Add mitohifi/mitohifi module (#3573)

* Add mitohifi module * Lint and add a note in pytest_modules * Fix prettier checks * Fix spelling * Fix data references * Make a note not to use conda * Change md5 values * Remove extra file * Fix code according to code review * ECLint check fix * Extend description of the output * Fix md5 hash for output * Fix prettier * Fix conda checks * Undo changes before merge * Skip conda test on gihub * Update md5sums --------- Co-authored-by: Ksenia Krasheninnikova <[email protected]> Co-authored-by: Priyanka Surana <[email protected]>
nf-core · Sep 5, 2023 · 02c3c39 · 02c3c39
1 parent 780e332
commit 02c3c39
Show file tree

Hide file tree

Showing 8 changed files with 222 additions and 0 deletions.
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -193,6 +193,8 @@ jobs:
             tags: merquryfk/merquryfk
           - profile: "conda"
             tags: merquryfk/ploidyplot
+          - profile: "conda"
+            tags: mitohifi/mitohifi
           - profile: "conda"
             tags: mitohifi/findmitoreference
           - profile: "conda"

diff --git a/modules/nf-core/mitohifi/mitohifi/main.nf b/modules/nf-core/mitohifi/mitohifi/main.nf
@@ -0,0 +1,66 @@
+process MITOHIFI_MITOHIFI {
+    tag "$meta.id"
+    label 'process_high'
+
+
+    // Docker image available at the project github repository
+    container 'ghcr.io/marcelauliano/mitohifi:master'
+
+    input:
+    tuple val(meta), path(reads), path(contigs)
+    path ref_fa
+    path ref_gb
+    val mito_code
+
+    output:
+    tuple val(meta), path("*fasta")                          , emit: fasta
+    tuple val(meta), path("*contigs_stats.tsv")              , emit: stats
+    tuple val(meta), path("*gb")                             , emit: gb, optional: true
+    tuple val(meta), path("*gff")                            , emit: gff, optional: true
+    tuple val(meta), path("*all_potential_contigs.fa")       , emit: all_potential_contigs, optional: true
+    tuple val(meta), path("*contigs_annotations.png")        , emit: contigs_annotations, optional: true
+    tuple val(meta), path("*contigs_circularization")        , emit: contigs_circularization, optional: true
+    tuple val(meta), path("*contigs_filtering")              , emit: contigs_filtering, optional: true
+    tuple val(meta), path("*coverage_mapping")               , emit: coverage_mapping, optional: true
+    tuple val(meta), path("*coverage_plot.png")              , emit: coverage_plot, optional: true
+    tuple val(meta), path("*final_mitogenome.annotation.png"), emit: final_mitogenome_annotation, optional: true
+    tuple val(meta), path("*final_mitogenome_choice")        , emit: final_mitogenome_choice, optional: true
+    tuple val(meta), path("*final_mitogenome.coverage.png")  , emit: final_mitogenome_coverage, optional: true
+    tuple val(meta), path("*potential_contigs")              , emit: potential_contigs, optional: true
+    tuple val(meta), path("*reads_mapping_and_assembly")     , emit: reads_mapping_and_assembly, optional: true
+    tuple val(meta), path("*shared_genes.tsv")               , emit: shared_genes, optional: true
+    path  "versions.yml"                                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        exit 1, "MitoHiFi module does not support Conda. Please use Docker / Singularity instead."
+    }
+
+    def args = task.ext.args ?: ''
+    def run_type = reads ? "-r ${reads}" :
+                    contigs ? "-c ${contigs}" :
+                    exit("Reads or contigs must be specified")
+    """
+    mitohifi.py ${run_type} -f ${ref_fa} -g ${ref_gb} -o ${mito_code} -t $task.cpus ${args}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mitohifi: \$( mitohifi.py --version 2>&1 | head -n1 | sed 's/^.*MitoHiFi //; s/ .*\$//' )
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    touch final_mitogenome.fasta
+    touch final_mitogenome.fasta
+    touch contigs_stats.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mitohifi: \$( mitohifi.py --version 2>&1 | head -n1 | sed 's/^.*MitoHiFi //; s/ .*\$//')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/mitohifi/mitohifi/meta.yml b/modules/nf-core/mitohifi/mitohifi/meta.yml
@@ -0,0 +1,109 @@
+name: "MITOHIFI_MITOHIFI"
+description: A python workflow that assembles mitogenomes from Pacbio HiFi reads
+keywords:
+  - mitochondrion
+  - chloroplast
+  - PacBio
+tools:
+  - "mitohifi.py":
+      description: A python workflow that assembles mitogenomes from Pacbio HiFi reads
+      homepage: https://github.com/marcelauliano/MitoHiFi
+      documentation: https://github.com/marcelauliano/MitoHiFi
+      tool_dev_url: https://github.com/marcelauliano/MitoHiFi
+      doi: "10.1101/2022.12.23.521667"
+      licence: ["MIT"]
+
+input:
+  - reads:
+      type: file
+      description: Path to PacBio HiFi reads
+      pattern: "*.{fa,fa.gz,fasta,fasta.gz}"
+  - contigs:
+      type: file
+      description: Path to genome assembly
+      pattern: "*.{fa,fasta}"
+  - ref_fa:
+      type: file
+      description: Reference sequence
+      pattern: "*.{fa,fasta}"
+  - ref_gb:
+      type: file
+      description: Reference annotation
+      pattern: "*.{gb}"
+  - code:
+      type: integer
+      description: Mitochndrial code for annotation
+      pattern: "[0-9]*"
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - fasta:
+      type: file
+      description: Mitochondrial sequence
+      pattern: "*.{fasta,fa}"
+  - gb:
+      type: file
+      description: Genome annotation in case mitofinder was used
+      pattern: "*.gb"
+  - gff:
+      type: file
+      description: Genome annotation in case mitos was used
+      pattern: "*.gff"
+  - all_potential_contigs:
+      type: file
+      description: Contains sequences of all potential contigs
+      pattern: "*all_potential_contigs.fa"
+  - contigs_annotations:
+      type: file
+      description: Graphical representation of annotated genes and tRNAs
+      pattern: "*contigs_annotations.png"
+  - contigs_circularization:
+      type: directory
+      description: Contains circularization reports
+      pattern: "*contigs_circularization"
+  - contigs_filtering:
+      type: directory
+      description: Contains files with initial blast matches
+      pattern: "*contigs_filtering"
+  - coverage_mapping:
+      type: directory
+      description: Contains statistics on coverage mapping
+      pattern: "*coverage_mapping"
+  - coverage_plot:
+      type: file
+      description: Read coverage plot for mitochondrial contigs
+      pattern: "*coverage_plot.png"
+  - final_mitogenome_annotation:
+      type: file
+      description: Graphical representation of annotated genes for the final mito contig
+      pattern: "*final_mitogenome.annotation.png"
+  - final_mitogenome_choice:
+      type: directory
+      description: Files with potential contigs clusterings and alignments
+      pattern: "*final_mitogenome_choice"
+  - final_mitogenome_coverage:
+      type: file
+      description: Graphical representation of reads coverage plot for the final mito contig
+      pattern: "*final_mitogenome.coverage.png"
+  - potential_contigs:
+      type: directory
+      description: Files with sequences and annotations of the potential contigs
+      pattern: "*potential_contigs"
+  - reads_mapping_and_assembly:
+      type: directory
+      description: Read mapping files for run from the raw reads
+      pattern: "*reads_mapping_and_assembly"
+  - shared_genes:
+      type: directory
+      description: Report on genes shared with the reference genome
+      pattern: "*shared_genes.tsv"
+  - versions:
+      type: file
+      description: Software versions used in the run
+      pattern: "versions.yml"
+
+authors:
+  - "@ksenia-krasheninnikova"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
@@ -2450,6 +2450,10 @@ mitohifi/findmitoreference:
   - modules/nf-core/mitohifi/findmitoreference/**
   - tests/modules/nf-core/mitohifi/findmitoreference/**
 
