new module: Plink epistasis analysis

modules/nf-core/plink/epistasis/environment.yml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "plink_epistasis"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::plink=1.90b6.21"

modules/nf-core/plink/epistasis/main.nf

@@ -0,0 +1,94 @@
+process PLINK_EPISTASIS {
+    tag "$meta.id"
+    label 'process_low'
+
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/plink:1.90b6.21--h031d066_5':
+        'biocontainers/plink:1.90b6.21--h031d066_5' }"
+
+    input:
+    tuple val(meta), path(bed), path(bim), path(fam)
+    tuple val(meta2), path(vcf)
+    tuple val(meta3), path(bcf)
+    tuple val(meta4), path(phe)
+
+    output:
+    tuple val(meta), path("*.epi.cc")        ,  emit: epi
+    tuple val(meta), path("*.epi.cc.summary"),  emit: episummary, optional:true
+    tuple val(meta), path("*.log")           ,  emit: log
+    tuple val(meta), path("*.nosex")         ,  emit: nosex, optional:true
+    path "versions.yml"                      ,  emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = ""
+    // define input string based on provided input files
+    // in hierarchical order
+    def input_command = ""
+    def outmeta = ""
+    if (bed){
+        input_command = "--bed ${bed} --bim ${bim} --fam ${fam}"
+        prefix = task.ext.prefix ?: "${meta.id}"
+    } else if (vcf) {
+        input_command = "--vcf ${vcf} --pheno ${phe}"
+        prefix = task.ext.prefix ?: "${meta2.id}"
+        meta = meta2
+    } else if (bcf) {
+        input_command = "--bcf ${bcf} --pheno ${phe}"
+        prefix = task.ext.prefix ?: "${meta3.id}"
+        meta = meta3
+    } else {
+        log.error 'ERROR: the input should be either plink native binary format, VCF or BCF'
+    }
+    """
+    plink \\
+        $input_command \\
+        --threads $task.cpus \\
+        --epistasis \\
+        $args \\
+        --out $prefix
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(samtools --version |& sed '1!d ; s/samtools //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = ""
+    // define input string based on provided input files
+    // in hierarchical order
+    def input_command = ""
+    def outmeta = ""
+    if (bed){
+        input_command = "--bed ${bed} --bim ${bim} --fam ${fam}"
+        prefix = task.ext.prefix ?: "${meta.id}"
+    } else if (vcf) {
+        input_command = "--vcf ${vcf}"
+        prefix = task.ext.prefix ?: "${meta2.id} --pheno ${pheno}"
+        meta = meta2
+    } else if (bcf) {
+        input_command = "--bcf ${bcf} --pheno ${pheno}"
+        prefix = task.ext.prefix ?: "${meta3.id}"
+        meta = meta3
+    } else {
+        log.error 'ERROR: the input should be either plink native binary format, VCF or BCF'
+    }
+    """
+    touch ${prefix}.epi
+    touch ${prefix}.episummary
+    touch ${prefix}.log
+    touch ${prefix}.nosex
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        plink: \$(echo \$(plink --version) | sed 's/^PLINK v//;s/64.*//')
+    END_VERSIONS
+    """
+}

