def make_one_hop_query():
query = build_query(
genes=["ENSEMBL:ENSG00000121879"],
therapeutic_wildcard=True,
one_hop=True,
)
with open('one_hop.json', 'w') as f_:
json.dump(query, f_)
def make_drug_wildcard_query():
for i in [1,2,5,10]:
query = build_query(
genes=["ENSEMBL:ENSG00000012048"],
disease="MONDO:0007254",
outcome=("EFO:0000714", ">=", 365*i),
therapeutic_wildcard=True,
)
with open('dw_brac1_{}yr.json'.format(i), 'w') as f_:
json.dump(query, f_)
def make_standard_probablistic_query_one_gene():
""" Build a standard probablistic query with one gene and one drug.
"""
query = build_query(
genes=["ENSEMBL:ENSG00000141510"],
therapeutic="CHEMBL:CHEMBL88",
disease="MONDO:0007254",
outcome=("EFO:0000714", ">=", 500)
)
with open('standard_one_gene.json', 'w') as f_:
json.dump(query, f_)
def make_gene_wildcard_query():
""" Builds a gene wildcard query
"""
query = build_query(
therapeutic="CHEMBL:CHEMBL88",
disease="MONDO:0007254",
outcome=("EFO:0000714", ">=", 500),
num_gene_wildcards=1,
)
with open('gene_wildcard.json', 'w') as f_:
json.dump(query, f_)
# Set number of queries to build
NUM_QUERIES = 10
# Set seed
random.seed(111)
# Get client
#client = get_client()
# Get curies
logger.info('Getting curies.')
curies = TrapiInterface().get_curies()
#curies = client.curies()
logger.info('Got curies.')
# Build all simple single gene, single drug, breast cancer, survival queries.
queries = []
for _ in range(NUM_QUERIES):
drug = [random.choice(list(curies["biolink:Drug"].keys()))]
q = build_query(
therapeutic=drug,
num_gene_wildcards=1,
one_hop=True,
)
print(json.dumps(q, indent=2))
queries.append(q)
# Pickle the queries
with open('random_gene_one_hop_queries.pk', 'wb') as f_:
pickle.dump(queries, f_)
# Set number of queries to build
NUM_QUERIES = 10
# Set seed
random.seed(111)
# Get client
#client = get_client()
# Get curies
logger.info('Getting curies.')
curies = TrapiInterface().get_curies()
#curies = client.curies()
logger.info('Got curies.')
# Build all simple single gene, single drug, breast cancer, survival queries.
queries = []
for _ in range(NUM_QUERIES):
genes = [random.choice(list(curies["biolink:Gene"].keys()))]
q = build_query(
genes=genes,
therapeutic_wildcard=True,
one_hop=True,
)
print(json.dumps(q, indent=2))
queries.append(q)
# Pickle the queries
with open('random_drug_one_hop_queries.pk', 'wb') as f_:
pickle.dump(queries, f_)
def _answer_query_using_CHP_client(
self, query_graph: QueryGraph,
log: ARAXResponse) -> QGOrganizedKnowledgeGraph:
qedge_key = next(qedge_key for qedge_key in query_graph.edges)
log.debug(
f"Processing query results for edge {qedge_key} by using CHP client"
)
final_kg = QGOrganizedKnowledgeGraph()
gene_label_list = ['gene']
drug_label_list = ['drug', 'chemicalsubstance']
# use for checking the requirement
source_pass_nodes = None
source_category = None
target_pass_nodes = None
target_category = None
qedge = query_graph.edges[qedge_key]
source_qnode_key = qedge.subject
target_qnode_key = qedge.object
source_qnode = query_graph.nodes[source_qnode_key]
target_qnode = query_graph.nodes[target_qnode_key]
# check if both ends of edge have no curie
if (source_qnode.id is None) and (target_qnode.id is None):
log.error(f"Both ends of edge {qedge_key} are None",
error_code="BadEdge")
return final_kg
# check if the query nodes are drug or disease
if source_qnode.id is not None:
if type(source_qnode.id) is str:
source_pass_nodes = [source_qnode.id]
else:
source_pass_nodes = source_qnode.id
has_error, pass_nodes, not_pass_nodes = self._check_id(
source_qnode.id, log)
if has_error:
return final_kg
else:
if len(not_pass_nodes) == 0 and len(pass_nodes) != 0:
source_pass_nodes = pass_nodes
elif len(not_pass_nodes) != 0 and len(pass_nodes) != 0:
source_pass_nodes = pass_nodes
if len(not_pass_nodes) == 1:
log.warning(
f"The curie id of {not_pass_nodes[0]} is not allowable based on CHP client"
)
else:
log.warning(
f"The curie ids of these nodes {not_pass_nodes} are not allowable based on CHP client"
)
else:
if type(source_qnode.id) is str:
log.error(
f"The curie id of {source_qnode.id} is not allowable based on CHP client",
error_code="NotAllowable")
return final_kg
else:
log.error(
f"The curie ids of {source_qnode.id} are not allowable based on CHP client",
error_code="NotAllowable")
return final_kg
else:
category = source_qnode.category[0].replace(
