Add gcta/adjustgrm module

modules/nf-core/gcta/adjustgrm/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::gcta=1.94.1

modules/nf-core/gcta/adjustgrm/main.nf

@@ -0,0 +1,42 @@
+process GCTA_ADJUSTGRM {
+    tag "${meta.id}"
+    label 'process_medium'
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/46/46b0d05f0daa47561d87d2a9cac5e51edc2c78e26f1bbab439c688386241a274/data'
+        : 'community.wave.seqera.io/library/gcta:1.94.1--9bc35dc424fcf6e9'}"
+
+    input:
+    tuple val(meta), path(grm_files), val(grm_adj)
+
+    output:
+    tuple val(meta), path("*_adj.grm.*"), emit: grm_files
+    tuple val("${task.process}"), val("gcta"), eval("gcta --version | sed -En 's/^[*] version v([0-9.]*).*/\\1/p'"), emit: versions_gcta, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def extra_args = task.ext.args ?: ''
+    def grm_adj_value = grm_adj == null ? 0 : grm_adj
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+
+    gcta \\
+        --grm ${meta.id} \\
+        --grm-adj ${grm_adj_value} \\
+        --make-grm \\
+        --out ${prefix}_adj \\
+        --thread-num ${task.cpus} \\
+        ${extra_args}
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_adj.grm.id
+    touch ${prefix}_adj.grm.bin
+    touch ${prefix}_adj.grm.N.bin
+    """
+}

modules/nf-core/gcta/adjustgrm/meta.yml

@@ -0,0 +1,77 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gcta_adjustgrm"
+description: Adjust a dense GRM for incomplete tagging using `gcta --grm-adj`
+keywords:
+  - gcta
+  - genome-wide complex trait analysis
+  - grm
+  - genetic relationship matrix
+  - genetics
+tools:
+  - "gcta":
+      description: "Genome-wide Complex Trait Analysis (GCTA) estimates genetic relationships, variance components, and association statistics from genome-wide data."
+      homepage: "https://yanglab.westlake.edu.cn/software/gcta/"
+      documentation: "https://yanglab.westlake.edu.cn/software/gcta/static/gcta_doc_latest.pdf"
+      tool_dev_url: "https://yanglab.westlake.edu.cn/software/gcta/"
+      licence: ["GPL-3.0-only"]
+      identifier: "biotools:gcta"
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy map containing dense GRM metadata.
+          `meta.id` is the required GRM basename consumed by `--grm` and must match
+          the staged dense GRM files.
+          e.g. `[ id:'tiny_dense' ]` requires
+          `tiny_dense.grm.id`, `tiny_dense.grm.bin`, and `tiny_dense.grm.N.bin`.
+    - grm_files:
+        type: file
+        description: Dense GRM file bundle with basename `${meta.id}`
+        pattern: "*.grm.*"
+        ontologies: []
+    - grm_adj:
+        type: integer
+        description: |
+          GRM adjustment value passed to `--grm-adj`.
+          If not provided (`null`), the module falls back to integer `0`.
+
+output:
+  grm_files:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing dense GRM metadata.
+            `meta.id` remains the dense-GRM basename contract used for `--grm`.
+      - "*_adj.grm.*":
+          type: file
+          description: Adjusted GRM file bundle
+          pattern: "*_adj.grm.*"
+          ontologies: []
+  versions_gcta:
+    - - "${task.process}":
+          type: string
+          description: The process the version was collected from
+      - "gcta":
+          type: string
+          description: The tool name
+      - "gcta --version | sed -En 's/^[*] version v([0-9.]*).*/\\1/p'":
+          type: eval
+          description: The command used to retrieve the GCTA version
+
+topics:
+  versions:
+    - - ${task.process}:
+          type: string
+          description: The process the version was collected from
+      - gcta:
+          type: string
+          description: The tool name
+      - "gcta --version | sed -En 's/^[*] version v([0-9.]*).*/\\1/p'":
+          type: eval
+          description: The command used to retrieve the GCTA version
+
+authors:
+  - "@lyh970817"
+maintainers:
+  - "@lyh970817"

