Update VEuPathDB meta keys

data/test/pipelines/dumper/dump_files/dumped_genome.json

@@ -7,9 +7,9 @@
         "taxonomy_id": 7159,
         "production_name": "aedes_aegypti"
     },
-    "BRC4": {
+    "veupathdb": {
         "organism_abbrev": "aaegL5",
-        "component": "VectorBase"
-
+        "component_db": "VectorBase",
+        "build_version": 65
     }
 }

data/test/pipelines/genome_prepare/input_dir_brc_on/gen_prep_in_meta.json

@@ -1,6 +1,7 @@
 {
- "BRC4": {
-  "component": "OrganismDB",
+ "veupathdb": {
+  "build_version": 65,
+  "component_db": "OrganismDB",
   "organism_abbrev": "organAbrev123"
  },
  "species": {},

pipelines/nextflow/subworkflows/genome_prepare/meta.yml

@@ -16,7 +16,7 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json
 
 name: "genome_prepare"
-description: BRC/Ensembl metazoa pipeline. Retrieve data for genome(s), obtained from INSDC and RefSeq, validate and prepare GFF3, FASTA, JSON files for each genome accession.
+description: VEuPathDB/Ensembl Metazoa pipeline. Retrieve data for genome(s), obtained from INSDC and RefSeq, validate and prepare GFF3, FASTA, JSON files for each genome accession.
 keywords:
   - fasta
   - gff3
@@ -45,7 +45,7 @@ input:
       type: directory
       description: |
         MANDATORY param. User supplied input directory name containing genome json(s) storing meta information including:
-        genome INSDC accession, BRC 'organism_abbrev', BRC 'component'.
+        genome INSDC accession, VEuPathDB 'organism_abbrev', VEuPathDB 'component_db', VEuPathDB 'build_version'.
       pattern: "input_dir/*.json"
 output:
   - fasta_dna:

pipelines/nextflow/workflows/genome_prepare/main.nf

@@ -45,8 +45,8 @@ def meta_from_genome_json(json_path) {
     prod_name = data.assembly.accession
     publish_dir = data.assembly.accession
     if ( params.brc_mode ) {
-        prod_name = data.BRC4.organism_abbrev
-        publish_dir = "${data.BRC4.component}/${data.BRC4.organism_abbrev}"
+        prod_name = data.veupathdb.organism_abbrev
+        publish_dir = "${data.veupathdb.component_db}/${data.veupathdb.organism_abbrev}"
     } else if ( data.species && data.species.production_name ) {
         prod_name = data.species.production_name
         publish_dir = prod_name

scripts/brc4/check_descriptions.pl

@@ -72,15 +72,15 @@ sub main {
   my @all_species = ($opt{species}) || @{$registry->get_all_species()};
   for my $species (sort @all_species) {
     my $ma = $registry->get_adaptor($species, "core", "MetaContainer");
-    my $component = get_meta_value($ma, 'BRC4.component');
+    my $component = get_meta_value($ma, 'veupathdb.component_db');
     if ($opt{component} and $opt{component} ne $component) {
       $ma->dbc->disconnect_if_idle();
       next;
     }
 
     my $count = check_genes($registry, $species);
-    my $build = get_build($ma, $species);
-    my $org = get_meta_value($ma, 'BRC4.organism_abbrev');
+    my $build = get_meta_value($ma, 'veupathdb.build_version');
+    my $org = get_meta_value($ma, 'veupathdb.organism_abbrev');
 
     $ma->dbc->disconnect_if_idle();
 
@@ -110,15 +110,6 @@ sub main {
   }
 }
 
-sub get_build {
-  my ($ma, $key) = @_;
-
-  my $dbname = $ma->dbc->dbname;
-  if ($dbname =~ /_(\d+)_\d+_\d+$/) {
-    return $1;
-  }
-}
-
 sub get_meta_value {
   my ($ma, $key) = @_;
 

scripts/brc4/get_metadata_from_redmine.py

@@ -18,8 +18,7 @@
 from redminelib import Redmine
 import argparse
 import os, json, re, time
-import requests
-import xml.etree.ElementTree as ET
+
 
 url = "https://redmine.apidb.org"
 default_fields = dict(
@@ -63,7 +62,7 @@ def retrieve_genomes(redmine, output_dir, build=None):
             failed_issues.append({"issue": issue, "desc": failure})
             continue
 
