feat: Add islandpath module (#65)

* feat: Add islandpath module

* chore: Fix version

* feat: Include islanpath into annotation

* test: Update test trace size

* refactor: Add log to islandpath

* fix: Add log to stub

* docs: Update doc with IslandPath info

* fix: Change prokka to bakta

* refactor: Rename tsv to gff (actual format)

CITATIONS.md

@@ -74,8 +74,12 @@
   > Page AJ, Taylor B, Delaney AJ, Soares J, Seemann T, Keane JA, Harris SR. SNP-sites: rapid efficient extraction of SNPs from multi-FASTA alignments. Microb Genom. 2016 Apr 29;2(4):e000056. doi: 10.1099/mgen.0.000056. PMID: 28348851; PMCID: PMC5320690.
 
 - [Unicycler](https://pubmed.ncbi.nlm.nih.gov/28594827/)
+
   > Wick RR, Judd LM, Gorrie CL, Holt KE. Unicycler: Resolving bacterial genome assemblies from short and long sequencing reads. PLoS Comput Biol. 2017 Jun 8;13(6):e1005595. doi: 10.1371/journal.pcbi.1005595. PMID: 28594827; PMCID: PMC5481147.
 
+- [IslandPath](https://doi.org/10.1093/bioinformatics/bty095)
+  > Claire Bertelli, Fiona S L Brinkman, Improved genomic island predictions with IslandPath-DIMOB, Bioinformatics, Volume 34, Issue 13, 01 July 2018, Pages 2161–2167, https://doi.org/10.1093/bioinformatics/bty095
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -37,6 +37,7 @@ Annotation:
 - (_optionally_) Prokka ([`prokka`](https://github.com/tseemann/prokka))
 - AMR ([`RGI`](https://github.com/arpcard/rgi))
 - Plasmids ([`mob_suite`](https://github.com/phac-nml/mob-suite))
+- Genomic Islands ([`IslandPath`](https://github.com/brinkmanlab/islandpath))
 - CAZY, VFDB, and BacMet query using DIAMOND ([`diamond`](https://github.com/bbuchfink/diamond))
 
 Phylogeny:

conf/modules.config

@@ -207,6 +207,14 @@ process {
         ]
     }
 
+    withName: ISLANDPATH {
+        publishDir = [
+            path: { "${params.outdir}/annotation/islandpath/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     // PopPUNK
 
     withName: POPPUNK_VISUALISE {

docs/output.md

@@ -187,6 +187,21 @@ MobRecon reconstructs individual plasmid sequences from draft genome assemblies
 
 [Diamond](https://github.com/bbuchfink/diamond) is a sequence aligner for protein and translated DNA searches, designed for high performance analysis of big sequence data. We use DIAMOND to predict the presence of virulence factors, heavy metal resistance determinants, and carbohydrate-active enzymes using [VFDB](http://www.mgc.ac.cn/VFs/), [BacMet](http://bacmet.biomedicine.gu.se/), and [CAZy](http://www.cazy.org/) respectively.
 
+### IslandPath
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `annotation/islandpath/`
+  - `${sample_id}/` : IslandPath results will be in one directory per genome.
+    - `${sample_id}.tsv` : IslandPath results
+    - `Dimob.log` : IslandPath execution log
+
+</details>
+
+[IslandPath](https://github.com/brinkmanlab/islandpath) is a standalone software to predict genomic islands
+in bacterial and archaeal genomes based on the presence of dinucleotide biases and mobility genes.
+
 ### Panaroo
 
 <details markdown="1">

modules/local/islandpath/main.nf

@@ -0,0 +1,49 @@
+process ISLANDPATH {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::islandpath=1.0.6"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/islandpath:1.0.6--hdfd78af_0':
+        'quay.io/biocontainers/islandpath:1.0.6--hdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(genome)
+
+    output:
+    tuple val(meta), path("${prefix}.gff"), emit: gff
+    path "Dimob.log"                      , emit: log
+    path "versions.yml"                   , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    // WARN: Version information not provided by tool on CLI. Please update this string when bumping container versions.
+    def VERSION = '1.0.6'
+    """
+    islandpath \\
+        $genome \\
+        ${prefix}.gff \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        islandpath: $VERSION
+    END_VERSIONS
+    """
+    stub:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    def VERSION = '1.0.6'
+    """
+    touch ${prefix}.gff
+    touch Dimob.log
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        islandpath: $VERSION
+    END_VERSIONS
+    """
+}

modules/local/islandpath/meta.yml

@@ -0,0 +1,38 @@
+name: islandpath
+description: Genomic island prediction in bacterial and archaeal genomes
+keywords:
+  - genomes
+  - genomic islands
+  - prediction
+tools:
+  - islandpath:
+    description: Genomic island prediction in bacterial and archaeal genomes
+    homepage: https://github.com/brinkmanlab/islandpath
+    documentation: https://github.com/brinkmanlab/islandpath#readme
+    tool_dev_url: https://github.com/brinkmanlab/islandpath
+    doi: "doi:10.1093/bioinformatics/bty095"
+    licence: ["GPL-3.0"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - genome:
+      type: file
+      description: |
+        Genome file in .gbk or .embl format.
+
+output:
+  - gff:
+      type: file
+      description: GFF file listing the predicted genomic islands and their coordinates
+      pattern: "*.gff"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+authors:
+  - "@jvfe"

subworkflows/local/annotation.nf

@@ -23,6 +23,7 @@ include { GET_SOFTWARE_VERSIONS } from '../../modules/local/get_software_version
 include { RGI;
           UPDATE_RGI_DB } from '../../modules/local/rgi'
 include { MOB_RECON } from '../../modules/local/mobsuite'
+include { ISLANDPATH } from '../../modules/local/islandpath/main'
 
 //
 // SUBWORKFLOWS
@@ -128,8 +129,8 @@ workflow ANNOTATE_ASSEMBLIES {
             ch_software_versions = ch_software_versions.mix(PROKKA.out.versions.first().ifEmpty(null))
             ch_ffn_files = PROKKA.out.ffn
             ch_gff_files = PROKKA.out.gff
+            ch_gbk_files = PROKKA.out.gbk
             ch_multiqc_files = ch_multiqc_files.mix(PROKKA.out.txt.collect{it[1]}.ifEmpty([]))
-
         }
         else {
 
@@ -144,7 +145,7 @@ workflow ANNOTATE_ASSEMBLIES {
             ch_software_versions = ch_software_versions.mix(BAKTA.out.versions.first().ifEmpty(null))
             ch_ffn_files = BAKTA.out.ffn
             ch_gff_files = BAKTA.out.gff
-
+            ch_gbk_files = BAKTA.out.gbff
         }
 
         /*
@@ -153,7 +154,8 @@ workflow ANNOTATE_ASSEMBLIES {
         MOB_RECON(assemblies)
         ch_software_versions = ch_software_versions.mix(MOB_RECON.out.version.first().ifEmpty(null))
 
-
+        ISLANDPATH(ch_gbk_files)
+        ch_software_versions = ch_software_versions.mix(ISLANDPATH.out.versions.first())
 
         /*
         * Run DIAMOND blast annotation with databases

tests/subworkflows/local/annotation.nf.test

@@ -30,7 +30,7 @@ nextflow_workflow {
 
         then {
             assert workflow.success
-            assert workflow.trace.tasks().size() >= 8
+            assert workflow.trace.tasks().size() >= 9
             assert workflow.out.gff.size() == 1
             assert workflow.out.gff.get(0).get(1) ==~ ".*/SRR14022735.gff"
         }