def _extract_chp_query(self, query, query_type=None):
evidence = {}
dynamic_targets = {}
# check edge for source and target
edge_key = list(query["query_graph"]["edges"].keys())[0]
edge = query["query_graph"]['edges'][edge_key]
subject = edge['subject']
obj = edge['object']
# Get non-wildcard node
if query_type == 'gene':
drug_curie = query["query_graph"]['nodes'][obj]['id']
evidence['_{}'.format(drug_curie)] = 'True'
elif query_type == 'drug':
gene_curie = query["query_graph"]['nodes'][obj]['id']
evidence['_{}'.format(gene_curie)] = 'True'
# default survival time
dynamic_targets.update(self.default_survival_target)
truth_target = ('EFO:0000714', '{} {}'.format(self.default_survival_target["EFO:0000714"]["op"],
self.default_survival_target["EFO:0000714"]["value"]))
chp_query = Query(evidence=evidence,
targets=None,
dynamic_evidence=None,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
chp_query.query_id = query["query_id"] if 'query_id' in query else None
return chp_query
def _extract_chp_query(self, query, query_type=None):
evidence = {}
dynamic_targets = {}
if len(query["query_graph"]['nodes']) > 2 or len(
query["query_graph"]['edges']) > 1:
sys.exit('1 hop quries can only have 2 nodes and 1 edge')
# check edge for source and target
edge_key = list(query["query_graph"]["edges"].keys())[0]
edge = query["query_graph"]['edges'][edge_key]
if 'subject' not in edge.keys() or 'object' not in edge.keys():
sys.exit(
'Edge must have both a \'subject\' and and \'object\' key')
subject = edge['subject']
obj = edge['object']
# Get non-wildcard node
if query_type == 'gene':
if query["query_graph"]['nodes'][subject][
'category'] != BIOLINK_GENE:
sys.exit('Subject node must be \'category\' {}'.format(
BIOLINK_GENE))
drug_curie = query["query_graph"]['nodes'][obj]['id']
if drug_curie not in self.curies[BIOLINK_DRUG]:
sys.exit('Invalid CHEMBL Identifier. Must be CHEMBL:<ID>')
evidence['_{}'.format(drug_curie)] = 'True'
elif query_type == 'drug':
if query["query_graph"]['nodes'][subject][
'category'] != BIOLINK_DRUG:
sys.exit('Subject node must be \'category\' {}'.format(
BIOLINK_DRUG))
gene_curie = query["query_graph"]['nodes'][obj]['id']
if gene_curie not in self.curies[BIOLINK_GENE]:
sys.exit('Invalid ENSEMBL Identifier. Must be ENSEMBL:<ID>')
evidence['_{}'.format(gene_curie)] = 'True'
# default survival time
dynamic_targets.update(self.default_survival_target)
truth_target = ('EFO:0000714', '{} {}'.format(
self.default_survival_target["EFO:0000714"]["op"],
self.default_survival_target["EFO:0000714"]["value"]))
chp_query = Query(evidence=evidence,
targets=None,
dynamic_evidence=None,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
chp_query.query_id = query["query_id"] if 'query_id' in query else None
return chp_query
def _extract_chp_query(self, query, query_type):
evidence = {}
targets = []
dynamic_evidence = {}
dynamic_targets = {}
# ensure we are using all nodes/edges
total_nodes = 0
total_edges = 0
# get phenotype node
targets = list()
acceptable_target_curies = ['EFO:0000714']
self.implicit_survival_node = False
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_PHENOTYPIC_FEATURE and node['id'] in acceptable_target_curies:
target_id = node_key
total_nodes += 1
if total_nodes == 0:
# Use Default Survival
self.implicit_survival_node = True
total_nodes += 1
#acceptable_target_curies_print = ','.join(acceptable_target_curies)
#sys.exit("Survival Node not found. Node category must be '{}' and id must be in: {}".format(BIOLINK_PHENOTYPIC_FEATURE,
# acceptable_target_curies_print))
elif total_nodes > 1:
sys.exit('Too many target nodes')
# get disease node info and ensure only 1 disease:
acceptable_disease_curies = ['MONDO:0007254']
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_DISEASE and node['id'] in acceptable_disease_curies:
disease_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_DISEASE_TO_PHENOTYPIC_FEATURE_PREDICATE and edge['subject'] == disease_id and edge['object'] == target_id:
if 'properties' in edge.keys():
days = edge['properties']['days']
qualifier = edge['properties']['qualifier']
else:
days = 970
qualifier = '>='
total_edges += 1
if total_edges > 1:
sys.exit('Disease has too many outgoing edges')
total_nodes += 1
if self.implicit_survival_node:
days=970
qualifier = '>='
total_edges += 1
if total_nodes == 1:
acceptable_disease_curies_print = ','.join(acceptable_disease_curies)
sys.exit("Disease node not found. Node type must be '{}' and curie must be in: {}".format(BIOLINK_DISEASE,
acceptable_disease_curies_print))
elif total_nodes > 2:
sys.exit('Too many disease nodes')
# set BKB target
dynamic_targets['EFO:0000714'] = {
"op": qualifier,
"value": days,
}
truth_target = ('EFO:0000714', '{} {}'.format(qualifier, days))
# get evidence
for node_key in query["query_graph"]['nodes'].keys():
# genes
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_GENE:
# check for appropriate gene node structure
gene_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_GENE_TO_DISEASE_PREDICATE and edge['subject'] == gene_id and edge['object'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit("Gene and disease edge not found. Edge type must be '{}'".format(BIOLINK_GENE_TO_DISEASE_PREDICATE))
elif total_edges > total_nodes:
sys.exit('Gene has too many outgoing edges')
# check for appropriate gene node curie
if query_type != 'gene':
gene_curie = node['id']
if gene_curie in self.curies[BIOLINK_GENE]:
gene = gene_curie
else:
sys.exit('Invalid ENSEMBL Identifier. Must be in form ENSEMBL:<ID>.')
