New module genomicsdbimport (#857)

* saving changes to checkout

* saving to sort out other branch

* removed yml tracking of files that cant be tracked due to directory name changing between runs

* test data added, ready for pr

* fix eol linting error

* Update modules/gatk4/genomicsdbimport/main.nf

Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com>

* merging with master

* update push to show progress

* tests now working untar able to pass data to genomicsdbimport

* commit to checkout

* tests updated, module reworked to simplify and emit updated gendb

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

* update meta.yml 

Priority of input options changed, updated to reflect this

* Update test.yml

name prefix changed in main script, test.yml updated to reflect this

* fix tests due to review changes

Co-authored-by: GCJMackenzie <gavin.mackenzie@nibsc.org>
Co-authored-by: Francesco L <53608000+lescai@users.noreply.github.com>
Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/gatk4/genomicsdbimport/functions.nf

@@ -0,0 +1,78 @@
+//
+//  Utility functions used in nf-core DSL2 module files
+//
+
+//
+// Extract name of software tool from process name using $task.process
+//
+def getSoftwareName(task_process) {
+    return task_process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()
+}
+
+//
+// Extract name of module from process name using $task.process
+//
+def getProcessName(task_process) {
+    return task_process.tokenize(':')[-1]
+}
+
+//
+// Function to initialise default values and to generate a Groovy Map of available options for nf-core modules
+//
+def initOptions(Map args) {
+    def Map options = [:]
+    options.args            = args.args ?: ''
+    options.args2           = args.args2 ?: ''
+    options.args3           = args.args3 ?: ''
+    options.publish_by_meta = args.publish_by_meta ?: []
+    options.publish_dir     = args.publish_dir ?: ''
+    options.publish_files   = args.publish_files
+    options.suffix          = args.suffix ?: ''
+    return options
+}
+
+//
+// Tidy up and join elements of a list to return a path string
+//
+def getPathFromList(path_list) {
+    def paths = path_list.findAll { item -> !item?.trim().isEmpty() }      // Remove empty entries
+    paths     = paths.collect { it.trim().replaceAll("^[/]+|[/]+\$", "") } // Trim whitespace and trailing slashes
+    return paths.join('/')
+}
+
+//
+// Function to save/publish module results
+//
+def saveFiles(Map args) {
+    def ioptions  = initOptions(args.options)
+    def path_list = [ ioptions.publish_dir ?: args.publish_dir ]
+
+    // Do not publish versions.yml unless running from pytest workflow
+    if (args.filename.equals('versions.yml') && !System.getenv("NF_CORE_MODULES_TEST")) {
+        return null
+    }
+    if (ioptions.publish_by_meta) {
+        def key_list = ioptions.publish_by_meta instanceof List ? ioptions.publish_by_meta : args.publish_by_meta
+        for (key in key_list) {
+            if (args.meta && key instanceof String) {
+                def path = key
+                if (args.meta.containsKey(key)) {
+                    path = args.meta[key] instanceof Boolean ? "${key}_${args.meta[key]}".toString() : args.meta[key]
+                }
+                path = path instanceof String ? path : ''
+                path_list.add(path)
+            }
+        }
+    }
+    if (ioptions.publish_files instanceof Map) {
+        for (ext in ioptions.publish_files) {
+            if (args.filename.endsWith(ext.key)) {
+                def ext_list = path_list.collect()
+                ext_list.add(ext.value)
+                return "${getPathFromList(ext_list)}/$args.filename"
+            }
+        }
+    } else if (ioptions.publish_files == null) {
+        return "${getPathFromList(path_list)}/$args.filename"
+    }
+}

