def answer_one_hop_query(
self, query_graph: QueryGraph
) -> Tuple[QGOrganizedKnowledgeGraph, Dict[str, Dict[str, str]]]:
"""
This function answers a one-hop (single-edge) query using the Molecular Provider.
:param query_graph: A Reasoner API standard query graph.
:return: A tuple containing:
1. an (almost) Reasoner API standard knowledge graph containing all of the nodes and edges returned as
results for the query. (Dictionary version, organized by QG IDs.)
2. a map of which nodes fulfilled which qnode_keys for each edge. Example:
{'KG1:111221': {'n00': 'DOID:111', 'n01': 'HP:124'}, 'KG1:111223': {'n00': 'DOID:111', 'n01': 'HP:126'}}
"""
log = self.response
final_kg = QGOrganizedKnowledgeGraph()
edge_to_nodes_map = dict()
# Verify this is a valid one-hop query graph and tweak its contents as needed for this KP
self._verify_one_hop_query_graph_is_valid(query_graph, log)
if log.status != 'OK':
return final_kg, edge_to_nodes_map
modified_query_graph = self._pre_process_query_graph(query_graph, log)
if log.status != 'OK':
return final_kg, edge_to_nodes_map
qedge = next(qedge for qedge in modified_query_graph.edges.values())
source_qnode_key = qedge.subject
target_qnode_key = qedge.object
# Answer the query using the KP and load its answers into our Swagger model
json_response = self._send_query_to_kp(modified_query_graph, log)
returned_kg = json_response.get('knowledge_graph')
if not returned_kg:
log.warning(
f"No KG is present in the response from {self.kp_name}")
else:
# Build a map of node/edge IDs to qnode/qedge IDs
qg_id_mappings = self._get_qg_id_mappings_from_results(
json_response['results'])
# Populate our final KG with nodes and edges
for returned_edge_key, returned_edge in returned_kg['edges'].items(
):
kp_edge_key, swagger_edge = self._create_swagger_edge_from_kp_edge(
returned_edge_key, returned_edge)
swagger_edge_key = self._create_unique_edge_key(
swagger_edge) # Convert to an ID that's unique for us
for qedge_key in qg_id_mappings['edges'][kp_edge_key]:
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
edge_to_nodes_map[swagger_edge_key] = {
source_qnode_key: swagger_edge.subject,
target_qnode_key: swagger_edge.object
}
for returned_node_key, returned_node in returned_kg['nodes'].items(
):
swagger_node_key, swagger_node = self._create_swagger_node_from_kp_node(
returned_node_key, returned_node)
for qnode_key in qg_id_mappings['nodes'][swagger_node_key]:
final_kg.add_node(swagger_node_key, swagger_node,
qnode_key)
return final_kg, edge_to_nodes_map
def _answer_query_using_kp(self, query_graph: QueryGraph) -> Tuple[QGOrganizedKnowledgeGraph, Dict[str, Dict[str, str]]]:
answer_kg = QGOrganizedKnowledgeGraph()
edge_to_nodes_map = dict()
# Strip non-essential and 'empty' properties off of our qnodes and qedges
stripped_qnodes = {qnode_key: self._strip_empty_properties(qnode)
for qnode_key, qnode in query_graph.nodes.items()}
stripped_qedges = {qedge_key: self._strip_empty_properties(qedge)
for qedge_key, qedge in query_graph.edges.items()}
# Send the query to the KP's API
body = {'message': {'query_graph': {'nodes': stripped_qnodes, 'edges': stripped_qedges}}}
self.log.debug(f"Sending query to {self.kp_name} API")
kp_response = requests.post(f"{self.kp_endpoint}/query", json=body, headers={'accept': 'application/json'})
json_response = kp_response.json()
if kp_response.status_code == 200:
if not json_response.get("message"):
self.log.warning(
f"No 'message' was included in the response from {self.kp_name}. Response from KP was: "
f"{json.dumps(json_response, indent=4)}")
elif not json_response["message"].get("results"):
self.log.warning(f"No 'results' were returned from {self.kp_name}. Response from KP was: "
f"{json.dumps(json_response, indent=4)}")
json_response["message"]["results"] = [] # Setting this to empty list helps downstream processing
else:
kp_message = ARAXMessenger().from_dict(json_response["message"])
# Build a map that indicates which qnodes/qedges a given node/edge fulfills
kg_to_qg_mappings = self._get_kg_to_qg_mappings_from_results(kp_message.results)
# Populate our final KG with the returned nodes and edges
for returned_edge_key, returned_edge in kp_message.knowledge_graph.edges.items():
