def make_edge_attribute_from_curies(self,
source_curie,
target_curie,
source_name="",
target_name="",
default=0.,
name=""):
"""
Generic function to make an edge attribute
:source_curie: CURIE of the source node for the edge under consideration
:target_curie: CURIE of the target node for the edge under consideration
:source_name: text name of the source node (in case the KP doesn't understand the CURIE)
:target: text name of the target node (in case the KP doesn't understand the CURIE)
:default: default value of the edge attribute
:name: name of the KP functionality you want to apply
"""
try:
# edge attributes
name = name
type = "data:0951"
url = "http://cohd.smart-api.info/"
value = default
node_curie_to_type = self.node_curie_to_type
source_type = node_curie_to_type[source_curie]
target_type = node_curie_to_type[target_curie]
# figure out which knowledge provider to use # TODO: should handle this in a more structured fashion, does there exist a standardized KP API format?
KP_to_use = None
for KP in self.who_knows_about_what:
# see which KP's can label both sources of information
if self.in_common(
source_type,
self.who_knows_about_what[KP]) and self.in_common(
target_type, self.who_knows_about_what[KP]):
KP_to_use = KP
if KP_to_use == 'COHD':
# convert CURIE to OMOP identifiers
source_OMOPs = [
str(x['omop_standard_concept_id'])
for x in COHD.get_xref_to_OMOP(source_curie, 1)
]
target_OMOPs = [
str(x['omop_standard_concept_id'])
for x in COHD.get_xref_to_OMOP(target_curie, 1)
]
# FIXME: Super hacky way to get around the fact that COHD can't map CHEMBL drugs
if source_curie.split('.')[0] == 'CHEMBL':
source_OMOPs = [
str(x['concept_id']) for x in COHD.find_concept_ids(
source_name, domain="Drug", dataset_id=3)
]
if target_curie.split('.')[0] == 'CHEMBL':
target_OMOPs = [
str(x['concept_id']) for x in COHD.find_concept_ids(
target_name, domain="Drug", dataset_id=3)
]
# uniquify everything
source_OMOPs = list(set(source_OMOPs))
target_OMOPs = list(set(target_OMOPs))
# Decide how to handle the response from the KP
if name == 'paired_concept_frequency':
# sum up all frequencies #TODO check with COHD people to see if this is kosher
frequency = default
for (omop1,
omop2) in itertools.product(source_OMOPs,
target_OMOPs):
freq_data = COHD.get_paired_concept_freq(
omop1, omop2, 3) # use the hierarchical dataset
if freq_data and 'concept_frequency' in freq_data:
frequency += freq_data['concept_frequency']
# decorate the edges
value = frequency
elif name == 'observed_expected_ratio':
# should probably take the largest obs/exp ratio # TODO: check with COHD people to see if this is kosher
# FIXME: the ln_ratio can be negative, so I should probably account for this, but the object model doesn't like -np.inf
value = float(
"-inf"
) # FIXME: unclear in object model if attribute type dictates value type, or if value always needs to be a string
###############################
# The following code was an experiment to see if it would speed things up, leaving it out for now since it's difficult to quantify if it does speed things up given the cacheing
#if len(source_OMOPs) < len(target_OMOPs):
# for omop1 in source_OMOPs:
# omop_to_ln_ratio = dict()
# response = COHD.get_obs_exp_ratio(omop1, domain="", dataset_id=3) # use the hierarchical dataset
# if response:
# for res in response:
# omop_to_ln_ratio[str(res['concept_id_2'])] = res['ln_ratio']
# for omop2 in target_OMOPs:
# if omop2 in omop_to_ln_ratio:
# temp_value = omop_to_ln_ratio[omop2]
# if temp_value > value:
# value = temp_value
#else:
