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 buildQueries(self):
# get evidence
evidence = dict()
meta_evidence = list()
for node in self.qg['nodes']:
if node['type'] == 'Gene':
gene_curie = node['curie']
try:
gene = self.gene_curie_dict[gene_curie]
except:
sys.exit(
'Invalid ENSEMBL Identifier. Must be in form ENSEMBL:<ID>.'
)
evidence["mut_" + gene] = 'True'
if node['type'] == 'Drug':
drug_curie = node['curie']
try:
drug = self.drug_curie_dict[drug_curie]
except:
sys.exit(
'Invalid CHEMBL Identifier. Must be in form CHEMBL:<ID>'
)
meta_evidence.append(('Drug_Name(s)', '==', drug))
# get target
targets = list()
for edge in self.qg['edges']:
if edge['type'] == 'causes':
if 'onset_qualifier' in list(edge.keys()):
days = edge['onset_qualifier']
# default value - needs to be documented in openAPI?
else:
days = 970
targets.append(('Survival_Time', '>=', days))
if len(list(evidence.keys())) + len(meta_evidence) > 1:
sys.exit('More than 1 piece of evidence')
if len(list(evidence.keys())) + len(meta_evidence) == 0:
sys.exit('No evidence provided')
if len(list(evidence.keys())) > 0:
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
elif len(meta_evidence) > 0:
query = Query(evidence=None,
targets=[],
meta_evidence=meta_evidence,
meta_targets=targets,
type='updating')
else:
sys.exit('Problem in constructing BKB query')
self.chp_query = query
return query
def run_synthetic_prob_queries(self, fused_bkbs, patient_dicts):
""" Each patient set two queries must be run:
1.) P(survival_time >= 1000 | gene & drug)
2.) P(survival_time >= 1000 | gene)
The probabilities for each set are returned in a list of
dictionaries indexed by 'drug' and 'no_drug'.
:param fused_bkbs: a list of fused AXLE bkbs
:type fused_bkbs: list
:param patient_dicts: a list of patient dict
:type patient_dicts: list
:return query_responses: a list of truth probability
assignments.
:rtype query_responses: list
"""
query_responses = []
for i in range(0, 11):
# with drug
reasoner = Reasoner(fused_bkb=fused_bkbs[i],
patient_data=patient_dicts[i])
gene_evidence = {'mut_RAF1': 'True'}
query_drug = Query(evidence=gene_evidence,
targets=list(),
meta_evidence=[('drug_curies', '==',
'CYCLOPHOSPHAMIDE')],
meta_targets=[('survival_time', '>=', 1000)],
type='updating')
query_drug1 = reasoner.analyze_query(copy.deepcopy(query_drug),
save_dir=None,
target_strategy='explicit',
interpolation='standard')
truth_assignment_drug, f_norm, t_unnorm, f_unnorm = self.get_synthetic_query_probs(
query_drug1)
# with no drug
reasoner = Reasoner(fused_bkb=fused_bkbs[i],
patient_data=patient_dicts[i])
query_no_drug = Query(evidence=gene_evidence,
targets=list(),
meta_evidence=None,
meta_targets=[('survival_time', '>=', 1000)],
type='updating')
query_no_drug = reasoner.analyze_query(query_no_drug,
save_dir=None,
target_strategy='explicit',
interpolation='standard')
truth_assignment_no_drug, f_norm, t_unnorm, f_unnorm = self.get_synthetic_query_probs(
query_no_drug)
# answers
query_responses.append({
'drug': truth_assignment_drug,
'no_drug': truth_assignment_no_drug
})
return query_responses
def _extract_chp_query(self, message, message_type):
evidence = {}
dynamic_targets = {}
dynamic_evidence = {}
if message_type == 'standard':
# Setup gene and drug evidence
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[
0] == BIOLINK_GENE_ENTITY or qnode.categories[
0] == BIOLINK_DRUG_ENTITY:
evidence['_{}'.format(qnode.ids[0])] = 'True'
elif message_type == 'gene':
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[0] == BIOLINK_DRUG_ENTITY:
#dynamic_evidence[qnode.ids[0]] = {
# "op": '==',
# "value": 'True',
# }
evidence['_{}'.format(qnode.ids[0])] = 'True'
elif message_type == 'drug':
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[0] == BIOLINK_GENE_ENTITY:
#dynamic_evidence[qnode.ids[0]] = {
# "op": '==',
# "value": 'True',
# }
evidence['_{}'.format(qnode.ids[0])] = 'True'
# Grab edge
for qedge_id, qedge in message.query_graph.edges.items():
break
# Process predicate proxy
dynamic_targets = self._process_predicate_proxy(qedge)
# Process predicate context
_evidence, _dynamic_evidence = self._process_predicate_context(
qedge, message_type)
evidence.update(_evidence)
dynamic_evidence.update(_dynamic_evidence)
#TODO: Probably need a more robust solution for when no context is provided in wildcard queries and you need it.