modules/gatk4/genomicsdbimport/main.nf

@@ -0,0 +1,67 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName; getProcessName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process GATK4_GENOMICSDBIMPORT {
+    tag "$meta.id"
+    label 'process_low'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), meta:meta, publish_by_meta:['id']) }
+
+    conda (params.enable_conda ? "bioconda::gatk4=4.2.0.0" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/gatk4:4.2.0.0--0"
+    } else {
+        container "quay.io/biocontainers/gatk4:4.2.0.0--0"
+    }
+
+    input:
+    tuple val(meta), path(vcf), path(tbi), path(intervalfile), val(intervalval), path(wspace)
+    val run_intlist
+    val run_updatewspace
+    val input_map
+
+    output:
+    tuple val(meta), path("*_genomicsdb")   , optional:true, emit: genomicsdb
+    tuple val(meta), path("$updated_db")    , optional:true, emit: updatedb
+    tuple val(meta), path("*.interval_list"), optional:true, emit: intervallist
+    path "versions.yml"                                    , emit: versions
+
+    script:
+    def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+
+    // settings for running default create gendb mode
+    def inputs_command = input_map ? "--sample-name-map ${vcf[0]}" : "${'-V ' + vcf.join(' -V')}"
+    def dir_command = "--genomicsdb-workspace-path ${prefix}"
+    def intervals_command = intervalfile ? " -L ${intervalfile} " : " -L ${intervalval} "
+
+    // settings changed for running get intervals list mode if run_intlist is true
+    if (run_intlist) {
+        inputs_command = ''
+        dir_command = "--genomicsdb-update-workspace-path ${wspace}"
+        intervals_command = "--output-interval-list-to-file ${prefix}.interval_list"
+    }
+
+    // settings changed for running update gendb mode. inputs_command same as default, update_db forces module to emit the updated gendb
+    if (run_updatewspace) {
+        dir_command = "--genomicsdb-update-workspace-path ${wspace}"
+        intervals_command = ''
+        updated_db = wspace.toString()
+    }
+
+    """
+    gatk GenomicsDBImport \\
+        $inputs_command \\
+        $dir_command \\
+        $intervals_command \\
+        $options.args
+
+    cat <<-END_VERSIONS > versions.yml
+    ${getProcessName(task.process)}:
+        ${getSoftwareName(task.process)}: \$(echo \$(gatk --version 2>&1) | sed 's/^.*(GATK) v//; s/ .*\$//')
+    END_VERSIONS
+    """
+}

modules/gatk4/genomicsdbimport/meta.yml

@@ -0,0 +1,80 @@
+name: gatk4_genomicsdbimport
+description: merge GVCFs from multiple samples. For use in joint genotyping or somatic panel of normal creation.
+keywords:
+  - gatk4
+  - genomicsdbimport
+  - genomicsdb
+  - panelofnormalscreation
+  - jointgenotyping
+tools:
+  - gatk4:
+      description: |
+        Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools
+        with a primary focus on variant discovery and genotyping. Its powerful processing engine
+        and high-performance computing features make it capable of taking on projects of any size.
+      homepage: https://gatk.broadinstitute.org/hc/en-us
+      documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+      doi: 10.1158/1538-7445.AM2017-3590
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test']
+  - vcf:
+      type: list
+      description: either a list of vcf files to be used to create or update a genomicsdb, or a file that contains a map to vcf files to be used.
+      pattern: "*.vcf.gz"
+
+  - tbi:
+      type: list
+      description: list of tbi files that match with the input vcf files
+      pattern: "*.vcf.gz_tbi"
+
+  - wspace:
+      type: path
+      description: path to an existing genomicsdb to be used in update db mode or get intervals mode. This WILL NOT specify name of a new genomicsdb in create db mode.
+      pattern: "/path/to/existing/gendb"
+
+  - intervalfile:
+      type: file
+      description: file containing the intervals to be used when creating the genomicsdb
+      pattern: "*.interval_list"
+
+  - intervalval:
+      type: string
+      description: if an intervals file has not been spcified, the value enetered here will be used as an interval via the "-L" argument
+      pattern: "example: chr1:1000-10000"
+
+  - run_intlist:
+      type: boolean
+      description: Specify whether to run get interval list mode, this option cannot be specified at the same time as run_updatewspace.
+      pattern: "true/false"
+
+  - run_updatewspace:
+      type: boolean
+      description: Specify whether to run update genomicsdb mode, this option takes priority over run_intlist.
+      pattern: "true/false"
+
+  - input_map:
+      type: boolean
+      description: Specify whether the vcf input is providing a list of vcf file(s) or a single file containing a map of paths to vcf files to be used to create or update a genomicsdb.
+      pattern: "*.sample_map"
+
+output:
+  - genomicsdb:
+      type: directory
+      description: Directory containing the files that compose the genomicsdb workspace, this is only output for create mode, as update changes an existing db
+      pattern: "*_genomicsdb"
+  - intervallist:
+      type: file
+      description: File containing the intervals used to generate the genomicsdb, only created by get intervals mode.
+      pattern: "*.interval_list"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@GCJMackenzie"

