def generate_targets_file(disease_id, outpath, anno_type: str = 'entrezgene') -> None:
"""Creates a disease list
:param disease_id: EFO code from the disease.
:param outpath:
:param anno_type: `entrezgene` for Entrez Id or `symbol` for Gene symbol.
:return:
"""
ot = OpenTargetsClient()
assoc = ot.get_associations_for_disease(
disease_id,
fields=['association_scoredatatypes', 'target.id']
).filter(
datatype='known_drug'
)
ensembl_list = [a['target']['id'] for a in assoc]
# TODO use the converters.get_converter_to_entrez
mg = mygene.MyGeneInfo()
id_mappings = mg.getgenes(ensembl_list, fields=anno_type)
with open(outpath, 'w+') as outfile:
for mapping in id_mappings:
if anno_type in mapping.keys():
outfile.write(mapping[anno_type])
outfile.write('\n')
def generate_disease_gene_association_file(disease_id,
outpath,
anno_type: str = 'entrezgene'):
"""Obtain the association scores from the specified disease that are
stored in the OpenTargets database.
:param disease_id: The EFO code to the disease.
:param outpath: The path to the file to be created.
:param anno_type: `entrezgene` for Entrez Id or `symbol` for Gene symbol.
:return:
"""
ot = OpenTargetsClient()
assoc = ot.get_associations_for_disease(
disease_id, fields=['association_scoreoverall', 'target.id'])
assoc_simple = [{
'id': a['target']['id'],
'score': a['association_score']['overall']
} for a in assoc]
ensembl_list = [a['id'] for a in assoc_simple]
# Obtain the symbols for the genes associated to disease_id
id_mappings = get_converter_to_entrez(ensembl_list)
# Get the symbols and the scores
ensembl_list = [(id_mappings[a['id']], a['score']) for a in assoc_simple
if a['id'] in id_mappings]
with open(outpath, 'w+') as outfile:
for symbol, score in ensembl_list:
print(f'{symbol}\t{score}', file=outfile)
def search_disease(x): from opentargets import OpenTargetsClient from sys import argv client = OpenTargetsClient() response = client.get_associations_for_disease(x) return response.to_dataframe()
def download_for_disease(disease_id, outpath):
ot = OpenTargetsClient()
assoc = ot.get_associations_for_disease(
disease_id, fields=['associationscore.datatypes',
'target.id']).filter(datatype='known_drug')
ensembl_list = [a['target']['id'] for a in assoc]
mg = mygene.MyGeneInfo()
id_mappings = mg.getgenes(ensembl_list, fields="entrezgene")
with open(outpath, 'w+') as outfile:
for mapping in id_mappings:
if 'entrezgene' in mapping.keys():
outfile.write(mapping['entrezgene'])
outfile.write('\n')
target_as = ot.get_associations_for_target(target_id)
print(target_as)
l = []
print('Target id associations:\n')
for a in target_as:
print(a['id'], a['association_score']['overall'])
l.append(a['association_score']['overall'])
print('Maximum target id association:', np.max(l))
print('Minimum target id association:', np.min(l))
print('Mean target id association:', np.mean(l))
print('Standard deviation of target id association:', np.std(l))
except ValueError:
print('Target id not found')
#Checks for a disease id as input
if disease_id is not None:
try:
disease_as = ot.get_associations_for_disease(disease_id)
l = []
for a in disease_as:
print(a['id'], a['association_score']['overall'])
l.append(a['association_score']['overall'])
print('Maximum disease id association:', np.max(l))
print('Minimum disease id association:', np.min(l))
print('Mean disease id association:', np.mean(l))
print('Standard deviation of disease id association:', np.std(l))
except ValueError:
print('Disease id not found')
class OpenTargetClientTest(unittest.TestCase):
_AUTO_GET_TOKEN = 'auto'
def setUp(self):
self.client = OpenTargetsClient()
self.http2_client = OpenTargetsClient(use_http2=True)
self.auth_client = OpenTargetsClient(
auth_app_name='test',
auth_secret='test',
)
def tearDown(self):
