Merge tag 'itrb-deployment-20240823' into production

ISSUE_TEMPLATES/kg2rollout.md

@@ -204,7 +204,7 @@ Before rolling out, we need to pre-upload the new databases (referenced in `conf
 
 #### 7. Roll-out to ITRB TEST
 - [ ] In GitHub, for the RTXteam/RTX project, merge `master` to `itrb-test`. Record this issue number in the merge message.
-- [ ] In GitHub, for the RTXteam/PloverDB project, merge `main` to `itrb-test`. Record this issue number in the merge message.
+- [ ] In GitHub, for the RTXteam/PloverDB project, merge `main` to `itrb-test`.
 - [ ] Tag the release using the `master` branch of RTXteam/RTX project.
 - [ ] Tag the release using the `main` branch of RTXteam/PloverDB project.
 - [ ] Via a message in the `#devops-teamexpanderagent` channel in the `NCATSTranslator` Slack workspace, put in a request to `@Sarah Stemann` to open a ticket to re-deploy ARAX, RTX-KG2, and PloverDB to ITRB test
@@ -215,7 +215,8 @@ Before rolling out, we need to pre-upload the new databases (referenced in `conf
 - [ ] Check proper functioning of `arax.test.transltr.io` (look at messages log `debug` mesages to verify that ARAX-Expand is indeed querying `kg2.test.transltr.io`)
 
 #### 8. Roll-out to ITRB PRODUCTION
-- [ ] In GitHub, merge `master` to `production`. Record this issue number in the merge message.
+- [ ] In GitHub, for the RTXteam/RTX project, merge `master` to `production`. Record this issue number in the merge message.
+- [ ] In GitHub, for the RTXteam/PloverDB project, merge `main` to `production`.
 - [ ] Via a message in the `#devops-teamexpanderagent` channel in the `NCATSTranslator` Slack workspace, put in a request to `@Sarah Stemann` to open a ticket to re-deploy ARAX, RTX-KG2, and PloverDB to ITRB production
 - [ ] Monitor the `#devops-teamexpanderagent` channel to follow (i.e., to see if there are any errors reported by ITRB) the roll-out of the updated services in ITRB production (this could take several days, as there is a formal approval process for deployments to ITRB production)
 - [ ] Check proper functioning of `kg2cploverdb.transltr.io`

code/ARAX/ARAXQuery/ARAX_decorator.py

@@ -33,9 +33,9 @@ def __init__(self):
             "description": Attribute(attribute_type_id="biolink:description",
                                      value_type_id="metatype:String"),
             "knowledge_level": Attribute(attribute_type_id="biolink:knowledge_level",
-                                         value_type_id="metatype:String"),
+                                         value_type_id="biolink:KnowledgeLevelEnum"),
             "agent_type": Attribute(attribute_type_id="biolink:agent_type",
-                                    value_type_id="metatype:String"),
+                                    value_type_id="biolink:AgentTypeEnum"),
             "all_categories": Attribute(attribute_type_id="biolink:category",
                                         value_type_id="metatype:Uriorcurie",
                                         description="Categories of all nodes in this synonym set in RTX-KG2."),

code/ARAX/ARAXQuery/ARAX_expander.py

@@ -349,7 +349,6 @@ def apply(self, response, input_parameters, mode: str = "ARAX"):
                 if inferred_qedge_keys and len(query_graph.edges) == 1:
                     for edge in query_sub_graph.edges.keys():
                         query_sub_graph.edges[edge].knowledge_type = 'lookup'
-
             # Expand the query graph edge-by-edge
             for qedge_key in ordered_qedge_keys_to_expand:
                 log.debug(f"Expanding qedge {qedge_key}")
@@ -655,7 +654,7 @@ def get_inferred_answers(inferred_qedge_keys: List[str],
                         response.update_query_plan(inferred_qedge_key, "arax-xdtd", "Error",
                                                    f"Process error-ed out with {response.status} after {wait_time} seconds")
 
-                elif set(['biolink:regulates']).intersection(set(qedge.predicates)):  # Figure out if this is a "regulates" query, then use call XCRG models
+                elif set(["biolink:affects"]).intersection(set(qedge.predicates)):  # Figure out if this is a "regulates" query, then use call XCRG models
                     # Call XCRG models and simply return whatever it returns
                     # Get the subject and object of this edge
                     subject_qnode = query_graph.nodes[qedge.subject]  # chemical

code/ARAX/ARAXQuery/Expand/expand_utilities.py

@@ -409,33 +409,8 @@ def get_preferred_categories(curie: Union[str, List[str]], log: ARAXResponse) ->
 def get_curie_names(curie: Union[str, List[str]], log: ARAXResponse) -> Dict[str, str]:
     curies = convert_to_list(curie)
     synonymizer = NodeSynonymizer()
-    log.debug(f"Looking up names for {len(curies)} input curies using NodeSynonymizer")
-    synonymizer_info = synonymizer.get_normalizer_results(curies)
-    curie_to_name_map = dict()
-    if synonymizer_info:
-        recognized_input_curies = {input_curie for input_curie in synonymizer_info if synonymizer_info.get(input_curie)}
-        unrecognized_curies = set(curies).difference(recognized_input_curies)
-        if unrecognized_curies:
-            log.warning(f"NodeSynonymizer did not recognize: {unrecognized_curies}")
-        input_curies_without_matching_node = set()
-        for input_curie in recognized_input_curies:
-            equivalent_nodes = synonymizer_info[input_curie]["nodes"]
-            # Find the 'node' in the synonymizer corresponding to this curie
-            input_curie_nodes = [node for node in equivalent_nodes if node["identifier"] == input_curie]
-            if not input_curie_nodes:
-                # Try looking for slight variation (KG2 vs. SRI discrepancy): "KEGG:C02700" vs. "KEGG.COMPOUND:C02700"
-                input_curie_stripped = input_curie.replace(".COMPOUND", "")
-                input_curie_nodes = [node for node in equivalent_nodes if node["identifier"] == input_curie_stripped]
-            # Record the name for this input curie
-            if input_curie_nodes:
-                curie_to_name_map[input_curie] = input_curie_nodes[0].get("label")
-            else:
-                input_curies_without_matching_node.add(input_curie)
-        if input_curies_without_matching_node:
-            log.warning(f"No matching nodes found in NodeSynonymizer for these input curies: "
-                        f"{input_curies_without_matching_node}. Cannot determine their specific names.")
-    else:
-        log.error(f"NodeSynonymizer returned None", error_code="NodeNormalizationIssue")
+    log.debug(f"Looking up names for {len(curies)} input curies using NodeSynonymizer.get_curie_names()")
+    curie_to_name_map = synonymizer.get_curie_names(curies)
     return curie_to_name_map