#if len(evidence) == 0:
# raise ValueError('Did not supply context with a query that required context.')
target = list(dynamic_targets.keys())[0]
truth_target = (target,
'{} {}'.format(dynamic_targets[target]["op"],
dynamic_targets[target]["value"]))
chp_query = Query(evidence=evidence,
targets=None,
dynamic_evidence=dynamic_evidence,
dynamic_targets=dynamic_targets,
type='updating')
# Set some other helpful attributes
chp_query.truth_target = truth_target
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 buildQueries(self):
""" Assumes Query Graph of structure: Disease -> |Intermediate Nodes, i.e. Genes, Drugs, etc.| -> UpdateTargetNode
- Update Target Node is designated by a 't' label in the QG, i.e. t1, t2, etc.
- The beginning disease node tells us which datasets to use.
- The intermediate nodes dictate the evidence to use during updating.
"""
queries = []
evidence = dict()
for node in self.qg['nodes']:
if node['type'] == 'Gene':
gene_curie = node['curie']
try:
gene = self.gene_curie_dict[gene_curie]
except:
sys.exit('Invalid ENSEMBL Identifier. Must be in form ENSEMBL:<ID>.')
evidence["mut_" + gene] = 'True'
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=self.probability_targets,
type='updating')
queries.append(query)
self.chp_query = query
return queries
def buildQueries(self):
evidence = dict()
targets = list()
acceptable_target_curies = ['EFO:0000714']
for node in self.qg['nodes']:
if node['type'] == 'Drug':
drug_curie = node['curie']
try:
self.drug = self.drug_curie_dict[drug_curie]
except:
sys.exit(
'Invalid CHEMBL Identifier. Must be in form CHEMBL:<ID>'
)
evidence['drug_{}'.format(self.drug)] = 'True'
for edge in self.qg['edges']:
if edge['type'] == 'chemical_to_disease_or_phenotypic_feature_association':
if 'value' in edge.keys():
self.days = edge['value']
else:
self.days = 970
targets.append(('Survival_Time', '>=', self.days))
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
self.chp_query = query
return query
def test_joint_reasoner_one_gene(self):
# Specify evidence
evidence = {'ENSEMBL:ENSG00000155657': 'True'}
# Specify targets
dynamic_targets = {"EFO:0000714": {"op": '>=', "value": 1000}}
# Setup query
query = Query(evidence=evidence, dynamic_targets=dynamic_targets)
query = self.joint_reasoner.run_query(query)
def test_dynamic_reasoner_one_gene(self):
# Specify evidence
evidence = {'_ENSEMBL:ENSG00000155657': 'True'}
# Specify targets
dynamic_targets = {"EFO:0000714": {"op": '>=', "value": 1000}}
# Setup query
query = Query(evidence=evidence, dynamic_targets=dynamic_targets)
query = self.dynamic_reasoner.run_query(query)
query.result.summary(include_contributions=False)
def test_dynamic_reasoner_one_drug_survival(self):
# Specify evidence
evidence = {
'_CHEMBL:CHEMBL83': 'True',
}
# Specify targets
dynamic_targets = {"EFO:0000714": {"op": '>=', "value": 1000}}
# Setup query
query = Query(evidence=evidence, dynamic_targets=dynamic_targets)
query = self.dynamic_reasoner.run_query(query, bkb_type='drug')
query.result.summary(include_contributions=False)
def run(self, i=0):
if i == 0:
print('Welcome to the BKB Pathways Driver.')
input('Press any key to begin reasoning...')
print("Let's build a query!")