-        abbrev = genome["BRC4"]["organism_abbrev"]
+        abbrev = genome["veupathdb"]["organism_abbrev"]
         group = "other"
         if "Reference change" in extra["operations"]:
             group = "reference_change"
@@ -110,7 +109,7 @@ def retrieve_genomes(redmine, output_dir, build=None):
                 pass
 
             for genome in genomes:
-                organism = genome["BRC4"]["organism_abbrev"]
+                organism = genome["veupathdb"]["organism_abbrev"]
                 organism_file = os.path.join(group_dir, organism + ".json")
                 with open(organism_file, "w") as f:
                     json.dump(genome, f, indent=True)
@@ -147,8 +146,9 @@ def parse_genome(issue):
 
     customs = get_custom_fields(issue)
     genome = {
-        "BRC4": {
-            "component": "",
+        "veupathdb": {
+            "build_version": 0,
+            "component_db": "",
             "organism_abbrev": "",
         },
         "species": {},
@@ -164,11 +164,14 @@ def parse_genome(issue):
         accession = check_accession(accession)
         genome["assembly"]["accession"] = accession
 
-    # Get BRC4 component
+    # Get VEuPathDB build version
+    genome["veupathdb"]["build_version"] = int(re.search(r"Build (\d+)", str(issue.fixed_version)).group(1))
+
+    # Get VEuPathDB component db
     if "Component DB" in customs:
         components = customs["Component DB"]["value"]
         if len(components) == 1:
-            genome["BRC4"]["component"] = components[0]
+            genome["veupathdb"]["component_db"] = components[0]
         elif len(components) > 1:
             raise Exception("More than 1 component for genome " + str(issue.id))
 
@@ -181,7 +184,7 @@ def parse_genome(issue):
             if not check_organism_abbrev(abbrev):
                 print(f"Invalid organism_abbrev in {issue.id}: {abbrev}")
             else:
-                genome["BRC4"]["organism_abbrev"] = abbrev
+                genome["veupathdb"]["organism_abbrev"] = abbrev
     except KeyError:
         print(f"Can't get organism abbrev for {issue.id} because: missing organism_abbrev")
         return
@@ -191,15 +194,13 @@ def parse_genome(issue):
         gff_path = customs["GFF 2 Load"]["value"]
         if gff_path:
             extra["GFF"] = True
-            # print("GFF2LOAD: separate gff file for %s: %s (issue %d)" % (genome["BRC4"]["organism_abbrev"], gff_path, issue.id))
     except:
         pass
 
     # Warn for replacement
     try:
         if customs["Replacement genome?"]["value"].startswith("Yes"):
             extra["Replacement"] = True
-            # print("REPLACEMENT: the organism %s is a replacement (issue %d)" % (genome["BRC4"]["organism_abbrev"], issue.id))
     except:
         pass
 
@@ -217,7 +218,7 @@ def check_genome(genome, extra):
     if not genome:
         return "No genome parsed"
 
-    if not "organism_abbrev" in genome["BRC4"] or not genome["BRC4"]["organism_abbrev"]:
+    if not "organism_abbrev" in genome["veupathdb"] or not genome["veupathdb"]["organism_abbrev"]:
         return "No organism_abbrev defined"
 
     operations = extra["operations"]

