def queryTerm(self, term):
method = "queryTerm"
attributes = self.findTermAttributesAndTypeByName(term)
response = self.createResponse()
if ( attributes["status"] == 'OK' ):
node1 = Node()
node1.id = "MESH:" + attributes["id"]
node1.uri = "http://purl.obolibrary.org/obo/MESH_" + attributes["id"]
node1.type = attributes["type"]
node1.name = attributes["name"]
node1.description = attributes["description"]
#### Create the first result (potential answer)
result1 = Result()
result1.id = "http://rtx.ncats.io/api/v1/result/0000"
result1.text = "The term " + attributes["name"] + " refers to " + attributes["description"]
result1.confidence = 1.0
#### Create a ResultGraph object and put the list of nodes and edges into it
result_graph = ResultGraph()
result_graph.node_list = [ node1 ]
#### Put the ResultGraph into the first result (potential answer)
result1.result_graph = result_graph
#### Put the first result (potential answer) into the response
result_list = [ result1 ]
response.result_list = result_list
else:
response.response_code = "TermNotFound"
response.message = "Unable to find term '" + term + "' in MeSH. No further information is available at this time."
response.id = None
return response
def _convert_kg2_node_to_swagger_node(self, neo4j_node):
swagger_node = Node()
swagger_node.id = neo4j_node.get('id')
swagger_node.name = neo4j_node.get('name')
swagger_node.description = neo4j_node.get('description')
swagger_node.uri = neo4j_node.get('iri')
swagger_node.node_attributes = []
node_category = neo4j_node.get('category_label')
swagger_node.type = eu.convert_string_or_list_to_list(node_category)
# Fill out the 'symbol' property (only really relevant for nodes from UniProtKB)
if swagger_node.symbol is None and swagger_node.id.lower().startswith(
"uniprot"):
swagger_node.symbol = neo4j_node.get('name')
swagger_node.name = neo4j_node.get('full_name')
# Add all additional properties on KG2 nodes as swagger NodeAttribute objects
additional_kg2_node_properties = [
'publications', 'synonym', 'category', 'provided_by', 'deprecated',
'update_date'
]
node_attributes = self._create_swagger_attributes(
"node", additional_kg2_node_properties, neo4j_node)
swagger_node.node_attributes += node_attributes
return swagger_node
def _convert_kg1_node_to_swagger_node(neo4j_node: Dict[str, any]) -> Node:
swagger_node = Node()
swagger_node.id = neo4j_node.get('id')
swagger_node.name = neo4j_node.get('name')
swagger_node.symbol = neo4j_node.get('symbol')
swagger_node.description = neo4j_node.get('description')
swagger_node.uri = neo4j_node.get('uri')
swagger_node.node_attributes = []
node_category = neo4j_node.get('category')
swagger_node.type = eu.convert_string_or_list_to_list(node_category)
return swagger_node
def add_subgraph(self,
nodes,
edges,
plain_text,
confidence,
return_result=False):
"""
Populate the object model using networkx neo4j subgraph
:param nodes: nodes in the subgraph (g.nodes(data=True))
:param edges: edges in the subgraph (g.edges(data=True))
:return: none
"""
# Get the relevant info from the nodes and edges
node_keys = []
node_descriptions = dict()
node_names = dict()
node_labels = dict()
node_uuids = dict()
node_accessions = dict()
node_iris = dict()
node_uuids2iri = dict()
node_curies = dict()
node_uuids2curie = dict()
for u, data in nodes:
node_keys.append(u)
if 'description' in data['properties']:
node_descriptions[u] = data['properties']['description']
else:
node_descriptions[u] = "None"
node_names[u] = data['properties']['name']
node_labels[u] = list(set(data['labels']).difference({'Base'}))[0]
node_uuids[u] = data['properties']['UUID']
node_accessions[u] = data['properties']['accession']
node_iris[u] = data['properties']['uri']
node_uuids2iri[data['properties']
['UUID']] = data['properties']['uri']
curie_id = data['properties']['id']
if curie_id.split(':')[0].upper() == "CHEMBL":
curie_id = "CHEMBL:CHEMBL" + curie_id.split(':')[1]
node_uuids2curie[data['properties']['UUID']] = curie_id