self.client.close()
def testSearchTargetCorrectResult(self):
target_symbol = 'BRAF'
response = self.client.search(target_symbol)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['type'], 'search-object-target')
self.assertEqual(result['id'], 'ENSG00000157764')
self.assertEqual(result['data']['approved_symbol'], target_symbol)
def testSearchTargetFetchAllResults(self):
target_symbol = 'BRAF'
response = self.client.search(target_symbol)
total_results = len(response)
self.assertGreater(total_results, 0)
c = 0
for i in response:
c += 1
self.assertEqual(total_results, c)
def testSearchTargetFetchAllResultsAuth(self):
target_symbol = 'BRAF'
response = self.auth_client.search(target_symbol)
total_results = len(response)
self.assertGreater(total_results, 0)
c = 0
for i in response:
c += 1
self.assertEqual(total_results, c)
def testSearchTargetCorrectResultHTTP2(self):
target_symbol = 'BRAF'
response = self.http2_client.search(target_symbol)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['type'], 'search-object-target')
self.assertEqual(result['id'], 'ENSG00000157764')
self.assertEqual(result['data']['approved_symbol'], target_symbol)
def testSearchTargetFetchAllResultsHTTP2(self):
target_symbol = 'BRAF'
response = self.http2_client.search(target_symbol)
total_results = len(response)
self.assertGreater(total_results, 0)
c = 0
for i in response:
c += 1
self.assertEqual(total_results, c)
def testSearchDiseaseCorrectResult(self):
disease_label = 'cancer'
response = self.client.search(disease_label)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['type'], 'search-object-disease')
self.assertEqual(result['id'], 'EFO_0000311')
# #this takes a lot to run
# def testSearchDiseaseFetchAllResults(self):
# disease_label = 'cancer'
# response = self.client.search(disease_label, size = 100)
# total_results = len(response)
# self.assertGreater(total_results,0)
# c=0
# for i in response:
# c+=1
# self.assertEqual(total_results, c)
# print(total_results, c)
def testGetAssociation(self):
association_id = "ENSG00000157764-EFO_0005803"
response = self.client.get_association(association_id)
self.assertEquals(len(response), 1)
self.assertEquals(association_id, response[0]['id'])
def testFilterAssociations(self):
response = self.client.filter_associations()
self.assertGreater(len(response), 0)
total = response.info.total
response.filter(target='ENSG00000157764')
self.assertLess(len(response), total)
total = response.info.total
response.filter(direct=True)
self.assertLess(len(response), total)
total = response.info.total
response.filter(scorevalue_min=0.2)
self.assertLess(len(response), total)
total = response.info.total
response.filter(therapeutic_area='efo_0000701')
self.assertLess(len(response), total)
results = []
for i, r in enumerate(response):
print(i, r['id'], r['association_score']['overall'],
r['disease']['efo_info']['label'])
results.append(r)
response_multi = self.client.filter_associations(
target='ENSG00000157764',
direct=True,
scorevalue_min=0.2,
therapeutic_area='efo_0000701')
self.assertEqual(len(response_multi), response.info.total)
for i, r in enumerate(response_multi):
self.assertEqual(results[i]['id'], r['id'])
response_chained = self.client.filter_associations().filter(
target='ENSG00000157764').filter(direct=True).filter(
therapeutic_area='efo_0000701').filter(scorevalue_min=0.2)
self.assertEqual(len(response_chained), response.info.total)
for i, r in enumerate(response_chained):
self.assertEqual(results[i]['id'], r['id'])
def testGetAssociationsForTarget(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(target_symbol,
size=30)
self.assertGreater(len(response), 0)
for i, result in enumerate(response):
self.assertEqual(result['target']['gene_info']['symbol'],
target_symbol)
if i > 90:
break
