Aded fasta_gxf_busco_plot sub workflow

CHANGELOG.md

@@ -3,12 +3,14 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## v1.0dev - [date]
+## v1.0dev - [27-Nov-2024]
 
-Initial release of ecoflow/genomeqc, created with the [nf-core](https://nf-co.re/) template.
+Initial release of nf-core/genomeqc, created with the [nf-core](https://nf-co.re/) template.
 
 ### `Added`
 
+1. Now using `FASTA_GXF_BUSCO_PLOT` sub workflow from nf-core/modules [#77](https://github.com/nf-core/genomeqc/issues/77)
+
 ### `Fixed`
 
 ### `Dependencies`

README.md

@@ -121,6 +121,7 @@ ecoflow/genomeqc was originally written by Chris Wyatt, Fernando Duarte.
 We thank the following people for their extensive assistance in the development of this pipeline:
 
 - [Stephen Turner](https://github.com/stephenturner/) ([Colossal Biosciences](https://colossal.com/))
+- [Usman Rashid](https://github.com/gallvp) ([The New Zealand Institute for Plant and Food Research](https://www.plantandfood.com/en-nz/))
 
 <!-- TODO nf-core: If applicable, make list of people who have also contributed -->
 

assets/multiqc_config.yml

@@ -12,3 +12,7 @@ report_section_order:
 export_plots: true
 
 disable_version_detection: true
+
+extra_fn_clean_exts:
+  - type: regex
+    pattern: "^short_summary\\.specific\\..*_odb10\\."

conf/modules.config

@@ -31,7 +31,7 @@ process {
         ]
     }
 
-    withName: 'GFFREAD' {
+    withName: '.*:FASTA_GXF_BUSCO_PLOT:EXTRACT_PROTEINS' {
         ext.args = '-y -S'
         publishDir = [
             path: { "${params.outdir}/gffread" },
@@ -57,7 +57,7 @@ process {
         ]
     }
 
-    withName: 'BUSCO_BUSCO' {
+    withName: '.*:GENOME:BUSCO_BUSCO' {
         publishDir = [
             path: { "${params.outdir}/busco" },
             mode: params.publish_dir_mode,
@@ -133,4 +133,42 @@ process {
         ]
     }
 
+    withName: '.*:FASTA_GXF_BUSCO_PLOT:BUSCO_ASSEMBLY' {
+        ext.args = '--metaeuk'
+        publishDir = [
+            path: { "${params.outdir}/busco/fasta" },
+            mode: params.publish_dir_mode,
+            pattern: 'short_summary.*.txt',
+            saveAs: { filename -> "short_summary.specific.${meta.id}.${lineage}.txt" }
+        ]
+    }
+
+    withName: '.*:FASTA_GXF_BUSCO_PLOT:PLOT_ASSEMBLY' {
+        ext.prefix = 'busco_figure'
+        publishDir = [
+            path: { "${params.outdir}/busco/fasta" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals("versions.yml") ? null : filename }
+        ]
+    }
+
+    withName: '.*:FASTA_GXF_BUSCO_PLOT:BUSCO_ANNOTATION' {
+        ext.args = '--metaeuk'
+        publishDir = [
+            path: { "${params.outdir}/busco/gff" },
+            mode: params.publish_dir_mode,
+            pattern: 'short_summary.*.txt',
+            saveAs: { filename -> "short_summary.specific.${meta.id}.${lineage}.txt" }
+        ]
+    }
+
+    withName: '.*:FASTA_GXF_BUSCO_PLOT:PLOT_ANNOTATION' {
+        ext.prefix = 'busco_figure'
+        publishDir = [
+            path: { "${params.outdir}/busco/gff" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals("versions.yml") ? null : filename }
+        ]
+    }
+
 }

modules.json

@@ -18,7 +18,12 @@
           "busco/busco": {
             "branch": "master",
             "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-            "installed_by": ["modules"]
+            "installed_by": ["fasta_gxf_busco_plot", "modules"]
+          },
+          "busco/generateplot": {
+            "branch": "master",
+            "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+            "installed_by": ["fasta_gxf_busco_plot"]
           },
           "fastavalidator": {
             "branch": "master",
@@ -33,7 +38,7 @@
           "gffread": {
             "branch": "master",
             "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
-            "installed_by": ["modules"]
+            "installed_by": ["fasta_gxf_busco_plot", "modules"]
           },
           "merqury/merqury": {
             "branch": "master",
@@ -109,6 +114,11 @@
             "git_sha": "ab80a04707104a4baf39341581dfbced5da05479",
             "installed_by": ["subworkflows"]
           },
+          "fasta_gxf_busco_plot": {
+            "branch": "master",
+            "git_sha": "3628d826c68eea367143e403412133054f607650",
+            "installed_by": ["subworkflows"]
+          },
           "utils_nextflow_pipeline": {
             "branch": "master",
             "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",