node_curies[
u] = curie_id # These are the actual CURIE IDS eg UBERON:00000941 (uri is the web address)
edge_keys = []
edge_types = dict()
edge_source_db = dict()
edge_source_iri = dict()
edge_target_iri = dict()
edge_source_curie = dict()
edge_target_curie = dict()
for u, v, data in edges:
edge_keys.append((u, v))
edge_types[(u, v)] = data['type']
edge_source_db[(u, v)] = data['properties']['provided_by']
edge_source_iri[(
u, v)] = node_uuids2iri[data['properties']['source_node_uuid']]
edge_target_iri[(
u, v)] = node_uuids2iri[data['properties']['target_node_uuid']]
edge_source_curie[(
u,
v)] = node_uuids2curie[data['properties']['source_node_uuid']]
edge_target_curie[(
u,
v)] = node_uuids2curie[data['properties']['target_node_uuid']]
# For each node, populate the relevant information
node_objects = []
node_iris_to_node_object = dict()
for node_key in node_keys:
node = Node()
node.id = node_curies[node_key]
node.type = node_labels[node_key]
node.name = node_names[node_key]
node.uri = node_iris[node_key]
node.accession = node_accessions[node_key]
node.description = node_descriptions[node_key]
node_objects.append(node)
node_iris_to_node_object[node_iris[node_key]] = node
# for each edge, create an edge between them
edge_objects = []
for u, v in edge_keys:
edge = Edge()
edge.type = edge_types[(u, v)]
edge.source_id = node_iris_to_node_object[edge_source_iri[(u,
v)]].id
edge.target_id = node_iris_to_node_object[edge_target_iri[(u,
v)]].id
#edge.origin_list = []
#edge.origin_list.append(edge_source_db[(u, v)]) # TODO: check with eric if this really should be a list and if it should contain the source DB('s)
edge_objects.append(edge)
#edge.attribute_list
#edge.confidence
#edge.evidence_type
edge.is_defined_by = "RTX"
#edge.provided_by = node_iris_to_node_object[edge_source_iri[(u, v)]].uri
edge.provided_by = edge_source_db[(u, v)]
#edge.publications
#edge.qualifiers
#edge.relation
#edge.source_id
#edge.target_id
#edge.type
# Create the result (potential answer)
result1 = Result()
result1.text = plain_text
result1.confidence = confidence
# Create a ResultGraph object and put the list of nodes and edges into it
result_graph = ResultGraph()
result_graph.node_list = node_objects
result_graph.edge_list = edge_objects
# Put the ResultGraph into the first result (potential answer)
result1.result_graph = result_graph
# Put the first result (potential answer) into the response
self._result_list.append(result1)
self.response.result_list = self._result_list
# Increment the number of results
self._num_results += 1
if self._num_results == 1:
self.response.message = "%s result found" % self._num_results
else:
self.response.message = "%s results found" % self._num_results
if return_result:
return result1
else:
pass
def add_neighborhood_graph(self, nodes, edges, confidence=None):
"""
Populate the object model using networkx neo4j subgraph
:param nodes: nodes in the subgraph (g.nodes(data=True))
:param edges: edges in the subgraph (g.edges(data=True))
:return: none
"""
# Get the relevant info from the nodes and edges
node_keys = []
node_descriptions = dict()
node_names = dict()
node_labels = dict()
node_uuids = dict()
node_accessions = dict()
node_iris = dict()
node_uuids2iri = dict()
node_curies = dict()
node_uuids2curie = dict()
for u, data in nodes:
node_keys.append(u)
if 'description' in data['properties']:
node_descriptions[u] = data['properties']['description']
else:
node_descriptions[u] = "None"
node_names[u] = data['properties']['name']
node_labels[u] = list(set(data['labels']).difference({'Base'}))[0]
node_uuids[u] = data['properties']['UUID']
node_accessions[u] = data['properties']['accession']
node_iris[u] = data['properties']['uri']
node_uuids2iri[data['properties']
['UUID']] = data['properties']['uri']
curie_id = data['properties']['id']
if curie_id.split(':')[0].upper() == "CHEMBL":
curie_id = "CHEMBL:CHEMBL" + curie_id.split(':')[1]
