Update eggnogmapper (#10274)

* checkpoint

* main updated, topics syntax, sarscov2 - proteome - diamond test updated

* stub test added, meta yml description updated

* meta updated

* update meta.yml

* snapshot updated for conda matching

* re-update snapshot

* fixed db dir logic and added mmseqs test

* no_Search test added

* updated meta.yml descriptions and ontologies

* Update modules/nf-core/eggnogmapper/main.nf

Co-authored-by: Martín Beracochea <mbc@ebi.ac.uk>

* spaces pushing

---------

Co-authored-by: Martín Beracochea <mbc@ebi.ac.uk>

Author: vagkaratzas

modules/nf-core/eggnogmapper/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::eggnog-mapper=2.1.12
+  - bioconda::eggnog-mapper=2.1.13

modules/nf-core/eggnogmapper/main.nf

@@ -4,64 +4,55 @@ process EGGNOGMAPPER {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/eggnog-mapper:2.1.12--pyhdfd78af_0':
-        'biocontainers/eggnog-mapper:2.1.12--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/eggnog-mapper:2.1.13--pyhdfd78af_2':
+        'biocontainers/eggnog-mapper:2.1.13--pyhdfd78af_2' }"
 
     input:
     tuple val(meta), path(fasta)
-    path(eggnog_db)
+    tuple val(search_mode), path(db)
     path(eggnog_data_dir)
-    tuple val(meta2), path(eggnog_diamond_db)
 
     output:
     tuple val(meta), path("*.emapper.annotations")   , emit: annotations
-    tuple val(meta), path("*.emapper.seed_orthologs"), emit: orthologs
-    tuple val(meta), path("*.emapper.hits")          , emit: hits
-    path "versions.yml"                              , emit: versions
+    tuple val(meta), path("*.emapper.seed_orthologs"), emit: orthologs, optional: true
+    tuple val(meta), path("*.emapper.hits")          , emit: hits     , optional: true
+    tuple val("${task.process}"), val('eggnog-mapper'), eval("emapper.py --version 2>&1 | grep -o 'emapper-[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+' | sed 's/emapper-//'"), topic: versions, emit: versions_eggnogmapper
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args            = task.ext.args                 ?: ''
-    def prefix          = task.ext.prefix               ?: "${meta.id}"
-    def is_compressed   = fasta.extension == '.gz'      ? true                              : false
-    def fasta_name      = is_compressed                 ? fasta.baseName                    : "$fasta"
-    def dbmem           = task.memory.toMega() > 40000  ? '--dbmem'                         : ''
-    def database_arg    = eggnog_db                     ? "--database $eggnog_db"           : ''
-    def dmnd_db_arg     = eggnog_diamond_db             ? "--dmnd_db $eggnog_diamond_db"    : ''
+    def args          = task.ext.args   ?: ''
+    def prefix        = task.ext.prefix ?: "${meta.id}"
+    def is_compressed = fasta.extension == '.gz'
+    def fasta_name    = is_compressed ? fasta.baseName : "$fasta"
+    def db_flags = ['diamond': '--dmnd_db', 'novel_fams': '--dmnd_db', 'mmseqs': '--mmseqs_db', 'hmmer': '--database', 'no_search': '--annotate_hits_table', 'cache': '--cache']
+    def db_path  = (db instanceof Path && db.isDirectory()) ? "${db}/${db.name}"                    : "$db"
+    def db_arg   = db && db_flags[search_mode]              ? "${db_flags[search_mode]} ${db_path}" : ''
+    def dbmem    = task.memory.toMega() > 40000             ? '--dbmem'                             : ''
     """
     if [ "$is_compressed" == "true" ]; then
         gzip -c -d $fasta > $fasta_name
     fi
 
     emapper.py \\
+        $args \\
         --cpu ${task.cpus} \\
         -i ${fasta_name} \\
         --data_dir ${eggnog_data_dir} \\
-        -m diamond \\
-        $dmnd_db_arg \\
-        $database_arg \\
-        --output ${prefix} \\
+        -m ${search_mode} \\
+        $db_arg \\
         ${dbmem} \\
-        $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        eggnog-mapper: \$(echo \$(emapper.py --version) | grep -o "emapper-[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+" | sed "s/emapper-//")
-    END_VERSIONS
+        --output ${prefix}
     """
 
     stub:
-    def prefix  = task.ext.prefix ?: "${meta.id}"
+    def prefix = task.ext.prefix ?: "${meta.id}"
     """
+    echo $args
+
     touch ${prefix}.emapper.annotations
     touch ${prefix}.emapper.seed_orthologs
     touch ${prefix}.emapper.hits
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        eggnog-mapper: \$(echo \$(emapper.py --version) | grep -o "emapper-[0-9]\\+\\.[0-9]\\+\\.[0-9]\\+" | sed "s/emapper-//")
-    END_VERSIONS
     """
 }

