refactor: Improve the way Bakta is used (#54)

* chore: Update bakta module * fix: Change path to bakta module * refactor: Rework how use bakta param is used - Now its a bool whether to run Bakta or not - If no --bakta-db is set but --use_bakta is set, the baktadbdownload module will run - By default, prokka is still the one used * feat: Add config for process single * test: Use bakta in annotation test * refactor: Use light bakta db in test * refactor: Use light db by default * Revert "test: Use bakta in annotation test" This reverts commit 343ab08. * test: Add light to ann test * refactor: Make Bakta the default ann software
beiko-lab · Mar 7, 2023 · 3cb354c · 3cb354c
1 parent fa56027
commit 3cb354c
Show file tree

Hide file tree

Showing 14 changed files with 166 additions and 58 deletions.
diff --git a/conf/base.config b/conf/base.config
@@ -26,6 +26,11 @@ process {
     //        adding in your local modules too.
     // TODO nf-core: Customise requirements for specific processes.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+    withLabel:process_single {
+        cpus   = { check_max( 1                  , 'cpus'    ) }
+        memory = { check_max( 6.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 4.h  * task.attempt, 'time'    ) }
+    }
     withLabel:process_low {
         cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
         memory = { check_max( 20.GB * task.attempt, 'memory'  ) }

diff --git a/conf/modules.config b/conf/modules.config
@@ -123,6 +123,10 @@ process {
         ]
     }
 
+    withName: BAKTADBDOWNLOAD {
+        ext.args = '--type light'
+    }
+
     withName: BAKTA {
         publishDir = [
             path: { "${params.outdir}/annotation/bakta/${meta.id}" },

diff --git a/conf/test.config b/conf/test.config
@@ -16,10 +16,10 @@ params {
 
     // Input data
     input_sample_table = "https://raw.githubusercontent.com/beiko-lab/arete/master/test/test_dataset.csv"
-    use_bakta = false
     db_cache = false
     use_full_alignment = false
     use_fasttree = true
+    use_prokka = true
     skip_kraken = true
     skip_poppunk = true
     light = true
@@ -31,6 +31,11 @@ process {
     memory = 6.GB
     time   = 4.h
 
+    withLabel:process_single {
+        cpus   =  1
+        memory = 6.GB
+        time   = 4.h
+    }
     withLabel:process_low {
         cpus   =  2
         memory = 6.GB

diff --git a/modules.json b/modules.json
@@ -5,9 +5,14 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
-                    "bakta": {
+                    "bakta/bakta": {
                         "branch": "master",
-                        "git_sha": "ade45f05a2659b5c130a483e09f50b7f33d075b2",
+                        "git_sha": "280c5c86b3da7dfcc92ebd5420584dd6ff26c4a8",
+                        "installed_by": ["modules"]
+                    },
+                    "bakta/baktadbdownload": {
+                        "branch": "master",
+                        "git_sha": "280c5c86b3da7dfcc92ebd5420584dd6ff26c4a8",
                         "installed_by": ["modules"]
                     },
                     "blast/blastn": {

diff --git a/modules/nf-core/bakta/main.nf → modules/nf-core/bakta/bakta/main.nf b/modules/nf-core/bakta/main.nf → modules/nf-core/bakta/bakta/main.nf
@@ -1,11 +1,11 @@
-process BAKTA {
+process BAKTA_BAKTA {
     tag "$meta.id"
     label 'process_medium'
 
-    conda (params.enable_conda ? "bioconda::bakta=1.4.0" : null)
+    conda "bioconda::bakta=1.7.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bakta:1.4.0--pyhdfd78af_1' :
-        'quay.io/biocontainers/bakta:1.4.0--pyhdfd78af_1' }"
+        'https://depot.galaxyproject.org/singularity/bakta:1.7.0--pyhdfd78af_1' :
+        'quay.io/biocontainers/bakta:1.7.0--pyhdfd78af_1' }"
 
     input:
     tuple val(meta), path(fasta)
@@ -33,20 +33,20 @@ process BAKTA {
     def args = task.ext.args   ?: ''
     prefix   = task.ext.prefix ?: "${meta.id}"
     def proteins_opt = proteins ? "--proteins ${proteins[0]}" : ""
-    def prodigal_opt = prodigal_tf ? "--prodigal-tf ${prodigal_tf[0]}" : ""
+    def prodigal_tf = prodigal_tf ? "--prodigal-tf ${prodigal_tf[0]}" : ""
     """
     bakta \\
+        $fasta \\
         $args \\
         --threads $task.cpus \\
         --prefix $prefix \\
-        --db $db \\
         $proteins_opt \\
         $prodigal_tf \\
-        $fasta
+        --db $db
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        bakta: \$( echo \$(bakta --version 2>&1) | sed 's/^.*bakta //' )
+        bakta: \$(echo \$(bakta --version) 2>&1 | cut -f '2' -d ' ')
     END_VERSIONS
     """
 
