def full_heatfile(disease, network):
"""
Output tab-separated ENSG and assoc scores for all nodes
in network, including zero values. Not needed?
disease = disease of interest (EFO code)
network = source network (stringdb or omnipath)
"""
#Read in network info frame
idFrame = pd.read_csv('./networks/' + network + 'IDFrame.csv')
idFrame = idFrame.set_index('geneID')
ot = OpenTargetsClient()
all_associations = ot.filter_associations(disease=disease)
#build frame of associations
assocFrame = pd.DataFrame(columns=['geneID', 'score'])
for i, r in enumerate(all_associations):
assocFrame.loc[len(assocFrame)] = [
r['target']['id'], r['association_score']['overall']
]
#Join with sample data
idFrame = idFrame.join(assocFrame.set_index('geneID'),
how='left').fillna(0.0000000001)
#Output to heatfile
with open('./data/heatfile', 'w') as outfile:
for index, row in idFrame.iterrows():
if isinstance(index, basestring):
outfile.write("{} {}\n".format(index, row['score']))
def search_known_drugs(x): from opentargets import OpenTargetsClient from sys import argv client = OpenTargetsClient() response = client.get_evidence_for_disease(x) return response.to_dataframe()
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 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 search_new_drugs(x): from opentargets import OpenTargetsClient from sys import argv client = OpenTargetsClient() response = client.search(x) return response.to_dataframe()
def run_analysis(queryType, identifier, verbose = False):
""" This function will run the actual analysis
Args:
queryType (str): based on what we are fetching data either disease or target
identifier (str): disease ID or target ID depending on the query type.
verbose (bool): if we want extra information printed to STDOUT
Returns:
Dictionary:
{
"queryTerm" : <str>
"target-disease-pairs" : <pandas.dataframe>,
"score_max" : <float>,
"score_min" : <float>,
"score_mean" : <float>,
"score_std" : <float>
}
The analysis values might be None if there are no returned values.
"""
# Initializing output variable:
analysisOutput = {
"queryTerm" : identifier,
"target-disease-pairs" : None,
"score_max" : None,
"score_min" : None,
"score_mean" : None,
"score_std" : None
}
# Initializing OTAR query object:
client = OpenTargetsClient()
otar_results = client.filter_associations()
# Retrieving queried data:
x = otar_results.filter(**{queryType : identifier})
# Submit result to parser:
OT_parser = OTAR_result_parser(x, verbose=verbose)
# If the result set is empty, we can't get stats:
if not len(OT_parser):
if verbose: print('[Warning] The result set is empty. Can\'t calculate stats.')
return analysisOutput
if verbose: print('[Info] Number of associations: {}'.format(len(OT_parser)))
# Retrieving target-disease pairs:
analysisOutput['target-disease-pairs'] = OT_parser.get_target_disease_pairs()
# Retrieving stats of the association scores:
analysisOutput['score_max'] = OT_parser.get_association_score_max()
analysisOutput['score_min'] = OT_parser.get_association_score_min()
analysisOutput['score_mean'] = OT_parser.get_association_score_mean()
analysisOutput['score_std'] = OT_parser.get_association_score_std()
return analysisOutput
def simple_heatfile(disease):
"""
Output tab-separated ENSG and assoc scores for nodes with non-zero assoc scores
disease = disease of interest (EFO code)
"""
ot = OpenTargetsClient()
all_associations = ot.filter_associations(disease=disease)
with open('./data/heatfile', 'w') as outfile:
for i, r in enumerate(all_associations):
outfile.write("{} {}\n".format(r['target']['id'],
r['association_score']['overall']))
def request(self, arg, query_type):
"""
Requests response from given endpoint
Args:
arg (str): Given command line argument to query endpoint with
query_type (str): Parameter for RESTful api query
url (str): Given RESTful api endpoint
Returns:
response: A JSON response
"""
ot = OpenTargetsClient()
a_for_target = ot.get_associations_for_target(arg)
for a in a_for_target:
print(a)
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')
def openTargets2():
'''
from opentargets import OpenTargetsClient
client = OpenTargetsClient()
response = client.get_associations_for_target('BRAF',
fields = ['associations_score.datasource*',
'associations_score.overall',
'target.gene_info.symbol',
'disease.efo_info.*']
)
response.to_excel('BRAF_associated_diseases_by_datasource.xls')
'''
client = OpenTargetsClient()
response = client.get_associations_for_target('ENSG00000157764',
fields=['association_score.datasource*','association_score.overall','target.gene_info.symbol','disease.efo_info.*'])
print(response)
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 download_targets_for_diseases(data_dir: str):
my_gene_info = MyGeneInfo()
open_targets_client = OpenTargetsClient()
for disease_efo_id, disease_abbreviation in zip(disease_efo_ids,
DISEASE_ABBREVIATIONS):
path = os.path.join(data_dir, disease_abbreviation,
opentargets_file_name)