def testGetAssociationsForDisease(self):
disease_label = 'cancer'
response = self.client.get_associations_for_disease(disease_label)
self.assertGreater(len(response), 0)
for result in response:
self.assertEqual(result['disease']['efo_info']['label'],
disease_label)
@unittest.expectedFailure
def testGetEvidence(self):
evidence_id = "03fba0599655b9040012b29cf0de8060"
response = self.client.get_evidence(evidence_id)
self.assertEquals(len(response), 1)
self.assertEquals(evidence_id, response[0]['id'])
def testFilterEvidence(self):
response = self.client.filter_evidence()
self.assertGreater(len(response), 0)
def testGetEvidenceForTarget(self):
target_symbol = 'BRAF'
response = self.client.get_evidence_for_target(target_symbol,
size=1000)
self.assertGreater(len(response), 0)
for i, result in enumerate(response):
self.assertEqual(result['target']['gene_info']['symbol'],
target_symbol)
if i > 100:
break
def testGetSimilarTargets(self):
target_symbol = 'BRAF'
response = self.client.get_similar_target(target_symbol)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['subject']['label'], target_symbol)
self.assertEqual(result['object']['label'], 'KRAS')
def testGetSimilarDisease(self):
disease_label = 'ulcerative colitis'
response = self.client.get_similar_disease(disease_label)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['subject']['label'], disease_label)
self.assertEqual(result['object']['label'], "Crohn's disease")
def testGetEvidenceForDisease(self):
disease_label = 'medulloblastoma'
response = self.client.get_evidence_for_disease(disease_label)
self.assertGreater(len(response), 0)
result = next(response)
self.assertEqual(result['disease']['efo_info']['label'], disease_label)
def testSerialiseToJson(self):
target_symbol = 'BRAF'
'''test iterable version'''
response = self.client.get_associations_for_target(target_symbol)
items = len(response)
self.assertGreater(len(response), 0)
json_output = response.to_json()
parsed_json = [json.loads(i) for i in json_output]
self.assertEqual(items, len(parsed_json))
'''test non iterable version'''
response = self.client.get_associations_for_target(target_symbol)
items = len(response)
self.assertGreater(len(response), 0)
json_output = response.to_json(iterable=False)
parsed_json = json.loads(json_output)
self.assertEqual(items, len(parsed_json))
def testResultToPandasDataFrame(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(target_symbol)
items = len(response)
self.assertGreater(len(response), 0)
dataframe = response.to_dataframe()
self.assertEqual(len(dataframe), items)
def testResultToPandasCSV(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(
target_symbol,
fields=[
'association_score.*', 'target.gene_info.symbol',
'disease.efo_info.*'
])
items = len(response)
self.assertGreater(len(response), 0)
csv = response.to_csv()
filename = 'braf_associations.csv'
open(filename, 'wb').write(csv.encode('utf-8'))
self.assertEqual(len(csv.split('\n')), items + 2)
self.assertTrue(os.path.isfile(filename))
os.remove(filename)
def testResultToPandasExcel(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(
target_symbol,
fields=[
'association_score.*', 'target.gene_info.symbol',
'disease.efo_info.*'
])
self.assertGreater(len(response), 0)
filename = 'braf_associations.xls'
response.to_excel(filename)
self.assertTrue(os.path.isfile(filename))
os.remove(filename)
def testResultToFile(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(
target_symbol,
fields=[
'association_score.*', 'target.gene_info.symbol',
'disease.efo_info.*'
])
self.assertGreater(len(response), 0)
filename = 'braf_associations.json.gz'
response.to_file(filename)
self.assertTrue(os.path.isfile(filename))
os.remove(filename)
def testSerialiseToObject(self):
