#3486_Standardising Orphanet to ORPHA

annotation/regexes.py

@@ -76,7 +76,7 @@ class DbRegexes:
     NIHMS = DbRefRegex(db="NIHMS", prefixes="NIHMS", link="https://www.ncbi.nlm.nih.gov/pubmed/?term=NIHMS${1}")
     # smallest OMIM starts with a 1, so there's no 0 padding there, expect min length
     OMIM = DbRefRegex(db="OMIM", prefixes=["OMIM", "MIM"], link=OntologyService.URLS[OntologyService.OMIM], min_length=OntologyService.EXPECTED_LENGTHS[OntologyService.OMIM], expected_length=OntologyService.EXPECTED_LENGTHS[OntologyService.OMIM])
-    ORPHA = DbRefRegex(db="Orphanet", prefixes=["ORPHANET", "ORPHA"], link=OntologyService.URLS[OntologyService.ORPHANET], expected_length=OntologyService.EXPECTED_LENGTHS[OntologyService.ORPHANET])
+    ORPHA = DbRefRegex(db="ORPHA", prefixes=["ORPHANET", "ORPHA"], link=OntologyService.URLS[OntologyService.ORPHANET], expected_length=OntologyService.EXPECTED_LENGTHS[OntologyService.ORPHANET])
     PUBMED_CENTRAL = DbRefRegex(db="PMCID", prefixes=["PMCID", "PubMedCentral", "PMC"], link="https://www.ncbi.nlm.nih.gov/pmc/articles/${1}", match_type=MatchType.OPT_ALPHA_MAN_NUMERIC)
     PUBMED = DbRefRegex(db="PMID", prefixes=["PubMed", "PMID"], link="https://www.ncbi.nlm.nih.gov/pubmed/${1}")
     SNP = DbRefRegex(db="SNP", prefixes="rs", link="https://www.ncbi.nlm.nih.gov/snp/${1}", match_type=MatchType.SIMPLE_NUMBERS)

classification/management/commands/fix_orphanet_revalidation.py

@@ -0,0 +1,15 @@
+from django.core.management.base import BaseCommand
+from classification.models import Classification
+from library.guardian_utils import admin_bot
+
+
+class Command(BaseCommand):
+
+    def handle(self, *args, **options):
+        user = admin_bot()
+        search_term_orpha = "ORPHANET"
+        classifications = Classification.objects.filter(evidence__search_terms__icontains=search_term_orpha)
+        print(f"Found {classifications.count()} classifications with '{search_term_orpha}' in literature")
+        for classification in classifications:
+            classification.revalidate(user=user)
+        self.stdout.write(self.style.SUCCESS("Revalidation complete for Orphanet classifications."))

classification/migrations/0105_fix_orphanet_revalidation.py

@@ -0,0 +1,20 @@
+# Generated by Django 4.2.2 on 2023-08-14 23:42
+from django.db import migrations
+from manual.operations.manual_operations import ManualOperation
+
+
+def _test_fix_orphanet_revalidation(apps):
+    Classification = apps.get_model("classification", "Classification")
+    search_term_orpha = "ORPHANET"
+    return Classification.objects.filter(evidence__search_terms__icontains=search_term_orpha).exists()
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('classification', '0104_discordancereport_admin_note'),
+    ]
+
+    operations = [
+        ManualOperation(task_id=ManualOperation.task_id_manage(["fix_orphanet_revalidation"]),
+                        test=_test_fix_orphanet_revalidation)
+    ]

ontology/migrations/0026_alter_ontologyterm_ontology_service.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.2 on 2023-08-14 23:52
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('ontology', '0025_alter_ontologyterm_ontology_service'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='ontologyterm',
+            name='ontology_service',
+            field=models.CharField(choices=[('MONDO', 'MONDO'), ('OMIM', 'OMIM'), ('HP', 'HP'), ('HGNC', 'HGNC'), ('DOID', 'DOID'), ('ORPHA', 'ORPHA'), ('MedGen', 'MedGen')], max_length=10),
+        ),
+    ]

ontology/models/models_ontology.py

@@ -45,7 +45,7 @@ class OntologyService(models.TextChoices):
     HGNC = "HGNC", "HGNC"
 
     DOID = "DOID", "DOID"
-    ORPHANET = "Orphanet", "Orphanet"
+    ORPHANET = "ORPHA", "ORPHA"
     MEDGEN = "MedGen", "MedGen"
 
     EXPECTED_LENGTHS: Dict[str, int] = Constant({
@@ -257,8 +257,8 @@ def normalize(dirty_id: str) -> 'OntologyIdNormalized':
             raise ValueError(f"Can not convert {dirty_id} to a proper id")
 
         prefix = parts[0].strip().upper()
-        if prefix == "ORPHANET":  # Orphanet is the one ontology (so far) where the standard is sentance case
-            prefix = "Orphanet"
+        if prefix == "ORPHA":  # Orphanet is the one ontology (so far) where the standard is sentance case
+            prefix = "ORPHA"
         elif prefix.upper() == "MIM":
             prefix = "OMIM"
         elif prefix.upper() == "MEDGEN":

ontology/models/ontology_search.py

@@ -27,7 +27,7 @@ def validate_ontology(term: OntologyTerm, preview_proxy: Optional[PreviewProxyMo
     return SearchResult(preview, messages=messages)
 
 
-ONTOLOGY_TERM_PATTERN = re.compile(r"^((MONDO|OMIM|MIM|HPO|HP|DOID|ORPHANET)\s*:\s*[0-9]+)|(MEDGEN\s*:\s*\w{0,2}[0-9]+)$", re.IGNORECASE)
+ONTOLOGY_TERM_PATTERN = re.compile(r"^((MONDO|OMIM|MIM|HPO|HP|DOID|ORPHA)\s*:\s*[0-9]+)|(MEDGEN\s*:\s*\w{0,2}[0-9]+)$", re.IGNORECASE)
 
 @search_receiver(
     search_type=OntologyTerm,