{vcf,vcf.gz}"
-    vcf_index:
-      type: file
-      description: Index for the VCF file.
-      pattern: "*.{tbi,csi}"
-
-  - meta:
-      type: map
-      description: Groovy map for the optional reference panel.
-    refpanel:
-      type: file
-      description: Optional BEAGLE reference panel VCF.
-      pattern: "*.{vcf,vcf.gz}"
-    refpanel_index:
-      type: file
-      description: Optional index for the reference panel.
-      pattern: "*.{tbi,csi}"
-
-  - meta:
-      type: map
-      description: Groovy map for the optional genetic map.
-    genmap:
-      type: file
-      description: Optional genetic map file for BEAGLE.
-      pattern: "*.map"
-
+  - vcf_ch:
+      description: Channel with genotyped VCF and index
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - vcf:
+            type: file
+            description: Genotyped VCF file
+            pattern: "*.{vcf,vcf.gz}"
+        - vcf_index:
+            type: file
+            description: Index for the VCF file
+            pattern: "*.{tbi,csi}"
+  - refpanel_ch:
+      description: Optional BEAGLE reference panel channel
+  - genmap_ch:
+      description: Optional BEAGLE genetic map channel
   - region:
-      type: val
-      description: Optional genomic region passed to BEAGLE.
-
+      type: string
+      description: Optional genomic region passed to BEAGLE
   - npcs:
-      type: val
-      description: Number of principal components to compute.
-
+      type: integer
+      description: Number of principal components to compute
   - use_approx:
-      type: val
-      description: Whether to use approximate PCA.
-
+      type: boolean
+      description: Whether to use approximate PCA
   - algorithm:
-      type: val
-      description: Clustering algorithm to use.
-
+      type: string
+      description: Clustering algorithm to use (kmeans or dbscan)
   - n_clusters:
-      type: val
-      description: Number of clusters for kmeans or similar methods.
-
+      type: integer
+      description: Number of clusters for k-means
   - dbscan_eps:
-      type: val
-      description: DBSCAN eps parameter.
-
+      type: float
+      description: DBSCAN eps parameter
   - dbscan_min_samples:
-      type: val
-      description: DBSCAN minimum samples parameter.
-
+      type: integer
+      description: DBSCAN minimum samples parameter
 output:
-  - imputed_vcf:
-      type: map
-      description: Groovy map of sample metadata.
-    vcf:
-      type: file
-      description: Imputed VCF from BEAGLE5.
-      pattern: "*.{vcf,vcf.gz}"
-
-  - pfiles:
-      type: map
-      description: Groovy map of sample metadata.
-    pgen:
-      type: file
-      description: PLINK2 pgen file.
-      pattern: "*.pgen"
-    psam:
-      type: file
-      description: PLINK2 psam file.
-      pattern: "*.psam"
-    pvar:
-      type: file
-      description: PLINK2 pvar file.
-      pattern: "*.pvar"
-
-  - pca:
-      type: map
-      description: Groovy map of sample metadata.
-    eigenvec:
-      type: file
-      description: PCA eigenvectors from PLINK2.
-      pattern: "*.eigenvec"
-    eigenval:
-      type: file
-      description: PCA eigenvalues from PLINK2.
-      pattern: "*.eigenval"
-
-  - eigenvec_tsv:
-      type: map
-      description: Groovy map of sample metadata.
-    tsv:
-      type: file
-      description: Tidy TSV converted from eigenvec by awk.
-      pattern: "*.tsv"
-
-  - cluster_labels:
-      type: map
-      description: Groovy map of sample metadata.
-    clusters:
-      type: file
-      description: Cluster labels output from PCA clustering.
-      pattern: "*.tsv"
-
-  - cluster_info:
-      type: map
-      description: Groovy map of sample metadata.
-    info:
-      type: file
-      description: Additional cluster info output.
-      pattern: "*.tsv"
-
-  - cluster_metrics:
-      type: map
-      description: Groovy map of sample metadata.
-    metrics:
-      type: file
-      description: Cluster quality metrics output.
-      pattern: "*.tsv"
-
-  - cluster_plots:
-      type: map
-      description: Groovy map of sample metadata.
-    plots:
-      type: file
-      description: Cluster visualization outputs.
-      pattern: "*.{png,pdf,html}"
-
-  - versions:
-      type: file
-      description: Software versions collected from the subworkflow.
-      pattern: "versions.yml"
-
+  imputed_vcf:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - vcf:
+        type: file
+        description: Imputed VCF from BEAGLE5
+        pattern: "*.{vcf,vcf.gz}"
+  beagle_log:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - log:
+        type: file
+        description: BEAGLE5 log file
+        pattern: "*.log"
+  pgen:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - pgen:
+        type: file
+        description: PLINK2 pgen file
+        pattern: "*.pgen"
+  pvar:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - pvar:
+        type: file
+        description: PLINK2 pvar file
+        pattern: "*.pvar"
+  psam:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - psam:
+        type: file
+        description: PLINK2 psam file
+        pattern: "*.psam"
+  evecfile:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - eigenvec:
+        type: file
+        description: PCA eigenvectors from PLINK2
+        pattern: "*.eigenvec"
+  evfile:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - eigenval:
+        type: file
+        description: PCA eigenvalues from PLINK2
+        pattern: "*.eigenval"
+  pca_log:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - log:
+        type: file
+        description: PLINK2 PCA log file
+        pattern: "*.log"
+  tsv:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - tsv:
+        type: file
+        description: TSV converted from eigenvec by gawk
+        pattern: "*.eigenvec"
+  clusters:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - clusters:
+        type: file
+        description: Cluster assignments
+        pattern: "*.clusters.csv"
+  cluster_info:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - info:
+        type: file
+        description: Clustering parameters and statistics
+        pattern: "*.clustering_info.json"
+  metrics:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - metrics:
+        type: file
+        description: Cluster quality metrics
+        pattern: "*.metrics.tsv"
+  k_sweep:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - k_sweep:
+        type: file
+        description: K sweep scores
+        pattern: "*.k_sweep.csv"
+  selected:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - selected:
+        type: file
+        description: Selected clustering parameters
+        pattern: "*.selected.json"
+  metric_plots:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - plots:
+        type: file
+        description: Cluster metric plots
+        pattern: "*.png"
+  umap_tsv:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - umap_tsv:
+        type: file
+        description: UMAP coordinates per sample
+        pattern: "*.umap.tsv"
+  tsne_tsv:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - tsne_tsv:
+        type: file
+        description: t-SNE coordinates per sample
+        pattern: "*.tsne.tsv"
+  umap_png:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - umap_png:
+        type: file
+        description: UMAP plot coloured by cluster
+        pattern: "*.umap.png"
+  tsne_png:
+    - meta:
+        type: map
+        description: Groovy map containing sample metadata
+    - tsne_png:
+        type: file
+        description: t-SNE plot coloured by cluster
+        pattern: "*.tsne.png"
 authors:
   - "@dbaku42"
 maintainers:
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 8a2af307932e..b1cb5388ec29 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -12,6 +12,7 @@ nextflow_workflow {
     tag "plink2/vcf"
     tag "plink2/pca"
     tag "beagle5/beagle"
+    tag "gawk"
     tag "custom/pcaclustering"
     tag "custom/clustermetrics"
     tag "custom/clustervisualization"
@@ -41,22 +42,19 @@ nextflow_workflow {
         }
 
         then {
-            assert workflow.success
-            assert snapshot(
-                workflow.out.clusters.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.cluster_info.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.metrics.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.versions
-            ).match()
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    sanitizeOutput(
+                        workflow.out,
+                        unstableKeys: [
+                            "umap_png",
+                            "tsne_png",
+                            "metric_plots"
+                        ]
+                    )
+                ).match() }
+            )
         }
     }
 
@@ -83,22 +81,19 @@ nextflow_workflow {
         }
 
         then {
-            assert workflow.success
-            assert snapshot(
-                workflow.out.clusters.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.cluster_info.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.metrics.collect { [
-                    it[0],
-                    path(it[1]).getFileName().toString()
-                ]},
-                workflow.out.versions
-            ).match()
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                    sanitizeOutput(
+                        workflow.out,
+                        unstableKeys: [
+                            "umap_png",
+                            "tsne_png",
+                            "metric_plots"
+                        ]
+                    )
+                ).match() }
+            )
         }
     }
 
@@ -126,8 +121,10 @@ nextflow_workflow {
         }
 
         then {
-            assert workflow.success
-            assert snapshot(sanitizeOutput(workflow.out)).match()
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
+            )
         }
     }
 
