def answer(source_node_ID,
target_node_type,
association_node_type,
use_json=False,
threshold=0.2,
n=20):
"""
Answers the question what X are similar to Y based on overlap of common Z nodes. X is target_node_type,
Y is source_node_ID, Z is association_node_type. The relationships are automatically determined in
SimilarNodesInCommon by looking for 1 hop relationships and poping the FIRST one (you are warned).
:param source_node_ID: actual name in the KG
:param target_node_type: kinds of nodes you want returned
:param association_node_type: kind of node you are computing the Jaccard overlap on
:param use_json: print the results in standardized format
:param threshold: only return results where jaccard is >= this threshold
:param n: number of results to return (default 20)
:return: reponse (or printed text)
"""
# Initialize the response class
response = FormatOutput.FormatResponse(5)
# add the column names for the row data
response.message.table_column_names = [
"source name", "source ID", "target name", "target ID",
"Jaccard index"
]
# Initialize the similar nodes class
similar_nodes_in_common = SimilarNodesInCommon.SimilarNodesInCommon()
# get the description
source_node_description = RU.get_node_property(source_node_ID, 'name')
# get the source node label
source_node_label = RU.get_node_property(source_node_ID, 'label')
# Get the nodes in common
node_jaccard_tuples_sorted, error_code, error_message = similar_nodes_in_common.get_similar_nodes_in_common_source_target_association(
source_node_ID, target_node_type, association_node_type, threshold)
# reduce to top 100
if len(node_jaccard_tuples_sorted) > n:
node_jaccard_tuples_sorted = node_jaccard_tuples_sorted[0:n]
# make sure that the input node isn't in the list
node_jaccard_tuples_sorted = [
i for i in node_jaccard_tuples_sorted if i[0] != source_node_ID
]
# check for an error
if error_code is not None or error_message is not None:
if not use_json:
print(error_message)
return
else:
response.add_error_message(error_code, error_message)
response.print()
return
#### If use_json not specified, then return results as a fairly plain list
if not use_json:
to_print = "The %s's involving similar %ss as %s are: \n" % (
target_node_type, association_node_type,
source_node_description)
for other_disease_ID, jaccard in node_jaccard_tuples_sorted:
to_print += "%s\t%s\tJaccard %f\n" % (
other_disease_ID,
RU.get_node_property(other_disease_ID, 'name'), jaccard)
print(to_print)
#### Else if use_json requested, return the results in the Translator standard API JSON format
else:
#### Create the QueryGraph for this type of question
query_graph = QueryGraph()
source_node = QNode()
source_node.id = "n00"
source_node.curie = source_node_ID
source_node.type = source_node_label
association_node = QNode()
association_node.id = "n01"
association_node.type = association_node_type
association_node.is_set = True
target_node = QNode()
target_node.id = "n02"
target_node.type = target_node_type
query_graph.nodes = [source_node, association_node, target_node]
#source_association_relationship_type = "unknown1"
edge1 = QEdge()
edge1.id = "en00-n01"
edge1.source_id = "n00"
edge1.target_id = "n01"
#edge1.type = source_association_relationship_type
#association_target_relationship_type = "unknown2"
edge2 = QEdge()
edge2.id = "en01-n02"
edge2.source_id = "n01"
edge2.target_id = "n02"
#edge2.type = association_target_relationship_type
query_graph.edges = [edge1, edge2]
#### DONT Suppress the query_graph because we can now do the knowledge_map with v0.9.1
response.message.query_graph = query_graph
#### Create a mapping dict with the source curie and node types and edge types. This dict is used for reverse lookups by type
#### for mapping to the QueryGraph. There is a potential point of failure here if there are duplicate node or edge types. FIXME
response._type_map = dict()
response._type_map[source_node.curie] = source_node.id
response._type_map[association_node.type] = association_node.id
response._type_map[target_node.type] = target_node.id
response._type_map["e" + edge1.source_id + "-" +
edge1.target_id] = edge1.id
response._type_map["e" + edge2.source_id + "-" +
edge2.target_id] = edge2.id
#### Extract the sorted IDs from the list of tuples
node_jaccard_ID_sorted = [
id for id, jac in node_jaccard_tuples_sorted
]
# print(RU.return_subgraph_through_node_labels(source_node_ID, source_node_label, node_jaccard_ID_sorted, target_node_type,
# [association_node_type], with_rel=[], directed=True, debug=True))
# get the entire subgraph
g = RU.return_subgraph_through_node_labels(source_node_ID,
source_node_label,
node_jaccard_ID_sorted,
target_node_type,
[association_node_type],
with_rel=[],
directed=False,
debug=False)
# extract the source_node_number
for node, data in g.nodes(data=True):
if data['properties']['id'] == source_node_ID:
source_node_number = node
break
# Get all the target numbers
target_id2numbers = dict()
node_jaccard_ID_sorted_set = set(node_jaccard_ID_sorted)
for node, data in g.nodes(data=True):
if data['properties']['id'] in node_jaccard_ID_sorted_set:
target_id2numbers[data['properties']['id']] = node
for other_disease_ID, jaccard in node_jaccard_tuples_sorted:
target_name = RU.get_node_property(other_disease_ID, 'name')
to_print = "The %s %s involves similar %ss as %s with similarity value %f" % (
target_node_type, target_name, association_node_type,
source_node_description, jaccard)