node_uuids2curie[data['properties']['UUID']] = curie_id
node_curies[
u] = curie_id # These are the actual CURIE IDS eg UBERON:00000941 (uri is the web address)
edge_keys = []
edge_types = dict()
edge_source_db = dict()
edge_source_iri = dict()
edge_target_iri = dict()
edge_source_curie = dict()
edge_target_curie = dict()
for u, v, data in edges:
edge_keys.append((u, v))
edge_types[(u, v)] = data['type']
edge_source_db[(u, v)] = data['properties']['provided_by']
edge_source_iri[(
u, v)] = node_uuids2iri[data['properties']['source_node_uuid']]
edge_target_iri[(
u, v)] = node_uuids2iri[data['properties']['target_node_uuid']]
edge_source_curie[(
u,
v)] = node_uuids2curie[data['properties']['source_node_uuid']]
edge_target_curie[(
u,
v)] = node_uuids2curie[data['properties']['target_node_uuid']]
# For each node, populate the relevant information
node_objects = []
node_iris_to_node_object = dict()
for node_key in node_keys:
node = Node()
node.id = node_curies[node_key]
node.type = node_labels[node_key]
node.name = node_names[node_key]
node.uri = node_iris[node_key]
node.accession = node_accessions[node_key]
node.description = node_descriptions[node_key]
node_objects.append(node)
node_iris_to_node_object[node_iris[node_key]] = node
# for each edge, create an edge between them
edge_objects = []
for u, v in edge_keys:
edge = Edge()
edge.type = edge_types[(u, v)]
edge.source_id = node_iris_to_node_object[edge_source_iri[(u,
v)]].id
edge.target_id = node_iris_to_node_object[edge_target_iri[(u,
v)]].id
#edge.origin_list = []
#edge.origin_list.append(edge_source_db[(u, v)]) # TODO: check with eric if this really should be a list and if it should contain the source DB('s)
edge.provided_by = edge_source_db[(u, v)]
edge.is_defined_by = "RTX"
edge_objects.append(edge)
# Create the result (potential answer)
result1 = Result()
text = "This is a subgraph extracted from the full RTX knowledge graph, including nodes and edges relevant to the query." \
" This is not an answer to the query per se, but rather an opportunity to examine a small region of the RTX knowledge graph for further study. " \
"Formal answers to the query are below."
result1.text = text
result1.confidence = confidence
result1.result_type = "neighborhood graph"
# Create a ResultGraph object and put the list of nodes and edges into it
result_graph = ResultGraph()
result_graph.node_list = node_objects
result_graph.edge_list = edge_objects
# Put the ResultGraph into the first result (potential answer)
result1.result_graph = result_graph
# Put the first result (potential answer) into the response
self._result_list.append(result1)
self.response.result_list = self._result_list
def add_subgraph(self,
nodes,
edges,
description,
confidence,
return_result=False,
suppress_bindings=False):
"""
Populate the object model using networkx neo4j subgraph
:param nodes: nodes in the subgraph (g.nodes(data=True))
:param edges: edges in the subgraph (g.edges(data=True))
:return: none
"""
# Get the relevant info from the nodes and edges
node_keys = []
node_descriptions = dict()
node_names = dict()
node_labels = dict()
node_uuids = dict()
node_accessions = dict()
node_iris = dict()
node_uuids2iri = dict()
node_curies = dict()
node_uuids2curie = dict()
for u, data in nodes:
node_keys.append(u)
if 'description' in data['properties']:
node_descriptions[u] = data['properties']['description']
else:
node_descriptions[u] = "None"
node_names[u] = data['properties']['name']
node_labels[u] = list(set(data['labels']).difference({'Base'}))[0]
node_uuids[u] = data['properties']['UUID']
node_accessions[u] = data['properties']['accession']
node_iris[u] = data['properties']['uri']
node_uuids2iri[data['properties']
['UUID']] = data['properties']['uri']
curie_id = data['properties']['id']
if curie_id.split(':')[0].upper() == "CHEMBL":
curie_id = "CHEMBL:CHEMBL" + curie_id.split(':')[1]
node_uuids2curie[data['properties']['UUID']] = curie_id
node_curies[
