fixed issue with strange gene name for proteins; fixed issue with empty string symbol for protein

drugstone/management/commands/import_from_nedrex.py

@@ -96,16 +96,24 @@ class NedrexImporter:
         if update:
             self.cache.init_proteins()
 
+        def format_prot_name(name):
+            if '{' in name:
+                idx1 = name.index('{')
+                adjusted_name = name[:idx1 - 1].strip() if idx1 > 0 else ''
+                if '=' in adjusted_name:
+                    idx2 = adjusted_name.index('=')
+                    return adjusted_name[idx2+1:].strip()
+                return adjusted_name
+            return name
+
         def add_protein(node):
             id = to_id(node['primaryDomainId'])
-            name = node['geneName']
+            name = format_prot_name(node['geneName'])
+            gene = name
+
             if len(node['synonyms']) > 0:
-                name = node['synonyms'][0]
-                if '{' in name:
-                    idx = name.index('{')
-                    if idx > 0:
-                        name = name[:idx - 1]
-            proteins[id] = models.Protein(uniprot_code=id, protein_name=name, gene=node['geneName'])
+                name = format_prot_name(node['synonyms'][0])
+            proteins[id] = models.Protein(uniprot_code=id, protein_name=name, gene=gene)
 
         def add_edges(edge):
             id = to_id(edge['sourceDomainId'])

drugstone/management/commands/populate_db.py

@@ -215,20 +215,20 @@ def populate(kwargs):
         print(f'Populated {n} DrDi associations from DrugBank.')
 
     if kwargs['protein_protein']:
-        # print('Importing PPIs from unlicenced NeDRexDB...')
-        # n = NedrexImporter.import_protein_protein_interactions(importer,
-        #                                                        DatasetLoader.get_ppi_nedrex(nedrex_api_url_unlicenced, False),
-        #                                                        update)
-        # total_n += n
-        # print(f'Imported {n} PPIs from unlicended NeDRexDB')
-        # print('Importing PPIs from licenced NeDRexDB...')
-        # n = NedrexImporter.import_protein_protein_interactions(importer,
-        #                                                        DatasetLoader.get_ppi_nedrex(nedrex_api_url_licenced,
-        #                                                                                     True),
-        #                                                        update)
-        # total_n += n
-        # nedrex_update = True
-        # print(f'Imported {n} PPIs from licended NeDRexDB')
+        print('Importing PPIs from unlicenced NeDRexDB...')
+        n = NedrexImporter.import_protein_protein_interactions(importer,
+                                                               DatasetLoader.get_ppi_nedrex(nedrex_api_url_unlicenced, False),
+                                                               update)
+        total_n += n
+        print(f'Imported {n} PPIs from unlicended NeDRexDB')
+        print('Importing PPIs from licenced NeDRexDB...')
+        n = NedrexImporter.import_protein_protein_interactions(importer,
+                                                               DatasetLoader.get_ppi_nedrex(nedrex_api_url_licenced,
+                                                                                            True),
+                                                               update)
+        total_n += n
+        nedrex_update = True
+        print(f'Imported {n} PPIs from licended NeDRexDB')
         print('Populating PPIs from STRING...')
         n = DataPopulator.populate_ppi_string(populator, DatasetLoader.get_ppi_string(), update)
         total_n += n

drugstone/util/query_db.py

@@ -24,7 +24,7 @@ def query_proteins_by_identifier(node_ids: Set[str], identifier: str) -> Tuple[L
             Returns name of backend attribute of Protein table
     """
     # query protein table
-    if(len(node_ids) == 0):
+    if (len(node_ids) == 0):
         return list(), identifier
     if identifier == 'symbol':
         protein_attribute = 'symbol'
@@ -70,7 +70,8 @@ def aggregate_nodes(nodes: List[OrderedDict]):
         for key, value in n.items():
             if isinstance(value, list):
                 for e in value:
-                    node[key].add(e)
-            else:
+                    if e is not None and len(e) > 0:
+                        node[key].add(e)
+            elif value is not None and len(value) > 0:
                 node[key].add(value)
     return {k: list(v) for k, v in node.items()}