arax_edge_key = self._get_arax_edge_key(returned_edge) # Convert to an ID that's unique for us
for qedge_key in kg_to_qg_mappings['edges'][returned_edge_key]:
answer_kg.add_edge(arax_edge_key, returned_edge, qedge_key)
for returned_node_key, returned_node in kp_message.knowledge_graph.nodes.items():
for qnode_key in kg_to_qg_mappings['nodes'][returned_node_key]:
answer_kg.add_node(returned_node_key, returned_node, qnode_key)
# Build a map that indicates which of an edge's nodes fulfill which qnode
if query_graph.edges:
qedge = next(qedge for qedge in query_graph.edges.values())
edge_to_nodes_map = self._create_edge_to_nodes_map(kg_to_qg_mappings, kp_message.knowledge_graph, qedge)
else:
self.log.warning(f"{self.kp_name} API returned response of {kp_response.status_code}. Response from KP was:"
f" {json.dumps(json_response, indent=4)}")
return answer_kg, edge_to_nodes_map
def _load_kp_json_response(
self, json_response: dict) -> QGOrganizedKnowledgeGraph:
# Load the results into the object model
answer_kg = QGOrganizedKnowledgeGraph()
if not json_response.get("message"):
self.log.warning(
f"{self.kp_name}: No 'message' was included in the response from {self.kp_name}. "
f"Response was: {json.dumps(json_response, indent=4)}")
return answer_kg
elif not json_response["message"].get("results"):
self.log.debug(f"{self.kp_name}: No 'results' were returned.")
json_response["message"]["results"] = [
] # Setting this to empty list helps downstream processing
return answer_kg
else:
self.log.debug(f"{self.kp_name}: Got results from {self.kp_name}.")
kp_message = ARAXMessenger().from_dict(json_response["message"])
# Build a map that indicates which qnodes/qedges a given node/edge fulfills
kg_to_qg_mappings = self._get_kg_to_qg_mappings_from_results(
kp_message.results)
# Populate our final KG with the returned nodes and edges
returned_edge_keys_missing_qg_bindings = set()
for returned_edge_key, returned_edge in kp_message.knowledge_graph.edges.items(
):
arax_edge_key = self._get_arax_edge_key(
returned_edge) # Convert to an ID that's unique for us
if not returned_edge.attributes:
returned_edge.attributes = []
# Put in a placeholder for missing required attribute fields to try to keep our answer TRAPI-compliant
for attribute in returned_edge.attributes:
if not attribute.attribute_type_id:
attribute.attribute_type_id = f"not provided (this attribute came from {self.kp_name})"
# Check if KPs are properly indicating that these edges came from them (indicate it ourselves if not)
attribute_has_kp_name = lambda value, kp_name: (type(
value) is list and kp_name in value) or (value == kp_name)
if not any(
attribute_has_kp_name(attribute.value, self.kp_name)
for attribute in returned_edge.attributes):
returned_edge.attributes.append(
eu.get_kp_source_attribute(self.kp_name))
# Add an attribute to indicate that this edge passed through ARAX
returned_edge.attributes.append(eu.get_arax_source_attribute())
if returned_edge_key in kg_to_qg_mappings['edges']:
for qedge_key in kg_to_qg_mappings['edges'][returned_edge_key]:
answer_kg.add_edge(arax_edge_key, returned_edge, qedge_key)
else:
returned_edge_keys_missing_qg_bindings.add(returned_edge_key)
if returned_edge_keys_missing_qg_bindings:
self.log.warning(
f"{self.kp_name}: {len(returned_edge_keys_missing_qg_bindings)} edges in the KP's answer "
f"KG have no bindings to the QG: {returned_edge_keys_missing_qg_bindings}"
)
returned_node_keys_missing_qg_bindings = set()
for returned_node_key, returned_node in kp_message.knowledge_graph.nodes.items(
):
if returned_node_key not in kg_to_qg_mappings['nodes']:
returned_node_keys_missing_qg_bindings.add(returned_node_key)
else:
for qnode_key in kg_to_qg_mappings['nodes'][returned_node_key]:
answer_kg.add_node(returned_node_key, returned_node,
qnode_key)
if returned_node.attributes:
for attribute in returned_node.attributes:
if not attribute.attribute_type_id:
attribute.attribute_type_id = f"not provided (this attribute came from {self.kp_name})"
if returned_node_keys_missing_qg_bindings:
self.log.warning(
f"{self.kp_name}: {len(returned_node_keys_missing_qg_bindings)} nodes in the KP's answer "
f"KG have no bindings to the QG: {returned_node_keys_missing_qg_bindings}"
)
return answer_kg