'biolink:', '').replace('_', '').lower()
source_category = category
if (category in drug_label_list) or (category in gene_label_list):
source_category = category
else:
log.error(
f"The category of query node {source_qnode_key} is unsatisfiable. It has to be drug/chemical_substance or gene",
error_code="CategoryError")
return final_kg
if target_qnode.id is not None:
if type(target_qnode.id) is str:
target_pass_nodes = [target_qnode.id]
else:
target_pass_nodes = target_qnode.id
has_error, pass_nodes, not_pass_nodes = self._check_id(
target_qnode.id, log)
if has_error:
return final_kg
else:
if len(not_pass_nodes) == 0 and len(pass_nodes) != 0:
target_pass_nodes = pass_nodes
elif len(not_pass_nodes) != 0 and len(pass_nodes) != 0:
target_pass_nodes = pass_nodes
if len(not_pass_nodes) == 1:
log.warning(
f"The curie id of {not_pass_nodes[0]} is not allowable based on CHP client"
)
else:
log.warning(
f"The curie ids of these nodes {not_pass_nodes} are not allowable based on CHP client"
)
else:
if type(target_qnode.id) is str:
log.error(
f"The curie id of {target_qnode.id} is not allowable based on CHP client",
error_code="CategoryError")
return final_kg
else:
log.error(
f"The curie ids of {target_qnode.id} are not allowable based on CHP client",
error_code="CategoryError")
return final_kg
else:
category = target_qnode.category[0].replace(
'biolink:', '').replace('_', '').lower()
target_category = category
if (category in drug_label_list) or (category in gene_label_list):
target_category = category
else:
log.error(
f"The category of query node {target_qnode_key} is unsatisfiable. It has to be drug/chemical_substance or gene",
error_code="CategoryError")
return final_kg
if (source_pass_nodes is None) and (target_pass_nodes is None):
return final_kg
elif (source_pass_nodes is not None) and (target_pass_nodes
is not None):
source_dict = dict()
target_dict = dict()
if source_pass_nodes[0] in self.allowable_drug_curies:
source_category_temp = 'drug'
else:
source_category_temp = 'gene'
if target_pass_nodes[0] in self.allowable_drug_curies:
target_category_temp = 'drug'
else:
target_category_temp = 'gene'
if source_category_temp == target_category_temp:
log.error(
f"The query nodes in both ends of edge are the same type which is {source_category_temp}",
error_code="CategoryError")
return final_kg
else:
for (source_curie, target_curie) in itertools.product(
source_pass_nodes, target_pass_nodes):
if source_category_temp == 'drug':
source_curie_temp = source_curie.replace(
'CHEMBL.COMPOUND:', 'CHEMBL:')
# Let's build a simple single query
q = build_query(genes=[target_curie],
therapeutic=source_curie_temp,
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=',
self.CHP_survival_threshold))
response = self.client.query(q)
max_probability = self.client.get_outcome_prob(
response)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
target_curie, source_curie, "paired_with",
max_probability)
else:
target_curie_temp = target_curie.replace(
'CHEMBL.COMPOUND:', 'CHEMBL:')
# Let's build a simple single query
q = build_query(genes=[source_curie],
therapeutic=target_curie_temp,
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=',
self.CHP_survival_threshold))
response = self.client.query(q)
max_probability = self.client.get_outcome_prob(
response)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
source_curie, target_curie, "paired_with",
max_probability)
source_dict[source_curie] = source_qnode_key
target_dict[target_curie] = target_qnode_key
# Finally add the current edge to our answer knowledge graph
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
# Add the nodes to our answer knowledge graph
if len(source_dict) != 0:
for source_curie in source_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
source_curie)
final_kg.add_node(swagger_node_key, swagger_node,
source_dict[source_curie])
if len(target_dict) != 0:
for target_curie in target_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
target_curie)
final_kg.add_node(swagger_node_key, swagger_node,
target_dict[target_curie])
return final_kg
elif source_pass_nodes is not None:
source_dict = dict()
target_dict = dict()
if source_pass_nodes[0] in self.allowable_drug_curies:
source_category_temp = 'drug'
else:
source_category_temp = 'gene'
if target_category in drug_label_list:
target_category_temp = 'drug'
else:
target_category_temp = 'gene'