modules/nf-core/gcta/adjustgrm/tests/main.nf.test

@@ -0,0 +1,200 @@
+nextflow_process {
+
+    name "Test Process GCTA_ADJUSTGRM"
+    script "../main.nf"
+    process "GCTA_ADJUSTGRM"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "gcta"
+    tag "gcta/adjustgrm"
+    tag "gcta/makegrm"
+
+    setup {
+        run("GCTA_MAKEGRM", alias: "GCTA_MAKEGRM_DENSE") {
+            script "../../makegrm/main.nf"
+            process {
+                """
+                file('plink_simulated.mbfile').text = 'plink_simulated\\n'
+
+                input[0] = [
+                    [ id:'tiny_dense' ],
+                    file('plink_simulated.mbfile'),
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true)
+                    ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true)
+                    ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
+                    ]
+                ]
+                """
+            }
+        }
+
+        run("GCTA_MAKEGRM", alias: "GCTA_MAKEGRM_DENSE_STUB") {
+            script "../../makegrm/main.nf"
+            process {
+                """
+                file('plink_simulated.mbfile').text = 'plink_simulated\\n'
+
+                input[0] = [
+                    [ id:'stub_dense' ],
+                    file('plink_simulated.mbfile'),
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true)
+                    ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true)
+                    ],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
+                    ]
+                ]
+                """
+            }
+        }
+    }
+
+    test("homo_sapiens popgen - adjust dense GRM") {
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = GCTA_MAKEGRM_DENSE.out.grm_files.map { meta, grm_files -> [meta, grm_files, 1] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.grm_files.size() == 1 },
+                { assert process.out.grm_files.get(0).get(0).id == "tiny_dense" },
+                {
+                    def grm_row = process.out.grm_files.get(0)
+                    def expected_prefix = "${grm_row.get(0).id}_adj"
+                    assert grm_row.get(1).collect { file(it).name }.sort() == [
+                        "${expected_prefix}.grm.N.bin",
+                        "${expected_prefix}.grm.bin",
+                        "${expected_prefix}.grm.id"
+                    ]
+                },
+                {
+                    assert snapshot(
+                        process.out.grm_files,
+                        process.out.findAll { key, val -> key.startsWith('versions') }
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("homo_sapiens popgen - adjust dense GRM with null fallback value") {
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = GCTA_MAKEGRM_DENSE.out.grm_files.map { meta, grm_files -> [meta, grm_files, null] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.grm_files.size() == 1 },
+                { assert process.out.grm_files.get(0).get(0).id == "tiny_dense" },
+                {
+                    def grm_row = process.out.grm_files.get(0)
+                    def expected_prefix = "${grm_row.get(0).id}_adj"
+                    assert grm_row.get(1).collect { file(it).name }.sort() == [
+                        "${expected_prefix}.grm.N.bin",
+                        "${expected_prefix}.grm.bin",
+                        "${expected_prefix}.grm.id"
+                    ]
+                },
+                {
+                    assert snapshot(
+                        process.out.grm_files,
+                        process.out.findAll { key, val -> key.startsWith('versions') }
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("homo_sapiens popgen - adjust dense GRM fails when meta.id is not GRM basename") {
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = GCTA_MAKEGRM_DENSE.out.grm_files.map { meta, grm_files -> [[ id:meta.id + '_mismatched' ], grm_files, 1] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert !process.success },
+                { assert process.exitStatus != 0 }
+            )
+        }
+    }
+
+    test("homo_sapiens popgen - adjust dense GRM fails for malformed GRM tuple") {
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = GCTA_MAKEGRM_DENSE.out.grm_files.map { meta, grm_files -> [meta, 1] }
+                """
+            }
+        }
+
+        then {
+            assert !process.success
+        }
+    }
+
+    test("homo_sapiens popgen - adjust dense GRM - stub") {
+        options "-stub"
+        config "./nextflow.config"
+
+        when {
+            process {
+                """
+                input[0] = GCTA_MAKEGRM_DENSE_STUB.out.grm_files.map { meta, grm_files -> [meta, grm_files, 1] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.grm_files.get(0).get(0).id == "stub_dense" },
+                {
+                    def grm_row = process.out.grm_files.get(0)
+                    def expected_prefix = "${grm_row.get(0).id}_adj"
+                    assert grm_row.get(1).collect { file(it).name }.sort() == [
+                        "${expected_prefix}.grm.N.bin",
+                        "${expected_prefix}.grm.bin",
+                        "${expected_prefix}.grm.id"
+                    ]
+                },
+                {
+                    assert snapshot(
+                        process.out.grm_files,
+                        process.out.findAll { key, val -> key.startsWith('versions') }
+                    ).match()
+                }
+            )
+        }
+    }
+}