@@ -66,7 +66,7 @@ process BAKTA {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        bakta: \$( echo \$(bakta --version 2>&1) | sed 's/^.*bakta //' )
+        bakta: \$(echo \$(bakta --version) 2>&1 | cut -f '2' -d ' ')
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/bakta/meta.yml → modules/nf-core/bakta/bakta/meta.yml b/modules/nf-core/bakta/meta.yml → modules/nf-core/bakta/bakta/meta.yml
@@ -1,4 +1,4 @@
-name: bakta
+name: bakta_bakta
 description: Annotation of bacterial genomes (isolates, MAGs) and plasmids
 keywords:
   - annotation
@@ -26,7 +26,7 @@ input:
   - db:
       type: file
       description: |
-        Path to the Bakta database
+        Path to the Bakta database. Must have amrfinderplus database directory already installed within it (in a directory called 'amrfinderplus-db/').
   - proteins:
       type: file
       description: FASTA/GenBank file of trusted proteins to first annotate from (optional)
@@ -88,3 +88,4 @@ output:
 authors:
   - "@rpetit3"
   - "@oschwengers"
+  - "@jfy133"
diff --git a/modules/nf-core/bakta/baktadbdownload/main.nf b/modules/nf-core/bakta/baktadbdownload/main.nf
@@ -0,0 +1,43 @@
+process BAKTA_BAKTADBDOWNLOAD {
+    label 'process_single'
+
+    conda "bioconda::bakta=1.7.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/bakta:1.7.0--pyhdfd78af_1' :
+        'quay.io/biocontainers/bakta:1.7.0--pyhdfd78af_1' }"
+
+    output:
+    path "db*"              , emit: db
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    bakta_db \\
+        download \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bakta: \$(echo \$(bakta_db --version) 2>&1 | cut -f '2' -d ' ')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    """
+    echo "bakta_db \\
+        download \\
+        $args"
+
+    mkdir db
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        bakta: \$(echo \$(bakta_db --version) 2>&1 | cut -f '2' -d ' ')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/bakta/baktadbdownload/meta.yml b/modules/nf-core/bakta/baktadbdownload/meta.yml
@@ -0,0 +1,31 @@
+name: "bakta_baktadbdownload"
+description: Downloads BAKTA database from Zenodo
+keywords:
+  - bakta
+  - annotation
+  - fasta
+  - bacteria
+  - database
+  - download
+tools:
+  - bakta:
+      description: Rapid & standardized annotation of bacterial genomes, MAGs & plasmids
+      homepage: https://github.com/oschwengers/bakta
+      documentation: https://github.com/oschwengers/bakta
+      tool_dev_url: https://github.com/oschwengers/bakta
+      doi: "10.1099/mgen.0.000685"
+      licence: ["GPL v3"]
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: directory
+      description: BAKTA database directory
+      pattern: "db*/"
+
+authors:
+  - "@jfy133"
+  - "@jasmezz"
diff --git a/nextflow.config b/nextflow.config
@@ -25,7 +25,8 @@ params {
     use_fasttree               = true
 
     // Annotation parameters
-    use_bakta                  = null
+    use_prokka                 = false
+    bakta_db                   = null
     light                      = false
 
     // References

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -74,7 +74,8 @@
             "properties": {
                 "skip_kraken": {
                     "type": "boolean",
-                    "description": "Don't run Kraken2 taxonomic classification"
+                    "description": "Don't run Kraken2 taxonomic classification",
+                    "fa_icon": "fas fa-forward"
                 }
             },
             "fa_icon": "fas fa-align-left"
@@ -86,15 +87,21 @@
             "default": "",
             "fa_icon": "fas fa-edit",
             "properties": {
-                "use_bakta": {
+                "bakta_db": {
                     "type": "string",
                     "default": "None",
-                    "description": "Location to the bakta database"
+                    "fa_icon": "fas fa-database"
                 },
                 "light": {
                     "type": "boolean",
                     "description": "Only run one DIAMOND annotation step - against VFDB",
-                    "hidden": true
+                    "hidden": true,
+                    "fa_icon": "fas fa-feather-alt"
+                },
+                "use_prokka": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-bacterium",
+                    "description": "Use Prokka (not Bakta) for annotating assemblies"
                 }
             }
         },
@@ -107,11 +114,14 @@
             "properties": {
                 "use_full_alignment": {
                     "type": "boolean",
-                    "description": "Use full alignment"
+                    "description": "Use full alignment",
+                    "fa_icon": "fas fa-align-justify"
                 },
                 "use_fasttree": {
                     "type": "boolean",
-                    "description": "Use FastTree"
+                    "description": "Use FastTree",
+                    "fa_icon": "fas fa-tree",
+                    "default": true
                 }
             }
         },
@@ -124,16 +134,19 @@
             "properties": {
                 "skip_poppunk": {
                     "type": "boolean",
-                    "description": "Skip PopPunk"
+                    "description": "Skip PopPunk",
+                    "fa_icon": "fas fa-forward"
                 },
                 "poppunk_model": {
                     "type": "string",
                     "default": "None",
-                    "description": "Which PopPunk model to use (bgmm, dbscan, refine, threshold or lineage)"
+                    "description": "Which PopPunk model to use (bgmm, dbscan, refine, threshold or lineage)",
+                    "fa_icon": "fas fa-indent"
                 },
                 "run_poppunk_qc": {
                     "type": "boolean",
-                    "description": "Whether to run the QC step for PopPunk"
+                    "description": "Whether to run the QC step for PopPunk",
+                    "fa_icon": "fas fa-industry"
                 }
             }
         },

