module: deepvariant (#572)

* Add stubs for deepvariant [ci skip]

* Update the stubs for deepvariant [ci skip]

* functional with google docker image

* cleanup

* consume docker container within singularity executor

* update the meta.yml file and ask for review

* tweak the input channel shape and test data

* tweak input data [ci skip]

* update for the new syntax

* remove the functions and rename meta vars

* Update the arguments mechanism

* update chr, region and checksum

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>
Co-authored-by: Maxime U. Garcia <max.u.garcia@gmail.com>
Co-authored-by: FriederikeHanssen <Friederike.hanssen@qbic.uni-tuebingen.de>

modules/deepvariant/main.nf

@@ -0,0 +1,43 @@
+process DEEPVARIANT {
+    tag "$meta.id"
+    label 'process_medium'
+
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the DeepVariant tool. Please use docker or singularity containers."
+    }
+
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'google/deepvariant:1.2.0' :
+        'google/deepvariant:1.2.0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai)
+    path(fasta)
+    path(fai)
+
+    output:
+    tuple val(meta), path("*.vcf.gz") ,  emit: vcf
+    tuple val(meta), path("*g.vcf.gz"),  emit: gvcf
+    path "versions.yml"               ,  emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    /opt/deepvariant/bin/run_deepvariant \\
+        --ref=${fasta} \\
+        --reads=${bam} \\
+        --output_vcf=${prefix}.vcf.gz \\
+        --output_gvcf=${prefix}.g.vcf.gz \\
+        ${args} \\
+        --num_shards=${task.cpus}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deepvariant: \$(echo \$(/opt/deepvariant/bin/run_deepvariant --version) | sed 's/^.*version //; s/ .*\$//' )
+    END_VERSIONS
+    """
+
+}

modules/deepvariant/meta.yml

@@ -0,0 +1,58 @@
+name: deepvariant
+description: DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data
+keywords:
+  - variant calling
+  - machine learning
+tools:
+  - deepvariant:
+      description: DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data
+      homepage: https://github.com/google/deepvariant
+      documentation: https://github.com/google/deepvariant
+      tool_dev_url: https://github.com/google/deepvariant
+      doi: "https://doi.org/10.1038/nbt.4235"
+      licence: ['BSD-3-clause']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: BAM file
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: Index of BAM file
+      pattern: "*.bai"
+  - fasta:
+      type: file
+      description: The reference fasta file
+      pattern: "*.fasta"
+  - fai:
+      type: file
+      description: Index of reference fasta file
+      pattern: "*.fai"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - vcf:
+      type: file
+      description: Compressed VCF file
+      pattern: "*.vcf.gz"
+  - gvcf:
+      type: file
+      description: Compressed GVCF file
+      pattern: "*.g.vcf.gz"
+  - version:
+      type: file
+      description: File containing software version
+      pattern: "*.{version.txt}"
+
+authors:
+  - "@abhi18av"

tests/config/pytest_modules.yml

@@ -396,6 +396,10 @@ deeptools/plotprofile:
   - modules/deeptools/plotprofile/**
   - tests/modules/deeptools/plotprofile/**
 
+deepvariant:
+  - modules/deepvariant/**
+  - tests/modules/deepvariant/**
+
 delly/call:
   - modules/delly/call/**
   - tests/modules/delly/call/**

tests/modules/deepvariant/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPVARIANT } from '../../../modules/deepvariant/main.nf'
+
+workflow test_deepvariant {
+
+    bam_tuple_ch = Channel.of([[ id:'test', single_end:false ], // meta map
+                               file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true),
+                               file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)])
+
+    fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
+
+    fai = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
+
+    DEEPVARIANT ( bam_tuple_ch, fasta, fai)
+}

tests/modules/deepvariant/nextflow.config

@@ -0,0 +1,10 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+    withName: DEEPVARIANT {
+         ext.args = ' --regions=\"chr22:0-40001\" --model_type=WGS '
+         ext.prefix = { "${meta.id}_out" }
+     }
+
+}

tests/modules/deepvariant/test.yml

@@ -0,0 +1,9 @@
+- name: deepvariant
+  command: nextflow run ./tests/modules/deepvariant -entry test_deepvariant -c tests/config/nextflow.config
+  tags:
+    - deepvariant
+  files:
+    - path: output/deepvariant/test_out.vcf.gz
+      md5sum: 66d86be7a9bafe1f5c6304ebee18ee20
+    - path: output/deepvariant/test_out.g.vcf.gz
+      md5sum: 4ca868f0a4fdb17a280c3ed083d228e0