if source_category_temp == target_category_temp:
log.error(
f"The query nodes in both ends of edge are the same type which is {source_category_temp}",
error_code="CategoryError")
return final_kg
else:
if source_category_temp == 'drug':
for source_curie in source_pass_nodes:
genes = [
curie for curie in self.allowable_gene_curies
if self.synonymizer.get_canonical_curies(curie)
[curie] is not None and target_category in [
category.replace('biolink:', '').replace(
'_', '').lower() for category in list(
self.synonymizer.get_canonical_curies(
curie, return_all_categories=True)
[curie]['all_categories'].keys())
]
]
therapeutic = source_curie.replace(
'CHEMBL.COMPOUND:', 'CHEMBL:')
disease = 'MONDO:0007254'
outcome = ('EFO:0000714', '>=',
self.CHP_survival_threshold)
queries = []
for gene in genes:
queries.append(
build_query(
genes=[gene],
therapeutic=therapeutic,
disease=disease,
outcome=outcome,
))
# use the query_all endpoint to run the batch of queries
res = self.client.query_all(queries)
for result, gene in zip(res["message"], genes):
prob = self.client.get_outcome_prob(result)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
gene, source_curie, "paired_with", prob)
source_dict[source_curie] = source_qnode_key
target_dict[gene] = target_qnode_key
# Finally add the current edge to our answer knowledge graph
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
else:
for source_curie in source_pass_nodes:
genes = [source_curie]
therapeutic = [
curie.replace('CHEMBL.COMPOUND:', 'CHEMBL:')
for curie in self.allowable_drug_curies
if self.synonymizer.get_canonical_curies(
curie.replace('CHEMBL:', 'CHEMBL.COMPOUND:'))
[curie.replace('CHEMBL:', 'CHEMBL.COMPOUND:')]
is not None and target_category in [
category.replace('biolink:', '').replace(
'_', '').lower()
for category in list(
self.synonymizer.get_canonical_curies(
curie.replace('CHEMBL:',
'CHEMBL.COMPOUND:'),
return_all_categories=True)[
curie.replace(
'CHEMBL:', 'CHEMBL.COMPOUND:')]
['all_categories'].keys())
]
]
disease = 'MONDO:0007254'
outcome = ('EFO:0000714', '>=',
self.CHP_survival_threshold)
queries = []
for drug in therapeutic:
queries.append(
build_query(
genes=genes,
therapeutic=drug,
disease=disease,
outcome=outcome,
))
# use the query_all endpoint to run the batch of queries
res = self.client.query_all(queries)
for result, drug in zip(res["message"], therapeutic):
drug = drug.replace('CHEMBL:', 'CHEMBL.COMPOUND:')
prob = self.client.get_outcome_prob(result)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
source_curie, drug, "paired_with", prob)
source_dict[source_curie] = source_qnode_key
target_dict[drug] = target_qnode_key
# Finally add the current edge to our answer knowledge graph
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
# Add the nodes to our answer knowledge graph
if len(source_dict) != 0:
for source_curie in source_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
source_curie)
final_kg.add_node(swagger_node_key, swagger_node,
source_dict[source_curie])
if len(target_dict) != 0:
for target_curie in target_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
target_curie)
final_kg.add_node(swagger_node_key, swagger_node,
target_dict[target_curie])
return final_kg
else:
source_dict = dict()
target_dict = dict()
if target_pass_nodes[0] in self.allowable_drug_curies:
target_category_temp = 'drug'
else:
target_category_temp = 'gene'
if source_category in drug_label_list:
source_category_temp = 'drug'
else:
source_category_temp = 'gene'
if source_category_temp == target_category_temp:
log.error(
f"The query nodes in both ends of edge are the same type which is {source_category_temp}",
error_code="CategoryError")
return final_kg
else:
if target_category_temp == 'drug':
for target_curie in target_pass_nodes:
genes = [
curie for curie in self.allowable_gene_curies
if self.synonymizer.get_canonical_curies(curie)
[curie] is not None and source_category in [
category.replace('biolink:', '').replace(
'_', '').lower() for category in list(
self.synonymizer.get_canonical_curies(
curie, return_all_categories=True)
[curie]['all_categories'].keys())
]
]
therapeutic = target_curie.replace(
'CHEMBL.COMPOUND:', 'CHEMBL:')
disease = 'MONDO:0007254'
outcome = ('EFO:0000714', '>=',
self.CHP_survival_threshold)
queries = []
for gene in genes:
queries.append(
build_query(
genes=[gene],