evidence["_" + gene] = 'True'
total_nodes += 1
# drugs
if node['category'] == BIOLINK_DRUG:
# check for appropriate drug node structure
drug_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_CHEMICAL_TO_DISEASE_OR_PHENOTYPIC_FEATURE_PREDICATE and edge['subject'] == drug_id and edge['object'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit("Drug and disease edge not found. Edge type must be '{}'".format(BIOLINK_CHEMICAL_TO_DISEASE_OR_PHENOTYPIC_FEATURE_PREDICATE))
elif total_edges > total_nodes:
sys.exit('Drug has too many outgoing edges')
# check for appropriate drug node curie
if query_type != 'drug':
drug_curie = node['id']
if drug_curie in self.curies[BIOLINK_DRUG]:
drug = drug_curie
else:
sys.exit('Invalid CHEMBL Identifier: {}. Must be in form CHEMBL:<ID>'.format(drug_curie))
evidence['_' + drug] = 'True'
total_nodes += 1
# Temporary solution to no evidence linking
if len(evidence.keys()) == 0 and len(dynamic_evidence.keys()) == 0:
self.no_evidence_probability_check = True
else:
self.no_evidence_probability_check = False
# produce BKB query
chp_query = Query(
evidence=evidence,
targets=targets,
dynamic_evidence=dynamic_evidence,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
chp_query.query_id = query["query_id"] if 'query_id' in query else None
return chp_query
def _extract_chp_query(self, query, query_type=None):
evidence = {}
targets = []
dynamic_evidence = {}
dynamic_targets = {}
# ensure we are using all nodes/edges
total_nodes = 0
total_edges = 0
# get phenotype node
targets = list()
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_PHENOTYPIC_FEATURE:
target_id = node_key
total_nodes += 1
# get disease node info and ensure only 1 disease:
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_DISEASE:
disease_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_DISEASE_TO_PHENOTYPIC_FEATURE_PREDICATE and edge[
'subject'] == disease_id and edge[
'object'] == target_id:
if 'properties' in edge.keys():
days = edge['properties']['days']
qualifier = edge['properties']['qualifier']
else:
days = 970
qualifier = '>='
total_edges += 1
total_nodes += 1
# set BKB target
dynamic_targets[node["id"]] = {
"op": qualifier,
"value": days,
}
truth_target = (node["id"], '{} {}'.format(qualifier, days))
# get evidence
for node_key in query["query_graph"]['nodes'].keys():
# genes
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_GENE:
# check for appropriate gene node structure
gene_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_GENE_TO_DISEASE_PREDICATE and edge[
'subject'] == gene_id and edge[
'object'] == disease_id:
total_edges += 1
# check for appropriate gene node curie
gene_curie = node['id']
gene = gene_curie
evidence["_" + gene] = 'True'
total_nodes += 1
# drugs
if node['category'] == BIOLINK_DRUG:
# check for appropriate drug node structure
drug_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_CHEMICAL_TO_DISEASE_OR_PHENOTYPIC_FEATURE_PREDICATE and edge[
'subject'] == drug_id and edge[
'object'] == disease_id:
total_edges += 1
# check for appropriate drug node curie
drug_curie = node['id']
drug = drug_curie
evidence[node["id"]] = 'True'
total_nodes += 1
# produce BKB query
chp_query = Query(evidence=evidence,
targets=targets,
dynamic_evidence=dynamic_evidence,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
chp_query.query_id = query["query_id"] if 'query_id' in query else None
return chp_query
def _extract_chp_query(self, query, query_type=None):
evidence = {}
targets = []
dynamic_evidence = {}
dynamic_targets = {}
# ensure we are using all nodes/edges
total_nodes = 0
total_edges = 0
# get phenotype node
targets = list()
acceptable_target_curies = ['EFO:0000714']
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_PHENOTYPIC_FEATURE and node[