@@ -155,8 +152,10 @@ nextflow_workflow {
         }
 
         then {
-            assert workflow.success
-            assert snapshot(sanitizeOutput(workflow.out)).match()
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
+            )
         }
     }
 }
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 4bd2b72cd485..f6d1862a39ad 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -1,57 +1,167 @@
 {
     "homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters": {
         "content": [
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.clusters.csv"
-                ]
-            ],
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.clustering_info.json"
-                ]
-            ],
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.metrics.tsv"
+            {
+                "beagle_log": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.log:md5,00f899a6db795f7d4bd79b5961ec7d10"
+                    ]
+                ],
+                "cluster_info": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,f4f73c989de9e52384b786ff6ac040e5"
+                    ]
+                ],
+                "clusters": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,be0a1b1d684974d5eff60be2c46ceedf"
+                    ]
+                ],
+                "evecfile": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenvec:md5,655e0a4283a1f9d9f13c7dbe0e6da1d9"
+                    ]
+                ],
+                "evfile": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
+                    ]
+                ],
+                "imputed_vcf": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.vcf.gz:md5,ef94995e50ba034aeb8119ad15fb6ccc"
+                    ]
+                ],
+                "k_sweep": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.k_sweep.csv:md5,113fa7245a810786ec404769f5ba5698"
+                    ]
+                ],
+                "metric_plots": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.calinski_harabasz.png",
+                            "test.davies_bouldin.png",
+                            "test.elbow.png",
+                            "test.silhouette.png"
+                        ]
+                    ]
+                ],
+                "metrics": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.metrics.tsv:md5,9f203e3c741435f1317dcb4ab44c43c3"
+                    ]
+                ],
+                "pca_log": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.log:md5,3d794ffb37ae49b03dbc8a06a408825f"
+                    ]
+                ],
+                "pgen": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pgen:md5,b183c72cbf75758521bd42a21a02e882"
+                    ]
+                ],
+                "psam": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
+                    ]
+                ],
+                "pvar": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pvar:md5,9c89b734017db356ccaa0190ab88c199"
+                    ]
+                ],
+                "selected": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.selected.json:md5,ddbef02b869e51b8eaadceebd9ebd064"
+                    ]
+                ],
+                "tsne_png": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.png"
+                    ]
+                ],
+                "tsne_tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.tsv:md5,20f545d08f1175bfe1825b3932833b8d"
+                    ]
+                ],
+                "tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,94681fa5806fbf33fa5c5041c3c29f29"
+                    ]
+                ],
+                "umap_png": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.png"
+                    ]
+                ],
+                "umap_tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.tsv:md5,a7d209592da80adf142c5f1c2bce9ea2"
+                    ]
                 ]
-            ],
-            [
-                [
-                    "SNPCLUSTERING:BEAGLE5_BEAGLE",
-                    "beagle",
-                    "5.5"
-                ],
-                [
-                    "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
-                    "gawk",
-                    "5.3.1"
-                ],
-                [
-                    "SNPCLUSTERING:PLINK2_PCA",
-                    "plink2",
-                    "2.00a5.10LM"
-                ],
-                [
-                    "SNPCLUSTERING:PLINK2_VCF",
-                    "plink2",
-                    "2.00a2.3LM"
-                ],
-                "versions.yml:md5,088adb486c0aa9f234effd310576eaf7",
-                "versions.yml:md5,5e7ab136010cdcda51f91b12562b28c7",
-                "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
-            ]
+            }
         ],
-        "timestamp": "2026-08-25T11:53:17.934676935",
+        "timestamp": "2026-08-26T15:28:38.960190054",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -59,57 +169,167 @@
     },
     "homo_sapiens - 1000GP.chr22.vcf.gz - dbscan": {
         "content": [
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.clusters.csv"
-                ]
-            ],
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.clustering_info.json"
-                ]
-            ],
-            [
-                [
-                    {
-                        "id": "test"
-                    },
-                    "test.metrics.tsv"
+            {
+                "beagle_log": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.log:md5,00f899a6db795f7d4bd79b5961ec7d10"
+                    ]
+                ],
+                "cluster_info": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clustering_info.json:md5,fa9a2eff36d06fe360a59f4c3cd63393"
+                    ]
+                ],
+                "clusters": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.clusters.csv:md5,c119dc1c716d66ceebc220219b02a535"
+                    ]
+                ],
+                "evecfile": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenvec:md5,cb7d3501265fb6e681f9a66552faff42"
+                    ]
+                ],
+                "evfile": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
+                    ]
+                ],
+                "imputed_vcf": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.bglout.vcf.gz:md5,ef94995e50ba034aeb8119ad15fb6ccc"
+                    ]
+                ],
+                "k_sweep": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.k_sweep.csv:md5,d75662c7c614f39e294601653c02de8d"
+                    ]
+                ],
+                "metric_plots": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            "test.calinski_harabasz.png",
+                            "test.davies_bouldin.png",
+                            "test.elbow.png",
+                            "test.silhouette.png"
+                        ]
+                    ]
+                ],
+                "metrics": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.metrics.tsv:md5,d3f1a0d467c21875176c6f8c691b8d71"
+                    ]
+                ],
+                "pca_log": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.log:md5,65d20c952985adb5fa7229a5d0d4fc0c"
+                    ]
+                ],
+                "pgen": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pgen:md5,b183c72cbf75758521bd42a21a02e882"
+                    ]
+                ],
+                "psam": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
+                    ]
+                ],
+                "pvar": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.pvar:md5,9c89b734017db356ccaa0190ab88c199"
+                    ]
+                ],
+                "selected": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.selected.json:md5,138b2bae0f67f913dcead80f8202d9af"
+                    ]
+                ],
+                "tsne_png": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.png"
+                    ]
+                ],
+                "tsne_tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsne.tsv:md5,f4952012bc87993ca78429d4a823edb1"
+                    ]
+                ],
+                "tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.tsv:md5,8009b5a5210c1dae667f40c40b450035"
+                    ]
+                ],
+                "umap_png": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.png"
+                    ]
+                ],
+                "umap_tsv": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        "test.umap.tsv:md5,26c791bc4d38dff6f979582611dbc27d"
+                    ]
                 ]
-            ],
-            [
-                [
-                    "SNPCLUSTERING:BEAGLE5_BEAGLE",
-                    "beagle",
-                    "5.5"
-                ],
-                [
-                    "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
-                    "gawk",
-                    "5.3.1"
-                ],
-                [
-                    "SNPCLUSTERING:PLINK2_PCA",
-                    "plink2",
-                    "2.00a5.10LM"
-                ],
-                [
-                    "SNPCLUSTERING:PLINK2_VCF",
-                    "plink2",
-                    "2.00a2.3LM"
-                ],
-                "versions.yml:md5,088adb486c0aa9f234effd310576eaf7",
-                "versions.yml:md5,5e7ab136010cdcda51f91b12562b28c7",
-                "versions.yml:md5,7406d1551e405376f2e1be27dd888f0f"
-            ]
+            }
         ],
-        "timestamp": "2026-08-25T11:53:57.926394897",
+        "timestamp": "2026-08-26T15:29:18.988004598",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -274,35 +494,10 @@
                         },
                         "test.umap.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
-                ],
-                "versions": [
-                    [
-                        "SNPCLUSTERING:BEAGLE5_BEAGLE",
-                        "beagle",
-                        "5.5"
-                    ],
-                    [
-                        "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
-                        "gawk",
-                        "5.3.1"
-                    ],
-                    [
-                        "SNPCLUSTERING:PLINK2_PCA",
-                        "plink2",
-                        "2.00a5.10LM"
-                    ],
-                    [
-                        "SNPCLUSTERING:PLINK2_VCF",
-                        "plink2",
-                        "2.00a2.3LM"
-                    ],
-                    "versions.yml:md5,a5331a41c30b50872e8f9dc902b1fbdb",
-                    "versions.yml:md5,c3f41cb637b4e448e41a2451ac6ea796",
-                    "versions.yml:md5,c9f69ed90f9787ff5d98fda995824a89"
                 ]
             }
         ],
-        "timestamp": "2026-08-25T11:54:24.140132513",
+        "timestamp": "2026-08-26T15:29:43.011468684",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -467,35 +662,10 @@
                         },
                         "test.umap.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
-                ],
-                "versions": [
-                    [
-                        "SNPCLUSTERING:BEAGLE5_BEAGLE",
-                        "beagle",
-                        "5.5"
-                    ],
-                    [
-                        "SNPCLUSTERING:GAWK_EIGENVEC_TO_TSV",
-                        "gawk",
-                        "5.3.1"
-                    ],
-                    [
-                        "SNPCLUSTERING:PLINK2_PCA",
-                        "plink2",
-                        "2.00a5.10LM"
-                    ],
-                    [
-                        "SNPCLUSTERING:PLINK2_VCF",
-                        "plink2",
-                        "2.00a2.3LM"
-                    ],
-                    "versions.yml:md5,a5331a41c30b50872e8f9dc902b1fbdb",
-                    "versions.yml:md5,c3f41cb637b4e448e41a2451ac6ea796",
-                    "versions.yml:md5,c9f69ed90f9787ff5d98fda995824a89"
                 ]
             }
         ],
-        "timestamp": "2026-08-25T11:54:10.985447937",
+        "timestamp": "2026-08-26T15:29:31.961527536",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From e29c96618404a05d30bb9e3277477424bef3eed9 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 15:57:26 +0200
Subject: [PATCH 15/34] Fixing linting and unstable md5

---
 subworkflows/nf-core/snpclustering/meta.yml   | 342 ++++++++++--------
 .../nf-core/snpclustering/tests/main.nf.test  |  39 +-
 .../snpclustering/tests/main.nf.test.snap     |  58 +--
 3 files changed, 238 insertions(+), 201 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/meta.yml b/subworkflows/nf-core/snpclustering/meta.yml
index 171a9f1e6e12..1d57e69d8915 100644
--- a/subworkflows/nf-core/snpclustering/meta.yml
+++ b/subworkflows/nf-core/snpclustering/meta.yml
@@ -62,158 +62,196 @@ input:
       type: integer
       description: DBSCAN minimum samples parameter
 output:
-  imputed_vcf:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - vcf:
-        type: file
-        description: Imputed VCF from BEAGLE5
-        pattern: "*.{vcf,vcf.gz}"
-  beagle_log:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - log:
-        type: file
-        description: BEAGLE5 log file
-        pattern: "*.log"
-  pgen:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - pgen:
-        type: file
-        description: PLINK2 pgen file
-        pattern: "*.pgen"
-  pvar:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - pvar:
-        type: file
-        description: PLINK2 pvar file
-        pattern: "*.pvar"
-  psam:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - psam:
-        type: file
-        description: PLINK2 psam file
-        pattern: "*.psam"
-  evecfile:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - eigenvec:
-        type: file
-        description: PCA eigenvectors from PLINK2
-        pattern: "*.eigenvec"
-  evfile:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - eigenval:
-        type: file
-        description: PCA eigenvalues from PLINK2
-        pattern: "*.eigenval"
-  pca_log:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - log:
-        type: file
-        description: PLINK2 PCA log file
-        pattern: "*.log"
-  tsv:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - tsv:
-        type: file
-        description: TSV converted from eigenvec by gawk
-        pattern: "*.eigenvec"
-  clusters:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - clusters:
-        type: file
-        description: Cluster assignments
-        pattern: "*.clusters.csv"
-  cluster_info:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - info:
-        type: file
-        description: Clustering parameters and statistics
-        pattern: "*.clustering_info.json"
-  metrics:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - metrics:
-        type: file
-        description: Cluster quality metrics
-        pattern: "*.metrics.tsv"
-  k_sweep:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - k_sweep:
-        type: file
-        description: K sweep scores
-        pattern: "*.k_sweep.csv"
-  selected:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - selected:
-        type: file
-        description: Selected clustering parameters
-        pattern: "*.selected.json"
-  metric_plots:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - plots:
-        type: file
-        description: Cluster metric plots
-        pattern: "*.png"
-  umap_tsv:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - umap_tsv:
-        type: file
-        description: UMAP coordinates per sample
-        pattern: "*.umap.tsv"
-  tsne_tsv:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - tsne_tsv:
-        type: file
-        description: t-SNE coordinates per sample
-        pattern: "*.tsne.tsv"
-  umap_png:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - umap_png:
-        type: file
-        description: UMAP plot coloured by cluster
-        pattern: "*.umap.png"
-  tsne_png:
-    - meta:
-        type: map
-        description: Groovy map containing sample metadata
-    - tsne_png:
-        type: file
-        description: t-SNE plot coloured by cluster
-        pattern: "*.tsne.png"
+  - imputed_vcf:
+      description: Imputed VCF from BEAGLE5
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - vcf:
+            type: file
+            description: Imputed VCF from BEAGLE5
+            pattern: "*.{vcf,vcf.gz}"
+  - beagle_log:
+      description: BEAGLE5 log file
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - log:
+            type: file
+            description: BEAGLE5 log file
+            pattern: "*.log"
+  - pgen:
+      description: PLINK2 pgen file
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - pgen:
+            type: file
+            description: PLINK2 pgen file
+            pattern: "*.pgen"
+  - pvar:
+      description: PLINK2 pvar file
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - pvar:
+            type: file
+            description: PLINK2 pvar file
+            pattern: "*.pvar"
+  - psam:
+      description: PLINK2 psam file
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - psam:
+            type: file
+            description: PLINK2 psam file
+            pattern: "*.psam"
+  - evecfile:
+      description: PCA eigenvectors from PLINK2
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - eigenvec:
+            type: file
+            description: PCA eigenvectors from PLINK2
+            pattern: "*.eigenvec"
+  - evfile:
+      description: PCA eigenvalues from PLINK2
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - eigenval:
+            type: file
+            description: PCA eigenvalues from PLINK2
+            pattern: "*.eigenval"
+  - pca_log:
+      description: PLINK2 PCA log file
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - log:
+            type: file
+            description: PLINK2 PCA log file
+            pattern: "*.log"
+  - tsv:
+      description: TSV converted from eigenvec by gawk
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - tsv:
+            type: file
+            description: TSV converted from eigenvec by gawk
+            pattern: "*.eigenvec"
+  - clusters:
+      description: Cluster assignments
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - clusters:
+            type: file
+            description: Cluster assignments
+            pattern: "*.clusters.csv"
+  - cluster_info:
+      description: Clustering parameters and statistics
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - info:
+            type: file
+            description: Clustering parameters and statistics
+            pattern: "*.clustering_info.json"
+  - metrics:
+      description: Cluster quality metrics
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - metrics:
+            type: file
+            description: Cluster quality metrics
+            pattern: "*.metrics.tsv"
+  - k_sweep:
+      description: K sweep scores
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - k_sweep:
+            type: file
+            description: K sweep scores
+            pattern: "*.k_sweep.csv"
+  - selected:
+      description: Selected clustering parameters
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - selected:
+            type: file
+            description: Selected clustering parameters
+            pattern: "*.selected.json"
+  - metric_plots:
+      description: Cluster metric plots
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - plots:
+            type: file
+            description: Cluster metric plots
+            pattern: "*.png"
+  - umap_tsv:
+      description: UMAP coordinates per sample
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - umap_tsv:
+            type: file
+            description: UMAP coordinates per sample
+            pattern: "*.umap.tsv"
+  - tsne_tsv:
+      description: t-SNE coordinates per sample
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - tsne_tsv:
+            type: file
+            description: t-SNE coordinates per sample
+            pattern: "*.tsne.tsv"
+  - umap_png:
+      description: UMAP plot coloured by cluster
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - umap_png:
+            type: file
+            description: UMAP plot coloured by cluster
+            pattern: "*.umap.png"
+  - tsne_png:
+      description: t-SNE plot coloured by cluster
+      structure:
+        - meta:
+            type: map
+            description: Groovy map containing sample metadata
+        - tsne_png:
+            type: file
+            description: t-SNE plot coloured by cluster
+            pattern: "*.tsne.png"
 authors:
   - "@dbaku42"
 maintainers:
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index b1cb5388ec29..01db045b0976 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -19,6 +19,23 @@ nextflow_workflow {
 