tests/config/pytest_modules.yml

@@ -450,6 +450,10 @@ gatk4/fastqtosam:
   - modules/gatk4/fastqtosam/**
   - tests/modules/gatk4/fastqtosam/**
 
+gatk4/genomicsdbimport:
+  - modules/gatk4/genomicsdbimport/**
+  - tests/modules/gatk4/genomicsdbimport/**
+
 gatk4/filtermutectcalls:
   - modules/gatk4/filtermutectcalls/**
   - tests/modules/gatk4/filtermutectcalls/**

tests/config/test_data.config

@@ -103,6 +103,7 @@ params {
                 genome_dict                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.dict"
                 genome_gff3                                    = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gff3"
                 genome_gtf                                     = "${test_data_dir}/genomics/homo_sapiens/genome/genome.gtf"
+                genome_interval_list                           = "${test_data_dir}/genomics/homo_sapiens/genome/genome.interval_list"
                 genome_sizes                                   = "${test_data_dir}/genomics/homo_sapiens/genome/genome.sizes"
                 genome_bed                                     = "${test_data_dir}/genomics/homo_sapiens/genome/genome.bed"
                 genome_header                                  = "${test_data_dir}/genomics/homo_sapiens/genome/genome.header"
@@ -181,6 +182,7 @@ params {
                 test2_baserecalibrator_table                   = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.baserecalibrator.table"
                 test_pileups_table                             = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test.pileups.table"
                 test2_pileups_table                            = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test2.pileups.table"
+                test_genomicsdb_tar_gz                         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/test_genomicsdb.tar.gz"
 
                 test_test2_paired_mutect2_calls_vcf_gz         = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz"
                 test_test2_paired_mutect2_calls_vcf_gz_tbi     = "${test_data_dir}/genomics/homo_sapiens/illumina/gatk/paired_mutect2_calls/test_test2_paired_mutect2_calls.vcf.gz.tbi"

