Added fasta_busco_plot workflow

Plant-Food-Research-Open · Feb 21, 2024 · 64eebf3 · 64eebf3
1 parent 75faf2e
commit 64eebf3
Show file tree

Hide file tree

Showing 8 changed files with 156 additions and 2 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -55,14 +55,22 @@ process {
         ]
     }
 
-    withName: RUN_BUSCO {
+    withName: BUSCO {
         publishDir = [
             path: { "${params.outdir}/busco" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals("versions.yml") ? null : filename }
         ]
     }
 
+    withName: BUSCO_PLOT {
+        publishDir = [
+            path: { "${params.outdir}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals("versions.yml") ? null : filename }
+        ]
+    }
+
     withName: RUN_KRAKEN2 {
         publishDir = [
             path: { "${params.outdir}/kraken2" },

diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy
@@ -52,6 +52,11 @@ class WorkflowMain {
         if (!params.ncbi_fcs_gx_skip && !params.ncbi_fcs_gx_db_path) {
             Nextflow.error('ncbi_fcs_gx_db_path must be provided when executing NCBI FCS GX')
         }
+
+        // Check for busco_lineage_datasets
+        if (!params.busco_skip && !params.busco_lineage_datasets) {
+            Nextflow.error('busco_lineage_datasets must be provided when executing BUSCO')
+        }
     }
     //
     // Get attribute from genome config file e.g. fasta

diff --git a/modules/local/busco.nf b/modules/local/busco.nf
@@ -0,0 +1,54 @@
+process BUSCO {
+    tag "${asm_tag}:${lineage_dataset}"
+    label 'process_high'
+
+    conda "bioconda::busco=5.2.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/busco:5.2.2--pyhdfd78af_0':
+        'quay.io/biocontainers/busco:5.2.2--pyhdfd78af_0' }"
+
+    input:
+    tuple val(asm_tag), path(fasta_file)
+    val lineage_dataset
+    val mode
+    val download_path
+
+    output:
+    path "${asm_tag}/short_summary.specific.${lineage_dataset}.${asm_tag}_${lineage_initials}.txt"  , emit: summary
+    path "versions.yml"                                                                             , emit: versions
+
+    script:
+    def lineages_path   = download_path ? "--download_path ${download_path}" : ''
+    lineage_initials    = "${lineage_dataset}".split("_")[0]
+
+    """
+    busco \\
+        -m ${mode} \\
+        -o ${asm_tag} \\
+        -i $fasta_file \\
+        -l ${lineage_dataset} \\
+        --update-data \\
+        $lineages_path \\
+        -c ${task.cpus}
+
+    mv $asm_tag/short_summary.specific.${lineage_dataset}.${asm_tag}.txt \\
+        $asm_tag/short_summary.specific.${lineage_dataset}.${asm_tag}_${lineage_initials}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
+    END_VERSIONS
+    """
+
+    stub:
+    lineage_initials    = "${lineage_dataset}".split("_")[0]
+    """
+    mkdir -p $asm_tag
+    touch $asm_tag/short_summary.specific.${lineage_dataset}.${asm_tag}_${lineage_initials}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        busco: \$( busco --version 2>&1 | sed 's/^BUSCO //' )
+    END_VERSIONS
+    """
+}
diff --git a/modules/local/busco_plot.nf b/modules/local/busco_plot.nf
@@ -0,0 +1,28 @@
+process BUSCO_PLOT {
+    tag 'all summaries'
+    label 'process_single'
+
+    conda "bioconda::busco=5.2.2"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/busco:5.2.2--pyhdfd78af_0':
+        'quay.io/biocontainers/busco:5.2.2--pyhdfd78af_0' }"
+
+    input:
+    path "short_summary.*", stageAs: 'busco/*'
+
+    output:
+    path 'busco/*.png', emit: png
+
+    script:
+    """
+    generate_plot.py \\
+        -wd ./busco
+    """
+
+    stub:
+    """
+    mkdir -p busco
+
+    touch busco/summary_plot.png
+    """
+}
diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -107,7 +107,7 @@
                 "busco_lineage_datasets": {
                     "type": "string",
                     "help_text": "Each input assembly is assessed against each lineage. It should be provided as a space-separated list of lineages: 'fungi_odb10 microsporidia_odb10' ",
-                    "pattern": "^(\\w+_odb10\\s)+\\w+_odb10$",
+                    "pattern": "^(\\w+_odb10\\s)*\\w+_odb10$",
                     "description": "BUSCO lineages"
                 },
                 "busco_download_path": {

