def queryTerm(self, term):
method = "queryTerm"
attributes = self.findTermAttributesAndTypeByName(term)
response = self.createResponse()
if (attributes["status"] == 'OK'):
node1 = Node()
node1.id = "https://www.ncbi.nlm.nih.gov/mesh/?term=" + attributes[
"id"]
node1.type = attributes["type"]
node1.name = attributes["name"]
node1.accession = "MeSH:" + attributes["id"]
node1.description = attributes["description"]
#### Create the first result (potential answer)
result1 = Result()
result1.id = "http://rtx.ncats.io/api/v1/response/0000/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.result_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 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 add_subgraph(self, nodes, edges, plain_text, confidence):
"""
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)
node_descriptions[u] = data['properties']['description']
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']['iri']
node_uuids2iri[data['properties']
['UUID']] = data['properties']['iri']
node_curies[u] = data['properties']['curie_id']
node_uuids2curie[data['properties']
['UUID']] = data['properties']['curie_id']
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']['sourcedb']
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.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)
# Create the result (potential answer)
result1 = Result()
#result1.id = "http://rtx.ncats.io/api/v1/response/1234/result/2345"
#result1.id = "-1"
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
def test1(self):
#### Create the response object and fill it with attributes about the response
response = Response()
response.context = "http://translator.ncats.io"
response.id = "http://rtx.ncats.io/api/v1/response/1234"
response.type = "medical_translator_query_response"
response.tool_version = "RTX 0.4"
response.schema_version = "0.5"
response.datetime = datetime.datetime.now().strftime(
"%Y-%m-%d %H:%M:%S")
response.original_question_text = "what proteins are affected by sickle cell anemia"
response.restated_question_text = "Which proteins are affected by sickle cell anemia?"
response.result_code = "OK"
response.message = "1 result found"
#### Create a disease node
node1 = Node()
node1.id = "http://omim.org/entry/603903"
node1.type = "disease"
node1.name = "sickle cell anemia"
node1.accession = "OMIM:603903"
node1.description = "A disease characterized by chronic hemolytic anemia..."
#### Create a protein node
node2 = Node()
node2.id = "https://www.uniprot.org/uniprot/P00738"
node2.type = "protein"
node2.name = "Haptoglobin"
node2.symbol = "HP"
node2.accession = "UNIPROT:P00738"
node2.description = "Haptoglobin captures, and combines with free plasma hemoglobin..."
#### Create a node attribute
node2attribute1 = NodeAttribute()
node2attribute1.type = "comment"
node2attribute1.name = "Complex_description"
node2attribute1.value = "The Hemoglobin/haptoglobin complex is composed of a haptoglobin dimer bound to two hemoglobin alpha-beta dimers"
node2.node_attributes = [node2attribute1]
#### Create an edge between these 2 nodes
edge1 = Edge()
edge1.type = "is_caused_by_a_defect_in"
edge1.source_id = node1.id
edge1.target_id = node2.id
edge1.confidence = 1.0
#### Add an origin and property for the edge
origin1 = Origin()
origin1.id = "https://api.monarchinitiative.org/api/bioentity/disease/OMIM:603903/genes/"
origin1.type = "Monarch_BioLink_API_Relationship"
#### Add an attribute
attribute1 = EdgeAttribute()
attribute1.type = "PubMed_article"
attribute1.name = "Orthopaedic Manifestations of Sickle Cell Disease"
attribute1.value = None
attribute1.url = "https://www.ncbi.nlm.nih.gov/pubmed/29309293"
origin1.attribute_list = [attribute1]
edge1.origin_list = [origin1]
#### Create the first result (potential answer)
result1 = Result()
result1.id = "http://rtx.ncats.io/api/v1/response/1234/result/2345"
result1.text = "A free text description of this result"
result1.confidence = 0.932
#### Create a ResultGraph object and put the list of nodes and edges into it
result_graph = ResultGraph()
result_graph.node_list = [node1, node2]
result_graph.edge_list = [edge1]
#### 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
print(response)