# for omop1 in target_OMOPs:
# omop_to_ln_ratio = dict()
# response = COHD.get_obs_exp_ratio(omop1, domain="", dataset_id=3) # use the hierarchical dataset
# if response:
# for res in response:
# omop_to_ln_ratio[str(res['concept_id_2'])] = res['ln_ratio']
# for omop2 in source_OMOPs:
# if omop2 in omop_to_ln_ratio:
# temp_value = omop_to_ln_ratio[omop2]
# if temp_value > value:
# value = temp_value
###################################
for (omop1,
omop2) in itertools.product(source_OMOPs,
target_OMOPs):
#print(f"{omop1},{omop2}")
response = COHD.get_obs_exp_ratio(
omop1, concept_id_2=omop2, domain="",
dataset_id=3) # use the hierarchical dataset
# response is a list, since this function is overloaded and can omit concept_id_2, take the first element
if response and 'ln_ratio' in response[0]:
temp_val = response[0]['ln_ratio']
if temp_val > value:
value = temp_val
elif name == 'chi_square':
value = float("inf")
for (omop1,
omop2) in itertools.product(source_OMOPs,
target_OMOPs):
response = COHD.get_chi_square(
omop1, concept_id_2=omop2, domain="",
dataset_id=3) # use the hierarchical dataset
# response is a list, since this function is overloaded and can omit concept_id_2, take the first element
if response and 'p-value' in response[0]:
temp_val = response[0]['p-value']
if temp_val < value: # looking at p=values, so lower is better
value = temp_val
# create the edge attribute
edge_attribute = EdgeAttribute(
type=type, name=name, value=str(value), url=url
) # populate the edge attribute # FIXME: unclear in object model if attribute type dictates value type, or if value always needs to be a string
return edge_attribute
else:
return None
except:
tb = traceback.format_exc()
error_type, error, _ = sys.exc_info()
self.response.error(tb, error_code=error_type.__name__)
self.response.error(
f"Something went wrong when adding the edge attribute from {KP_to_use}."
)
def test_get_chi_square(self):
# default dataset_id
result = QueryCOHD.get_chi_square("192855", "2008271", "Condition")
self.assertIsNotNone(result)
self.assertEqual(len(result), 1)
self.assertEqual(result, [{'chi_square': 306.2816108187519,
'concept_id_1': 192855,
'concept_id_2': 2008271,
'dataset_id': 1,
'p-value': 1.4101531778039801e-68}])
# dataset_id == 2
result = QueryCOHD.get_chi_square("192855", "2008271", "Condition", 2)
self.assertIsNotNone(result)
self.assertEqual(len(result), 1)
self.assertEqual(result, [{'chi_square': 7065.7865572100745,
'concept_id_1': 192855,
'concept_id_2': 2008271,
'dataset_id': 2,
'p-value': 0.0}])
# default domain and dataset_id
result = QueryCOHD.get_chi_square("192855", "2008271")
self.assertIsNotNone(result)
self.assertEqual(len(result), 1)
self.assertEqual(result, [{'chi_square': 306.2816108187519,
'concept_id_1': 192855,
'concept_id_2': 2008271,
'dataset_id': 1,
'p-value': 1.4101531778039801e-68}])
# no concept_id_2, default domain and dataset_id
result = QueryCOHD.get_chi_square("192855")
self.assertIsNotNone(result)
self.assertEqual(len(result), 768)
# no concept_id_2, default dataset_id
result = QueryCOHD.get_chi_square("192855", "", "Condition")
self.assertIsNotNone(result)
self.assertEqual(len(result), 226)
# no concept_id_2, dataset_id == 2
result = QueryCOHD.get_chi_square("192855", "", "Condition", 2)
self.assertIsNotNone(result)
self.assertEqual(len(result), 991)
# no concept_id_2, dataset_id == 2, default domain
result = QueryCOHD.get_chi_square("192855", "", "", 2)
self.assertIsNotNone(result)
self.assertEqual(len(result), 2735)
# invalid concept_id_1 type
result = QueryCOHD.get_chi_square(192855, "", "", 1)
self.assertEqual(result, [])
# invalid concept_id_2 type
result = QueryCOHD.get_chi_square("192855", 2008271, "", 1)
self.assertEqual(result, [])
# invalid dataset_id value
result = QueryCOHD.get_chi_square("192855", "2008271", "condition", 10)
self.assertEqual(result, [])