Added Somalier extract module (#1986)

* Added Somalier extract module

* changed somalier_dbg4 to somalier for versions.yml

* added  and minor changes in meta.yml

* Apply suggestions from code review

* Update main.nf

* Typo in quay.io rl

* updated the input

* new updates

* linting

* linting

* changed the test.yml

* Update modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update tests/modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update tests/modules/somalier/extract/test.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* last changes

* Update modules/somalier/extract/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Update modules/somalier/extract/main.nf

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/somalier/extract/main.nf

@@ -0,0 +1,39 @@
+
+process SOMALIER_EXTRACT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::somalier=0.2.15" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/somalier:0.2.15--h37c5b7d_0':
+        'quay.io/biocontainers/somalier:0.2.15--h37c5b7d_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    tuple path(ref), path(refidx)
+    path(sites)
+
+    output:
+    tuple val(meta), path("*.somalier"), emit: extract
+    path "versions.yml"                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    somalier extract \\
+    --sites ${sites} \\
+    -f ${ref} \\
+    ${bam} \\
+    ${args}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        somalier: \$(echo \$(somalier 2>&1) | sed 's/^.*somalier version: //; s/Commands:.*\$//')
+    END_VERSIONS
+    """
+}

modules/somalier/extract/meta.yml

@@ -0,0 +1,65 @@
+name: "somalier_extract"
+description: Somalier can extract informative sites, evaluate relatedness, and perform quality-control on BAM/CRAM/BCF/VCF/GVCF or from jointly-called VCFs
+keywords:
+  - relatedness
+  - QC
+  - bam
+  - cram
+  - vcf
+  - gvcf
+  - ancestry
+  - identity
+  - kinship
+  - informative sites
+  - family
+tools:
+  - "somalier":
+      description: "Somalier can extract informative sites, evaluate relatedness, and perform quality-control on BAM/CRAM/BCF/VCF/GVCF or from jointly-called VCFs"
+      homepage: "https://github.com/brentp/somalier"
+      documentation: "https://github.com/brentp/somalier/blob/master/README.md"
+      tool_dev_url: "https://github.com/brentp/somalier"
+      doi: "https://doi.org/10.1186/s13073-020-00761-2"
+      licence: "MIT License"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM/SAM/BCF/VCF/GVCF or jointly-called VCF file
+  - input_index:
+      type: file
+      description: index file of the input data, e.g., bam.bai, cram.crai
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.{fasta,fna,fas,fa}"
+  - fai:
+      type: file
+      description: FASTA index file
+      pattern: "*.fai"
+  - sites:
+      type: file
+      description: sites file in VCF format which can be taken from https://github.com/brentp/somalier
+      pattern: "*.vcf.gz"
+
+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"
+  - somalierExtract:
+      type: file
+      description: binary output file based on extracted sites
+      pattern: "*.{somalier}"
+
+authors:
+  - "@ashotmarg"

tests/config/pytest_modules.yml

@@ -2215,6 +2215,10 @@ snpsites:
   - modules/snpsites/**
   - tests/modules/snpsites/**
 
+somalier/extract:
+  - modules/somalier/extract/**
+  - tests/modules/somalier/extract/**
+
 sourmash/sketch:
   - modules/sourmash/sketch/**
   - tests/modules/sourmash/sketch/**

tests/modules/somalier/extract/main.nf

@@ -0,0 +1,23 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SOMALIER_EXTRACT } from '../../../../modules/somalier/extract/main.nf'
+
+fasta       = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta'], checkIfExists: true)
+
+fasta_fai   = file(params.test_data['homo_sapiens']['genome']['genome_21_fasta_fai'], checkIfExists: true)
+
+sites       = file("https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/somalier/sites_chr21.hg38.vcf.gz", checkIfExists: true)
+
+
+workflow test_somalier_extract {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_markduplicates_sorted_bam'], checkIfExists: true),
+        file(params.test_data['homo_sapiens']['illumina']['test_paired_end_markduplicates_sorted_bam_bai'], checkIfExists: true)
+    ]
+
+    SOMALIER_EXTRACT ( input, [fasta, fasta_fai], sites )
+}

tests/modules/somalier/extract/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/somalier/extract/test.yml

@@ -0,0 +1,8 @@
+- name: somalier extract test_somalier_extract
+  command: nextflow run ./tests/modules/somalier/extract/main.nf -c ./tests/config/nextflow.config -c ./tests/modules/somalier/extract/nextflow.config -entry test_somalier_extract
+  tags:
+    - somalier/extract
+    - somalier
+  files:
+    - path: output/somalier/normal.somalier
+      md5sum: 21f0b980edd42ddaa8ab964959c1de02