+mitohifi/mitohifi:
+  - modules/nf-core/mitohifi/mitohifi/**
+  - tests/modules/nf-core/mitohifi/mitohifi/**
+
 mlst:
   - modules/nf-core/mlst/**
   - tests/modules/nf-core/mlst/**

diff --git a/tests/config/test_data.config b/tests/config/test_data.config
@@ -655,6 +655,14 @@ params {
                 pretext = "${params.test_data_base}/data/genomics/eukaryotes/galaxea_fascicularis/hic/jaGalFasc40_2.pretext"
             }
         }
+        'deilephila_porcellus' {
+            'mito' {
+                ref_fa      = "${params.test_data_base}/data/genomics/eukaryotes/deilephila_porcellus/mito/MW539688.1.fasta"
+                ref_gb      = "${params.test_data_base}/data/genomics/eukaryotes/deilephila_porcellus/mito/MW539688.1.gb"
+                hifi_reads  = "${params.test_data_base}/data/genomics/eukaryotes/deilephila_porcellus/mito/ilDeiPorc1.HiFi.reads.fa"
+                contigs     = "${params.test_data_base}/data/genomics/eukaryotes/deilephila_porcellus/mito/ilDeiPorc1.contigs.fa"
+            }
+        }
         'imaging' {
             'h5' {
                 plant_wga                       = "${params.test_data_base}/data/imaging/h5/plant_wga.h5"

diff --git a/tests/modules/nf-core/mitohifi/mitohifi/main.nf b/tests/modules/nf-core/mitohifi/mitohifi/main.nf
@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MITOHIFI_MITOHIFI as MITOHIFI_MITOHIFI } from '../../../../../modules/nf-core/mitohifi/mitohifi/main.nf'
+
+workflow test_mitohifi_mitohifi {
+
+    species = "'Deilephila porcellus'"
+
+    data_contigs = Channel.of([[id:"ilDeiPorc1"],[],file(params.test_data['deilephila_porcellus']['mito']['contigs'], checkIfExists: true)])
+    ref_gb = file(params.test_data['deilephila_porcellus']['mito']['ref_gb'], checkIfExists: true)
+    ref_fa = file(params.test_data['deilephila_porcellus']['mito']['ref_fa'], checkIfExists: true)
+    code = 5
+    MITOHIFI_MITOHIFI ( data_contigs, ref_fa, ref_gb, code )
+}
diff --git a/tests/modules/nf-core/mitohifi/mitohifi/nextflow.config b/tests/modules/nf-core/mitohifi/mitohifi/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
+}
diff --git a/tests/modules/nf-core/mitohifi/mitohifi/test.yml b/tests/modules/nf-core/mitohifi/mitohifi/test.yml
@@ -0,0 +1,12 @@
+- name: mitohifi mitohifi test_mitohifi_mitohifi
+  command: nextflow run ./tests/modules/nf-core/mitohifi/mitohifi -entry test_mitohifi_mitohifi -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/mitohifi/mitohifi/nextflow.config
+  tags:
+    - mitohifi
+    - mitohifi/mitohifi
+  files:
+    - path: output/mitohifi/final_mitogenome.fasta
+      md5sum: 5654c418bbf991483d9e618dd849af03
+    - path: output/mitohifi/final_mitogenome.gb
+      md5sum: 3b4659a0d7f27fd89510a25c0588909d
+    - path: output/mitohifi/versions.yml
+      md5sum: 2a4db1ea8ac4b9b11ea47e1c3963f591