Add gcta/bivariateremlldms module

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

@@ -0,0 +1,47 @@
+process GCTA_BIVARIATEREMLLDMS {
+    tag "${meta.id}_${meta2.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/sha256/46/46b0d05f0daa47561d87d2a9cac5e51edc2c78e26f1bbab439c688386241a274/data'
+        : 'community.wave.seqera.io/library/gcta:1.94.1--9bc35dc424fcf6e9'}"
+
+    input:
+    tuple val(meta), path(mgrm_file), path(grm_files)
+    tuple val(meta2), path(phenotype_file), val(phenotype_col1), val(phenotype_col2)
+    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("${task.process}"), val("gcta"), eval("gcta --version | sed -En 's/^[*] version v([0-9.]*).*/\\1/p'"), emit: versions_gcta, topic: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reml_bivar_param = phenotype_col1 && phenotype_col2 ? "--reml-bivar ${phenotype_col1} ${phenotype_col2}" : "--reml-bivar"
+    def qcovar_param = quant_covariates_file ? "--qcovar ${quant_covariates_file}" : ''
+    def covar_param = cat_covariates_file ? "--covar ${cat_covariates_file}" : ''
+    """
+    gcta \\
+        ${reml_bivar_param} \\
+        --mgrm ${mgrm_file} \\
+        --pheno "${phenotype_file}" \\
+        ${qcovar_param} \\
+        ${covar_param} \\
+        --out "${prefix}" \\
+        --thread-num ${task.cpus} \\
+        ${args}
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch "${prefix}.hsq"
+    touch "${prefix}.log"
+    """
+}

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

@@ -0,0 +1,139 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gcta_bivariateremlldms"
+description: Run bivariate REML-LDMS analysis with an MGRM manifest
+keywords:
+  - gcta
+  - genome-wide complex trait analysis
+  - reml
+  - restricted maximum likelihood
+  - bivariate
+  - ldms
+  - linkage disequilibrium and minor allele frequency stratification
+  - 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 MGRM metadata
+          `meta.id` should match the MGRM manifest basename, for example
+          `plink_simulated_ldms` for `plink_simulated_ldms.mgrm`
+    - mgrm_file:
+        type: file
+        description: MGRM manifest file
+        pattern: "*.mgrm"
+        ontologies:
+          - edam: "http://edamontology.org/format_2330"
+    - grm_files:
+        type: file
+        description: GRM bundles referenced by `mgrm_file`; each manifest entry
+          should have matching `*.grm.{id,bin,N.bin}` files in this bundle
+        pattern: "*.grm.*"
+        ontologies: []
+  - - meta2:
+        type: map
+        description: |
+          Groovy map containing phenotype file metadata for the same analysis
+          unit as the primary MGRM metadata
+          e.g. `[ id:'plink_simulated_ldms' ]`
+    - phenotype_file:
+        type: file
+        description: Shared bivariate phenotype file passed to `--pheno`
+        pattern: "*.{phe,pheno,txt,tsv}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+    - phenotype_col1:
+        type: integer
+        description: |
+          First phenotype column passed to `--reml-bivar` (for example `1`).
+          Pass an empty value together with `phenotype_col2` to use GCTA's
+          default bivariate phenotype columns.
+    - phenotype_col2:
+        type: integer
+        description: |
+          Second phenotype column passed to `--reml-bivar` (for example `2`).
+          Pass an empty value together with `phenotype_col1` to use GCTA's
+          default bivariate phenotype columns.
+  - - meta3:
+        type: map
+        description: |
+          Groovy map containing quantitative covariate metadata for the same
+          analysis unit as the primary MGRM metadata
+          e.g. `[ id:'plink_simulated_ldms' ]`
+    - 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 for the same
+          analysis unit as the primary MGRM metadata
+          e.g. `[ id:'plink_simulated_ldms' ]`
+    - 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 MGRM metadata
+            `meta.id` is used as the default output prefix
+      - "*.hsq":
+          type: file
+          description: Bivariate REML-LDMS result file
+          pattern: "*.{hsq}"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+  log_file:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing MGRM metadata
+            `meta.id` is used as the default output prefix
+      - "*.log":
+          type: file
+          description: Bivariate REML-LDMS 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"