therapeutic=therapeutic,
disease=disease,
outcome=outcome,
))
# use the query_all endpoint to run the batch of queries
res = self.client.query_all(queries)
for result, gene in zip(res["message"], genes):
prob = self.client.get_outcome_prob(result)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
gene, target_curie, "paired_with", prob)
source_dict[gene] = source_qnode_key
target_dict[target_curie] = target_qnode_key
# Finally add the current edge to our answer knowledge graph
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
else:
for target_curie in target_pass_nodes:
genes = [target_curie]
therapeutic = [
curie.replace('CHEMBL.COMPOUND:', 'CHEMBL:')
for curie in self.allowable_drug_curies
if self.synonymizer.get_canonical_curies(
curie.replace('CHEMBL:', 'CHEMBL.COMPOUND:'))
[curie.replace('CHEMBL:', 'CHEMBL.COMPOUND:')]
is not None and source_category in [
category.replace('biolink:', '').replace(
'_', '').lower()
for category in list(
self.synonymizer.get_canonical_curies(
curie.replace('CHEMBL:',
'CHEMBL.COMPOUND:'),
return_all_categories=True)[
curie.replace(
'CHEMBL:', 'CHEMBL.COMPOUND:')]
['all_categories'].keys())
]
]
disease = 'MONDO:0007254'
outcome = ('EFO:0000714', '>=',
self.CHP_survival_threshold)
queries = []
for drug in therapeutic:
queries.append(
build_query(
genes=genes,
therapeutic=drug,
disease=disease,
outcome=outcome,
))
# use the query_all endpoint to run the batch of queries
res = self.client.query_all(queries)
for result, drug in zip(res["message"], therapeutic):
drug = drug.replace('CHEMBL:', 'CHEMBL.COMPOUND:')
prob = self.client.get_outcome_prob(result)
swagger_edge_key, swagger_edge = self._convert_to_swagger_edge(
target_curie, drug, "paired_with", prob)
source_dict[drug] = source_qnode_key
target_dict[target_curie] = target_qnode_key
# Finally add the current edge to our answer knowledge graph
final_kg.add_edge(swagger_edge_key, swagger_edge,
qedge_key)
# Add the nodes to our answer knowledge graph
if len(source_dict) != 0:
for source_curie in source_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
source_curie)
final_kg.add_node(swagger_node_key, swagger_node,
source_dict[source_curie])
if len(target_dict) != 0:
for target_curie in target_dict:
swagger_node_key, swagger_node = self._convert_to_swagger_node(
target_curie)
final_kg.add_node(swagger_node_key, swagger_node,
target_dict[target_curie])
return final_kg
import pickle
import numpy as np
from chp.trapi_interface import TrapiInterface
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)
# Get curies
logger.info('Getting curies.')
curies = TrapiInterface().get_curies()
logger.info('Got curies.')
survival_times = list(np.linspace(350, 5000, 10))
genes = [gene for gene in curies["gene"]]
queries = []
for gene_curie in tqdm.tqdm(genes, desc='Building gene queries', leave=False):
for st in survival_times:
queries.append(
build_query(
genes=[gene_curie],
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=', st),
))
# Pickle the queries
with open('simple_queries_1.pk', 'wb') as f_:
pickle.dump(queries, f_)
logger.setLevel(logging.INFO)
# Get curies
logger.info('Getting curies.')
curies = TrapiInterface().get_curies()
#curies = client.curies()
logger.info('Got curies.')
# Build queries
queries = []
# One gene curie
queries.append(
build_query(
genes=['ENSEMBL:ENSG00000155657'],
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=', 1000),
))
# One gene one drug curie
queries.append(
build_query(
genes=['ENSEMBL:ENSG00000155657'],
therapeutic='CHEMBL:CHEMBL83',
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=', 1000),
))
# Two gene one drug curie
queries.append(
build_query(
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)
# Get curies
logger.info('Getting curies.')
curies = TrapiInterface().get_curies()
logger.info('Got curies.')
survival_times = list(np.linspace(350, 5000, 10))
genes = [gene for gene in curies["gene"]]
drugs = [drug for drug in curies["chemical_substance"]]
queries = []
for gene_curie in tqdm.tqdm(genes, desc='Building gene queries', leave=False):
for drug_curie in drugs:
for st in survival_times:
queries.append(
build_query(
genes=[gene_curie],
therapeutic=drug_curie,
disease='MONDO:0007254',
outcome=('EFO:0000714', '>=', st),
)
)
print(len(queries))
# Pickle the queries
with open('all_simple_queries.pk', 'wb') as f_:
pickle.dump(queries, f_)
