Add gcta/fastgwa module

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

@@ -0,0 +1,60 @@
+process GCTA_FASTGWA {
+    tag "${meta.id}:${mpheno}"
+    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(bed_pgen), path(bim_pvar), path(fam_psam)
+    tuple val(meta2), path(sparse_grm_files)
+    tuple val(meta3), path(phenotype_file), val(mpheno), val(is_binary)
+    tuple val(meta4), path(quant_covariates_file)
+    tuple val(meta5), path(cat_covariates_file)
+    val mlm_exact
+
+    output:
+    tuple val(meta), path("*.fastGWA"), val(mpheno), val(is_binary), emit: results
+    tuple val(meta), path("*.log"), val(mpheno), val(is_binary), emit: log
+    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 genotype_suffix = bed_pgen.name.tokenize('.').last()
+    def genotype_flag = genotype_suffix == 'pgen' ? '--pfile' : '--bfile'
+    def genotype_prefix = bed_pgen.baseName
+    def grm_arg = sparse_grm_files ? "--grm-sparse ${meta2.id}" : ''
+    def mode_arg = is_binary ? '--fastGWA-lr' : (mlm_exact ? '--fastGWA-mlm-exact' : '--fastGWA-mlm')
+    def qcovar_arg = quant_covariates_file ? "--qcovar ${quant_covariates_file}" : ''
+    def covar_arg = cat_covariates_file ? "--covar ${cat_covariates_file}" : ''
+    def mpheno_arg = mpheno ? "--mpheno ${mpheno}" : ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def out = mpheno ? "${prefix}_${mpheno}" : "${prefix}"
+    def extra_args = task.ext.args ?: ''
+
+    """
+    set -euo pipefail
+
+    gcta \\
+        ${genotype_flag} ${genotype_prefix} \\
+        ${grm_arg} \\
+        ${mode_arg} \\
+        --pheno ${phenotype_file} \\
+        ${qcovar_arg} \\
+        ${covar_arg} \\
+        ${mpheno_arg} \\
+        --thread-num ${task.cpus} \\
+        --out ${out} ${extra_args}
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def out = mpheno ? "${prefix}_${mpheno}" : "${prefix}"
+    """
+    touch ${out}.fastGWA
+    touch ${out}.log
+    """
+}

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

@@ -0,0 +1,161 @@
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "gcta_fastgwa"
+description: Run GCTA fastGWA association modes (`--fastGWA-mlm`, `--fastGWA-mlm-exact`, and `--fastGWA-lr`) with PLINK genotype inputs
+keywords:
+  - gcta
+  - genome-wide complex trait analysis
+  - fastgwa
+  - fast genome-wide association
+  - gwas
+  - genome-wide association study
+  - 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 PLINK genotype metadata
+          e.g. `[ id:'plink_simulated' ]`
+    - bed_pgen:
+        type: file
+        description: PLINK primary genotype file, either `.bed` or `.pgen`
+        pattern: "*.{bed,pgen}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3003"
+    - bim_pvar:
+        type: file
+        description: PLINK sidecar file, either `.bim` or `.pvar`
+        pattern: "*.{bim,pvar}"
+        ontologies: []
+    - fam_psam:
+        type: file
+        description: PLINK sidecar file, either `.fam` or `.psam`
+        pattern: "*.{fam,psam}"
+        ontologies: []
+  - - meta2:
+        type: map
+        description: |
+          Groovy map containing sparse GRM metadata
+          e.g. `[ id:'plink_simulated_sp' ]`
+          Used when sparse GRM files are supplied
+    - sparse_grm_files:
+        type: file
+        description: Sparse GRM sidecar files, pass `[]` when absent
+        pattern: "*.grm.{id,sp}"
+        ontologies: []
+  - - meta3:
+        type: map
+        description: |
+          Groovy map containing phenotype metadata
+          Keep only stable phenotype metadata in this map
+          e.g. `[ id:'plink_simulated' ]`
+    - phenotype_file:
+        type: file
+        description: Phenotype file
+        pattern: "*.{phe,pheno,txt,tsv}"
+        ontologies:
+          - edam: "http://edamontology.org/format_3475"
+    - mpheno:
+        type: integer
+        description: |
+          Phenotype column selector passed to `--mpheno`.
+          Pass `[]` when absent.
+    - is_binary:
+        type: boolean
+        description: Whether to run logistic fastGWA mode for a binary trait
+  - - meta4:
+        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"
+  - - meta5:
+        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"
+  - mlm_exact:
+      type: boolean
+      description: |
+        Apply `--fastGWA-mlm-exact` for non-binary phenotypes.
+        Ignored when `is_binary` is true because binary phenotypes use `--fastGWA-lr`.
+output:
+  results:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing PLINK genotype metadata
+            e.g. `[ id:'plink_simulated' ]`
+      - "*.fastGWA":
+          type: file
+          description: FastGWA association results
+          pattern: "*.fastGWA"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+      - mpheno:
+          type: integer
+          description: Phenotype column selector used for the emitted result
+      - is_binary:
+          type: boolean
+          description: Whether `--fastGWA-lr` was used for the emitted result
+  log:
+    - - meta:
+          type: map
+          description: |
+            Groovy map containing PLINK genotype metadata
+            e.g. `[ id:'plink_simulated' ]`
+      - "*.log":
+          type: file
+          description: GCTA fastGWA log file
+          pattern: "*.log"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330"
+      - mpheno:
+          type: integer
+          description: Phenotype column selector used for the emitted log
+      - is_binary:
+          type: boolean
+          description: Whether `--fastGWA-lr` was used for the emitted log
+  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"