modules/nf-core/eggnogmapper/meta.yml

@@ -1,91 +1,134 @@
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/yaml-schema.json
 name: "eggnogmapper"
 description: Fast genome-wide functional annotation through orthology assignment.
 keywords:
   - annotation
+  - functional annotation
   - orthology
   - genomics
+  - eggnog
 tools:
   - "eggnogmapper":
-      description: "Fast genome-wide functional annotation through orthology assignment."
+      description: |
+        EggNOG-mapper is a tool for fast functional annotation of novel sequences.
+        It uses precomputed orthologous groups and phylogenies from the eggNOG database
+        to transfer functional information from fine-grained orthologs only.
       homepage: "https://github.com/eggnogdb/eggnog-mapper"
       documentation: "https://github.com/eggnogdb/eggnog-mapper/wiki"
       tool_dev_url: "https://github.com/eggnogdb/eggnog-mapper"
       doi: "10.1093/molbev/msab293"
-      licence: ["AGPL v3"]
-      identifier: ""
+      licence:
+        - "AGPL v3"
+      identifier: "biotools:eggnog-mapper-v2"
 input:
   - - meta:
         type: map
         description: |
           Groovy Map containing sample information
-          e.g. `[ id:'test', single_end:false ]`
+          e.g. `[ id:'sample1' ]`
     - fasta:
         type: file
-        description: Database of sequences in FASTA format
-        pattern: "*.{fasta,fa,fasta.gz,fa.gz}"
-        ontologies: []
-  - eggnog_db:
-      type: file
-      description: The eggnog database file (e.g. eggnog-mapper/data/eggnog.db)
-      pattern: "*.db"
-      ontologies: []
+        description: Input sequences in FASTA format (plain or gzip-compressed)
+        pattern: "*.{fasta,faa,fa}(.gz)?"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+  - - search_mode:
+        type: string
+        description: |
+          Search mode passed to emapper.py via -m. Determines which backend
+          is used and which database flag is applied internally.
+          Supported modes:
+            - diamond: DIAMOND-based homology search (--dmnd_db)
+            - novel_fams: DIAMOND search against novel families (--dmnd_db)
+            - mmseqs: MMseqs2-based search (--mmseqs_db)
+            - hmmer: HMMER-based search (--database)
+            - no_search: Skip search step and annotate from a precomputed
+              *.emapper.seed_orthologs file (--annotate_hits_table)
+            - cache: Reuse a previously generated hits table (--cache)
+        enum: [diamond, novel_fams, mmseqs, hmmer, no_search, cache]
+    - db:
+        type: file
+        description: |
+          Database file, directory, or precomputed results file required by the
+          selected search_mode. The module automatically assigns the correct
+          flag depending on search_mode:
+            - diamond / novel_fams: DIAMOND database (*.dmnd)
+            - mmseqs: MMseqs2 database directory or prefix
+            - hmmer: HMM database (*.hmm, *.h3m)
+            - no_search: Precomputed *.emapper.seed_orthologs file
+            - cache: Previously generated *.emapper.hits file
+          This input is mandatory but its expected format depends on search_mode.
+        pattern: "*"
+        ontologies:
+          - edam: http://edamontology.org/format_1370 # HMMER format
+          - edam: http://edamontology.org/format_3475 # TSV
   - eggnog_data_dir:
       type: directory
-      description: Directory containing eggnog database files (e.g. eggnog-mapper/data)
+      description: |
+        Directory containing eggnog-mapper database files
+        (e.g. can be downloaded via download_eggnog_data.py,
+        found in the eggnog-mapper repository)
       pattern: "*"
-  - - meta2:
-        type: map
-        description: |
-          Groovy Map containing database information
-          e.g. `[ id:'test' ]`
-    - eggnog_diamond_db:
-        type: file
-        description: The eggnog Diamond protein database file (e.g. eggnog-mapper/data/eggnog_proteins.dmnd)
-        pattern: "*.dmnd"
-        ontologies: []
 output:
   annotations:
     - - meta:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. `[ id:'test', single_end:false ]`
+            e.g. `[ id:'sample1' ]`
       - "*.emapper.annotations":
           type: file
-          description: TSV with the results from the annotation phase
+          description: TSV file with the results from the annotation phase, including
+            functional annotations, GO terms, KEGG pathways, and COG categories
           pattern: "*.emapper.annotations"
-          ontologies: []
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
   orthologs:
     - - meta:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. `[ id:'test', single_end:false ]`
+            e.g. `[ id:'sample1' ]`
       - "*.emapper.seed_orthologs":
           type: file
-          description: TSV with the results from parsing the hits, linking queries with
-            seed orthologs (with commented metadata)
+          description: TSV file with the results from parsing the hits, linking queries
+            with their best seed orthologs (includes commented metadata header)
           pattern: "*.emapper.seed_orthologs"
-          ontologies: []
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
   hits:
     - - meta:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. `[ id:'test', single_end:false ]`
+            e.g. `[ id:'sample1' ]`
       - "*.emapper.hits":
           type: file
-          description: TSV with the results from the Diamond search phase
+          description: TSV file with the raw search hits from the Diamond/MMseqs2/HMMER
+            search phase before annotation
           pattern: "*.emapper.hits"
-          ontologies: []
+          ontologies:
+            - edam: http://edamontology.org/format_3475 # TSV
+  versions_eggnogmapper:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - eggnog-mapper:
+          type: string
+          description: The name of the tool
+      - emapper.py --version 2>&1 | grep -o 'emapper-[0-9]\+\.[0-9]\+\.[0-9]\+' | sed 's/emapper-//':
+          type: eval
+          description: The expression to obtain the version of the tool
+topics:
   versions:
-    - versions.yml:
-        type: file
-        description: File containing software versions
-        pattern: "versions.yml"
-        ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - eggnog-mapper:
+          type: string
+          description: The name of the tool
+      - emapper.py --version 2>&1 | grep -o 'emapper-[0-9]\+\.[0-9]\+\.[0-9]\+' | sed 's/emapper-//':
+          type: eval
+          description: The expression to obtain the version of the tool
 authors:
   - "@vagkaratzas"
 maintainers: