Add svdb/query (#1249)

* first commit

* add test data

modules/svdb/query/main.nf

@@ -0,0 +1,34 @@
+process SVDB_QUERY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::svdb=2.5.0" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/svdb:2.5.0--py39hcbe4a3b_0':
+        'quay.io/biocontainers/svdb:2.5.0--py39hcbe4a3b_0' }"
+
+    input:
+    tuple val(meta), path(vcf)
+    path (vcf_db)
+
+    output:
+    tuple val(meta), path("*_ann_svdbq.vcf"), emit: vcf
+    path "versions.yml"                     , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    svdb \\
+        --query \\
+        $args \\
+        --db $vcf_db \\
+        --query_vcf $vcf \\
+        >${prefix}_ann_svdbq.vcf
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        svdb: \$( echo \$(svdb) | head -1 | sed 's/usage: SVDB-\\([0-9]\\.[0-9]\\.[0-9]\\).*/\\1/' )
+    END_VERSIONS
+    """
+}

modules/svdb/query/meta.yml

@@ -0,0 +1,43 @@
+name: svdb_query
+description: Query a structural variant database, using a vcf file as query
+keywords:
+  - structural variants
+tools:
+  - svdb:
+      description: structural variant database software
+      homepage: https://github.com/J35P312/SVDB
+      documentation: https://github.com/J35P312/SVDB/blob/master/README.md
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: query vcf file
+      pattern: "*.{vcf,vcf.gz}"
+  - vcf_db:
+      type: file
+      description: database vcf file
+      pattern: "*.{vcf,vcf.gz}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - vcf:
+      type: file
+      description:  Annotated output VCF file
+      pattern: "*_ann_svdbq.vcf"
+
+authors:
+  - "@ramprasadn"

tests/config/pytest_modules.yml

@@ -1437,6 +1437,10 @@ subread/featurecounts:
   - modules/subread/featurecounts/**
   - tests/modules/subread/featurecounts/**
 
+svdb/query:
+  - modules/svdb/query/**
+  - tests/modules/svdb/query/**
+
 tabix/bgzip:
   - modules/tabix/bgzip/**
   - tests/modules/tabix/bgzip/**

tests/config/test_data.config

@@ -131,6 +131,7 @@ params {
                 mills_and_1000g_indels_vcf_gz_tbi              = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/mills_and_1000G.indels.vcf.gz.tbi"
                 syntheticvcf_short_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz"
                 syntheticvcf_short_vcf_gz_tbi                  = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/syntheticvcf_short.vcf.gz.tbi"
+                gnomad_r2_1_1_sv_vcf_gz                        = "${test_data_dir}/genomics/homo_sapiens/genome/vcf/gnomAD.r2.1.1-sv.vcf.gz"
 
                 hapmap_3_3_hg38_21_vcf_gz                      = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz"
                 hapmap_3_3_hg38_21_vcf_gz_tbi                  = "${test_data_dir}/genomics/homo_sapiens/genome/chr21/germlineresources/hapmap_3.3.hg38.vcf.gz.tbi"
@@ -277,6 +278,7 @@ params {
                 cutandrun_bedgraph_test_2                     = "${test_data_dir}/genomics/homo_sapiens/illumina/bedgraph/cutandtag_igg_test_1.bedGraph"
 
                 test_rnaseq_vcf                               =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/test.rnaseq.vcf"
+                test_sv_vcf                                   =  "${test_data_dir}/genomics/homo_sapiens/illumina/vcf/sv_query.vcf.gz"
             }
             'pacbio' {
                 primers                                       = "${test_data_dir}/genomics/homo_sapiens/pacbio/fasta/primers.fasta"

tests/modules/svdb/query/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SVDB_QUERY } from '../../../../modules/svdb/query/main.nf'
+
+workflow test_svdb_query {
+
+    input = [ [ id:'test' ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_sv_vcf'], checkIfExists: true) ]
+            ]
+
+    vcf_db = [
+                file(params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_sv_vcf_gz'], checkIfExists: true)
+            ]
+
+    SVDB_QUERY ( input, vcf_db )
+}

tests/modules/svdb/query/nextflow.config

@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: SVDB_QUERY {
+         ext.args = '--in_occ AC --out_occ gnomad_svAC --in_frq AF --out_frq gnomad_svAF'
+     }
+
+}

tests/modules/svdb/query/test.yml

@@ -0,0 +1,7 @@
+- name: svdb query
+  command: nextflow run ./tests/modules/svdb/query -entry test_svdb_query -c ./tests/config/nextflow.config -c ./tests/modules/svdb/query/nextflow.config
+  tags:
+    - svdb
+    - svdb/query
+  files:
+    - path: output/svdb/test_ann_svdbq.vcf