     config "./nextflow.config"
 
+    def unstable = [
+        "umap_png",
+        "tsne_png",
+        "metric_plots",
+        "beagle_log",
+        "pca_log",
+        "imputed_vcf",
+        "pgen",
+        "pvar",
+        "psam",
+        "evecfile",
+        "evfile",
+        "tsv",
+        "umap_tsv",
+        "tsne_tsv"
+    ]
+
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
         when {
             workflow {
@@ -44,16 +61,7 @@ nextflow_workflow {
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(
-                    sanitizeOutput(
-                        workflow.out,
-                        unstableKeys: [
-                            "umap_png",
-                            "tsne_png",
-                            "metric_plots"
-                        ]
-                    )
-                ).match() }
+                { assert snapshot(sanitizeOutput(workflow.out, unstableKeys: unstable)).match() }
             )
         }
     }
@@ -83,16 +91,7 @@ nextflow_workflow {
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(
-                    sanitizeOutput(
-                        workflow.out,
-                        unstableKeys: [
-                            "umap_png",
-                            "tsne_png",
-                            "metric_plots"
-                        ]
-                    )
-                ).match() }
+                { assert snapshot(sanitizeOutput(workflow.out, unstableKeys: unstable)).match() }
             )
         }
     }
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index f6d1862a39ad..91ca7a3b6258 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -7,7 +7,7 @@
                         {
                             "id": "test"
                         },
-                        "test.bglout.log:md5,00f899a6db795f7d4bd79b5961ec7d10"
+                        "test.bglout.log"
                     ]
                 ],
                 "cluster_info": [
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,f4f73c989de9e52384b786ff6ac040e5"
+                        "test.clustering_info.json:md5,fe931a66180b920fb76958dc4026eae2"
                     ]
                 ],
                 "clusters": [
@@ -31,7 +31,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenvec:md5,655e0a4283a1f9d9f13c7dbe0e6da1d9"
+                        "test.eigenvec"
                     ]
                 ],
                 "evfile": [
@@ -39,7 +39,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
+                        "test.eigenval"
                     ]
                 ],
                 "imputed_vcf": [
@@ -47,7 +47,7 @@
                         {
                             "id": "test"
                         },
-                        "test.bglout.vcf.gz:md5,ef94995e50ba034aeb8119ad15fb6ccc"
+                        "test.bglout.vcf.gz"
                     ]
                 ],
                 "k_sweep": [
@@ -55,7 +55,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,113fa7245a810786ec404769f5ba5698"
+                        "test.k_sweep.csv:md5,c45d6918834e00a28498ca5ca8c0813e"
                     ]
                 ],
                 "metric_plots": [
@@ -76,7 +76,7 @@
                         {
                             "id": "test"
                         },
-                        "test.metrics.tsv:md5,9f203e3c741435f1317dcb4ab44c43c3"
+                        "test.metrics.tsv:md5,554b253a6508b4aa3d5396c94b41e829"
                     ]
                 ],
                 "pca_log": [
@@ -84,7 +84,7 @@
                         {
                             "id": "test"
                         },
-                        "test.log:md5,3d794ffb37ae49b03dbc8a06a408825f"
+                        "test.log"
                     ]
                 ],
                 "pgen": [
@@ -92,7 +92,7 @@
                         {
                             "id": "test"
                         },
-                        "test.pgen:md5,b183c72cbf75758521bd42a21a02e882"
+                        "test.pgen"
                     ]
                 ],
                 "psam": [
@@ -100,7 +100,7 @@
                         {
                             "id": "test"
                         },
-                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
+                        "test.psam"
                     ]
                 ],
                 "pvar": [
@@ -108,7 +108,7 @@
                         {
                             "id": "test"
                         },
-                        "test.pvar:md5,9c89b734017db356ccaa0190ab88c199"
+                        "test.pvar"
                     ]
                 ],
                 "selected": [
@@ -116,7 +116,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json:md5,ddbef02b869e51b8eaadceebd9ebd064"
+                        "test.selected.json:md5,40dcca755ed1cc16c4ecd73a8f71ddcc"
                     ]
                 ],
                 "tsne_png": [
@@ -132,7 +132,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,20f545d08f1175bfe1825b3932833b8d"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -140,7 +140,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv:md5,94681fa5806fbf33fa5c5041c3c29f29"
+                        "test.tsv"
                     ]
                 ],
                 "umap_png": [
@@ -156,12 +156,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,a7d209592da80adf142c5f1c2bce9ea2"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:28:38.960190054",
+        "timestamp": "2026-08-26T15:54:35.227818603",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -175,7 +175,7 @@
                         {
                             "id": "test"
                         },
-                        "test.bglout.log:md5,00f899a6db795f7d4bd79b5961ec7d10"
+                        "test.bglout.log"
                     ]
                 ],
                 "cluster_info": [
@@ -199,7 +199,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenvec:md5,cb7d3501265fb6e681f9a66552faff42"
+                        "test.eigenvec"
                     ]
                 ],
                 "evfile": [
@@ -207,7 +207,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
+                        "test.eigenval"
                     ]
                 ],
                 "imputed_vcf": [
@@ -215,7 +215,7 @@
                         {
                             "id": "test"
                         },
-                        "test.bglout.vcf.gz:md5,ef94995e50ba034aeb8119ad15fb6ccc"
+                        "test.bglout.vcf.gz"
                     ]
                 ],
                 "k_sweep": [
@@ -223,7 +223,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,d75662c7c614f39e294601653c02de8d"
+                        "test.k_sweep.csv:md5,f3d4ba46963ec779099d616d23cf8156"
                     ]
                 ],
                 "metric_plots": [
@@ -252,7 +252,7 @@
                         {
                             "id": "test"
                         },
-                        "test.log:md5,65d20c952985adb5fa7229a5d0d4fc0c"
+                        "test.log"
                     ]
                 ],
                 "pgen": [
@@ -260,7 +260,7 @@
                         {
                             "id": "test"
                         },
-                        "test.pgen:md5,b183c72cbf75758521bd42a21a02e882"
+                        "test.pgen"
                     ]
                 ],
                 "psam": [
@@ -268,7 +268,7 @@
                         {
                             "id": "test"
                         },
-                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
+                        "test.psam"
                     ]
                 ],
                 "pvar": [
@@ -276,7 +276,7 @@
                         {
                             "id": "test"
                         },
-                        "test.pvar:md5,9c89b734017db356ccaa0190ab88c199"
+                        "test.pvar"
                     ]
                 ],
                 "selected": [
@@ -300,7 +300,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,f4952012bc87993ca78429d4a823edb1"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -308,7 +308,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv:md5,8009b5a5210c1dae667f40c40b450035"
+                        "test.tsv"
                     ]
                 ],
                 "umap_png": [
@@ -324,12 +324,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,26c791bc4d38dff6f979582611dbc27d"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:29:18.988004598",
+        "timestamp": "2026-08-26T15:55:13.730658349",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 59e09ba60ebba387c66bf90a3374fb81cfb41fc2 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Wed, 26 Aug 2026 16:09:30 +0200
Subject: [PATCH 16/34] Update import paths in main.nf for modules

---
 subworkflows/nf-core/snpclustering/main.nf | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 3b8fb56bf670..edb439e8f14a 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,10 +1,10 @@
 include { BEAGLE5_BEAGLE                } from '../../../modules/nf-core/beagle5/beagle'
-include { PLINK2_VCF                    } from '../../../modules/nf-core/plink2/vcf/main'
-include { PLINK2_PCA                    } from '../../../modules/nf-core/plink2/pca/main'
-include { GAWK as GAWK_EIGENVEC_TO_TSV  } from '../../../modules/nf-core/gawk/main'
-include { CUSTOM_PCACLUSTERING          } from '../../../modules/nf-core/custom/pcaclustering/main'
-include { CUSTOM_CLUSTERMETRICS         } from '../../../modules/nf-core/custom/clustermetrics/main'
-include { CUSTOM_CLUSTERVISUALIZATION   } from '../../../modules/nf-core/custom/clustervisualization/main'
+include { PLINK2_VCF                    } from '../../../modules/nf-core/plink2/vcf'
+include { PLINK2_PCA                    } from '../../../modules/nf-core/plink2/pca'
+include { GAWK as GAWK_EIGENVEC_TO_TSV  } from '../../../modules/nf-core/gawk'
+include { CUSTOM_PCACLUSTERING          } from '../../../modules/nf-core/custom/pcaclustering'
+include { CUSTOM_CLUSTERMETRICS         } from '../../../modules/nf-core/custom/clustermetrics'
+include { CUSTOM_CLUSTERVISUALIZATION   } from '../../../modules/nf-core/custom/clustervisualization'
 
 workflow SNPCLUSTERING {
     take:

From cc0a0528a2287b90f7b31b2a182b1567a2222c20 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 19:14:27 +0200
Subject: [PATCH 17/34] Set seed 1 plink2_pca

---
 .../nf-core/snpclustering/tests/main.nf.test  |  8 +--
 .../snpclustering/tests/main.nf.test.snap     | 54 +++++++++----------
 .../snpclustering/tests/nextflow.config       |  3 ++
 3 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 01db045b0976..ab54d600b2ab 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -20,9 +20,6 @@ nextflow_workflow {
     config "./nextflow.config"
 
     def unstable = [
-        "umap_png",
-        "tsne_png",
-        "metric_plots",
         "beagle_log",
         "pca_log",
         "imputed_vcf",
@@ -30,10 +27,7 @@ nextflow_workflow {
         "pvar",
         "psam",
         "evecfile",
-        "evfile",
-        "tsv",
-        "umap_tsv",
-        "tsne_tsv"
+        "evfile"
     ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 91ca7a3b6258..fca6b4aa8b84 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,fe931a66180b920fb76958dc4026eae2"
+                        "test.clustering_info.json:md5,0fb1dbe8182e71725eb0d910c400d49f"
                     ]
                 ],
                 "clusters": [
@@ -55,7 +55,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,c45d6918834e00a28498ca5ca8c0813e"
+                        "test.k_sweep.csv:md5,d05da63474596a4a20cac7160907228d"
                     ]
                 ],
                 "metric_plots": [
@@ -64,10 +64,10 @@
                             "id": "test"
                         },
                         [
-                            "test.calinski_harabasz.png",
-                            "test.davies_bouldin.png",
-                            "test.elbow.png",
-                            "test.silhouette.png"
+                            "test.calinski_harabasz.png:md5,126ae1fd131c3d312200dede14daf921",
+                            "test.davies_bouldin.png:md5,e30697feedfe4eef4256f1a29cd5a174",
+                            "test.elbow.png:md5,58642a6c45ca085b73f65062a094ed94",
+                            "test.silhouette.png:md5,4036cc8163eafff1bfbc45648e9bfa03"
                         ]
                     ]
                 ],
@@ -76,7 +76,7 @@
                         {
                             "id": "test"
                         },
-                        "test.metrics.tsv:md5,554b253a6508b4aa3d5396c94b41e829"
+                        "test.metrics.tsv:md5,82d8ff162f7ae167e5613afc9ca41311"
                     ]
                 ],
                 "pca_log": [
@@ -116,7 +116,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json:md5,40dcca755ed1cc16c4ecd73a8f71ddcc"
+                        "test.selected.json:md5,b0da8d7265531d757724e3ec8b358167"
                     ]
                 ],
                 "tsne_png": [
@@ -124,7 +124,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.png"
+                        "test.tsne.png:md5,d298f009fc6ae29b3e902069c2c19116"
                     ]
                 ],
                 "tsne_tsv": [
@@ -132,7 +132,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv"
+                        "test.tsne.tsv:md5,f3be272b77fdc209611d7f552443c54d"
                     ]
                 ],
                 "tsv": [
@@ -140,7 +140,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv"
+                        "test.tsv:md5,402ff5581c491c03227f66e59d55e189"
                     ]
                 ],
                 "umap_png": [
@@ -148,7 +148,7 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.png"
+                        "test.umap.png:md5,42641c121e5040434e8b365dfd4ad18a"
                     ]
                 ],
                 "umap_tsv": [
@@ -156,12 +156,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv"
+                        "test.umap.tsv:md5,cd124eb5e14ed6d02f3cce45a2ae2559"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:54:35.227818603",
+        "timestamp": "2026-08-26T19:12:30.318638023",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -223,7 +223,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,f3d4ba46963ec779099d616d23cf8156"
+                        "test.k_sweep.csv:md5,d05da63474596a4a20cac7160907228d"
                     ]
                 ],
                 "metric_plots": [
@@ -232,10 +232,10 @@
                             "id": "test"
                         },
                         [
-                            "test.calinski_harabasz.png",
-                            "test.davies_bouldin.png",
-                            "test.elbow.png",
-                            "test.silhouette.png"
+                            "test.calinski_harabasz.png:md5,126ae1fd131c3d312200dede14daf921",
+                            "test.davies_bouldin.png:md5,e30697feedfe4eef4256f1a29cd5a174",
+                            "test.elbow.png:md5,58642a6c45ca085b73f65062a094ed94",
+                            "test.silhouette.png:md5,4036cc8163eafff1bfbc45648e9bfa03"
                         ]
                     ]
                 ],
@@ -292,7 +292,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.png"
+                        "test.tsne.png:md5,23fc4ac667d9ef86bfd56652a8d79eab"
                     ]
                 ],
                 "tsne_tsv": [
@@ -300,7 +300,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv"
+                        "test.tsne.tsv:md5,971871b2a4befda6baa9a9521cc1084d"
                     ]
                 ],
                 "tsv": [
@@ -308,7 +308,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv"
+                        "test.tsv:md5,402ff5581c491c03227f66e59d55e189"
                     ]
                 ],
                 "umap_png": [
@@ -316,7 +316,7 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.png"
+                        "test.umap.png:md5,3df8ccc41ea0cd080224879353d3f5bf"
                     ]
                 ],
                 "umap_tsv": [
@@ -324,12 +324,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv"
+                        "test.umap.tsv:md5,0b660d0fbd3df1f6cd130eb50339afe3"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:55:13.730658349",
+        "timestamp": "2026-08-26T19:13:10.66966192",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -497,7 +497,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:29:43.011468684",
+        "timestamp": "2026-08-26T18:02:19.483018891",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -665,7 +665,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T15:29:31.961527536",
+        "timestamp": "2026-08-26T18:01:09.390553721",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 93f8ed077be8..0d5b9ffa89f2 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -8,6 +8,9 @@ params {
 }
 
 process {
+    withName: 'PLINK2_PCA' {
+        ext.args = '--seed 1'
+    }
     withName: GAWK_EIGENVEC_TO_TSV {
         ext.args   = "-v OFS='\\t'"
         ext.suffix = "tsv"

From 44bb942437ff70e1e18baaabb48444003c4ae935 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 19:55:59 +0200
Subject: [PATCH 18/34] Added tsv in unstable md5

---
 .../nf-core/snpclustering/tests/main.nf.test  |  6 ++++-
 .../snpclustering/tests/main.nf.test.snap     | 22 +++++++++----------
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index ab54d600b2ab..ad0a394907d2 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -27,7 +27,11 @@ nextflow_workflow {
         "pvar",
         "psam",
         "evecfile",
-        "evfile"
+        "evfile",
+        "umap_png",
+        "tsne_png",
+        "umap_tsv",
+        "tsne_tsv"
     ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index fca6b4aa8b84..d1108974dd9e 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,0fb1dbe8182e71725eb0d910c400d49f"
+                        "test.clustering_info.json:md5,23e8966d37219b6ebe614eaaebd8636d"
                     ]
                 ],
                 "clusters": [
@@ -124,7 +124,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.png:md5,d298f009fc6ae29b3e902069c2c19116"
+                        "test.tsne.png"
                     ]
                 ],
                 "tsne_tsv": [
@@ -132,7 +132,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,f3be272b77fdc209611d7f552443c54d"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -148,7 +148,7 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.png:md5,42641c121e5040434e8b365dfd4ad18a"
+                        "test.umap.png"
                     ]
                 ],
                 "umap_tsv": [
@@ -156,12 +156,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,cd124eb5e14ed6d02f3cce45a2ae2559"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T19:12:30.318638023",
+        "timestamp": "2026-08-26T19:54:05.005883762",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -292,7 +292,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.png:md5,23fc4ac667d9ef86bfd56652a8d79eab"
+                        "test.tsne.png"
                     ]
                 ],
                 "tsne_tsv": [
@@ -300,7 +300,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,971871b2a4befda6baa9a9521cc1084d"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -316,7 +316,7 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.png:md5,3df8ccc41ea0cd080224879353d3f5bf"
+                        "test.umap.png"
                     ]
                 ],
                 "umap_tsv": [
@@ -324,12 +324,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,0b660d0fbd3df1f6cd130eb50339afe3"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-26T19:13:10.66966192",
+        "timestamp": "2026-08-26T19:54:38.94631929",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 44baf0f0b1ab7028199dd5dc6b8eabc2ec349969 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Wed, 26 Aug 2026 20:09:57 +0200
Subject: [PATCH 19/34] Add UMAP and t-SNE output file references

Added new output files for UMAP and t-SNE visualizations.
---
 subworkflows/nf-core/snpclustering/tests/main.nf.test | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index ab54d600b2ab..4f09fc2098ef 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -26,8 +26,10 @@ nextflow_workflow {
         "pgen",
         "pvar",
         "psam",
-        "evecfile",
-        "evfile"
+        "umap_png",
+        "tsne_png",
+        "umap_tsv",
+        "tsne_tsv
     ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {

From 6017365f2958ba3dd24650b30e1f406f38dce119 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Wed, 26 Aug 2026 20:13:58 +0200
Subject: [PATCH 20/34] Fix typo in tsne_tsv variable declaration

---
 subworkflows/nf-core/snpclustering/tests/main.nf.test | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 4f09fc2098ef..48ac5c9b7650 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -29,7 +29,7 @@ nextflow_workflow {
         "umap_png",
         "tsne_png",
         "umap_tsv",
-        "tsne_tsv
+        "tsne_tsv"
     ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {

From 90425b64e574c18eb43fb6a742d7a8e17e5da805 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 20:59:30 +0200
Subject: [PATCH 21/34] Update snapshot

---
 subworkflows/nf-core/snpclustering/tests/main.nf.test.snap | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index d1108974dd9e..d7928a65d525 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,23e8966d37219b6ebe614eaaebd8636d"
+                        "test.clustering_info.json:md5,32112858ff769d83d1558ec56c212dd2"
                     ]
                 ],
                 "clusters": [
@@ -161,7 +161,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T19:54:05.005883762",
+        "timestamp": "2026-08-26T20:57:46.611731056",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 94751cce4aeb1a83dec9285b1941d4c9be0432c8 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 26 Aug 2026 21:14:54 +0200
Subject: [PATCH 22/34] Update snapshot

---
 subworkflows/nf-core/snpclustering/tests/main.nf.test.snap | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index d7928a65d525..6b8b53861054 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,32112858ff769d83d1558ec56c212dd2"
+                        "test.clustering_info.json:md5,0fb1dbe8182e71725eb0d910c400d49f"
                     ]
                 ],
                 "clusters": [
@@ -161,7 +161,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T20:57:46.611731056",
+        "timestamp": "2026-08-26T21:09:37.53551214",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 2e0c680c375d9aba10b9c42ad490047ca996244f Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 27 Aug 2026 11:47:59 +0200
Subject: [PATCH 23/34] stabilizing through config file

---
 .../nf-core/snpclustering/tests/main.nf.test  |  7 ++-
 .../snpclustering/tests/main.nf.test.snap     | 36 ++++++-------
 .../snpclustering/tests/nextflow.config       | 53 +++++++++++++++++--
 3 files changed, 73 insertions(+), 23 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 152cdcf616ad..9e87e34e4c1c 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -19,7 +19,7 @@ nextflow_workflow {
 
     config "./nextflow.config"
 