meta_evidence = self.chooseDemoEvidence()
evidence = self.chooseStandardEvidence()
meta_targets = self.chooseDemoTargets()
targets = self.chooseStandardTargets()
while True:
print('Choose reasoning Type:\n1)\tRevision\n2)\tUpdating')
reason_type = int(input('Your Choice: '))
if reason_type == 1:
reason_type = 'revision'
break
elif reason_type == 2:
reason_type = 'updating'
break
else:
print('Unrecognized reasoning type.')
query = Query(evidence=evidence,
targets=targets,
meta_evidence=meta_evidence,
meta_targets=meta_targets,
type=reason_type)
#print(meta_evidence)
query = self.reasoner.analyze_query(query)
query.getReport()
again = input('Do you wish to reason again? ([y],n): ') or 'y'
if again == 'y':
self.run(i=i + 1)
else:
return
def buildQueries(self):
""" Parses over the sent query graph to form a BKB query.
:return: A internal CHP query.
:rtype: Query
"""
evidence = dict()
targets = list()
self.contribution_target = None
if len(self.qg['nodes']) > 2 or len(self.qg['edges']) > 1:
sys.exit('1 hop quries can only have 2 nodes and 1 edge')
# check edge for source and target
edge_key = list(self.qg['edges'].keys())[0]
edge = self.qg['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 drug node
if self.qg['nodes'][subject]['category'] != 'biolink:Drug':
sys.exit('Subject node must be \'category\' biolink:Drug')
elif 'id' not in self.qg['nodes'][subject].keys():
sys.exit('Must have \'id\' key in drug node')
self.drug_curie = self.qg['nodes'][subject]['id']
if self.drug_curie not in self.drug_curie_dict.keys():
sys.exit('Invalid CHEMBL Identifier. Must be CHEMBL:<ID>')
evidence['demo_{}'.format(self.drug_curie)] = 'True'
# ensure gene is wildcard
if self.qg['nodes'][obj]['category'] != 'biolink:Gene':
sys.exit('Object node must be \'category\' biolink:Gene')
elif 'id' in self.qg['nodes'][obj].keys():
sys.exit('Must NOT have \'id\' key in gene node')
# default survival time
targets.append(('survival_time', self.op, self.value))
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
self.chp_query = query
return query
def _extract_chp_query(self, query, message_type):
# Extract Message
message = query.message
# Initialize CHP BKB Query
chp_query = ChpQuery(reasoning_type='updating')
# Grab edge
for qedge_id, qedge in message.query_graph.edges.items():
break
# Process predicate proxy
chp_query = self._process_predicate_proxy(qedge, chp_query)
# Process predicate context
chp_query = self._process_predicate_context(qedge, message_type,
chp_query)
#TODO: Probably need a more robust solution for when no context is provided in wildcard queries and you need it.
#if len(evidence) == 0:
# raise ValueError('Did not supply context with a query that required context.')
if message_type == 'standard':
# Setup gene and drug evidence
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[
0] == BIOLINK_GENE_ENTITY or qnode.categories[
0] == BIOLINK_DRUG_ENTITY:
chp_query.add_meta_evidence(qnode.ids[0], 'True')
elif message_type == 'gene' or message_type == 'drug_two_hop':
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[0] == BIOLINK_DRUG_ENTITY:
if qnode.ids is not None:
chp_query.add_meta_evidence(qnode.ids[0], 'True')
elif message_type == 'drug' or message_type == 'gene_two_hop':
for qnode_id, qnode in message.query_graph.nodes.items():
if qnode.categories[0] == BIOLINK_GENE_ENTITY:
if qnode.ids is not None:
chp_query.add_meta_evidence(qnode.ids[0], 'True')
target = list(chp_query.dynamic_targets.keys())[0]
truth_target = (target, '{} {}'.format(
chp_query.dynamic_targets[target]["op"],
chp_query.dynamic_targets[target]["value"]))
# Set some other helpful attributes
chp_query.truth_target = truth_target
return chp_query
def buildQueries(self):
""" Parses over the sent query graph to form a BKB query.
:return: A internal CHP query.
:rtype: Query
"""
evidence = dict()
targets = list()
acceptable_target_curies = ['EFO:0000714']
self.contribution_target = None
for node_id, node in self.qg['nodes'].items():
if 'id' not in node.keys():
if self.contribution_target is None:
self.contribution_target = node['category']
else:
sys.exit(
'You can only have one contribution target. Make sure to leave only one node with a black curie.'
