def _get_best_equivalent_bte_curie(equivalent_curies: List[str], node_category: str) -> str:
# Curie prefixes in order of preference for different node types (not all-inclusive)
preferred_node_prefixes_dict = {'chemical_substance': ['CHEMBL.COMPOUND', 'CHEBI'],
'protein': ['UNIPROTKB', 'PR'],
'gene': ['NCBIGENE', 'ENSEMBL', 'HGNC', 'GO'],
'disease': ['DOID', 'MONDO', 'OMIM', 'MESH'],
'phenotypic_feature': ['HP', 'OMIM'],
'anatomical_entity': ['UBERON', 'FMA', 'CL'],
'pathway': ['REACTOME'],
'biological_process': ['GO'],
'cellular_component': ['GO']}
prefixes_in_order_of_preference = preferred_node_prefixes_dict.get(eu.convert_string_to_snake_case(node_category), [])
equivalent_curies.sort()
# Pick the curie that uses the (relatively) most preferred prefix
lowest_ranking = 10000
best_curie = None
for curie in equivalent_curies:
uppercase_prefix = eu.get_curie_prefix(curie).upper()
if uppercase_prefix in prefixes_in_order_of_preference:
ranking = prefixes_in_order_of_preference.index(uppercase_prefix)
if ranking < lowest_ranking:
lowest_ranking = ranking
best_curie = curie
# Otherwise, just try to pick one that isn't 'NAME:___'
if not best_curie:
non_name_curies = [curie for curie in equivalent_curies if eu.get_curie_prefix(curie).upper() != 'NAME']
best_curie = non_name_curies[0] if non_name_curies else equivalent_curies[0]
return best_curie
def _add_answers_to_kg(self, answer_kg: QGOrganizedKnowledgeGraph, reasoner_std_response: Dict[str, any],
input_qnode_key: str, output_qnode_key: str, qedge_key: str, log: ARAXResponse) -> QGOrganizedKnowledgeGraph:
kg_to_qg_ids_dict = self._build_kg_to_qg_id_dict(reasoner_std_response['results'])
if reasoner_std_response['knowledge_graph']['edges']:
remapped_node_keys = dict()
log.debug(f"Got results back from BTE for this query "
f"({len(reasoner_std_response['knowledge_graph']['edges'])} edges)")
for node in reasoner_std_response['knowledge_graph']['nodes']:
swagger_node = Node()
bte_node_key = node.get('id')
swagger_node.name = node.get('name')
swagger_node.category = eu.convert_to_list(eu.convert_string_to_snake_case(node.get('type')))
# Map the returned BTE qg_ids back to the original qnode_keys in our query graph
bte_qg_id = kg_to_qg_ids_dict['nodes'].get(bte_node_key)
if bte_qg_id == "n0":
qnode_key = input_qnode_key
elif bte_qg_id == "n1":
qnode_key = output_qnode_key
else:
log.error("Could not map BTE qg_id to ARAX qnode_key", error_code="UnknownQGID")
return answer_kg
# Find and use the preferred equivalent identifier for this node (if it's an output node)
if qnode_key == output_qnode_key:
if bte_node_key in remapped_node_keys:
swagger_node_key = remapped_node_keys.get(bte_node_key)
else:
equivalent_curies = [f"{prefix}:{eu.get_curie_local_id(local_id)}" for prefix, local_ids in
node.get('equivalent_identifiers').items() for local_id in local_ids]
swagger_node_key = self._get_best_equivalent_bte_curie(equivalent_curies, swagger_node.category[0])
remapped_node_keys[bte_node_key] = swagger_node_key
else:
swagger_node_key = bte_node_key
answer_kg.add_node(swagger_node_key, swagger_node, qnode_key)
for edge in reasoner_std_response['knowledge_graph']['edges']:
swagger_edge = Edge()
swagger_edge_key = edge.get("id")
swagger_edge.predicate = edge.get('type')
swagger_edge.subject = remapped_node_keys.get(edge.get('source_id'), edge.get('source_id'))
swagger_edge.object = remapped_node_keys.get(edge.get('target_id'), edge.get('target_id'))
swagger_edge.attributes = [Attribute(name="provided_by", value=edge.get('edge_source'), type=eu.get_attribute_type("provided_by")),
Attribute(name="is_defined_by", value="BTE", type=eu.get_attribute_type("is_defined_by"))]
# Map the returned BTE qg_id back to the original qedge_key in our query graph
bte_qg_id = kg_to_qg_ids_dict['edges'].get(swagger_edge_key)
if bte_qg_id != "e1":
log.error("Could not map BTE qg_id to ARAX qedge_key", error_code="UnknownQGID")
return answer_kg
answer_kg.add_edge(swagger_edge_key, swagger_edge, qedge_key)
return answer_kg