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(target_symbol)
items = len(response)
self.assertGreater(len(response), 0)
obj_output = list(response.to_object())
for i, result in enumerate(obj_output):
self.assertIsNotNone(result.target.id)
self.assertEqual(items, i + 1)
def testGetStats(self):
response = self.client.get_stats()
self.assertEquals(len(response), 0)
def testAutodetectPost(self):
self.assertFalse(
Connection._auto_detect_post({'target': ['ENSG00000157764']}))
self.assertTrue(
Connection._auto_detect_post({
'target': [
'ENSG00000157764',
'ENSG00000171862',
'ENSG00000136997',
'ENSG00000012048',
'ENSG00000139618',
]
}))
def testGetToPost(self):
response = self.client.conn.get('/platform/public/association/filter',
params={
'target': [
'ENSG00000157764',
'ENSG00000171862',
'ENSG00000136997',
'ENSG00000012048',
'ENSG00000139618',
]
})
self.assertGreater(len(response), 0)
def testCustomScore(self):
def score_with_datatype_subset(datatypes, results):
for r in results:
datatype_scores = r['association_score']['datatypes']
filtered_scores = [datatype_scores[dt] for dt in datatypes]
custom_score = HarmonicSumScorer.harmonic_sum(filtered_scores)
if custom_score:
yield (round(custom_score, 3), r['disease']['id'],
dict(zip(datatypes, filtered_scores)))
target_symbol = 'BRAF'
response = self.client.get_associations_for_target(target_symbol)
self.assertGreater(len(response), 0)
for i, filtered_data in enumerate(
score_with_datatype_subset(
['genetic_association', 'known_drug', 'somatic_mutation'],
response)):
self.assertGreater(filtered_data[0], 0.)
self.assertLess(i, len(response))
def testGetAvailableEndpoints(self):
endpoints = self.client.conn.get_api_endpoints()
self.assertTrue('/platform/public/search' in endpoints)
def testGetEndpointDocs(self):
docs = self.client.conn.api_endpoint_docs('/platform/public/search')
self.assertGreater(len(docs['get']['parameters']), 0)
def testPing(self):
response = self.client.conn.ping()
if isinstance(response, bool):
self.assertTrue(response)
else:
self.assertIsNotNone(response)
def main(t, d):
# Quick Check - arguments (none/both)
if t == '' and d == '':sys.exit(1)
if t != '' and d != '':sys.exit(1)
# Load Func re opentargets querying ( pip install opentargets )
# https://opentargets.readthedocs.io/en/stable/index.html
from opentargets import OpenTargetsClient
ot = OpenTargetsClient()
# dir(ot)
# Define Func re statistical analyses
def doScoreStats(search_score):
import statistics
print('-----')
print('Max:', max(search_score))
print('Min:', min(search_score))
print('Ave:', statistics.mean(search_score))
print('SD:', statistics.stdev(search_score))
# Run Analysis re TARGET (t)
if t != '':
search_id = t;
a_for_target = ot.get_associations_for_target(search_id)
# Quick Check - correct 'target' queried
if a_for_target.info['query']['target'] == [search_id]:
search_score = [] # initialise list
# Loop Over Entries
for a in a_for_target:
search_score.append(a['association_score']['overall'])
print(a['target']['id'], a['disease']['id'], a['association_score']['overall'])
doScoreStats(search_score)
else:
print("please check best match (exited) -", [search_id], " vs ", a_for_target.info['query']['target'])
sys.exit(1)
# Run Analysis re DISEASE (d)
elif d != '':
search_id = d
a_for_disease = ot.get_associations_for_disease(search_id)
# Quick Check - correct 'disease' queried
if a_for_disease.info['query']['disease'] == [search_id]:
search_score = [] # initialise list
# Loop Over Entries
for a in a_for_disease:
search_score.append(a['association_score']['overall'])
print(a['target']['id'], a['disease']['id'], a['association_score']['overall'])
doScoreStats(search_score)
else:
print("please check best match (exited) - ", [search_id], " vs ", a_for_disease.info['query']['disease'])
sys.exit(1)
