From 9d7208504d1898757cfdbb3065718e6545940408 Mon Sep 17 00:00:00 2001
From: "James A. Fellows Yates" <jfy133@gmail.com>
Date: Wed, 22 Jun 2022 13:43:45 +0200
Subject: [PATCH] Add gecco/run module (#1790)

* Add gecco/run module

* Fix container URLs

* Apply suggestions from code review

Co-authored-by: Jasmin F <73216762+jasmezz@users.noreply.github.com>
---
 modules/gecco/run/main.nf               | 47 +++++++++++++++++
 modules/gecco/run/meta.yml              | 67 +++++++++++++++++++++++++
 tests/config/pytest_modules.yml         |  4 ++
 tests/modules/gecco/run/main.nf         | 17 +++++++
 tests/modules/gecco/run/nextflow.config |  5 ++
 tests/modules/gecco/run/test.yml        | 13 +++++
 6 files changed, 153 insertions(+)
 create mode 100644 modules/gecco/run/main.nf
 create mode 100644 modules/gecco/run/meta.yml
 create mode 100644 tests/modules/gecco/run/main.nf
 create mode 100644 tests/modules/gecco/run/nextflow.config
 create mode 100644 tests/modules/gecco/run/test.yml

diff --git a/modules/gecco/run/main.nf b/modules/gecco/run/main.nf
new file mode 100644
index 00000000..7103250c
--- /dev/null
+++ b/modules/gecco/run/main.nf
@@ -0,0 +1,47 @@
+process GECCO_RUN {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::gecco=0.9.2" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/gecco:0.9.2--pyhdfd78af_0':
+        'quay.io/biocontainers/gecco:0.9.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(input), path(hmm)
+    path model_dir
+
+
+    output:
+    tuple val(meta), path("*.genes.tsv")           , emit: genes
+    tuple val(meta), path("*.features.tsv")        , emit: features
+    tuple val(meta), path("*.clusters.tsv") , emit: clusters
+    tuple val(meta), path("*_cluster_*.gbk"), optional: true, emit: gbk
+    tuple val(meta), path("*.json")         , optional: true, emit: json
+
+    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 = model_dir ? "--model ${model_dir}" : ""
+    def custom_hmm = hmm ? "--hmm ${hmm}" : ""
+    """
+    gecco \\
+        run \\
+        $args \\
+        -j $task.cpus \\
+        -o ./ \\
+        -g ${input} \\
+        $custom_model \\
+        $custom_hmm
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        gecco: \$(echo \$(gecco --version) | cut -f 2 -d ' ' )
+    END_VERSIONS
+    """
+}
diff --git a/modules/gecco/run/meta.yml b/modules/gecco/run/meta.yml
new file mode 100644
index 00000000..bfa55586
--- /dev/null
+++ b/modules/gecco/run/meta.yml
@@ -0,0 +1,67 @@
+name: "gecco_run"
+description: GECCO is a fast and scalable method for identifying putative novel Biosynthetic Gene Clusters (BGCs) in genomic and metagenomic data using Conditional Random Fields (CRFs).
+keywords:
+  - bgc
+  - detection
+  - metagenomics
+  - contigs
+tools:
+  - "gecco":
+      description: "Biosynthetic Gene Cluster prediction with Conditional Random Fields."
+      homepage: "https://gecco.embl.de"
+      documentation: "https://gecco.embl.de"
+      tool_dev_url: "https://github.com/zellerlab/GECCO"
+      doi: "10.1101/2021.05.03.442509"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: A genomic file containing one or more sequences as input. Input type is any supported by Biopython (fasta, gbk, etc.)
+      pattern: "*"
+  - hmm:
+      file: file
+      description: Alternative HMM file(s) to use in HMMER format
+      pattern: "*.hmm"
+  - model_dir:
+      file: directory
+      description: Path to an alternative CRF (Conditional Random Fields) module to use
+
+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"
+  - genes:
+      type: file
+      description: TSV file containing detected/predicted genes with BGC probability scores
+      pattern: "*.genes.tsv"
+  - features:
+      type: file
+      description: TSV file containing identified domains
+      pattern: "*.features.tsv"
+  - clusters:
+      type: file
+      description: TSV file containing coordinates of predicted clusters and BGC types
+      pattern: "*.clusters.tsv"
+  - gbk:
+      type: file
+      description: Per cluster GenBank file (if found) containing sequence with annotations
+      pattern: "*.gbk"
+  - json:
+      type: file
+      description: AntiSMASH v6 sideload JSON file (if --antismash-sideload) supplied
+      pattern: "*.gbk"
+
+authors:
+  - "@jfy133"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 6bd5b230..017e7752 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -915,6 +915,10 @@ gatk4/variantrecalibrator:
   - modules/gatk4/variantrecalibrator/**
   - tests/modules/gatk4/variantrecalibrator/**
 
+gecco/run:
+  - modules/gecco/run/**
+  - tests/modules/gecco/run/**
+
 genescopefk:
   - modules/genescopefk/**
   - tests/modules/genescopefk/**
diff --git a/tests/modules/gecco/run/main.nf b/tests/modules/gecco/run/main.nf
new file mode 100644
index 00000000..42ff5f3d
--- /dev/null
+++ b/tests/modules/gecco/run/main.nf
@@ -0,0 +1,17 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { GECCO_RUN } from '../../../../modules/gecco/run/main.nf'
+
+workflow test_gecco_run {
+
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['candidatus_portiera_aleyrodidarum']['genome']['genome_fasta'], checkIfExists: true),
+        []
+    ]
+    model_dir = []
+
+    GECCO_RUN ( input, model_dir )
+}
diff --git a/tests/modules/gecco/run/nextflow.config b/tests/modules/gecco/run/nextflow.config
new file mode 100644
index 00000000..50f50a7a
--- /dev/null
+++ b/tests/modules/gecco/run/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file
diff --git a/tests/modules/gecco/run/test.yml b/tests/modules/gecco/run/test.yml
new file mode 100644
index 00000000..0fe67e68
--- /dev/null
+++ b/tests/modules/gecco/run/test.yml
@@ -0,0 +1,13 @@
+- name: gecco run test_gecco_run
+  command: nextflow run ./tests/modules/gecco/run -entry test_gecco_run -c ./tests/config/nextflow.config  -c ./tests/modules/gecco/run/nextflow.config
+  tags:
+    - gecco/run
+    - gecco
+  files:
+    - path: output/gecco/NC_018507.1_cluster_1.gbk
+    - path: output/gecco/genome.clusters.tsv
+      md5sum: 6560ec765f6bbae50645896fd93b35cd
+    - path: output/gecco/genome.features.tsv
+      md5sum: 07492cf186003311ba9829056c65787f
+    - path: output/gecco/genome.genes.tsv
+      md5sum: 031a37dc603f8a5296f462608fd7bcc3