Add deeparg (#1234)

* Add deeparg download data

* Tweak downloaddata test.yml

* Add deeparg tests

* Apply suggestions from code review

* Fix output file paths in test

* Fix tests again md5sum to string

modules/deeparg/downloaddata/main.nf

@@ -0,0 +1,30 @@
+def VERSION='1.0.2'
+
+process DEEPARG_DOWNLOADDATA {
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::deeparg=1.0.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/deeparg:1.0.2--pyhdfd78af_1' :
+        'quay.io/biocontainers/deeparg:1.0.2--pyhdfd78af_1' }"
+
+    input:
+
+    output:
+    path "db/"          , emit: db
+    path "versions.yml" , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    deeparg \\
+        download_data \\
+        $args \\
+        -o db/
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deeparg: $VERSION
+    END_VERSIONS
+    """
+}

modules/deeparg/downloaddata/meta.yml

@@ -0,0 +1,33 @@
+name: deeparg_downloaddata
+description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+keywords:
+  - download
+  - database
+  - deeparg
+  - antimicrobial resistance genes
+  - deep learning
+  - prediction
+tools:
+  - deeparg:
+      description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+      homepage: https://bench.cs.vt.edu/deeparg
+      documentation: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      tool_dev_url: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      doi: "10.1186/s40168-018-0401-z"
+      licence: ['MIT']
+
+input:
+  - none: There is no input. This module downloads a pre-built database for use with deepARG.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: directory
+      description: Directory containing database required for deepARG.
+      pattern: "db/"
+
+authors:
+  - "@jfy133"

modules/deeparg/predict/main.nf

@@ -0,0 +1,40 @@
+def VERSION="1.0.2"
+
+process DEEPARG_PREDICT {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::deeparg=1.0.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity//deeparg:1.0.2--pyhdfd78af_1' :
+        'quay.io/biocontainers/deeparg:1.0.2--pyhdfd78af_1' }"
+
+    input:
+    tuple val(meta), path(fasta), val(model)
+    tuple path(db)
+
+    output:
+    tuple val(meta), path("*.align.daa")            , emit: daa
+    tuple val(meta), path("*.align.daa.tsv")        , emit: daa_tsv
+    tuple val(meta), path("*.mapping.ARG")          , emit: arg
+    tuple val(meta), path("*.mapping.potential.ARG"), emit: potential_arg
+    path "versions.yml"                             , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    deeparg \\
+        predict \\
+        $args \\
+        -i $fasta \\
+        -o ${prefix} \\
+        -d $db \\
+        --model $model
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        deeparg: $VERSION
+    END_VERSIONS
+    """
+}

modules/deeparg/predict/meta.yml

@@ -0,0 +1,68 @@
+name: deeparg_predict
+description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+keywords:
+  - deeparg
+  - antimicrobial resistance
+  - antimicrobial resistance genes
+  - arg
+  - deep learning
+  - prediction
+  - contigs
+  - metagenomes
+tools:
+  - deeparg:
+      description: A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes
+      homepage: https://bench.cs.vt.edu/deeparg
+      documentation: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      tool_dev_url: https://bitbucket.org/gusphdproj/deeparg-ss/src/master/
+      doi: "10.1186/s40168-018-0401-z"
+      licence: ['MIT']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test' ]
+  - fasta:
+      type: file
+      description: FASTA file containing gene-like sequences
+      pattern: "*.{fasta,fa,fna}"
+  - model:
+      type: string
+      description: Which model to use, depending on input data. Either 'LS' or 'SS' for long or short sequences respectively
+      pattern: "LS|LS"
+  - db:
+      type: directory
+      description: Path to a directory containing the deepARG pre-built models
+      pattern: "*/"
+
+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"
+  - daa:
+      type: file
+      description: Sequences of ARG-like sequences from DIAMOND alignment
+      pattern: "*.align.daa"
+  - daa_tsv:
+      type: file
+      description: Alignments scores against ARG-like sequences from DIAMOND alignment
+      pattern: "*.align.daa.tsv"
+  - arg:
+      type: file
+      description: Table containing sequences with an ARG-like probability of more than specified thresholds
+      pattern: "*.mapping.ARG"
+  - potential_arg:
+      type: file
+      description: Table containing sequences with an ARG-like probability of less than specified thresholds, and requires manual inspection
+      pattern: "*.mapping.potential.ARG"
+
+authors:
+  - "@jfy133"

tests/config/pytest_modules.yml

@@ -380,6 +380,14 @@ dedup:
   - modules/dedup/**
   - tests/modules/dedup/**
 
+deeparg/downloaddata:
+  - modules/deeparg/downloaddata/**
+  - tests/modules/deeparg/downloaddata/**
+
+deeparg/predict:
+  - modules/deeparg/predict/**
+  - tests/modules/deeparg/predict/**
+
 deeptools/computematrix:
   - modules/deeptools/computematrix/**
   - tests/modules/deeptools/computematrix/**

tests/modules/deeparg/downloaddata/main.nf

@@ -0,0 +1,9 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPARG_DOWNLOADDATA } from '../../../../modules/deeparg/downloaddata/main.nf'
+
+workflow test_deeparg_downloaddata {
+    DEEPARG_DOWNLOADDATA ()
+}

tests/modules/deeparg/downloaddata/nextflow.config

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

tests/modules/deeparg/downloaddata/test.yml

@@ -0,0 +1,9 @@
+- name: deeparg downloaddata test_deeparg_downloaddata
+  command: nextflow run tests/modules/deeparg/downloaddata -entry test_deeparg_downloaddata -c tests/config/nextflow.config
+  tags:
+    - deeparg
+    - deeparg/downloaddata
+  files:
+    - path: output/deeparg/db/
+    - path: output/deeparg/db/data/gg13/dataset.rev.2.bt2
+      md5sum: 99d90f132fc2795d5a527ce31f1c4d30

tests/modules/deeparg/predict/main.nf

@@ -0,0 +1,19 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { DEEPARG_DOWNLOADDATA } from '../../../../modules/deeparg/downloaddata/main.nf'
+include { DEEPARG_PREDICT      } from '../../../../modules/deeparg/predict/main.nf'
+
+workflow test_deeparg_predict {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['bacteroides_fragilis']['genome']['genome_fna_gz'], checkIfExists: true),
+        'LS'
+    ]
+
+    DEEPARG_DOWNLOADDATA()
+    DEEPARG_PREDICT ( input, DEEPARG_DOWNLOADDATA.out.db )
+
+}

tests/modules/deeparg/predict/nextflow.config

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

tests/modules/deeparg/predict/test.yml

@@ -0,0 +1,17 @@
+- name: deeparg predict test_deeparg_predict
+  command: nextflow run tests/modules/deeparg/predict -entry test_deeparg_predict -c tests/config/nextflow.config
+  tags:
+    - deeparg/predict
+    - deeparg
+  files:
+    - path: output/deeparg/test.align.daa
+      md5sum: c52d0af8362244f214da25bc45f2bf42
+    - path: output/deeparg/test.align.daa.tsv
+      md5sum: a4aa1da2db98274ede2b927fa8227e5a
+    - path: output/deeparg/test.mapping.ARG
+      md5sum: 0e049e99eab4c55666062df21707d5b9
+    - path: output/deeparg/test.mapping.potential.ARG
+      contains:
+        - "#ARG"
+    - path: output/deeparg/versions.yml
+      md5sum: e848ddab324e8c6fd18eaa6b2656f195