diff --git a/subworkflows/local/fasta_busco_plot.nf b/subworkflows/local/fasta_busco_plot.nf
@@ -0,0 +1,32 @@
+include { BUSCO             } from '../../modules/local/busco'
+include { BUSCO_PLOT        } from '../../modules/local/busco_plot'
+
+workflow FASTA_BUSCO_PLOT {
+    take:
+    tuple_of_hap_file       // Channel
+    lineage                 // val
+    mode                    // val
+    download_path           // val; Use [] to use work directory. Useful on AWS
+
+    main:
+    // MODULE: BUSCO
+    BUSCO(
+        tuple_of_hap_file,
+        lineage,
+        mode,
+        download_path
+    )
+
+    ch_busco_summaries      = BUSCO.out.summary
+                            | collect
+
+    // MODULE: BUSCO_PLOT
+    BUSCO_PLOT ( ch_busco_summaries )
+
+    ch_busco_plot           = BUSCO_PLOT.out.png
+
+    emit:
+    summary                 = BUSCO.out.summary
+    plot                    = ch_busco_plot
+    versions                = Channel.empty().mix(BUSCO.out.versions.first())
+}
diff --git a/tests/stub/stub.config b/tests/stub/stub.config
@@ -10,6 +10,9 @@ params {
     ncbi_fcs_gx_tax_id          = 12
     ncbi_fcs_gx_db_path         = 'tests/stub/gxdb/test'
 
+    busco_skip                  = false
+    busco_lineage_datasets      = 'fungi_odb10 hypocreales_odb10'
+
     // Limit resources so that this can run on GitHub Actions
     max_cpus                    = 2
     max_memory                  = '6.GB'

diff --git a/workflows/assemblyqc.nf b/workflows/assemblyqc.nf
@@ -32,6 +32,7 @@ include { GFF3_VALIDATE                     } from '../subworkflows/pfr/gff3_val
 include { NCBI_FCS_ADAPTOR                  } from '../modules/local/ncbi_fcs_adaptor'
 include { NCBI_FCS_GX                       } from '../subworkflows/local/ncbi_fcs_gx'
 include { ASSEMBLATHON_STATS                } from '../modules/local/assemblathon_stats'
+include { FASTA_BUSCO_PLOT                  } from '../subworkflows/local/fasta_busco_plot'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -253,6 +254,29 @@ workflow ASSEMBLYQC {
     ch_assemblathon_stats                   = ASSEMBLATHON_STATS.out.stats
     ch_versions                             = ch_versions.mix(ASSEMBLATHON_STATS.out.versions.first())
 
+    // SUBWORKFLOW: FASTA_BUSCO_PLOT
+    ch_busco_inputs                         = params.busco_skip
+                                            ? Channel.empty()
+                                            : ch_clean_assembly
+                                            | combine(
+                                                Channel.of(params.busco_lineage_datasets)
+                                                | map { it.split(' ') }
+                                                | flatten
+                                            )
+                                            | map { tag, fa, lineage ->
+                                                [ tag, file(fa, checkIfExists: true), lineage ]
+                                            }
+    FASTA_BUSCO_PLOT(
+        ch_busco_inputs.map { tag, fa, lineage -> [ tag, fa ] },
+        ch_busco_inputs.map { tag, fa, lineage -> lineage },
+        params.busco_mode,
+        params.busco_download_path ?: []
+    )
+
+    ch_busco_summary                        = FASTA_BUSCO_PLOT.out.summary
+    ch_busco_plot                           = FASTA_BUSCO_PLOT.out.plot
+    ch_versions                             = ch_versions.mix(FASTA_BUSCO_PLOT.out.versions)
+
     // MODULE: CUSTOM_DUMPSOFTWAREVERSIONS
     CUSTOM_DUMPSOFTWAREVERSIONS (
         ch_versions.unique().collectFile(name: 'collated_versions.yml')