Update app.py

app.py

@@ -73,6 +73,15 @@ num_cores_Gliner_forDemo = 0  # 0 means use the GPU for Gliner !
 tokenizerGliner = AutoTokenizer.from_pretrained('microsoft/deberta-v3-large')
 
 
+POSSIBLE_KGchoices_List = ['AEO', 'BFO', 'BIM', 'BCGO', 'CL', 'CHIRO', 'CHEBI', 'DCM', 'FMA', 'GO', 'GENO',
+             'GeoSPARQL', 'HL7', 'DOID', 'HP', 'HP_O', 'IDO', 'IAO', 'ICD10', 'LOINC', 'MESH',
+             'MONDO', 'NCIT', 'NCBITAXON', 'NCBITaxon_', 'NIFCELL', 'NIFSTD', 'GML', 'OBCS', 'OCHV', 'OHPI',
+             'OPB', 'TRANS', 'PLOSTHES', 'RADLEX', 'RO', 'STY', 'SO', 'SNOMED', 'STATO',
+             'SYMP', 'FoodOn', 'UBERON', 'VO', 'EuroSciVoc']
+
+ONLY_Ontologies_OnBIOPORTAL = ["AEO", "BCGO", "BFO", "BIM", "CHEBI", "CHIRO", "CL", "DCM", "DOID", "FMA", "FOODON", "GENO", "GML", "GO", "GEOSPARQL", "HL7", "HP", "HP_O", "IAO", "ICD10", "IDO", "LOINC", "MESH", "MONDO", "NCBITAXON", "NCIT", "NIFCELL", "NIFSTD", "OBCS", "OCHV", "OHPI", "OPB", "PLOSTHES", "RADLEX", "OBOREL", "SNOMEDCT", "SO", "STATO", "STY", "SYMP", "PTRANS", "UBERON", "VO"]
+
+
 encod = encoding_getter('microsoft/deberta-v3-large')
 text_splitter = TokenTextSplitter(
     # separators=separators,
@@ -219,7 +228,8 @@ def process_row_BioPortal_api(args, key_bioportal, row):
             #     choice = "NCBITAXON,NCBITaxon_"
             elif choice.upper() == "NCBITaxon_":
                 choice = "NCBITAXON"
-            onto_clauses=onto_clauses+choice+","
+            if choice in ONLY_Ontologies_OnBIOPORTAL:
+                onto_clauses=onto_clauses+choice+","
 
         if onto_clauses and onto_clauses[-1] == ",":
             onto_clauses=onto_clauses[:-1]
@@ -946,20 +956,24 @@ def getUrlBioAndAllOtherBioConcepts(word, args, key_virtuoso, cache_map_virtuoso
 
         ### this is for Bioportal url api:
         onto_clauses = ""
+
         for choice in args.KG_restriction:
-            if choice.upper() == "SNOMEDCT":
-                choice = "SNOMED"
-            elif choice.upper() == "OBOREL":
-                choice = "RO"
-            elif choice.upper() == "PTRANS":
-                choice = "TRANS"
-            elif choice.upper() == "FOODON":
-                choice = "FoodOn"
-            elif choice.upper() == "GEOSPARQL":
-                choice = "GeoSPARQL"
-            elif choice.upper() == "NCBITAXON":
-                choice = "NCBITAXON,NCBITaxon_"
-            onto_clauses = onto_clauses + choice + ","
+            if choice.upper() == "SNOMED":
+                choice="SNOMEDCT"
+            elif choice.upper() == "RO":
+                choice = "OBOREL"
+            elif choice.upper() == "TRANS":
+                choice = "PTRANS"
+            elif choice.upper() == "FoodOn":
+                choice = "FOODON"
+            elif choice.upper() == "GeoSPARQL":
+                choice = "GEOSPARQL"
+            # elif choice.upper() == "NCBITAXON":
+            #     choice = "NCBITAXON,NCBITaxon_"
+            elif choice.upper() == "NCBITaxon_":
+                choice = "NCBITAXON"
+            if choice in ONLY_Ontologies_OnBIOPORTAL:
+                onto_clauses = onto_clauses + choice + ","
 
         if onto_clauses and onto_clauses[-1] == ",":
             onto_clauses = onto_clauses[:-1]
@@ -1966,7 +1980,7 @@ def elinking(df_annotated_combined, text_splitter, args, key_geonames, cache_map
 
 
 
-def nerBio(text, ModelsSelection, CategoriesSelection, ScoreFilt, EntityLinking, history_dict: dict):
+def nerBio(text, ModelsSelection, CategoriesSelection, ScoreFilt, EntityLinking, KGchoices, history_dict: dict):
 
     if EntityLinking:
         EnableNEL="True"
@@ -2012,6 +2026,15 @@ def nerBio(text, ModelsSelection, CategoriesSelection, ScoreFilt, EntityLinking,
 
     parser.add_argument("--temperature", type=int, default=0.01)
 
+    #consose 20250205:
+    #KGchoices = None
+    # KGchoices = ['SNOMED', 'LOINC', 'ICD10', 'NCIT']
+    #KGchoices = ['SNOMED', 'LOINC', 'ICD10', 'MESH', 'NCIT']  # restricts the input to these values only
+    if KGchoices:
+        KGchoices.sort()
+    parser.add_argument("--KG_restriction", nargs='+', choices=KGchoices, default=KGchoices,
+                        help="List of ontologies to which restrict the entity linking task.")
+
     args = parser.parse_args()