modules/nf-core/plink/epistasis/meta.yml

@@ -0,0 +1,97 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "plink_epistasis"
+description: Epistasis in PLINK, analyzing how the effects of one gene depend on the presence of others.
+keywords:
+  - interactions
+  - variants
+  - regression
+tools:
+  - "plink":
+      description: "Whole genome association analysis toolset, designed to perform a range of basic, large-scale analyses in a computationally efficient manner."
+      homepage: "https://www.cog-genomics.org/plink"
+      documentation: "https://www.cog-genomics.org/plink/1.9/data#recode"
+      tool_dev_url: "https://www.cog-genomics.org/plink/1.9/dev"
+      licence: ["GPL"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+        meta is associated to the PLINK native file input
+  - meta2:
+      type: map
+      description: |
+        Groovy Map containing sample information,
+        e.g. [ id:'test', single_end:false ]
+        meta2 is associated to VCF file input
+  - meta3:
+      type: map
+      description: |
+        Groovy Map containing sample information,
+        e.g. [ id:'test', single_end:false ]
+        meta3 is associated to BCF file input
+  - meta4:
+      type: map
+      description: |
+        Groovy Map containing sample information,
+        e.g. [ id:'test', single_end:false ]
+        meta4 is associated to phenotype file input
+  - bed:
+      type: file
+      description: PLINK binary biallelic genotype table file
+      pattern: "*.{bed}"
+  - bim:
+      type: file
+      description: PLINK extended MAP file
+      pattern: "*.{bim}"
+  - fam:
+      type: file
+      description: PLINK sample information file
+      pattern: "*.{fam}"
+  - bcf:
+      type: file
+      description: PLINK variant information + sample ID + genotype call binary file
+      pattern: "*.{bcf}"
+  - vcf:
+      type: file
+      description: Variant calling file (vcf)
+      pattern: "*.{vcf}"
+  - phe:
+      type: file
+      description: PLINK file containing phenotype information. This phenotype information can be read from the third column with the --pheno option or from a specific column with the --pheno-name option.
+      pattern: "*.{phe}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - epi:
+      type: file
+      description: PLINK epistasis file
+      pattern: "*.{epi.cc}"
+  - episummary:
+      type: file
+      description: PLINK epistasis summary file
+      pattern: "*.{epi.cc.summary}"
+  - log:
+      type: file
+      description: PLINK epistasis log file
+      pattern: "*.{log}"
+  - nosex:
+      type: file
+      description: Ambiguous sex ID file
+      pattern: "*.{nosex}"
+
+authors:
+  - "@davidebag"
+maintainers:
+  - "@davidebag"

modules/nf-core/plink/epistasis/tests/main.nf.test

@@ -0,0 +1,190 @@
+nextflow_process {
+
+    name "Test Process PLINK_EPISTASIS"
+    script "../main.nf"
+    process "PLINK_EPISTASIS"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "plink"
+    tag "plink/epistasis"
+
+    test("plink - VCF") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_case_control_vcf_gz'], checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_simulated_phe'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.version).match("version") },
+                { assert snapshot(
+                    process.out.epi,
+                    process.out.episummary,
+                    process.out.nosex
+                    ).match() },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" }
+            )
+        }
+    }
+
+    test("plink - VCF with phenotype name") {
+
+        config "./pheno_name.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_case_control_vcf_gz'], checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_simulated_phenoname'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.epi,
+                    process.out.episummary,
+                    process.out.nosex
+                    ).match() },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" }
+            )
+        }
+    }
+
+    test("plink - binary") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [
+                        [id:"test"],
+                        file(params.test_data['homo_sapiens']['popgen']['plink_case_control_bed'], checkIfExists: true),
+                        file(params.test_data['homo_sapiens']['popgen']['plink_case_control_bim'], checkIfExists: true),
+                        file(params.test_data['homo_sapiens']['popgen']['plink_case_control_fam'], checkIfExists: true)
+                ]
+                input[1] = [ [id:"null"], []]
+                input[2] = [ [id:"null"], []]
+                input[3] = [ [id:"null"], []]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.epi,
+                    process.out.episummary,
+                    process.out.nosex
+                    ).match() },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" }
+            )
+        }
+    }
+
+    test("plink - BCF") {
+
+        config "./nextflow.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [ [id:"null"], []]
+                input[2] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_case_control_bcf_gz'], checkIfExists: true)
+                ]
+                input[3] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_simulated_phe'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.epi,
+                    process.out.episummary,
+                    process.out.nosex
+                    ).match() },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" }
+            )
+        }
+    }
+
+    test("plink - BCF with phenotype name") {
+
+        config "./pheno_name.config"
+
+        when {
+            params {
+                outdir = "test"
+            }
+            process {
+                """
+                input[0] = [ [id:"null"], [], [], []]
+                input[1] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_case_control_vcf_gz'], checkIfExists: true)
+                ]
+                input[2] = [ [id:"null"], []]
+                input[3] = [
+                    [id:"test"],
+                    file(params.test_data['homo_sapiens']['popgen']['plink_simulated_phenoname'], checkIfExists: true)
+                ]
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.epi,
+                    process.out.episummary,
+                    process.out.nosex
+                    ).match() },
+                { assert process.out.log.get(0).get(1) ==~ ".*/*.log" }
+            )
+        }
+    }
+}