u] = curie_id # These are the actual CURIE IDS eg UBERON:00000941 (uri is the web address)
edge_keys = []
edge_types = dict()
edge_source_db = dict()
edge_source_iri = dict()
edge_target_iri = dict()
edge_source_curie = dict()
edge_target_curie = dict()
edge_ids = dict()
for u, v, data in edges:
edge_keys.append((u, v))
edge_types[(u, v)] = data['type']
edge_source_db[(u, v)] = data['properties']['provided_by']
edge_source_iri[(
u, v)] = node_uuids2iri[data['properties']['source_node_uuid']]
edge_target_iri[(
u, v)] = node_uuids2iri[data['properties']['target_node_uuid']]
edge_source_curie[(
u,
v)] = node_uuids2curie[data['properties']['source_node_uuid']]
edge_target_curie[(
u,
v)] = node_uuids2curie[data['properties']['target_node_uuid']]
edge_ids[(u, v)] = data['properties']['provided_by'] # FIXME
# For each node, populate the relevant information
node_objects = []
node_iris_to_node_object = dict()
for node_key in node_keys:
node = Node()
node.id = node_curies[node_key]
node.type = [node_labels[node_key]]
node.name = node_names[node_key]
node.uri = node_iris[node_key]
node.accession = node_accessions[node_key]
node.description = node_descriptions[node_key]
node_objects.append(node)
node_iris_to_node_object[node_iris[node_key]] = node
#### Add this node to the master knowledge graph
if node.id not in self._node_ids:
self.message.knowledge_graph.nodes.append(node)
self._node_ids[node.id] = node.type[
0] # Just take the first of potentially several FIXME
#### Create the bindings lists
node_bindings = list()
edge_bindings = list()
# for each edge, create an edge between them
edge_objects = []
for u, v in edge_keys:
edge = Edge()
#edge.id is set below when building the bindings
edge.type = edge_types[(u, v)]
edge.source_id = node_iris_to_node_object[edge_source_iri[(u,
v)]].id
edge.target_id = node_iris_to_node_object[edge_target_iri[(u,
v)]].id
edge_objects.append(edge)
#edge.attribute_list
#edge.confidence
#edge.evidence_type
edge.is_defined_by = "RTX"
edge.provided_by = edge_source_db[(u, v)]
#edge.publications
#edge.qualifiers
#edge.relation
#edge.source_id
#edge.target_id
#edge.type
#### Add this edge to the master knowledge graph
edge_str = "%s -%s- %s" % (edge.source_id, edge.type,
edge.target_id)
if edge_str not in self._edge_ids:
self.message.knowledge_graph.edges.append(edge)
edge.id = "%d" % self._edge_counter
self._edge_ids[edge_str] = edge.id
self._edge_counter += 1
else:
edge.id = self._edge_ids[edge_str]
#### Try to figure out how the source fits into the query_graph for the bindings
source_type = self._node_ids[edge.source_id]
if edge.source_id in self._type_map:
source_knowledge_map_key = self._type_map[edge.source_id]
else:
source_knowledge_map_key = self._type_map[source_type]
if not source_knowledge_map_key:
eprint(
"Expected to find '%s' in the response._type_map, but did not"
% source_type)
raise Exception(
"Expected to find '%s' in the response._type_map, but did not"
% source_type)
node_bindings.append(
NodeBinding(qg_id=source_knowledge_map_key,
kg_id=edge.source_id))
# if source_knowledge_map_key not in node_bindings:
# node_bindings[source_knowledge_map_key] = list()
# node_bindings_dict[source_knowledge_map_key] = dict()
# if edge.source_id not in node_bindings_dict[source_knowledge_map_key]:
# node_bindings[source_knowledge_map_key].append(edge.source_id)
# node_bindings_dict[source_knowledge_map_key][edge.source_id] = 1
#### Try to figure out how the target fits into the query_graph for the knowledge map
target_type = self._node_ids[edge.target_id]
if edge.target_id in self._type_map:
target_knowledge_map_key = self._type_map[edge.target_id]
else:
target_knowledge_map_key = self._type_map[target_type]
if not target_knowledge_map_key:
eprint(
"ERROR: Expected to find '%s' in the response._type_map, but did not"
% target_type)
raise Exception(
"Expected to find '%s' in the response._type_map, but did not"
% target_type)
node_bindings.append(
NodeBinding(qg_id=target_knowledge_map_key,