-        def unstable = [
+    def unstable = [
         "beagle_log",
         "pca_log",
         "imputed_vcf",
@@ -28,11 +28,14 @@ nextflow_workflow {
         "psam",
         "evecfile",
         "evfile",
+        "k_sweep",
+        "metric_plots",
+        "selected",
         "umap_png",
         "tsne_png",
         "umap_tsv",
         "tsne_tsv"
-    ]    
+    ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
         when {
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 148ccbaeb915..3c325fd8eea2 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,32112858ff769d83d1558ec56c212dd2"
+                        "test.clustering_info.json:md5,e3cfaf9b4966910425fe730fe80299fa"
                     ]
                 ],
                 "clusters": [
@@ -55,7 +55,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,d05da63474596a4a20cac7160907228d"
+                        "test.k_sweep.csv"
                     ]
                 ],
                 "metric_plots": [
@@ -64,10 +64,10 @@
                             "id": "test"
                         },
                         [
-                            "test.calinski_harabasz.png:md5,126ae1fd131c3d312200dede14daf921",
-                            "test.davies_bouldin.png:md5,e30697feedfe4eef4256f1a29cd5a174",
-                            "test.elbow.png:md5,58642a6c45ca085b73f65062a094ed94",
-                            "test.silhouette.png:md5,4036cc8163eafff1bfbc45648e9bfa03"
+                            "test.calinski_harabasz.png",
+                            "test.davies_bouldin.png",
+                            "test.elbow.png",
+                            "test.silhouette.png"
                         ]
                     ]
                 ],
@@ -76,7 +76,7 @@
                         {
                             "id": "test"
                         },
-                        "test.metrics.tsv:md5,82d8ff162f7ae167e5613afc9ca41311"
+                        "test.metrics.tsv:md5,82e1eecd3e94e64de5c1a2f5d44eb9f5"
                     ]
                 ],
                 "pca_log": [
@@ -116,7 +116,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json:md5,b0da8d7265531d757724e3ec8b358167"
+                        "test.selected.json"
                     ]
                 ],
                 "tsne_png": [
@@ -140,7 +140,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv:md5,402ff5581c491c03227f66e59d55e189"
+                        "test.tsv:md5,f5ec5abd246d89cf50d333d432e4366a"
                     ]
                 ],
                 "umap_png": [
@@ -161,7 +161,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T21:30:27.835190347",
+        "timestamp": "2026-08-27T11:45:42.400185807",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -223,7 +223,7 @@
                         {
                             "id": "test"
                         },
-                        "test.k_sweep.csv:md5,d05da63474596a4a20cac7160907228d"
+                        "test.k_sweep.csv"
                     ]
                 ],
                 "metric_plots": [
@@ -232,10 +232,10 @@
                             "id": "test"
                         },
                         [
-                            "test.calinski_harabasz.png:md5,126ae1fd131c3d312200dede14daf921",
-                            "test.davies_bouldin.png:md5,e30697feedfe4eef4256f1a29cd5a174",
-                            "test.elbow.png:md5,58642a6c45ca085b73f65062a094ed94",
-                            "test.silhouette.png:md5,4036cc8163eafff1bfbc45648e9bfa03"
+                            "test.calinski_harabasz.png",
+                            "test.davies_bouldin.png",
+                            "test.elbow.png",
+                            "test.silhouette.png"
                         ]
                     ]
                 ],
@@ -284,7 +284,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json:md5,138b2bae0f67f913dcead80f8202d9af"
+                        "test.selected.json"
                     ]
                 ],
                 "tsne_png": [
@@ -308,7 +308,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsv:md5,402ff5581c491c03227f66e59d55e189"
+                        "test.tsv:md5,f5ec5abd246d89cf50d333d432e4366a"
                     ]
                 ],
                 "umap_png": [
@@ -329,7 +329,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T19:54:38.94631929",
+        "timestamp": "2026-08-27T11:46:23.671901862",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 0d5b9ffa89f2..f3c12ec19a78 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -1,6 +1,6 @@
 params {
     npcs               = 8
-    use_approx         = true
+    use_approx         = false
     algorithm          = "kmeans"
     n_clusters         = 3
     dbscan_eps         = 0.5
@@ -8,11 +8,58 @@ params {
 }
 
 process {
+    withName: 'BEAGLE5_BEAGLE' {
+        cpus     = 4
+        memory   = '8 GB'
+        ext.args = 'seed=1 nthreads=4'
+    }
+
+    withName: 'PLINK2_VCF' {
+        ext.args = '--seed 1'
+    }
+
     withName: 'PLINK2_PCA' {
         ext.args = '--seed 1'
     }
-    withName: GAWK_EIGENVEC_TO_TSV {
+
+    withName: 'GAWK_EIGENVEC_TO_TSV' {
         ext.args   = "-v OFS='\\t'"
-        ext.suffix = "tsv"
+        ext.suffix = 'tsv'
+    }
+
+    withName: 'CUSTOM_PCACLUSTERING' {
+        cpus = 1
+        env {
+            OMP_NUM_THREADS      = '1'
+            OPENBLAS_NUM_THREADS = '1'
+            MKL_NUM_THREADS      = '1'
+            NUMEXPR_NUM_THREADS  = '1'
+        }
+    }
+
+    withName: 'CUSTOM_CLUSTERMETRICS' {
+        cpus     = 1
+        ext.args = '--k-min 2 --k-max 12'
+        env {
+            OMP_NUM_THREADS      = '1'
+            OPENBLAS_NUM_THREADS = '1'
+            MKL_NUM_THREADS      = '1'
+            NUMEXPR_NUM_THREADS  = '1'
+            NUMBA_NUM_THREADS    = '1'
+        }
+    }
+
+    withName: 'CUSTOM_CLUSTERVISUALIZATION' {
+        cpus     = 1
+        ext.args = '--umap-neighbors 15 --tsne-perplexity 30'
+        env {
+            OMP_NUM_THREADS      = '1'
+            OPENBLAS_NUM_THREADS = '1'
+            MKL_NUM_THREADS      = '1'
+            NUMEXPR_NUM_THREADS  = '1'
+            NUMBA_NUM_THREADS    = '1'
+            NUMBA_CACHE_DIR      = '/tmp'
+            MPLCONFIGDIR         = '/tmp'
+        }
     }
 }

From 78122f0b9ad6230369b64a7410313e888ae3869e Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 27 Aug 2026 12:36:40 +0200
Subject: [PATCH 24/34] Fixing env block

---
 .../snpclustering/tests/main.nf.test.snap     |  4 +--
 .../snpclustering/tests/nextflow.config       | 34 ++++++-------------
 2 files changed, 13 insertions(+), 25 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 3c325fd8eea2..b5fb67b176cc 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,e3cfaf9b4966910425fe730fe80299fa"
+                        "test.clustering_info.json:md5,ffab1c4d2fa185211fe024365e7bc432"
                     ]
                 ],
                 "clusters": [
@@ -161,7 +161,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-27T11:45:42.400185807",
+        "timestamp": "2026-08-27T12:32:09.448470818",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index f3c12ec19a78..29057c7a404f 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -7,10 +7,20 @@ params {
     dbscan_min_samples = 5
 }
 
+env {
+    OMP_NUM_THREADS      = '1'
+    OPENBLAS_NUM_THREADS = '1'
+    MKL_NUM_THREADS      = '1'
+    NUMEXPR_NUM_THREADS  = '1'
+    NUMBA_NUM_THREADS    = '1'
+    NUMBA_CACHE_DIR      = '/tmp'
+    MPLCONFIGDIR         = '/tmp'
+}
+
 process {
     withName: 'BEAGLE5_BEAGLE' {
         cpus     = 4
-        memory   = '8 GB'
+        memory   = 8.GB
         ext.args = 'seed=1 nthreads=4'
     }
 
@@ -29,37 +39,15 @@ process {
 
     withName: 'CUSTOM_PCACLUSTERING' {
         cpus = 1
-        env {
-            OMP_NUM_THREADS      = '1'
-            OPENBLAS_NUM_THREADS = '1'
-            MKL_NUM_THREADS      = '1'
-            NUMEXPR_NUM_THREADS  = '1'
-        }
     }
 
     withName: 'CUSTOM_CLUSTERMETRICS' {
         cpus     = 1
         ext.args = '--k-min 2 --k-max 12'
-        env {
-            OMP_NUM_THREADS      = '1'
-            OPENBLAS_NUM_THREADS = '1'
-            MKL_NUM_THREADS      = '1'
-            NUMEXPR_NUM_THREADS  = '1'
-            NUMBA_NUM_THREADS    = '1'
-        }
     }
 
     withName: 'CUSTOM_CLUSTERVISUALIZATION' {
         cpus     = 1
         ext.args = '--umap-neighbors 15 --tsne-perplexity 30'
-        env {
-            OMP_NUM_THREADS      = '1'
-            OPENBLAS_NUM_THREADS = '1'
-            MKL_NUM_THREADS      = '1'
-            NUMEXPR_NUM_THREADS  = '1'
-            NUMBA_NUM_THREADS    = '1'
-            NUMBA_CACHE_DIR      = '/tmp'
-            MPLCONFIGDIR         = '/tmp'
-        }
     }
 }

From 2d428b297ec677ca9b8cf7f11bac83d74519c8a1 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Thu, 27 Aug 2026 15:23:11 +0200
Subject: [PATCH 25/34] Remove unused output variables from tests to check md5
 stabilty

---
 subworkflows/nf-core/snpclustering/tests/main.nf.test | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 9e87e34e4c1c..5a17f1fd3607 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -25,16 +25,10 @@ nextflow_workflow {
         "imputed_vcf",
         "pgen",
         "pvar",
-        "psam",
-        "evecfile",
-        "evfile",
         "k_sweep",
         "metric_plots",
-        "selected",
         "umap_png",
-        "tsne_png",
-        "umap_tsv",
-        "tsne_tsv"
+        "tsne_png"
     ]
 
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {

From da18b2fcc45c286f1c80f8a17ed7922e6bc6540f Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 27 Aug 2026 15:36:26 +0200
Subject: [PATCH 26/34] Update snapshot

