Add gcta/bivariatereml module

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

@@ -0,0 +1,62 @@
+process GCTA_BIVARIATEREML {
+    tag "bivariate_reml_${meta.id}_${meta2.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(phenotype_file), val(mpheno), val(prevalence)
+    tuple val(meta2), path(grm_files)
+    tuple val(meta3), path(quant_covariates_file)
+    tuple val(meta4), path(cat_covariates_file)
+
+    output:
+    tuple val(meta), path("*.hsq"), emit: bivariate_results
+    tuple val(meta), path("*.log"), emit: log_file
+    tuple val("${task.process}"), val("gcta"), eval("gcta --version | sed -En 's/^[*] version v([0-9.]*).*/\\1/p'"), emit: versions_gcta, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def pair_id = prefix
+    def qcovar_param = quant_covariates_file ? "--qcovar ${quant_covariates_file}" : ''
+    def covar_param = cat_covariates_file ? "--covar ${cat_covariates_file}" : ''
+    def extra_args = task.ext.args ?: ''
+    def bivar_traits = mpheno ?: '1 2'
+    def prevalence_param = prevalence ? "--reml-bivar-prevalence ${prevalence}" : ''
+    def grm_file_list = grm_files instanceof List ? grm_files : [grm_files]
+    def grm_id = grm_file_list.find { grm_file -> grm_file.name.endsWith('.grm.id') }
+    if (!grm_id) {
+        throw new IllegalArgumentException("GCTA_BIVARIATEREML contract violation: grm_files must include a .grm.id file")
+    }
+    def expected_grm_basename = grm_id.name.replaceFirst(/\.grm\.id$/, '')
+    if (meta2.id != expected_grm_basename) {
+        throw new IllegalArgumentException("GCTA_BIVARIATEREML contract violation: meta2.id '${meta2.id}' must match GRM basename '${expected_grm_basename}'")
+    }
+
+    """
+    set -euo pipefail
+
+    gcta \\
+        --reml-bivar ${bivar_traits} \\
+        --grm ${meta2.id} \\
+        --pheno "${phenotype_file}" \\
+        ${prevalence_param} \\
+        ${qcovar_param} \\
+        ${covar_param} \\
+        --out "${pair_id}" \\
+        --thread-num ${task.cpus} ${extra_args}
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def pair_id = prefix
+    """
+    touch "${pair_id}.hsq"
+    touch "${pair_id}.log"
+    """
+}

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

@@ -0,0 +1,126 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gcta_bivariatereml"
+description: Run bivariate REML analysis with a single dense GRM
+keywords:
+  - gcta
+  - genome-wide complex trait analysis
+  - reml
+  - restricted maximum likelihood
+  - bivariate
+  - 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 shared bivariate phenotype metadata
+          `meta.id` must contain both trait names, for example `trait1__trait2`
+    - phenotype_file:
+        type: file
+        description: Shared bivariate phenotype file passed to `--pheno`
+        pattern: "*.{phe,pheno,txt,tsv}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+    - mpheno:
+        type: string
+        description: |
+          Optional pair of phenotype column indices passed to `--reml-bivar`;
+          pass `[]` to use the module default of `1 2`
+    - prevalence:
+        type: string
+        description: |
+          Optional pair of disease prevalence values passed to `--reml-bivar-prevalence`
+          for binary traits; pass `[]` for quantitative traits
+  - - meta2:
+        type: map
+        description: |
+          Groovy map containing dense GRM metadata
+          Public contract: `meta2.id` must be the GRM basename passed to `--grm`
+          (for example `plink_simulated_dense` for `plink_simulated_dense.grm.{id,bin,N.bin}`)
+    - grm_files:
+        type: file
+        description: Dense GRM bundle containing sample identifier, binary matrix,
+          and sample-count matrix files
+        pattern: "*.grm.*"
+        ontologies: []
+  - - meta3:
+        type: map
+        description: |
+          Groovy map containing quantitative covariate metadata
+          e.g. `[ id:'covariates_quant' ]`
+    - quant_covariates_file:
+        type: file
+        description: Quantitative covariates file, pass `[]` when absent
+        pattern: "*.{covar,cov,txt,tsv}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+  - - meta4:
+        type: map
+        description: |
+          Groovy map containing categorical covariate metadata
+          e.g. `[ id:'covariates_cat' ]`
+    - cat_covariates_file:
+        type: file
+        description: Categorical covariates file, pass `[]` when absent
+        pattern: "*.{covar,cov,txt,tsv}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+output:
+  bivariate_results:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing shared bivariate phenotype metadata
+            `meta.id` must contain both trait names, for example `trait1__trait2`
+      - "*.hsq":
+          type: file
+          description: Bivariate REML result file
+          pattern: "*.{hsq}"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+  log_file:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing shared bivariate phenotype metadata
+            `meta.id` must contain both trait names, for example `trait1__trait2`
+      - "*.log":
+          type: file
+          description: Bivariate REML log file
+          pattern: "*.{log}"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+  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"