'id'] in acceptable_target_curies:
target_id = node_key
total_nodes += 1
if total_nodes == 0:
acceptable_target_curies_print = ','.join(acceptable_target_curies)
sys.exit(
'Survival Node not found. Node category must be \'biolink:PhenotypicFeature\' and id must be in: '
+ acceptable_target_curies_print)
elif total_nodes > 1:
sys.exit('Too many target nodes')
# get disease node info and ensure only 1 disease:
acceptable_disease_curies = ['MONDO:0007254']
for node_key in query["query_graph"]['nodes'].keys():
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_DISEASE and node[
'id'] in acceptable_disease_curies:
disease_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_DISEASE_TO_PHENOTYPIC_FEATURE_PREDICATE and edge[
'subject'] == disease_id and edge[
'object'] == target_id:
if 'properties' in edge.keys():
days = edge['properties']['days']
qualifier = edge['properties']['qualifier']
else:
days = 970
qualifier = '>='
total_edges += 1
if total_edges == 0:
sys.exit(
'Disease and target edge not found. Edge type must be \'biolink:DiseaseToPhenotypicFeatureAssociation\''
)
elif total_edges > 1:
sys.exit('Disease has too many outgoing edges')
total_nodes += 1
if total_nodes == 1:
acceptable_disease_curies_print = ','.join(
acceptable_disease_curies)
sys.exit(
'Disease node not found. Node type must be \'biolink:Disease\' and curie must be in: '
+ acceptable_disease_curies_print)
elif total_nodes > 2:
sys.exit('Too many disease nodes')
# set BKB target
dynamic_targets[node["id"]] = {
"op": qualifier,
"value": days,
}
truth_target = (node["id"], '{} {}'.format(qualifier, days))
# get evidence
for node_key in query["query_graph"]['nodes'].keys():
# genes
node = query["query_graph"]['nodes'][node_key]
if node['category'] == BIOLINK_GENE:
# check for appropriate gene node structure
gene_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_GENE_TO_DISEASE_PREDICATE and edge[
'subject'] == gene_id and edge[
'object'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit(
"Gene and disease edge not found. Edge type must be '{}'"
.format(BIOLINK_GENE_TO_DISEASE_PREDICATE))
elif total_edges > total_nodes:
sys.exit('Gene has too many outgoing edges')
# check for appropriate gene node curie
gene_curie = node['id']
if gene_curie in self.curies[BIOLINK_GENE]:
gene = gene_curie
else:
sys.exit(
'Invalid ENSEMBL Identifier. Must be in form ENSEMBL:<ID>.'
)
evidence["_" + gene] = 'True'
total_nodes += 1
# drugs
if node['category'] == BIOLINK_DRUG:
# check for appropriate drug node structure
drug_id = node_key
for edge_key in query["query_graph"]['edges'].keys():
edge = query["query_graph"]['edges'][edge_key]
if edge['predicate'] == BIOLINK_CHEMICAL_TO_DISEASE_OR_PHENOTYPIC_FEATURE_PREDICATE and edge[
'subject'] == drug_id and edge[
'object'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit(
"Drug and disease edge not found. Edge type must be '{}'"
.format(
BIOLINK_CHEMICAL_TO_DISEASE_OR_PHENOTYPIC_FEATURE_PREDICATE
))
elif total_edges > total_nodes:
sys.exit('Drug has too many outgoing edges')
# check for appropriate drug node curie
drug_curie = node['id']
if drug_curie in self.curies[BIOLINK_DRUG]:
drug = drug_curie
else:
sys.exit(
'Invalid CHEMBL Identifier: {}. Must be in form CHEMBL:<ID>'
.format(drug_curie))
evidence[node["id"]] = 'True'
total_nodes += 1
if total_nodes != len(
query["query_graph"]['nodes']) or total_edges != len(
query["query_graph"]['edges']):
sys.exit('There are extra components in the provided QG structure')
# produce BKB query
chp_query = Query(evidence=evidence,
targets=targets,
dynamic_evidence=dynamic_evidence,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
chp_query.query_id = query["query_id"] if 'query_id' in query else None
return chp_query