# get all the shortest paths between source and target
all_paths = nx.all_shortest_paths(
g, source_node_number, target_id2numbers[other_disease_ID])
# get all the nodes on these paths
#try:
if 1 == 1:
rel_nodes = set()
for path in all_paths:
for node in path:
rel_nodes.add(node)
if rel_nodes:
# extract the relevant subgraph
sub_g = nx.subgraph(g, rel_nodes)
# add it to the response
res = response.add_subgraph(sub_g.nodes(data=True),
sub_g.edges(data=True),
to_print,
jaccard,
return_result=True)
res.essence = "%s" % target_name # populate with essence of question result
res.essence_type = target_node_type
row_data = [] # initialize the row data
row_data.append("%s" % source_node_description)
row_data.append("%s" % source_node_ID)
row_data.append("%s" % target_name)
row_data.append("%s" % other_disease_ID)
row_data.append("%f" % jaccard)
res.row_data = row_data
# except:
# pass
response.print()
def add_qedge(self, message, input_parameters, describe=False):
"""
Adds a new QEdge object to the QueryGraph inside the Message object
:return: Response object with execution information
:rtype: Response
"""
# #### Internal documentation setup
allowable_parameters = {
'id': {
'Any string that is unique among all QEdge id fields, with recommended format e00, e01, e02, etc.'
},
'source_id': {
'id of the source QNode already present in the QueryGraph (e.g. n01, n02)'
},
'target_id': {
'id of the target QNode already present in the QueryGraph (e.g. n01, n02)'
},
'type': {
'Any valid Translator/BioLink relationship type (e.g. physically_interacts_with, participates_in)'
},
}
if describe:
#allowable_parameters['action'] = { 'None' }
#allowable_parameters = dict()
allowable_parameters[
'dsl_command'] = '`add_qedge()`' # can't get this name at run-time, need to manually put it in per https://www.python.org/dev/peps/pep-3130/
allowable_parameters[
'brief_description'] = """The `add_qedge` method adds an additional QEdge to the QueryGraph in the Message object. Currently
source_id and target_id QNodes must already be present in the QueryGraph. The specified type is not currently checked that it is a
valid Translator/BioLink relationship type, but it should be."""
return allowable_parameters
#### Define a default response
response = Response()
self.response = response
self.message = message
#### Basic checks on arguments
if not isinstance(input_parameters, dict):
response.error("Provided parameters is not a dict",
error_code="ParametersNotDict")
return response
#### Define a complete set of allowed parameters and their defaults
parameters = {
'id': None,
'source_id': None,
'target_id': None,
'type': None,
}
#### Loop through the input_parameters and override the defaults and make sure they are allowed
for key, value in input_parameters.items():
if key not in parameters:
response.error(f"Supplied parameter {key} is not permitted",
error_code="UnknownParameter")
else:
parameters[key] = value
#### Return if any of the parameters generated an error (showing not just the first one)
if response.status != 'OK':
return response
#### Store these final parameters for convenience
response.data['parameters'] = parameters
self.parameters = parameters
#### Now apply the filters. Order of operations is probably quite important
#### Scalar value filters probably come first like minimum_confidence, then complex logic filters
#### based on edge or node properties, and then finally maximum_results
response.info(
f"Adding a QueryEdge to Message with parameters {parameters}")
#### Make sure there's a query_graph already here
if message.query_graph is None:
message.query_graph = QueryGraph()
message.query_graph.nodes = []
message.query_graph.edges = []
if message.query_graph.edges is None:
message.query_graph.edges = []
#### Create a QEdge
qedge = QEdge()
if parameters['id'] is not None:
id = parameters['id']
else:
id = self.__get_next_free_edge_id()
qedge.id = id
#### Get the list of available node_ids
qnodes = message.query_graph.nodes
ids = {}
for qnode in qnodes:
id = qnode.id
ids[id] = 1
#### Add the source_id
if parameters['source_id'] is not None:
if parameters['source_id'] not in ids:
response.error(
f"While trying to add QEdge, there is no QNode with id {parameters['source_id']}",
error_code="UnknownSourceId")
return response
qedge.source_id = parameters['source_id']
else:
response.error(
f"While trying to add QEdge, source_id is a required parameter",
error_code="MissingSourceId")
return response
#### Add the target_id
if parameters['target_id'] is not None:
if parameters['target_id'] not in ids:
response.error(
f"While trying to add QEdge, there is no QNode with id {parameters['target_id']}",
error_code="UnknownTargetId")
return response
qedge.target_id = parameters['target_id']
else:
response.error(
f"While trying to add QEdge, target_id is a required parameter",
error_code="MissingTargetId")
return response
#### Add the type if any. Need to verify it's an allowed type. FIXME
if parameters['type'] is not None:
qedge.type = parameters['type']
#### Add it to the query_graph edge list
message.query_graph.edges.append(qedge)
#### Return the response
return response
def answer(self,
source_name,
target_label,
relationship_type,
use_json=False,
directed=False):
"""
Answer a question of the type "What proteins does drug X target" but is general:
what <node X type> does <node Y grounded> <relatioship Z> that can be answered in one hop in the KG (increasing the step size if necessary).