)
else:
if node['category'] == 'biolink:Drug':
self.drug_curie = node['id']
if self.drug_curie not in self.drug_curie_dict.keys():
sys.exit(
'Invalid CHEMBL Identifier. Must be in form CHEMBL:<ID>'
)
evidence['demo_{}'.format(self.drug_curie)] = 'True'
for edge_id, edge in self.qg['edges'].items():
if edge['predicate'] == 'biolink:DiseaseToPhenotypicFeatureAssociation':
if 'properties' in edge:
self.op = edge['properties']['qualifier']
self.value = edge['properties']['days']
else:
self.op = '>='
self.value = 970
targets.append(('survival_time', self.op, self.value))
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
self.chp_query = query
return query
def make_query(self,
patient_hash,
target,
supported_compnames,
evidence_type='mutation'):
evidence = dict()
if evidence_type == 'mutation':
patientMutationEvidence = dict()
for mut in self.patient_data[patient_hash]["Patient_Genes"]:
compName = '_mut_' + mut
if compName in supported_compnames:
patientMutationEvidence[compName] = 'True'
if len(patientMutationEvidence) == 0:
return None
#print(patientMutationEvidence)
query = Query(evidence=patientMutationEvidence,
targets=[],
meta_targets=[target])
return query
def test_dynamic_reasoner_one_gene_one_drug(self):
# Specify evidence
dynamic_evidence = {
'CHEMBL:CHEMBL83': {
"op": '==',
"value": 'True',
}
}
meta_evidence = {
'ENSEMBL:ENSG00000155657': 'True',
}
# Specify targets
dynamic_targets = {"EFO:0000714": {"op": '>=', "value": 1000}}
# Setup query
query = Query(dynamic_evidence=dynamic_evidence,
meta_evidence=meta_evidence,
dynamic_targets=dynamic_targets)
query = self.dynamic_reasoner.run_query(query)
query.result.summary(include_contributions=False)
def processUiQuery(dict_):
query_dict = dict()
query_dict['name'] = dict_['name']
query_dict['evidence'] = dict_['genetic_evidence']
query_dict['targets'] = dict_['genetic_targets']
if dict_['demographic_evidence'] is not None:
query_dict['meta_evidence'] = [
tuple(demo) for demo in dict_['demographic_evidence']
]
else:
query_dict['meta_evidence'] = None
if dict_['demographic_targets'] is not None:
query_dict['meta_targets'] = [
tuple(demo) for demo in dict_['demographic_targets']
]
else:
query_dict['meta_targets'] = None
query = Query(**query_dict)
return query
def run_synthetic_contribution_queries(self, fused_bkbs, patient_dicts):
""" Runs the following query on a wildcard BKB:
P(survival_time >= 1000 | drug)
Calculates the wild card gene contributions using
the patient analysis.
:param fused_bkbs: A set of fused wildcard BKBs
:type fused_bkbs: list
:param patient_dicts: a set of patient_dicts
:type fused_bkbs: list
:return query_responses: a list of gene contributions in both
the true/false survival instantiations for each query
:rtype list:
"""
query_responses = []
for i in range(0, 11):
reasoner = Reasoner(fused_bkb=fused_bkbs[i],
patient_data=patient_dicts[i])
drug_evidence = {'demo_CYCLOPHOSPHAMIDE': 'True'}
query_drug = Query(evidence=drug_evidence,
targets=list(),
meta_evidence=None,
meta_targets=[('survival_time', '>=', 1000)],
type='updating')
query_drug = reasoner.analyze_query(copy.deepcopy(query_drug),
save_dir=None,
target_strategy='explicit',
interpolation='standard')
report = query_drug.jsonExplanations(
contributions_include_srcs=False,
contributions_top_n_inodes=30,
contributions_ignore_prefixes=['_'])
t_norm, f_norm, t_unnorm, f_unnorm = self.get_synthetic_query_probs(
query_drug)
analysis = {
'patient_analysis': report['Patient Analysis'],
'contribution_analysis': report['Contributions Analysis']
}
if 'survival_time >= 1000 = True' in analysis[
'contribution_analysis'].keys():
true_contrib = analysis['contribution_analysis'][
'survival_time >= 1000 = True'][
'demo_CYCLOPHOSPHAMIDE = True']
true_pats = len(
analysis['patient_analysis']['All Involved Patients']
['survival_time >= 1000 = True'].keys())
true_ind_cont = float(true_contrib) / float(
true_pats) / t_unnorm
else:
true_ind_cont = 0
if 'survival_time >= 1000 = False' in analysis[
'contribution_analysis'].keys():
false_contrib = analysis['contribution_analysis'][
'survival_time >= 1000 = False'][
'demo_CYCLOPHOSPHAMIDE = True']