---
 .../snpclustering/tests/main.nf.test.snap     | 28 +++++++++----------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index b5fb67b176cc..b04ec8ffebd4 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -31,7 +31,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenvec"
+                        "test.eigenvec:md5,0e5d88169892d522252827b7897c0369"
                     ]
                 ],
                 "evfile": [
@@ -39,7 +39,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenval"
+                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
                     ]
                 ],
                 "imputed_vcf": [
@@ -100,7 +100,7 @@
                         {
                             "id": "test"
                         },
-                        "test.psam"
+                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
                     ]
                 ],
                 "pvar": [
@@ -116,7 +116,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json"
+                        "test.selected.json:md5,d085933630a002310508c3ef0879f1c8"
                     ]
                 ],
                 "tsne_png": [
@@ -132,7 +132,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv"
+                        "test.tsne.tsv:md5,1a3bbc0cd0c62160252b8bd6c23b5934"
                     ]
                 ],
                 "tsv": [
@@ -156,12 +156,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv"
+                        "test.umap.tsv:md5,9cd5ff6fd3a036d721882eb02ce6617a"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-27T12:32:09.448470818",
+        "timestamp": "2026-08-27T15:34:32.894346349",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -199,7 +199,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenvec"
+                        "test.eigenvec:md5,0e5d88169892d522252827b7897c0369"
                     ]
                 ],
                 "evfile": [
@@ -207,7 +207,7 @@
                         {
                             "id": "test"
                         },
-                        "test.eigenval"
+                        "test.eigenval:md5,a5d4576064133a95bbf629b99b43a0c3"
                     ]
                 ],
                 "imputed_vcf": [
@@ -268,7 +268,7 @@
                         {
                             "id": "test"
                         },
-                        "test.psam"
+                        "test.psam:md5,31604b4a3b20fb02ef1c59e9ead65f00"
                     ]
                 ],
                 "pvar": [
@@ -284,7 +284,7 @@
                         {
                             "id": "test"
                         },
-                        "test.selected.json"
+                        "test.selected.json:md5,138b2bae0f67f913dcead80f8202d9af"
                     ]
                 ],
                 "tsne_png": [
@@ -300,7 +300,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv"
+                        "test.tsne.tsv:md5,f58cb946289e5c96f7a3c2a7908ef020"
                     ]
                 ],
                 "tsv": [
@@ -324,12 +324,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv"
+                        "test.umap.tsv:md5,29d8fa6c7cd768a652d208628f704cc5"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-27T11:46:23.671901862",
+        "timestamp": "2026-08-27T15:35:20.040760668",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From f788b1ae89a8b606d642956cf5ac790a382e45cb Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Thu, 27 Aug 2026 15:58:47 +0200
Subject: [PATCH 27/34] TSNE and UMAP tsv unstable md5

---
 .../nf-core/snpclustering/tests/main.nf.test         |  2 ++
 .../nf-core/snpclustering/tests/main.nf.test.snap    | 12 ++++++------
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 5a17f1fd3607..368e45c16240 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -28,6 +28,8 @@ nextflow_workflow {
         "k_sweep",
         "metric_plots",
         "umap_png",
+        "tsne_tsv",
+        "umap_tsv",
         "tsne_png"
     ]
 
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index b04ec8ffebd4..ba1ae9179c91 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -132,7 +132,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,1a3bbc0cd0c62160252b8bd6c23b5934"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -156,12 +156,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,9cd5ff6fd3a036d721882eb02ce6617a"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-27T15:34:32.894346349",
+        "timestamp": "2026-08-27T15:56:45.881810208",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -300,7 +300,7 @@
                         {
                             "id": "test"
                         },
-                        "test.tsne.tsv:md5,f58cb946289e5c96f7a3c2a7908ef020"
+                        "test.tsne.tsv"
                     ]
                 ],
                 "tsv": [
@@ -324,12 +324,12 @@
                         {
                             "id": "test"
                         },
-                        "test.umap.tsv:md5,29d8fa6c7cd768a652d208628f704cc5"
+                        "test.umap.tsv"
                     ]
                 ]
             }
         ],
-        "timestamp": "2026-08-27T15:35:20.040760668",
+        "timestamp": "2026-08-27T15:57:35.308865685",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 7c590bde1c6c58e50bd9753cbafdb834eed83594 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Mon, 31 Aug 2026 12:25:26 +0200
Subject: [PATCH 28/34] fix(snpclustering): keep test config to seeds and gawk
 suffix

Drop env/cpu overrides and default ext.args. Pin BEAGLE/PLINK2 seeds
for stable hashes and set GAWK_EIGENVEC_TO_TSV ext.suffix=tsv so the
output does not collide with PLINK2 ${meta.id}.eigenvec.
---
 .../snpclustering/awk/eigenvec_to_tsv.awk     | 18 +++++++---
 .../nf-core/snpclustering/tests/main.nf.test  | 36 +++++++++----------
 .../snpclustering/tests/main.nf.test.snap     | 10 +++---
 .../snpclustering/tests/nextflow.config       | 29 +--------------
 4 files changed, 38 insertions(+), 55 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk b/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
index c84a0c3e9160..be40fe450b82 100644
--- a/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
+++ b/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
@@ -1,9 +1,19 @@
-NR==1 {
+BEGIN {
+    FS = OFS = "\t"
+}
+
+NR == 1 {
     sub(/^#/, "")
-    if ($1 == "IID") {
-        $1 = "sample_id"
+    $0 = $0
+    for (i = 1; i <= NF; i++) {
+        if ($i == "IID") {
+            $i = "sample_id"
+        }
     }
     print
     next
 }
-{ print }
+
+{
+    print
+}
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 368e45c16240..f80b487bdb32 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -45,12 +45,12 @@ nextflow_workflow {
                 input[1] = Channel.empty()
                 input[2] = Channel.empty()
                 input[3] = ""
-                input[4] = params.npcs
-                input[5] = params.use_approx
+                input[4] = 8
+                input[5] = false
                 input[6] = "kmeans"
                 input[7] = 3
-                input[8] = params.dbscan_eps
-                input[9] = params.dbscan_min_samples
+                input[8] = 0.5
+                input[9] = 5
                 """
             }
         }
@@ -75,12 +75,12 @@ nextflow_workflow {
                 input[1] = Channel.empty()
                 input[2] = Channel.empty()
                 input[3] = ""
-                input[4] = params.npcs
-                input[5] = params.use_approx
+                input[4] = 8
+                input[5] = false
                 input[6] = "dbscan"
-                input[7] = params.n_clusters
-                input[8] = params.dbscan_eps
-                input[9] = params.dbscan_min_samples
+                input[7] = 3
+                input[8] = 0.5
+                input[9] = 5
                 """
             }
         }
@@ -106,12 +106,12 @@ nextflow_workflow {
                 input[1] = Channel.empty()
                 input[2] = Channel.empty()
                 input[3] = ""
-                input[4] = params.npcs
-                input[5] = params.use_approx
+                input[4] = 8
+                input[5] = false
                 input[6] = "kmeans"
                 input[7] = 3
-                input[8] = params.dbscan_eps
-                input[9] = params.dbscan_min_samples
+                input[8] = 0.5
+                input[9] = 5
                 """
             }
         }
@@ -137,12 +137,12 @@ nextflow_workflow {
                 input[1] = Channel.empty()
                 input[2] = Channel.empty()
                 input[3] = ""
-                input[4] = params.npcs
-                input[5] = params.use_approx
+                input[4] = 8
+                input[5] = false
                 input[6] = "dbscan"
-                input[7] = params.n_clusters
-                input[8] = params.dbscan_eps
-                input[9] = params.dbscan_min_samples
+                input[7] = 3
+                input[8] = 0.5
+                input[9] = 5
                 """
             }
         }
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index ba1ae9179c91..8aa645c8a1a2 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,ffab1c4d2fa185211fe024365e7bc432"
+                        "test.clustering_info.json:md5,5bfc98c30e4e6d7d4bd730e55fa90ca7"
                     ]
                 ],
                 "clusters": [
@@ -161,7 +161,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-27T15:56:45.881810208",
+        "timestamp": "2026-08-31T12:13:13.95854724",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -329,7 +329,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-27T15:57:35.308865685",
+        "timestamp": "2026-08-31T12:13:46.467083247",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -497,7 +497,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T18:02:19.483018891",
+        "timestamp": "2026-08-31T12:14:11.172911335",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -665,7 +665,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-26T18:01:09.390553721",
+        "timestamp": "2026-08-31T12:13:58.254898619",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index 29057c7a404f..c68232c7a163 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -7,21 +7,9 @@ params {
     dbscan_min_samples = 5
 }
 
-env {
-    OMP_NUM_THREADS      = '1'
-    OPENBLAS_NUM_THREADS = '1'
-    MKL_NUM_THREADS      = '1'
-    NUMEXPR_NUM_THREADS  = '1'
-    NUMBA_NUM_THREADS    = '1'
-    NUMBA_CACHE_DIR      = '/tmp'
-    MPLCONFIGDIR         = '/tmp'
-}
-
 process {
     withName: 'BEAGLE5_BEAGLE' {
-        cpus     = 4
-        memory   = 8.GB
-        ext.args = 'seed=1 nthreads=4'
+        ext.args = 'seed=1'
     }
 
     withName: 'PLINK2_VCF' {
@@ -33,21 +21,6 @@ process {
     }
 
     withName: 'GAWK_EIGENVEC_TO_TSV' {
-        ext.args   = "-v OFS='\\t'"
         ext.suffix = 'tsv'
     }
-
-    withName: 'CUSTOM_PCACLUSTERING' {
-        cpus = 1
-    }
-
-    withName: 'CUSTOM_CLUSTERMETRICS' {
-        cpus     = 1
-        ext.args = '--k-min 2 --k-max 12'
-    }
-
-    withName: 'CUSTOM_CLUSTERVISUALIZATION' {
-        cpus     = 1
-        ext.args = '--umap-neighbors 15 --tsne-perplexity 30'
-    }
 }

From 50fe64c418106bd786b62c639ad2640218498d63 Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Mon, 31 Aug 2026 12:56:20 +0200
Subject: [PATCH 29/34] Fix unstable md5sum

---
 .../nf-core/snpclustering/tests/main.nf.test  | 33 +++++++++-
 .../snpclustering/tests/main.nf.test.snap     | 64 +++++++++++++++++--
 2 files changed, 91 insertions(+), 6 deletions(-)

diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index f80b487bdb32..77c8398c2bfa 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -27,12 +27,31 @@ nextflow_workflow {
         "pvar",
         "k_sweep",
         "metric_plots",
+        "cluster_info",
         "umap_png",
         "tsne_tsv",
         "umap_tsv",
         "tsne_png"
     ]
 