:param query_terms: a triple consisting of a source node name (KG neo4j node name, the target label (KG neo4j
"node label") and the relationship type (KG neo4j "Relationship type")
:param source_name: KG neo4j node name (eg "carbetocin")
:param target_label: KG node label (eg. "protein")
:param relationship_type: KG relationship type (eg. "physically_interacts_with")
:param use_json: If the answer should be in Eric's Json standardized API output format
:return: list of dictionaries containing the nodes that are one hop (along relationship type) that connect source to target.
"""
# Get label/kind of node the source is
source_label = RU.get_node_property(source_name, "label")
# Get the subgraph (all targets along relationship)
has_intermediate_node = False
try:
g = RU.return_subgraph_paths_of_type(source_name,
source_label,
None,
target_label,
[relationship_type],
directed=directed)
except CustomExceptions.EmptyCypherError:
try:
has_intermediate_node = True
g = RU.return_subgraph_paths_of_type(
source_name,
source_label,
None,
target_label, ['subclass_of', relationship_type],
directed=directed)
except CustomExceptions.EmptyCypherError:
error_message = "No path between %s and %s via relationship %s" % (
source_name, target_label, relationship_type)
error_code = "NoPathsFound"
response = FormatOutput.FormatResponse(3)
response.add_error_message(error_code, error_message)
return response
# extract the source_node_number
for node, data in g.nodes(data=True):
if data['properties']['id'] == source_name:
source_node_number = node
break
# Get all the target numbers
target_numbers = []
for node, data in g.nodes(data=True):
if data['properties']['id'] != source_name:
target_numbers.append(node)
# if there's an intermediate node, get the name
if has_intermediate_node:
neighbors = list(g.neighbors(source_node_number))
if len(neighbors) > 1:
error_message = "More than one intermediate node"
error_code = "AmbiguousPath"
response = FormatOutput.FormatResponse(3)
response.add_error_message(error_code, error_message)
return response
else:
intermediate_node = neighbors.pop()
#### If use_json not specified, then return results as a fairly plain list
if not use_json:
results_list = list()
for target_number in target_numbers:
data = g.nodes[target_number]
results_list.append({
'type':
list(set(data['labels']) - {'Base'}).pop(),
'name':
data['properties']['name'],
'desc':
data['properties']['name'],
'prob':
1
}) # All these are known to be true
return results_list
#### Else if use_json requested, return the results in the Translator standard API JSON format
else:
response = FormatOutput.FormatResponse(3) # it's a Q3 question
response.message.table_column_names = [
"source name", "source ID", "target name", "target ID"
]
source_description = g.nodes[source_node_number]['properties'][
'name']
#### Create the QueryGraph for this type of question
query_graph = QueryGraph()
source_node = QNode()
source_node.id = "n00"
source_node.curie = g.nodes[source_node_number]['properties']['id']
source_node.type = g.nodes[source_node_number]['properties'][
'category']
target_node = QNode()
target_node.id = "n01"
target_node.type = target_label
query_graph.nodes = [source_node, target_node]
edge1 = QEdge()
edge1.id = "e00"
edge1.source_id = "n00"
edge1.target_id = "n01"
edge1.type = relationship_type
query_graph.edges = [edge1]
response.message.query_graph = query_graph
#### Create a mapping dict with the source curie and the target type. This dict is used for reverse lookups by type
#### for mapping to the QueryGraph.
response._type_map = dict()
response._type_map[source_node.curie] = source_node.id
response._type_map[target_node.type] = target_node.id
response._type_map[edge1.type] = edge1.id
#### Loop over all the returned targets and put them into the response structure
for target_number in target_numbers:
target_description = g.nodes[target_number]['properties'][
'name']
if not has_intermediate_node:
subgraph = g.subgraph([source_node_number, target_number])
else:
subgraph = g.subgraph(
[source_node_number, intermediate_node, target_number])
res = response.add_subgraph(
subgraph.nodes(data=True),
subgraph.edges(data=True),
"%s and %s are connected by the relationship %s" %
(source_description, target_description,
relationship_type),
1,
return_result=True)
res.essence = "%s" % target_description # populate with essence of question result
res.essence_type = g.nodes[target_number]['properties'][
'category'] # populate with the type of the essence of question result
row_data = [] # initialize the row data
row_data.append("%s" % source_description)
row_data.append(
"%s" % g.nodes[source_node_number]['properties']['id'])
row_data.append("%s" % target_description)
row_data.append("%s" %
g.nodes[target_number]['properties']['id'])
res.row_data = row_data
return response