diff --git a/subworkflows/local/annotation.nf b/subworkflows/local/annotation.nf
@@ -2,7 +2,8 @@
 // MODULE: Installed directly from nf-core/modules
 //
 include { PROKKA                } from '../../modules/nf-core/prokka/main'
-include { BAKTA } from '../../modules/nf-core/bakta/main'
+include { BAKTA_BAKTA as BAKTA } from '../../modules/nf-core/bakta/bakta/main'
+include { BAKTA_BAKTADBDOWNLOAD as BAKTADBDOWNLOAD } from '../../modules/nf-core/bakta/baktadbdownload/main'
 include { GET_CAZYDB;
           GET_VFDB;
           GET_BACMET} from '../../modules/local/blast_databases.nf'
@@ -43,6 +44,7 @@ workflow ANNOTATE_ASSEMBLIES {
     main:
 
         //if (params.input_sample_table){ ch_input = file(params.input_sample_table) } else { exit 1, 'Input samplesheet not specified!' }
+        ch_multiqc_files = Channel.empty()
         ch_software_versions = Channel.empty()
         /*
         * SUBWORKFLOW: Read in samplesheet, validate and stage input files
@@ -104,23 +106,33 @@ workflow ANNOTATE_ASSEMBLIES {
         /*
         * Run gene finding software (Prokka or Bakta)
         */
-        ch_ffn_files = Channel.empty()
-        ch_gff_files = Channel.empty()
-        if (bakta_db){
-            BAKTA(assemblies, bakta_db, [], [])
-            ch_software_versions = ch_software_versions.mix(BAKTA.out.versions.first().ifEmpty(null))
-            ch_ffn_files = ch_ffn_files.mix(BAKTA.out.ffn)
-            ch_gff_files = ch_gff_files.mix(BAKTA.out.gff)
-        }
-        else{
+        if (params.use_prokka) {
+
             PROKKA (
             assemblies,
             [],
             []
             ) //Assembly, protein file, pre-trained prodigal
             ch_software_versions = ch_software_versions.mix(PROKKA.out.versions.first().ifEmpty(null))
-            ch_ffn_files = ch_ffn_files.mix(PROKKA.out.ffn)
-            ch_gff_files = ch_gff_files.mix(PROKKA.out.gff)
+            ch_ffn_files = PROKKA.out.ffn
+            ch_gff_files = PROKKA.out.gff
+            ch_multiqc_files = ch_multiqc_files.mix(PROKKA.out.txt.collect{it[1]}.ifEmpty([]))
+
+        }
+        else {
+
+            if (bakta_db){
+                BAKTA(assemblies, bakta_db, [], [])
+            } else {
+                BAKTADBDOWNLOAD()
+                BAKTADBDOWNLOAD.out.db.set { bakta_db }
+                BAKTA(assemblies, bakta_db, [], [])
+            }
+
+            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
+
         }
 
         /*
@@ -151,10 +163,6 @@ workflow ANNOTATE_ASSEMBLIES {
             CAZY_FILTER(DIAMOND_BLAST_CAZY.out.txt, "CAZY", blast_columns)
         }
         ch_software_versions = ch_software_versions.mix(DIAMOND_MAKE_VFDB.out.versions.ifEmpty(null))
-        ch_multiqc_files = Channel.empty()
-        if(!bakta_db){
-            ch_multiqc_files = ch_multiqc_files.mix(PROKKA.out.txt.collect{it[1]}.ifEmpty([]))
-        }
 
     emit:
         annotation_software = ch_software_versions

diff --git a/tests/nextflow.config b/tests/nextflow.config
@@ -9,12 +9,14 @@ params {
     cpus   = 2
     memory = 4.GB
     time   = 4.h
-
-    skip_kraken = true
-    light = true
 }
 
 process {
+    withLabel:process_single {
+        cpus   =  1
+        memory = 6.GB
+        time   = 4.h
+    }
     withLabel:process_low {
         cpus   =  2
         memory = 4.GB

diff --git a/tests/subworkflows/local/annotation.nf.test b/tests/subworkflows/local/annotation.nf.test
@@ -9,6 +9,8 @@ nextflow_workflow {
         when {
             params {
                 // define parameters here. Example:
+                light = true
+                use_prokka = true
                 outdir = "$outputDir"
             }
             workflow {