src/python/ensembl/io/genomio/data/schemas/genome.json

@@ -87,15 +87,17 @@
         "name"
       ]
     },
-    "BRC4_info": {
+    "vpdb_info": {
       "type": "object",
       "additionalProperties": false,
       "properties": {
-        "component" : { "type" : "string" },
+        "build_version" : { "type" : "integer" },
+        "component_db" : { "type" : "string" },
         "organism_abbrev" : { "type" : "string" }
       },
       "required": [
-        "component",
+        "build_version",
+        "component_db",
         "organism_abbrev"
       ]
     },
@@ -122,7 +124,7 @@
         "annotation" : { "$ref" : "#/definitions/annotation_info" },
         "genebuild" : { "$ref" : "#/definitions/genebuild_info" },
         "provider" : { "$ref" : "#/definitions/provider_info" },
-        "BRC4" : { "$ref" : "#/definitions/BRC4_info" },
+        "veupathdb" : { "$ref" : "#/definitions/vpdb_info" },
         "added_seq" : { "$ref" : "#/definitions/added_sequence_info" }
       },
       "required" : [

src/python/ensembl/io/genomio/database/factory.py

@@ -35,9 +35,9 @@ def format_db_data(server_url: URL, dbs: List[str], brc_mode: bool = False) -> L
     Args:
         server: Server URL where all the databases are hosted.
         dbs: List of database names.
-        brc_mode: If true, assign ``BRC4.organism_abbrev`` as the species, and ``BRC4.component`` as the
-            division. Otherwise, the species will be ``species.production_name`` and the division will be
-            ``species.division``.
+        brc_mode: If true, assign `veupathdb.organism_abbrev` as the species, `veupathdb.component_db` as the
+            division and `veupathdb.build_version` as the project release. Otherwise, the species will be
+            `species.production_name` and the division will be `species.division`.
 
     Returns:
         List of dictionaries with 3 keys: "database", "species" and "division".
@@ -55,12 +55,15 @@ def format_db_data(server_url: URL, dbs: List[str], brc_mode: bool = False) -> L
         project_release = core_db.get_project_release()
 
         if brc_mode:
-            brc_organism = core_db.get_meta_value("BRC4.organism_abbrev")
-            brc_component = core_db.get_meta_value("BRC4.component")
-            if brc_organism is not None:
-                species = brc_organism
-            if brc_component is not None:
-                division = brc_component
+            vpdb_organism = core_db.get_meta_value("veupathdb.organism_abbrev")
+            vpdb_component = core_db.get_meta_value("veupathdb.component_db")
+            vpdb_build = core_db.get_meta_value("veupathdb.build_version")
+            if vpdb_organism is not None:
+                species = vpdb_organism
+            if vpdb_component is not None:
+                division = vpdb_component
+            if vpdb_build is not None:
+                project_release = vpdb_build
 
         if not division:
             division = "all"
@@ -137,7 +140,10 @@ def main() -> None:
     parser.add_argument(
         "--brc_mode",
         action="store_true",
-        help="Enable BRC mode, i.e. use organism_abbrev for species, component for division",
+        help=(
+            "Enable BRC mode, i.e. use organism_abbrev for species, component_db for division, "
+            "build_version for project release"
+        ),
     )
     parser.add_log_arguments()
     args = parser.parse_args()

src/python/ensembl/io/genomio/events/dump.py

@@ -17,7 +17,7 @@
 __all__ = [
     "IdsSet",
     "DictToIdsSet",
-    "BRC4_START_DATE",
+    "VPDB_START_DATE",
     "Pair",
     "UnsupportedEvent",
     "Event",
@@ -38,7 +38,7 @@
 from ensembl.utils.logging import init_logging_with_args
 
 
-BRC4_START_DATE = datetime(2020, 5, 1)
+VPDB_START_DATE = datetime(2020, 5, 1)
 IdsSet = Set[str]
 DictToIdsSet = Dict[str, IdsSet]
 
@@ -89,7 +89,7 @@ class Event:
         name: Name of the event (will be updated automatically).
         pairs: All pair of ids for this event.
 
-    Any gene set before 2019-09 is dubbed pre-BRC4.
+    Any gene set before 2019-09 is dubbed pre-VPDB.
 
