add module AMPlify (#1498)

* add module AMPlify

* Apply suggestions from code review

Thanks for the review!

Co-authored-by: Moritz E. Beber <midnighter@posteo.net>

* removed trailing whitespaces

* Apply suggestions from code review

Thanks again!

Co-authored-by: Moritz E. Beber <midnighter@posteo.net>

* Apply suggestions from code review

Thank you for the suggestions!

Co-authored-by: Sateesh Peri <33637490+sateeshperi@users.noreply.github.com>
Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Apply suggestions from code review

Co-authored-by: Sateesh Peri <33637490+sateeshperi@users.noreply.github.com>

* including review suggestions

* fix versions.yml

* add model_dir input

* add model_dir to meta.yml

* complete faa pattern in meta.yml

* add fa.gz to pattern

Co-authored-by: Moritz E. Beber <midnighter@posteo.net>
Co-authored-by: Sateesh Peri <33637490+sateeshperi@users.noreply.github.com>
Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/amplify/predict/main.nf

@@ -0,0 +1,41 @@
+def VERSION = '1.0.3' // Version information not provided by tool
+
+process AMPLIFY_PREDICT {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::amplify=1.0.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/amplify:1.0.3--py36hdfd78af_0':
+        'quay.io/biocontainers/amplify:1.0.3--py36hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(faa)
+    path(model_dir)
+
+    output:
+    tuple val(meta), path('*.tsv'), emit: tsv
+    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}"
+    def custom_model_dir = model_dir ? "-md ${model_dir}" : ""
+    """
+    AMPlify \\
+        $args \\
+        ${custom_model_dir} \\
+        -s '${faa}'
+
+    #rename output, because tool includes date and time in name
+    mv *.tsv ${prefix}.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        AMPlify: $VERSION
+    END_VERSIONS
+    """
+}

modules/amplify/predict/meta.yml

@@ -0,0 +1,47 @@
+name: "amplify_predict"
+description: AMPlify is an attentive deep learning model for antimicrobial peptide prediction.
+keywords:
+  - antimicrobial peptides
+  - AMPs
+  - prediction
+  - model
+tools:
+  - "amplify":
+      description: "Attentive deep learning model for antimicrobial peptide prediction"
+      homepage: "https://github.com/bcgsc/AMPlify"
+      documentation: "https://github.com/bcgsc/AMPlify"
+      tool_dev_url: "https://github.com/bcgsc/AMPlify"
+      doi: "https://doi.org/10.1186/s12864-022-08310-4"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - faa:
+      type: file
+      description: amino acid sequences fasta
+      pattern: "*.{fa,fa.gz,faa,faa.gz,fasta,fasta.gz}"
+  - model_dir:
+      type: directory
+      description: Directory of where models are stored (optional)
+
+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"
+  - tsv:
+      type: file
+      description: amino acid sequences with prediction (AMP, non-AMP) and probability scores
+      pattern: "*.{tsv}"
+
+authors:
+  - "@louperelo"

tests/config/pytest_modules.yml

@@ -26,6 +26,10 @@ allelecounter:
   - modules/allelecounter/**
   - tests/modules/allelecounter/**
 
+amplify/predict:
+  - modules/amplify/predict/**
+  - tests/modules/amplify/predict/**
+
 amps:
   - modules/amps/**
   - tests/modules/amps/**

tests/modules/amplify/predict/main.nf

@@ -0,0 +1,18 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { PRODIGAL } from '../../../modules/prodigal/main.nf' addParams( options: [:] )
+include { AMPLIFY_PREDICT } from '../../../../modules/amplify/predict/main.nf' addParams( options: [:] )
+
+workflow amplify_predict {
+    
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true)
+    ]
+    model_dir = []
+
+    PRODIGAL ( input, "gff" )
+    AMPLIFY_PREDICT ( PRODIGAL.out.amino_acid_fasta, model_dir)
+}

tests/modules/amplify/predict/nextflow.config

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

tests/modules/amplify/predict/test.yml

@@ -0,0 +1,9 @@
+- name: amplify predict amplify_predict
+  command: nextflow run tests/modules/amplify/predict -entry amplify_predict -c tests/config/nextflow.config
+  tags:
+    - amplify/predict
+    - amplify
+  files:
+    - path: output/amplify/test.tsv
+      md5sum: 1951084ce1d410028be86754997e5852
+    - path: output/amplify/versions.yml