false_pats = len(
analysis['patient_analysis']['All Involved Patients']
['survival_time >= 1000 = False'].keys())
false_ind_cont = float(false_contrib) / float(
false_pats) / f_unnorm
# gene contributions
true_gene_contrib = {'RAF1': 0}
false_gene_contrib = {'RAF1': 0}
for pat_key, pat in patient_dicts[i].items():
if pat['survival_time'] > 1000 and 'CYCLOPHOSPHAMIDE' in pat[
'drug_curies']:
if 'RAF1' in pat['gene_curies']:
true_gene_contrib['RAF1'] += true_ind_cont
elif pat['survival_time'] < 1000 and 'CYCLOPHOSPHAMIDE' in pat[
'drug_curies']:
if 'RAF1' in pat['gene_curies']:
false_gene_contrib['RAF1'] += false_ind_cont
query_responses.append((true_gene_contrib, false_gene_contrib))
return query_responses
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, message, message_type):
# Initialize CHP BKB Query
chp_query = ChpQuery(reasoning_type='updating')
# ensure we are using all nodes/edges
total_nodes = 0
total_edges = 0
query_graph = message.query_graph
# get phenotype node
targets = list()
acceptable_target_curies = ['EFO:0000714']
self.implicit_survival_node = False
for node_key in query_graph.nodes.keys():
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_PHENOTYPIC_FEATURE_ENTITY and node.ids[0] 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(BIOLINK_PHENOTYPIC_FEATURE),
# acceptable_target_curies_print))
survival_value = 970
survival_operator = '>='
# get disease node info and ensure only 1 disease:
acceptable_disease_curies = ['MONDO:0007254']
for node_key in query_graph.nodes.keys():
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_DISEASE_ENTITY and node.ids[0] in acceptable_disease_curies:
disease_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(edge.predicates[0], BIOLINK_HAS_PHENOTYPE_ENTITY) and edge.subject == disease_id and edge.object == target_id:
survival_time_constraint = edge.find_constraint(name='survival_time')
if survival_time_constraint is not None:
survival_value = survival_time_constraint.value
survival_operator = survival_time_constraint.operator
if survival_operator == 'matches':
survival_operator = '=='
total_edges += 1
total_nodes += 1
if self.implicit_survival_node:
days=970
qualifier = '>='
total_edges += 1
# set BKB target
chp_query.add_dynamic_target('EFO:0000714', survival_operator, survival_value)
truth_target = ('EFO:0000714', '{} {}'.format(survival_operator, survival_value))
# get evidence
for node_key in query_graph.nodes.keys():
# genes
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_GENE_ENTITY:
# check for appropriate gene node structure
gene_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(edge.predicates[0], BIOLINK_GENE_ASSOCIATED_WITH_CONDITION_ENTITY) and edge.subject == gene_id and edge.object == disease_id:
total_edges += 1
# check for appropriate gene node curie
if message_type != 'gene':
gene_curie = node.ids[0]
if gene_curie in self.curies[BIOLINK_GENE_ENTITY.get_curie()]:
gene = gene_curie
chp_query.add_meta_evidence(gene, 'True')
total_nodes += 1
# drugs
if node.categories[0] == BIOLINK_DRUG_ENTITY:
# check for appropriate drug node structure
drug_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(edge.predicates[0], BIOLINK_TREATS_ENTITY) and edge.subject == drug_id and edge.object == disease_id:
total_edges += 1
# check for appropriate drug node curie
if message_type != 'drug':
drug_curie = node.ids[0]
if drug_curie in self.curies[BIOLINK_DRUG_ENTITY.get_curie()]:
drug = drug_curie
chp_query.add_meta_evidence(drug, 'True')
total_nodes += 1
# Temporary solution to no evidence linking
if len(chp_query.evidence.keys()) == 0 and len(chp_query.dynamic_evidence.keys()) == 0:
self.no_evidence_probability_check = True
else:
self.no_evidence_probability_check = False
# Set some other helpful attributes
chp_query.truth_target = truth_target
return chp_query
def _extract_chp_query(self, message, message_type=None):
# Initialize Chp Query
chp_query = ChpQuery(reasoning_type='updating')
# Ensure we are using all nodes/edges
total_nodes = 0
total_edges = 0
query_graph = message.query_graph
# get phenotype node
targets = list()