kg_id=edge.target_id))
# if target_knowledge_map_key not in node_bindings:
# node_bindings[target_knowledge_map_key] = list()
# node_bindings_dict[target_knowledge_map_key] = dict()
# if edge.target_id not in node_bindings_dict[target_knowledge_map_key]:
# node_bindings[target_knowledge_map_key].append(edge.target_id)
# node_bindings_dict[target_knowledge_map_key][edge.target_id] = 1
#### Try to figure out how the edge fits into the query_graph for the knowledge map
source_target_key = "e" + source_knowledge_map_key + "-" + target_knowledge_map_key
target_source_key = "e" + target_knowledge_map_key + "-" + source_knowledge_map_key
if edge.type in self._type_map:
knowledge_map_key = self._type_map[edge.type]
elif source_target_key in self._type_map:
knowledge_map_key = source_target_key
elif target_source_key in self._type_map:
knowledge_map_key = target_source_key
else:
eprint(
"ERROR: Expected to find '%s' or '%s' or '%s' in the response._type_map, but did not"
% (edge.type, source_target_key, target_source_key))
knowledge_map_key = "ERROR"
edge_bindings.append(
EdgeBinding(qg_id=knowledge_map_key, kg_id=edge.id))
# if knowledge_map_key not in edge_bindings:
# edge_bindings[knowledge_map_key] = list()
# edge_bindings_dict[knowledge_map_key] = dict()
# if edge.id not in edge_bindings_dict[knowledge_map_key]:
# edge_bindings[knowledge_map_key].append(edge.id)
# edge_bindings_dict[knowledge_map_key][edge.id] = 1
# Create the result (potential answer)
result1 = Result()
result1.reasoner_id = "RTX"
result1.description = description
result1.confidence = confidence
if suppress_bindings is False:
result1.node_bindings = node_bindings
result1.edge_bindings = edge_bindings
# Create a KnowledgeGraph object and put the list of nodes and edges into it
#### This is still legal, then is redundant with the knowledge map, so leave it out maybe
knowledge_graph = KnowledgeGraph()
knowledge_graph.nodes = node_objects
knowledge_graph.edges = edge_objects
if suppress_bindings is True:
result1.result_graph = knowledge_graph
# Put the first result (potential answer) into the message
self._results.append(result1)
self.message.results = self._results
# Increment the number of results
self._num_results += 1
if self._num_results == 1:
self.message.code_description = "%s result found" % self._num_results
else:
self.message.code_description = "%s results found" % self._num_results
#### Finish and return the result if requested
if return_result:
return result1
else:
pass
def answer(self, entity, use_json=False):
"""
Answer a question of the type "What is X" but is general:
:param entity: KG neo4j node name (eg "carbetocin")
:param use_json: If the answer should be in Translator standardized API output format
:return: a description and type of the node
"""
#### See if this entity is in the KG via the index
eprint("Looking up '%s' in KgNodeIndex" % entity)
kgNodeIndex = KGNodeIndex()
curies = kgNodeIndex.get_curies(entity)
#### If not in the KG, then return no information
if not curies:
if not use_json:
return None
else:
error_code = "TermNotFound"
error_message = "This concept is not in our knowledge graph"
response = FormatOutput.FormatResponse(0)
response.add_error_message(error_code, error_message)
return response.message
# Get label/kind of node the source is
eprint("Getting properties for '%s'" % curies[0])
properties = RU.get_node_properties(curies[0])
eprint("Properties are:")
eprint(properties)
#### By default, return the results just as a plain simple list of data structures
if not use_json:
return properties
#### Or, if requested, format the output as the standardized API output format
else:
#### Create a stub Message object
response = FormatOutput.FormatResponse(0)
response.message.table_column_names = [
"id", "type", "name", "description", "uri"
]
response.message.code_description = None
#### Create a Node object and fill it
node1 = Node()
node1.id = properties["id"]
