Creation of Glimpse Chunk (#1985)

* Creation of Glimpse Chunk
Add sub tools chunk with configuration and needed files for unitest.

* Code linting correction

* Prettier ran
Newline deleted in nextflow.config

* New final line and white spaces

* Change Pytest.yml to work as a subtool.

* Control for the parameters deleted.
Control for the size/count of the window and buffer not needed.
They have some defaults value.

* Changed the different recommended part by @nvnieuwk

Co-authored-by: nvnieuwk <101190534+nvnieuwk@users.noreply.github.com>

modules/glimpse/chunk/main.nf

@@ -0,0 +1,39 @@
+process GLIMPSE_CHUNK {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::glimpse-bio=1.1.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/glimpse-bio:1.1.1--h2ce4488_2':
+        'quay.io/biocontainers/glimpse-bio:1.1.1--hce55b13_1' }"
+
+    input:
+    tuple val(meta), path(input)
+    val region
+
+    output:
+    tuple val(meta), path("*.txt"), emit: chunk_chr
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def args    = task.ext.args   ?: ""
+    def VERSION = '1.1.1' // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+
+    """
+    GLIMPSE_chunk \\
+        $args \\
+        --input $input \\
+        --region $region \\
+        --thread $task.cpus \\
+        --output ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        glimpse: $VERSION
+    END_VERSIONS
+    """
+}

modules/glimpse/chunk/meta.yml

@@ -0,0 +1,52 @@
+name: "glimpse_chunk"
+description: Defines chunks where to run imputation
+keywords:
+  - chunk
+  - imputation
+tools:
+  - "glimpse":
+      description: "GLIMPSE is a phasing and imputation method for large-scale low-coverage sequencing studies."
+      homepage: "https://odelaneau.github.io/GLIMPSE"
+      documentation: "https://odelaneau.github.io/GLIMPSE/commands.html"
+      tool_dev_url: "https://github.com/odelaneau/GLIMPSE"
+      doi: "10.1038/s41588-020-00756-0"
+      licence: "['MIT']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - input:
+      type: file
+      description: |
+        Target dataset in VCF/BCF format defined at all variable positions.
+        The file could possibly be without GT field (for efficiency reasons a file containing only the positions is recommended).
+      pattern: "*.{vcf,bcf}"
+
+  - region:
+      type: string
+      description: |
+        Target region, usually a full chromosome (e.g. chr20:1000000-2000000 or chr20).
+        For chrX, please treat PAR and non-PAR regions as different choromosome in order to avoid mixing ploidy.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - txt:
+      type: file
+      description: Tab delimited output txt file containing buffer and imputation regions.
+      pattern: "*.{txt}"
+
+authors:
+  - "@louislenezet"

tests/config/pytest_modules.yml

@@ -1015,6 +1015,10 @@ gffread:
   - modules/gffread/**
   - tests/modules/gffread/**
 
+glimpse/chunk:
+  - modules/glimpse/chunk/**
+  - tests/modules/glimpse/chunk/**
+
 glnexus:
   - modules/glnexus/**
   - tests/modules/glnexus/**

tests/modules/glimpse/chunk/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GLIMPSE_CHUNK } from '../../../../modules/glimpse/chunk/main.nf'
+
+workflow test_glimpse_chunk {
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        [file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz_tbi'], checkIfExists: true)]
+    ]
+    GLIMPSE_CHUNK (input,"chr21")
+}

tests/modules/glimpse/chunk/nextflow.config

@@ -0,0 +1,10 @@
+process {
+    withName: glimpse_chunk {
+        ext.args = [
+            "--window-size 2000000",
+            "--buffer-size 200000"
+        ].join(' ')
+        ext.prefix = { "${meta.id}" }
+    }
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+}

tests/modules/glimpse/chunk/test.yml

@@ -0,0 +1,8 @@
+- name: glimpse chunk test_glimpse_chunk
+  command: nextflow run ./tests/modules/glimpse/chunk -entry test_glimpse_chunk -c ./tests/config/nextflow.config  -c ./tests/modules/glimpse/chunk/nextflow.config
+  tags:
+    - glimpse
+    - glimpse/chunk
+  files:
+    - path: output/glimpse/test.txt
+      md5sum: c690cdcc7aa086bb85431bb2b193176f