     """
 
@@ -234,14 +234,14 @@ def add_pair(self, pair: Pair) -> None:
         self.pairs.append(pair)
 
     def get_full_release(self) -> str:
-        """Returns the expanded release name, pre-BRC4 or `BRC4 = build`."""
+        """Returns the expanded release name, pre-VPDB or `VPDB = build`."""
         release = self.release
         date = self.date
 
-        if date and date > BRC4_START_DATE:
+        if date and date > VPDB_START_DATE:
             release = f"build {release}"
         else:
-            release = f"pre-BRC4 {release}"
+            release = f"pre-VPDB {release}"
 
         return release
 

src/python/ensembl/io/genomio/genome_metadata/dump.py

@@ -45,7 +45,7 @@
         "provider_url": str,
         "version": int,
     },
-    "BRC4": {"organism_abbrev": str, "component": str},
+    "veupathdb": {"organism_abbrev": str, "component_db": str, "build_version": int},
     "genebuild": {"id": str, "method": str, "method_display": str, "start_date": str, "version": str},
     "species": {
         "alias": str,

src/python/ensembl/io/genomio/gff3/id_allocator.py

@@ -43,7 +43,7 @@ class StableIDAllocator:
     def set_prefix(self, genome: Dict) -> None:
         """Sets the ID prefix using the organism abbrev if it exists in the genome metadata."""
         try:
-            org = genome["BRC4"]["organism_abbrev"]
+            org = genome["veupathdb"]["organism_abbrev"]
         except KeyError:
             prefix = "TMP_PREFIX_"
         else:

src/python/tests/database/test_factory.py

@@ -20,7 +20,7 @@
 """
 
 from pathlib import Path
-from typing import Dict, List, Optional
+from typing import Any, Dict, List, Optional
 from unittest.mock import call, Mock, patch
 
 from deepdiff import DeepDiff
@@ -35,8 +35,9 @@
     "species.production_name": "dog",
     "species.division": "metazoa",
     "assembly.accession": "GCA_000111222.3",
-    "BRC4.organism_abbrev": "brc_dog",
-    "BRC4.component": "brc_db",
+    "veupathdb.organism_abbrev": "brc_dog",
+    "veupathdb.component_db": "brc_db",
+    "veupathdb.build_version": 12,
 }
 
 
@@ -124,15 +125,15 @@ def test_format_db_data(
         server_url: Server URL where all the databases are hosted.
         dbs: List of database names.
         brc_mode: BRC mode?
-        skip_keys: Return `None` instead of the assigned value for "BRC4.*" meta keys.
+        skip_keys: Return `None` instead of the assigned value for "veupathdb.*" meta keys.
         output: Expected list of dictionaries with metadata per database.
     """
 
-    def _get_meta_value(meta_key: str) -> Optional[str]:
+    def _get_meta_value(meta_key: str) -> Optional[Any]:
         """Return empty string if "species.division" is requested in BRC mode, "Metazoa" otherwise."""
         if (meta_key == "species.division") and brc_mode:
             return ""
-        if meta_key.startswith("BRC4.") and skip_keys:
+        if meta_key.startswith("veupathdb.") and skip_keys:
             return None
         return _META[meta_key]
 
@@ -146,7 +147,11 @@ def _get_meta_value(meta_key: str) -> Optional[str]:
     if dbs:
         calls = [call("species.production_name"), call("species.division"), call("assembly.accession")]
         if brc_mode:
-            calls += [call("BRC4.organism_abbrev"), call("BRC4.component")]
+            calls += [
+                call("veupathdb.organism_abbrev"),
+                call("veupathdb.component_db"),
+                call("veupathdb.build_version"),
+            ]
         dbconnection.get_meta_value.assert_has_calls(calls)
         dbconnection.get_project_release.assert_called()
 

src/python/tests/genome_metadata/test_extend/genome.json

@@ -1,8 +1,4 @@
 {
-    "BRC4": {
-        "component": "PlasmoDB",
-        "organism_abbrev": "pfal3D7"
-    },
     "assembly": {
         "accession": "GCA_000002765.1",
         "provider_name": "RefSeq",
@@ -16,5 +12,10 @@
     "species": {
         "scientific_name": "Plasmodium falciparum",
         "taxonomy_id": 36329
+    },
+    "veupathdb": {
+        "build_version": 65,
+        "component_db": "PlasmoDB",
+        "organism_abbrev": "pfal3D7"
     }
 }