+    def embedStats = { path ->
+        def rows = file(path).readLines().findAll { it }
+        def header = rows.head().split('\t') as List
+        [
+            header : header,
+            n_rows : rows.size() - 1,
+            n_cols : header.size()
+        ]
+    }
+
+    def clusterInfo = { path ->
+        def info_data = new groovy.json.JsonSlurper().parse(file(path))
+        if (info_data.containsKey('inertia')) {
+            info_data.inertia = (info_data.inertia as Double).round(4)
+        }
+        info_data
+    }
+
     test("homo_sapiens - 1000GP.chr22.vcf.gz - kmeans 3 clusters") {
         when {
             workflow {
@@ -58,7 +77,12 @@ nextflow_workflow {
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(sanitizeOutput(workflow.out, unstableKeys: unstable)).match() }
+                { assert snapshot(
+                    sanitizeOutput(workflow.out, unstableKeys: unstable),
+                    clusterInfo(workflow.out.cluster_info[0][1]),
+                    embedStats(workflow.out.umap_tsv[0][1]),
+                    embedStats(workflow.out.tsne_tsv[0][1])
+                ).match() }
             )
         }
     }
@@ -88,7 +112,12 @@ nextflow_workflow {
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(sanitizeOutput(workflow.out, unstableKeys: unstable)).match() }
+                { assert snapshot(
+                    sanitizeOutput(workflow.out, unstableKeys: unstable),
+                    clusterInfo(workflow.out.cluster_info[0][1]),
+                    embedStats(workflow.out.umap_tsv[0][1]),
+                    embedStats(workflow.out.tsne_tsv[0][1])
+                ).match() }
             )
         }
     }
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index 8aa645c8a1a2..eb11e4cc6b4c 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -15,7 +15,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,5bfc98c30e4e6d7d4bd730e55fa90ca7"
+                        "test.clustering_info.json"
                     ]
                 ],
                 "clusters": [
@@ -159,9 +159,36 @@
                         "test.umap.tsv"
                     ]
                 ]
+            },
+            {
+                "algorithm": "kmeans",
+                "k": 3,
+                "inertia": 6.2255,
+                "n_samples": 3202,
+                "n_features": 8
+            },
+            {
+                "header": [
+                    "sample_id",
+                    "Dim1",
+                    "Dim2",
+                    "cluster"
+                ],
+                "n_rows": 3202,
+                "n_cols": 4
+            },
+            {
+                "header": [
+                    "sample_id",
+                    "Dim1",
+                    "Dim2",
+                    "cluster"
+                ],
+                "n_rows": 3202,
+                "n_cols": 4
             }
         ],
-        "timestamp": "2026-08-31T12:13:13.95854724",
+        "timestamp": "2026-08-31T12:49:22.352660673",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -183,7 +210,7 @@
                         {
                             "id": "test"
                         },
-                        "test.clustering_info.json:md5,fa9a2eff36d06fe360a59f4c3cd63393"
+                        "test.clustering_info.json"
                     ]
                 ],
                 "clusters": [
@@ -327,9 +354,38 @@
                         "test.umap.tsv"
                     ]
                 ]
+            },
+            {
+                "algorithm": "dbscan",
+                "eps": 0.5,
+                "min_samples": 5,
+                "n_clusters_found": 1,
+                "n_noise": 0,
+                "n_samples": 3202,
+                "n_features": 8
+            },
+            {
+                "header": [
+                    "sample_id",
+                    "Dim1",
+                    "Dim2",
+                    "cluster"
+                ],
+                "n_rows": 3202,
+                "n_cols": 4
+            },
+            {
+                "header": [
+                    "sample_id",
+                    "Dim1",
+                    "Dim2",
+                    "cluster"
+                ],
+                "n_rows": 3202,
+                "n_cols": 4
             }
         ],
-        "timestamp": "2026-08-31T12:13:46.467083247",
+        "timestamp": "2026-08-31T12:49:54.909445446",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"

From 029813808f71ea684887f6c4a6bca63dd2b441ea Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Thu, 3 Sep 2026 08:49:27 +0200
Subject: [PATCH 30/34] Update subworkflows/nf-core/snpclustering/main.nf

Co-authored-by: Niklas Schandry <schandry@gmail.com>
---
 subworkflows/nf-core/snpclustering/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index edb439e8f14a..fb7afd77570c 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -12,7 +12,7 @@ workflow SNPCLUSTERING {
     refpanel_ch
     genmap_ch
     region
-    npcs
+    n_pcs
     use_approx
     algorithm
     n_clusters

From bbaa6d42663ef340406ea8db48044898fecd9f92 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Thu, 3 Sep 2026 08:49:47 +0200
Subject: [PATCH 31/34] Update subworkflows/nf-core/snpclustering/main.nf

Co-authored-by: Niklas Schandry <schandry@gmail.com>
---
 subworkflows/nf-core/snpclustering/main.nf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index fb7afd77570c..963e33dcba1c 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -60,7 +60,7 @@ workflow SNPCLUSTERING {
         .join(PLINK2_VCF.out.pvar)
         .join(PLINK2_VCF.out.psam)
         .map { meta, pgen, pvar, psam ->
-            tuple(meta, npcs, use_approx, pgen, psam, pvar)
+            tuple(meta, n_pcs, use_approx, pgen, psam, pvar)
         }
 
     PLINK2_PCA(ch_plink_pca_input)

From bd4bd3cb3cadd3ce257b1feec42ef4d226123f6c Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Wed, 9 Sep 2026 11:21:09 +0200
Subject: [PATCH 32/34] Enhance description for clustering metrics

Updated the description to include k-distance analysis.
---
 modules/nf-core/custom/clustermetrics/meta.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/modules/nf-core/custom/clustermetrics/meta.yml b/modules/nf-core/custom/clustermetrics/meta.yml
index 92a1bea0d37b..2cc8800d81a4 100644
--- a/modules/nf-core/custom/clustermetrics/meta.yml
+++ b/modules/nf-core/custom/clustermetrics/meta.yml
@@ -1,5 +1,5 @@
 name: "CUSTOM_CLUSTERMETRICS"
-description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz, Davies-Bouldin) and performs k-sweep analysis"
+description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz, Davies-Bouldin), performs k-sweep and k-distance analysis"
 keywords:
   - clustering
   - metrics

From 2897267696d35fd23826103cc05fa16e939b78d6 Mon Sep 17 00:00:00 2001
From: Donald Baku <141358602+dbaku42@users.noreply.github.com>
Date: Wed, 9 Sep 2026 11:22:26 +0200
Subject: [PATCH 33/34] Format description in meta.yml for readability

Split the description into multiple lines for better readability.
---
 modules/nf-core/custom/clustermetrics/meta.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/modules/nf-core/custom/clustermetrics/meta.yml b/modules/nf-core/custom/clustermetrics/meta.yml
index 2cc8800d81a4..4b53608ebae1 100644
--- a/modules/nf-core/custom/clustermetrics/meta.yml
+++ b/modules/nf-core/custom/clustermetrics/meta.yml
@@ -1,5 +1,6 @@
 name: "CUSTOM_CLUSTERMETRICS"
-description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz, Davies-Bouldin), performs k-sweep and k-distance analysis"
+description: "Computes clustering quality metrics (silhouette, Calinski-Harabasz,
+  Davies-Bouldin), performs k-sweep and k-distance analysis"
 keywords:
   - clustering
   - metrics

From 1e7ac0f50b54f6f3fa552807cb653deea2d0f0fd Mon Sep 17 00:00:00 2001
From: dbaku42 <dbaku42@gmail.com>
Date: Wed, 9 Sep 2026 10:59:44 +0200
Subject: [PATCH 34/34] fix(snpclustering): drop gawk; consume PLINK2 eigenvec
 directly

---
 .../custom/clustervisualization/meta.yml      | 10 +--
 modules/nf-core/custom/pcaclustering/meta.yml | 11 ++--
 .../snpclustering/awk/eigenvec_to_tsv.awk     | 19 ------
 subworkflows/nf-core/snpclustering/main.nf    | 61 +++----------------
 subworkflows/nf-core/snpclustering/meta.yml   | 14 +----
 .../nf-core/snpclustering/tests/main.nf.test  |  1 -
 .../snpclustering/tests/main.nf.test.snap     | 44 +++----------
 .../snpclustering/tests/nextflow.config       |  3 -
 8 files changed, 30 insertions(+), 133 deletions(-)
 delete mode 100644 subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk

diff --git a/modules/nf-core/custom/clustervisualization/meta.yml b/modules/nf-core/custom/clustervisualization/meta.yml
index 0b71dedc9490..7f3abf907165 100644
--- a/modules/nf-core/custom/clustervisualization/meta.yml
+++ b/modules/nf-core/custom/clustervisualization/meta.yml
@@ -35,7 +35,7 @@ input:
           numeric features (e.g. PCA scores).
         pattern: "*.{tsv,txt,eigenvec}"
         ontologies:
-          - edam: http://edamontology.org/format_3475 # TSV
+          - edam: http://edamontology.org/format_3475
     - clusters:
         type: file
         description: |
@@ -43,7 +43,7 @@ input:
           `cluster` columns. Label -1 is treated as DBSCAN noise.
         pattern: "*.csv"
         ontologies:
-          - edam: http://edamontology.org/format_3752 # CSV
+          - edam: http://edamontology.org/format_3752
 output:
   umap_tsv:
     - - meta:
@@ -55,7 +55,7 @@ output:
           pattern: "*.umap.tsv"
           ontologies:
             - edam: "http://edamontology.org/operation_2432"
-            - edam: http://edamontology.org/format_3475 # TSV
+            - edam: http://edamontology.org/format_3475
   tsne_tsv:
     - - meta:
           type: map
@@ -66,7 +66,7 @@ output:
           pattern: "*.tsne.tsv"
           ontologies:
             - edam: "http://edamontology.org/operation_2432"
-            - edam: http://edamontology.org/format_3475 # TSV
+            - edam: http://edamontology.org/format_3475
   umap_png:
     - - meta:
           type: map
@@ -91,7 +91,7 @@ output:
         description: "Software versions used in the module"
         pattern: "versions.yml"
         ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+          - edam: http://edamontology.org/format_3750
 topics:
   versions:
     - versions.yml:
diff --git a/modules/nf-core/custom/pcaclustering/meta.yml b/modules/nf-core/custom/pcaclustering/meta.yml
index 76ed03367b9d..4b867e771edc 100644
--- a/modules/nf-core/custom/pcaclustering/meta.yml
+++ b/modules/nf-core/custom/pcaclustering/meta.yml
@@ -1,5 +1,6 @@
 name: "CUSTOM_PCACLUSTERING"
-description: "Performs KMeans or DBSCAN clustering on a sample-by-feature numeric matrix (e.g. principal components, embeddings)"
+description: "Performs KMeans or DBSCAN clustering on a sample-by-feature numeric
+  matrix (e.g. principal components, embeddings)"
 keywords:
   - clustering
   - kmeans
@@ -32,7 +33,7 @@ input:
           `sample_id`.
         pattern: "*.{tsv,txt,eigenvec}"
         ontologies:
-          - edam: http://edamontology.org/format_3475 # TSV
+          - edam: http://edamontology.org/format_3475
   - algorithm:
       type: string
       description: Clustering algorithm to use (kmeans or dbscan)
@@ -55,7 +56,7 @@ output:
           description: CSV file with sample_id and assigned cluster
           pattern: "*.clusters.csv"
           ontologies:
-            - edam: http://edamontology.org/format_3752 # CSV
+            - edam: http://edamontology.org/format_3752
   info:
     - - meta:
           type: map
@@ -65,14 +66,14 @@ output:
           description: JSON file with clustering parameters and statistics
           pattern: "*.clustering_info.json"
           ontologies:
-            - edam: http://edamontology.org/format_3464 # JSON
+            - edam: http://edamontology.org/format_3464
   versions:
     - "versions.yml":
         type: file
         description: File containing software versions
         pattern: "versions.yml"
         ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+          - edam: http://edamontology.org/format_3750
 topics:
   versions:
     - versions.yml:
diff --git a/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk b/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
deleted file mode 100644
index be40fe450b82..000000000000
--- a/subworkflows/nf-core/snpclustering/awk/eigenvec_to_tsv.awk
+++ /dev/null
@@ -1,19 +0,0 @@
-BEGIN {
-    FS = OFS = "\t"
-}
-
-NR == 1 {
-    sub(/^#/, "")
-    $0 = $0
-    for (i = 1; i <= NF; i++) {
-        if ($i == "IID") {
-            $i = "sample_id"
-        }
-    }
-    print
-    next
-}
-
-{
-    print
-}
diff --git a/subworkflows/nf-core/snpclustering/main.nf b/subworkflows/nf-core/snpclustering/main.nf
index 963e33dcba1c..dc312450f280 100644
--- a/subworkflows/nf-core/snpclustering/main.nf
+++ b/subworkflows/nf-core/snpclustering/main.nf
@@ -1,10 +1,9 @@
-include { BEAGLE5_BEAGLE                } from '../../../modules/nf-core/beagle5/beagle'
-include { PLINK2_VCF                    } from '../../../modules/nf-core/plink2/vcf'
-include { PLINK2_PCA                    } from '../../../modules/nf-core/plink2/pca'
-include { GAWK as GAWK_EIGENVEC_TO_TSV  } from '../../../modules/nf-core/gawk'
-include { CUSTOM_PCACLUSTERING          } from '../../../modules/nf-core/custom/pcaclustering'
-include { CUSTOM_CLUSTERMETRICS         } from '../../../modules/nf-core/custom/clustermetrics'
-include { CUSTOM_CLUSTERVISUALIZATION   } from '../../../modules/nf-core/custom/clustervisualization'
+include { BEAGLE5_BEAGLE              } from '../../../modules/nf-core/beagle5/beagle'
+include { PLINK2_VCF                  } from '../../../modules/nf-core/plink2/vcf'
+include { PLINK2_PCA                  } from '../../../modules/nf-core/plink2/pca'
+include { CUSTOM_PCACLUSTERING        } from '../../../modules/nf-core/custom/pcaclustering'
+include { CUSTOM_CLUSTERMETRICS       } from '../../../modules/nf-core/custom/clustermetrics'
+include { CUSTOM_CLUSTERVISUALIZATION } from '../../../modules/nf-core/custom/clustervisualization'
 
 workflow SNPCLUSTERING {
     take:
@@ -20,17 +19,6 @@ workflow SNPCLUSTERING {
     dbscan_min_samples
 
     main:
-    // Bundled awk program (see ./awk/eigenvec_to_tsv.awk); shipped alongside
-    // the subworkflow and passed to GAWK_EIGENVEC_TO_TSV as `program_file` so
-    // the awk source stays readable as awk rather than as an escaped Groovy
-    // string.
-    ch_eigenvec_to_tsv_awk = file("${moduleDir}/awk/eigenvec_to_tsv.awk", checkIfExists: true)
-
-    /*
-     * Build BEAGLE input tuple:
-     * tuple val(meta), path(vcf), path(vcf_index), path(refpanel), path(refpanel_index),
-     *       path(genmap), path(exclsamples), path(exclmarkers), val(region)
-     */
     ch_beagle_input = vcf_ch.map { meta, vcf, vcf_index ->
         tuple(
             meta,
@@ -46,16 +34,8 @@ workflow SNPCLUSTERING {
     }
 
     BEAGLE5_BEAGLE(ch_beagle_input)
-
-    /*
-     * Convert imputed VCF to PLINK2 pfiles
-     */
     PLINK2_VCF(BEAGLE5_BEAGLE.out.vcf)
 
-    /*
-     * PLINK2_PCA expects:
-     * tuple val(meta), val(npcs), val(use_approx), path(pgen), path(psam), path(pvar)
-     */
     ch_plink_pca_input = PLINK2_VCF.out.pgen
         .join(PLINK2_VCF.out.pvar)
         .join(PLINK2_VCF.out.psam)
@@ -65,38 +45,18 @@ workflow SNPCLUSTERING {
 
     PLINK2_PCA(ch_plink_pca_input)
 
-    /*
-     * Convert .eigenvec to a tab-separated file for downstream clustering
-     * modules: strips the leading '#' from the header and renames the IID
-     * column to sample_id. Output keeps its default naming (<meta.id>.eigenvec)
-     * — only the tab-separated content matters downstream, not the extension.
-     */
-    GAWK_EIGENVEC_TO_TSV(
-        PLINK2_PCA.out.evecfile,
-        ch_eigenvec_to_tsv_awk,
-        false
-    )
-
-    /*
-     * PCA clustering
-     * CUSTOM_PCACLUSTERING(tsv, algorithm, n_clusters, dbscan_eps, dbscan_min_samples)
-     */
     CUSTOM_PCACLUSTERING(
-        GAWK_EIGENVEC_TO_TSV.out.output,
+        PLINK2_PCA.out.evecfile,
         algorithm,
         n_clusters,
         dbscan_eps,
         dbscan_min_samples
     )
 
-    /*
-     * Metrics and visualization both expect one tuple input channel
-     * built from: meta + tsv + cluster assignments
-     */
-    ch_cluster_analysis_input = GAWK_EIGENVEC_TO_TSV.out.output
+    ch_cluster_analysis_input = PLINK2_PCA.out.evecfile
         .join(CUSTOM_PCACLUSTERING.out.clusters)
-        .map { meta, tsv, clusters ->
-            tuple(meta, tsv, clusters)
+        .map { meta, eigenvec, clusters ->
+            tuple(meta, eigenvec, clusters)
         }
 
     CUSTOM_CLUSTERMETRICS(ch_cluster_analysis_input)
@@ -111,7 +71,6 @@ workflow SNPCLUSTERING {
     evecfile      = PLINK2_PCA.out.evecfile
     evfile        = PLINK2_PCA.out.evfile
     pca_log       = PLINK2_PCA.out.logfile
-    tsv           = GAWK_EIGENVEC_TO_TSV.out.output
     clusters      = CUSTOM_PCACLUSTERING.out.clusters
     cluster_info  = CUSTOM_PCACLUSTERING.out.info
     metrics       = CUSTOM_CLUSTERMETRICS.out.metrics
diff --git a/subworkflows/nf-core/snpclustering/meta.yml b/subworkflows/nf-core/snpclustering/meta.yml
index 1d57e69d8915..6ba3f0622b02 100644
--- a/subworkflows/nf-core/snpclustering/meta.yml
+++ b/subworkflows/nf-core/snpclustering/meta.yml
@@ -2,8 +2,7 @@
 name: "snpclustering"
 description: >
   Subworkflow for SNP clustering. Takes genotyped VCF files, imputes missing
-  genotypes with BEAGLE5, converts to PLINK2 pgen format, performs PCA,
-  converts eigenvec to TSV with awk, then runs PCA-based clustering,
+  genotypes with BEAGLE5, converts to PLINK2 pgen format, performs PCA,then runs PCA-based clustering,
   cluster metrics, and cluster visualization.
 keywords:
   - snp
@@ -17,7 +16,6 @@ components:
   - beagle5/beagle
   - plink2/vcf
   - plink2/pca
-  - gawk
   - custom/pcaclustering
   - custom/clustermetrics
   - custom/clustervisualization
@@ -142,16 +140,6 @@ output:
             type: file
             description: PLINK2 PCA log file
             pattern: "*.log"
-  - tsv:
-      description: TSV converted from eigenvec by gawk
-      structure:
-        - meta:
-            type: map
-            description: Groovy map containing sample metadata
-        - tsv:
-            type: file
-            description: TSV converted from eigenvec by gawk
-            pattern: "*.eigenvec"
   - clusters:
       description: Cluster assignments
       structure:
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test b/subworkflows/nf-core/snpclustering/tests/main.nf.test
index 77c8398c2bfa..29a3e0e2d9d3 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test
@@ -12,7 +12,6 @@ nextflow_workflow {
     tag "plink2/vcf"
     tag "plink2/pca"
     tag "beagle5/beagle"
-    tag "gawk"
     tag "custom/pcaclustering"
     tag "custom/clustermetrics"
     tag "custom/clustervisualization"
diff --git a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
index eb11e4cc6b4c..48255cca9687 100644
--- a/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
+++ b/subworkflows/nf-core/snpclustering/tests/main.nf.test.snap
@@ -67,6 +67,7 @@
                             "test.calinski_harabasz.png",
                             "test.davies_bouldin.png",
                             "test.elbow.png",
+                            "test.k_distance.png",
                             "test.silhouette.png"
                         ]
                     ]
@@ -135,14 +136,6 @@
                         "test.tsne.tsv"
                     ]
                 ],
-                "tsv": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.tsv:md5,f5ec5abd246d89cf50d333d432e4366a"
-                    ]
-                ],
                 "umap_png": [
                     [
                         {
@@ -188,7 +181,7 @@
                 "n_cols": 4
             }
         ],
-        "timestamp": "2026-08-31T12:49:22.352660673",
+        "timestamp": "2026-09-09T10:30:31.743191089",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -262,6 +255,7 @@
                             "test.calinski_harabasz.png",
                             "test.davies_bouldin.png",
                             "test.elbow.png",
+                            "test.k_distance.png",
                             "test.silhouette.png"
                         ]
                     ]
@@ -330,14 +324,6 @@
                         "test.tsne.tsv"
                     ]
                 ],
-                "tsv": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.tsv:md5,f5ec5abd246d89cf50d333d432e4366a"
-                    ]
-                ],
                 "umap_png": [
                     [
                         {
@@ -385,7 +371,7 @@
                 "n_cols": 4
             }
         ],
-        "timestamp": "2026-08-31T12:49:54.909445446",
+        "timestamp": "2026-09-09T10:31:04.29645672",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -459,6 +445,7 @@
                             "test.calinski_harabasz.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.davies_bouldin.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.elbow.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.k_distance.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.silhouette.png:md5,d41d8cd98f00b204e9800998ecf8427e"
                         ]
                     ]
@@ -527,14 +514,6 @@
                         "test.tsne.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "tsv": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
                 "umap_png": [
                     [
                         {
@@ -553,7 +532,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-31T12:14:11.172911335",
+        "timestamp": "2026-09-09T10:31:26.336556716",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
@@ -627,6 +606,7 @@
                             "test.calinski_harabasz.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.davies_bouldin.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.elbow.png:md5,d41d8cd98f00b204e9800998ecf8427e",
+                            "test.k_distance.png:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "test.silhouette.png:md5,d41d8cd98f00b204e9800998ecf8427e"
                         ]
                     ]
@@ -695,14 +675,6 @@
                         "test.tsne.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
-                "tsv": [
-                    [
-                        {
-                            "id": "test"
-                        },
-                        "test.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
-                    ]
-                ],
                 "umap_png": [
                     [
                         {
@@ -721,7 +693,7 @@
                 ]
             }
         ],
-        "timestamp": "2026-08-31T12:13:58.254898619",
+        "timestamp": "2026-09-09T10:31:16.00969678",
         "meta": {
             "nf-test": "0.9.5",
             "nextflow": "26.04.6"
diff --git a/subworkflows/nf-core/snpclustering/tests/nextflow.config b/subworkflows/nf-core/snpclustering/tests/nextflow.config
index c68232c7a163..b7b0b81220e5 100644
--- a/subworkflows/nf-core/snpclustering/tests/nextflow.config
+++ b/subworkflows/nf-core/snpclustering/tests/nextflow.config
@@ -20,7 +20,4 @@ process {
         ext.args = '--seed 1'
     }
 
-    withName: 'GAWK_EIGENVEC_TO_TSV' {
-        ext.suffix = 'tsv'
-    }
 }