modules/nf-core/busco/generateplot/environment.yml

@@ -0,0 +1,7 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::busco=5.7.1

modules/nf-core/busco/generateplot/main.nf

@@ -0,0 +1,45 @@
+process BUSCO_GENERATEPLOT {
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/busco:5.7.1--pyhdfd78af_0':
+        'biocontainers/busco:5.7.1--pyhdfd78af_0' }"
+
+    input:
+    path short_summary_txt, stageAs: 'busco/*'
+
+    output:
+    path '*.png'        , emit: png
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args     ?: ''
+    def prefix  = task.ext.prefix   ?: 'busco_figure'
+    """
+    generate_plot.py \\
+        $args \\
+        -wd busco
+
+    mv ./busco/busco_figure.png ${prefix}.png
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix  = task.ext.prefix   ?: 'busco_figure'
+    """
+    touch ${prefix}.png
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
+    END_VERSIONS
+    """
+}

modules/nf-core/busco/generateplot/meta.yml

@@ -0,0 +1,40 @@
+name: "busco_generateplot"
+description: BUSCO plot generation tool
+keywords:
+  - genome
+  - fasta
+  - annotation
+  - busco
+  - transcriptome
+  - quality control
+tools:
+  - busco:
+      description: BUSCO provides measures for quantitative assessment of genome assembly,
+        gene set, and transcriptome completeness based on evolutionarily informed expectations
+        of gene content from near-universal single-copy orthologs selected from OrthoDB.
+      homepage: https://busco.ezlab.org/
+      documentation: https://busco.ezlab.org/busco_userguide.html
+      tool_dev_url: https://gitlab.com/ezlab/busco
+      doi: "10.1007/978-1-4939-9173-0_14"
+      licence: ["MIT"]
+      identifier: biotools:busco
+input:
+  - - short_summary_txt:
+        type: file
+        description: One or more short summary txt files from BUSCO
+        pattern: "short_summary.*.txt"
+output:
+  - png:
+      - "*.png":
+          type: file
+          description: A summary plot in png format
+          pattern: "*.png"
+  - versions:
+      - versions.yml:
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+authors:
+  - "@GallVp"
+maintainers:
+  - "@GallVp"

modules/nf-core/busco/generateplot/tests/main.nf.test

@@ -0,0 +1,72 @@
+nextflow_process {
+
+    name "Test Process BUSCO_GENERATEPLOT"
+    script "../main.nf"
+    process "BUSCO_GENERATEPLOT"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "busco"
+    tag "busco/busco"
+    tag "busco/generateplot"
+
+    test("bacteroides_fragilis-genome_fna_gz") {
+
+        setup {
+            run("BUSCO_BUSCO") {
+                script "../../busco"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test' ], // meta map
+                        file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                    ]
+                    input[1] = 'genome'
+                    input[2] = 'bacteria_odb10'
+                    input[3] = []
+                    input[4] = []
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                input[0] = BUSCO_BUSCO.out.short_summaries_txt.map { meta, summary -> summary }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match("versions") },
+                { assert process.out.png != null } // PNGs with same data but different meta-data. Not sure how to get around this, yet!
+            )
+        }
+
+    }
+
+    test("stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = file(params.modules_testdata_base_path + 'genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}

modules/nf-core/busco/generateplot/tests/main.nf.test.snap

@@ -0,0 +1,37 @@
+{
+    "versions": {
+        "content": [
+            [
+                "versions.yml:md5,726fa3440ea3a0b2e9d032d7e4d25e74"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-03T15:40:01.523993"
+    },
+    "stub": {
+        "content": [
+            {
+                "0": [
+                    "busco_figure.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "1": [
+                    "versions.yml:md5,726fa3440ea3a0b2e9d032d7e4d25e74"
+                ],
+                "png": [
+                    "busco_figure.png:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "versions": [
+                    "versions.yml:md5,726fa3440ea3a0b2e9d032d7e4d25e74"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-05-03T15:40:11.864276"
+    }
+}

modules/nf-core/busco/generateplot/tests/tags.yml

@@ -0,0 +1,2 @@
+busco/generateplot:
+  - "modules/nf-core/busco/generateplot/**"