tests/modules/gatk4/genomicsdbimport/main.nf

@@ -0,0 +1,61 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { UNTAR           } from '../../../../modules/untar/main.nf'           addParams( options: [:] )
+include { GATK4_GENOMICSDBIMPORT } from '../../../../modules/gatk4/genomicsdbimport/main.nf' addParams( options: [:] )
+
+workflow test_gatk4_genomicsdbimport_create_genomicsdb {
+
+    input = [ [ id:'test_genomicsdb'], // meta map
+              file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz'], checkIfExists: true) ,
+              file(params.test_data['homo_sapiens']['illumina']['test_genome_vcf_gz_tbi'], checkIfExists: true) ,
+              file(params.test_data['homo_sapiens']['genome']['genome_interval_list'], checkIfExists: true) ,
+              [] ,
+              [] ]
+
+    run_intlist = false
+    run_updatewspace = false
+    input_map = false
+
+    GATK4_GENOMICSDBIMPORT ( input, run_intlist, run_updatewspace, input_map )
+}
+
+workflow test_gatk4_genomicsdbimport_get_intervalslist {
+    db    = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+
+    UNTAR ( db )
+
+    def input = Channel.of([ [ id:'test_genomicsdb'], // meta map
+              [] ,
+              [] ,
+              [] ,
+              [] ])
+              .combine(UNTAR.out.untar)
+
+    run_intlist = true
+    run_updatewspace = false
+    input_map = false
+
+    GATK4_GENOMICSDBIMPORT ( input, run_intlist, run_updatewspace, input_map )
+}
+
+workflow test_gatk4_genomicsdbimport_update_genomicsdb {
+    db    = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+
+    UNTAR ( db )
+
+    def input = Channel.of([ [ id:'test_genomicsdb'], // meta map
+              file( params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz'] , checkIfExists: true) ,
+              file( params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz_tbi'] , checkIfExists: true) ,
+              [] ,
+              [] ])
+              .combine(UNTAR.out.untar)
+
+    run_intlist = false
+    run_updatewspace = true
+    input_map = false
+
+    GATK4_GENOMICSDBIMPORT ( input, run_intlist, run_updatewspace, input_map )
+
+}

tests/modules/gatk4/genomicsdbimport/test.yml

@@ -0,0 +1,50 @@
+- name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_create_genomicsdb
+  command: nextflow run tests/modules/gatk4/genomicsdbimport -entry test_gatk4_genomicsdbimport_create_genomicsdb -c tests/config/nextflow.config
+  tags:
+    - gatk4/genomicsdbimport
+    - gatk4
+  files:
+    - path: output/gatk4/test_genomicsdb/__tiledb_workspace.tdb
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_genomicsdb/callset.json
+      md5sum: a7d07d1c86449bbb1091ff29368da07a
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/.__consolidation_lock
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/__array_schema.tdb
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
+      md5sum: 2502f79658bc000578ebcfddfc1194c0
+    - path: output/gatk4/test_genomicsdb/vcfheader.vcf
+      contains: 
+        - "FORMAT=<ID=AD,Number=R,Type=Integer,Description="
+    - path: output/gatk4/test_genomicsdb/vidmap.json
+      md5sum: 18d3f68bd2cb6f4474990507ff95017a
+
+- name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_get_intervalslist
+  command: nextflow run tests/modules/gatk4/genomicsdbimport -entry test_gatk4_genomicsdbimport_get_intervalslist -c tests/config/nextflow.config
+  tags:
+    - gatk4/genomicsdbimport
+    - gatk4
+  files:
+    - path: output/gatk4/test_genomicsdb.interval_list
+      md5sum: 4c85812ac15fc1cd29711a851d23c0bf
+
+- name: gatk4 genomicsdbimport test_gatk4_genomicsdbimport_update_genomicsdb
+  command: nextflow run tests/modules/gatk4/genomicsdbimport -entry test_gatk4_genomicsdbimport_update_genomicsdb -c tests/config/nextflow.config
+  tags:
+    - gatk4/genomicsdbimport
+    - gatk4
+  files:
+    - path: output/gatk4/test_genomicsdb/__tiledb_workspace.tdb
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_genomicsdb/callset.json
+      md5sum: 1ea31b59b9a218dd5681164aff4a5e07
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/.__consolidation_lock
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/__array_schema.tdb
+      md5sum: 35e7fdd18149be80c0c3f56fa1f23971
+    - path: output/gatk4/test_genomicsdb/chr22$1$40001/genomicsdb_meta_dir/genomicsdb_column_bounds.json
+      md5sum: 2502f79658bc000578ebcfddfc1194c0
+    - path: output/gatk4/test_genomicsdb/vcfheader.vcf
+      md5sum: 47a615385a49f9261e088104b903bb9b
+    - path: output/gatk4/test_genomicsdb/vidmap.json
+      md5sum: 18d3f68bd2cb6f4474990507ff95017a