node1.uri = properties["uri"]
node1.type = [properties["category"]]
node1.name = properties["name"]
node1.description = properties["description"]
#### Create the first result (potential answer)
result1 = Result()
result1.id = "http://arax.ncats.io/api/v1/result/0000"
result1.description = "The term %s is in our knowledge graph and is defined as %s" % (
properties["name"], properties["description"])
result1.confidence = 1.0
result1.essence = properties["name"]
result1.essence_type = properties["category"]
node_types = ",".join(node1.type)
result1.row_data = [
node1.id, node_types, node1.name, node1.description, node1.uri
]
#### Create a KnowledgeGraph object and put the list of nodes and edges into it
result_graph = KnowledgeGraph()
result_graph.nodes = [node1]
result_graph.edges = []
#### Put the ResultGraph into the first result (potential answer)
result1.result_graph = result_graph
#### Put the first result (potential answer) into the message
results = [result1]
response.message.results = results
#### Also put the union of all result_graph components into the top Message KnowledgeGraph
#### Normally the knowledge_graph will be much more complex than this, but take a shortcut for this single-node result
response.message.knowledge_graph = result_graph
#### Also manufacture a query_graph post hoc
qnode1 = QNode()
qnode1.id = "n00"
qnode1.curie = properties["id"]
qnode1.type = None
query_graph = QueryGraph()
query_graph.nodes = [qnode1]
query_graph.edges = []
response.message.query_graph = query_graph
#### Create the corresponding knowledge_map
node_binding = NodeBinding(qg_id="n00", kg_id=properties["id"])
result1.node_bindings = [node_binding]
result1.edge_bindings = []
#eprint(response.message)
return response.message
def queryTerm(self, term):
method = "queryTerm"
attributes = self.findTermAttributesAndTypeByName(term)
message = self.createMessage()
if ( attributes["status"] == 'OK' ):
message.code_description = "1 result found"
message.table_column_names = [ "id", "type", "name", "description", "uri" ]
#### Create a Node object and fill it
node1 = Node()
node1.id = "MESH:" + attributes["id"]
node1.uri = "http://purl.obolibrary.org/obo/MESH_" + attributes["id"]
node1.type = [ attributes["type"] ]
node1.name = attributes["name"]
node1.description = attributes["description"]
#### Create the first result (potential answer)
result1 = Result()
result1.id = "http://rtx.ncats.io/api/v1/result/0000"
result1.description = "The term " + attributes["name"] + " refers to " + attributes["description"]
result1.confidence = 1.0
result1.essence = attributes["name"]
result1.essence_type = attributes["type"]
node_types = ",".join(node1.type)
result1.row_data = [ node1.id, node_types, node1.name, node1.description, node1.uri ]
#### Create a KnowledgeGraph object and put the list of nodes and edges into it
result_graph = KnowledgeGraph()
result_graph.nodes = [ node1 ]
#### Put the ResultGraph into the first result (potential answer)
result1.result_graph = result_graph
#### Put the first result (potential answer) into the message
results = [ result1 ]
message.results = results
#### Also put the union of all result_graph components into the top Message KnowledgeGraph
#### Normally the knowledge_graph will be much more complex than this, but take a shortcut for this single-node result
message.knowledge_graph = result_graph
#### Also manufacture a query_graph post hoc
qnode1 = QNode()
qnode1.node_id = "n00"
qnode1.curie = "MESH:" + attributes["id"]
qnode1.type = None
query_graph = QueryGraph()
query_graph.nodes = [ qnode1 ]
query_graph.edges = []
message.query_graph = query_graph
#### Create the corresponding knowledge_map
knowledge_map = { "n00": "MESH:" + attributes["id"] }
result1.knowledge_map = knowledge_map
else:
message.message_code = "TermNotFound"
message.code_description = "Unable to find this term in MeSH. No further information is available at this time."
message.id = None
return message