for node_key in query_graph.nodes.keys():
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_PHENOTYPIC_FEATURE_ENTITY:
target_id = node_key
total_nodes += 1
survival_value = 970
survival_operator = '>='
# get disease node info and ensure only 1 disease:
for node_key in query_graph.nodes.keys():
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_DISEASE_ENTITY:
disease_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(
edge.predicates[0], BIOLINK_HAS_PHENOTYPE_ENTITY
) and edge.subject == disease_id and edge.object == target_id:
survival_time_constraint = edge.find_constraint(
name='survival_time')
if survival_time_constraint is not None:
survival_value = survival_time_constraint.value
survival_operator = survival_time_constraint.operator
if survival_operator == 'matches':
survival_operator = '=='
total_edges += 1
total_nodes += 1
# set BKB target
chp_query.add_dynamic_target(node.ids[0], survival_operator,
survival_value)
truth_target = (node.ids[0], '{} {}'.format(survival_operator,
survival_value))
# get evidence
for node_key in query_graph.nodes.keys():
# genes
node = query_graph.nodes[node_key]
if node.categories[0] == BIOLINK_GENE_ENTITY:
# check for appropriate gene node structure
gene_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(
edge.predicates[0],
BIOLINK_GENE_ASSOCIATED_WITH_CONDITION_ENTITY
) and edge.subject == gene_id and edge.object == disease_id:
total_edges += 1
# check for appropriate gene node curie
gene_curie = node.ids[0]
gene = gene_curie
chp_query.add_meta_evidence(gene, 'True')
total_nodes += 1
# drugs
if node.categories[0] == BIOLINK_DRUG_ENTITY:
# check for appropriate drug node structure
drug_id = node_key
for edge_key in query_graph.edges.keys():
edge = query_graph.edges[edge_key]
if self.check_predicate_support(
edge.predicates[0], BIOLINK_TREATS_ENTITY
) and edge.subject == drug_id and edge.object == disease_id:
total_edges += 1
# check for appropriate drug node curie
drug_curie = node.ids[0]
drug = drug_curie
chp_query.add_dynamic_evidence(node.ids[0], '==', 'True')
total_nodes += 1
# Set some other helpful attributes
chp_query.truth_target = truth_target
return chp_query
def buildQueries(self):
# 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 in self.qg['nodes']:
if node['type'] == 'PhenotypicFeature' and node[
'curie'] in acceptable_target_curies:
target_id = node['id']
total_nodes += 1
if total_nodes == 0:
acceptable_target_curies_print = ','.join(acceptable_target_curies)
sys.exit(
'Survival Node not found. Node type muse be \'PhenotypicFeature\' and curie 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 in self.qg['nodes']:
if node['type'] == 'disease' and node[
'curie'] in acceptable_disease_curies:
disease_id = node['id']
for edge in self.qg['edges']:
if edge['type'] == 'disease_to_phenotype_association' and edge[
'source_id'] == disease_id and edge[
'target_id'] == target_id and 'value' in list(
edge.keys()):
self.days = edge['value']
if isinstance(self.days, str):
self.days = int(self.days)
total_edges += 1
if total_edges == 0:
sys.exit(
'Disease and target edge not found. Edge type must be \'disease_to_phenotype_association\''
)
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 \'disease\' and curie must be in: '
+ acceptable_disease_curies_print)
elif total_nodes > 2:
sys.exit('Too many disease nodes')
# set BKB target
targets.append(('Survival_Time', '>=', self.days))
# get evidence
evidence = dict()
meta_evidence = list()
for node in self.qg['nodes']:
# genes
if node['type'] == 'Gene':
# check for appropriate gene node structure
gene_id = node['id']
for edge in self.qg['edges']:
if edge['type'] == 'gene_to_disease_association' and edge[
'source_id'] == gene_id and edge[
'target_id'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit(
'Gene and disease edge not found. Edge type must be \'gene_to_disease_association\''
)
elif total_edges > total_nodes:
sys.exit('Gene has too many outgoing edges')
# check for appropriate gene node curie
gene_curie = node['curie']
try:
gene = self.gene_curie_dict[gene_curie]
except:
sys.exit(
'Invalid ENSEMBL Identifier. Must be in form ENSEMBL:<ID>.'
)
evidence["_mut_" + gene] = 'True'
total_nodes += 1
# drugs
if node['type'] == 'Drug':
# check for appropriate drug node structure
drug_id = node['id']
for edge in self.qg['edges']:
if edge['type'] == 'chemical_to_disease_or_phenotypic_feature_association' and edge[
'source_id'] == drug_id and edge[
'target_id'] == disease_id:
total_edges += 1
if total_edges == total_nodes - 1:
sys.exit(
'Drug and disease edge not found. Edge type must be \'chemical_to_disease_or_phenotypic_feature_association\''
)
elif total_edges > total_nodes:
sys.exit('Drug has too many outgoing edges')
# check for appropriate drug node curie
drug_curie = node['curie']
try:
drug = self.drug_curie_dict[drug_curie]
except:
sys.exit(
'Invalid CHEMBL Identifier. Must be in form CHEMBL:<ID>'
)
meta_evidence.append(('Drug_Name(s)', '==', drug))
total_nodes += 1
if total_nodes != len(self.qg['nodes']) or total_edges != len(
self.qg['edges']):
sys.exit('There are extra components in the provided QG structure')
if len(list(evidence.keys())) == 0:
sys.exit('Needs at least 1 gene')
# produce BKB query
if len(meta_evidence) > 0 and len(list(evidence.keys())) > 0:
query = Query(evidence=evidence,
targets=[],
meta_evidence=meta_evidence,
meta_targets=targets,
type='updating')
elif len(list(evidence.keys())) > 0:
query = Query(evidence=evidence,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
elif len(meta_evidence) > 0:
query = Query(evidence=None,
targets=[],
meta_evidence=meta_evidence,
meta_targets=targets,
type='updating')
else:
query = Query(evidence=None,
targets=[],
meta_evidence=None,
meta_targets=targets,
type='updating')
self.chp_query = query
return query
}
return {'genetic_info': inode_names, 'demographic_info': demographics}
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='BKB Pathway Provider Minimal Driver')
parser.add_argument('--config_file', default='driver.config', type=str)
parser.add_argument('--headless', action='store_true')
parser.add_argument('--query_file', type=str)
parser.add_argument('--save_dir', type=str, default=os.getcwd())
parser.add_argument('--get_variables', type=str, default=None)
args = parser.parse_args()
if args.headless:
driver = Driver(args.config_file)
#-- Load Query from query file
query = Query().read(args.query_file)
result_query = driver.run_query(query)
#-- Save Query
result_query.save(args.save_dir, only_json=True)
elif args.get_variables is not None:
driver = Driver(args.config_file)
vars_ = driver.collectVariables()
with open(args.get_variables, 'wb') as f_:
pickle.dump(file=f_, obj=vars_)
else:
driver = Driver(args.config_file)
driver.run()
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
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
#-- Set the patient data file
reasoner.set_src_metadata(patient_data_file)
#reasoner.collapsed_bkb.makeGraph()
#-- If you want to see what genetic or demographic evidence is avaliable, uncomment the line below
#print(reasoner.metadata_ranges)
'''
#-- Make a query (evidence is for genetic info, and meta_ is for demographic info)
query0 = Query(evidence={'mut_TMEM245=': 'True'},
targets=list(),
meta_evidence=[('Age_of_Diagnosis', '>=',20000)],
meta_targets=[('Survival_Time', '>=', 300)])
'''
query0 = Query(evidence={'_mut_AADAC': 'True'},
targets=list(),
meta_targets=[('Survival_Time', '>=', 300)])
#-- Run the query.
query = reasoner.analyze_query(query0,
check_mutex=False,
interpolation='standard',
target_strategy='explicit')
#-- Return the report
query.getReport()
#print(query.result.print_contributions())
#print(query.result.completed_inferences_report())
query.bkb.makeGraph()
#-- Check for mutex if you want to.