if os.path.exists(path):
continue
with open(path, 'w+') as file:
download_targets_for_disease(
disease_efo_id=disease_efo_id,
my_gene_info=my_gene_info,
open_targets_client=open_targets_client,
file=file,
)
def drug_info_for_genes(args):
if not os.path.exists(args.outdir):
os.makedirs(args.outdir)
with open(args.genes) as infile:
genes = [s.strip() for s in infile]
client = OpenTargetsClient()
all_results = {}
all_diseases = defaultdict(int)
num_genes = len(genes)
diseases = set(args.disease)
if args.disease_file is not None:
with open(args.disease_file) as infile:
for d in infile:
diseases.add(d.strip())
print("Diseases: " + str(diseases))
for i, g in enumerate(genes):
print('%s - %d of %d' % (g, i + 1, num_genes))
result = get_drugs(client, g, all_diseases, diseases, args.trial_phase)
all_results[g] = result
with open(os.path.join(args.outdir, 'diseases.tsv'), 'w') as outfile:
for disease in sorted(all_diseases.keys()):
outfile.write('%s\t%d\n' % (disease, all_diseases[disease]))
with open(os.path.join(args.outdir, 'gene_opentargets.json'),
'w') as outfile:
json.dump(all_results, outfile)
# write unique results
unique_results = uniqify(all_results)
with open(
os.path.join(
os.path.join(args.outdir, 'gene_opentargets_unique.json')),
'w') as outfile:
json.dump(unique_results, outfile)
# write backgrounds
compute_backgrounds(unique_results, args.outdir)
def download_targets_for_disease(
disease_efo_id: str,
open_targets_client: Optional[OpenTargetsClient] = None,
my_gene_info: Optional[MyGeneInfo] = None,
file: Optional[TextIO] = None,
) -> None:
"""
:param disease_efo_id: A disease's EFO identifier
:param open_targets_client: An OpenTargetsClient
:param my_gene_info: A MyGeneInfo client
:param file: Place to output targets for disease
"""
if open_targets_client is None:
open_targets_client = OpenTargetsClient()
associations = open_targets_client.get_associations_for_disease(
disease_efo_id,
fields=[
'associationscore.datatypes',
'target.id',
],
).filter(
datatype='known_drug',
)
ensembl_list = [
association['target']['id']
for association in associations
]
if my_gene_info is None:
my_gene_info = MyGeneInfo()
id_mappings = my_gene_info.getgenes(ensembl_list, fields="entrezgene")
print('efo', 'ncbigene', file=file, sep='\t')
for mapping in id_mappings:
entrez_gene_id = mapping.get('entrezgene')
if entrez_gene_id is not None:
print(disease_efo_id, entrez_gene_id, file=file, sep='\t')
fout = open(args.ofile, "w+") if args.ofile else sys.stdout
ids = []
if args.ifile:
fin = open(args.ifile)
while True:
line = fin.readline()
if not line: break
if line.rstrip(): ids.append(line.rstrip())
fin.close()
elif args.ids:
ids = re.split(r'[,\s]+', args.ids)
if ids: logging.info('Input IDs: {}'.format(len(ids)))
otclient = OpenTargetsClient()
logging.debug(otclient.get_stats().info)
if args.op == 'searchAssociations':
if not ids: parser.error('--i or --ids required.')
opentargets.Utils.SearchAssociations(otclient, ids, args.idtype,
args.minscore, args.skip,
args.nmax, fout)
elif args.op == 'getEvidence':
parser.error('Unimplemented operation: {}'.format(args.op))
if not ids: parser.error('--i or --ids required.')
#opentargets.Utils.Target2Disease_Evidence(otclient, tid, args.did, fout)
else:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
A script for gathering data in format suitable for bulk input into Elasticsearch index.
Combines disease codes with additional disease information from EBI Ontology Lookup Service
and associated drug interactions from Open Targets client.
@author: jderoberts
"""
from opentargets import OpenTargetsClient
import requests
import json
ot = OpenTargetsClient()
data = {}
#codes = ['EFO_0000249', 'EFO_0003885', 'EFO_0000685', 'EFO_0000313', 'EFO_0001071', 'EFO_0000305', 'EFO_0002890', 'EFO_0000478', 'EFO_1001516', 'EFO_0007460', 'Orphanet_2781', 'Orphanet_3261']
#uniqueEFOs - disease id extracted from every OpenTargets evidence object and reduced to set of unique values
codes = set()
with open('uniqueEFOs.txt') as infile:
for line in infile:
codes.add(line.rstrip())
otdata = ot.filter_associations()
j = 0
k = len(codes)
for code in codes:
#!/home/shraddhapai/anaconda2/bin/python
from opentargets import OpenTargetsClient
import sys
client = OpenTargetsClient()
disease_ID = sys.argv[1]
print disease_ID
with open('Biomart_ENGSIDs_190405.txt', mode='rU') as fp:
for line_term in fp:
line = line_term.rstrip('\n')
response = client.filter_evidence()
response.filter(target=line, disease=disease_ID)
for i, r in enumerate(response):
src = r['sourceID']
if src == 'gwas_catalog':
print(r['target']['gene_info']['symbol'],
r['target']['gene_info']['name'],
r['disease']['efo_info']['label'],
r['unique_association_fields'])
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)
import pandas as pd
import numpy as np
import os.path
import json
import urllib
from opentargets import OpenTargetsClient
from SPARQLWrapper import SPARQLWrapper, JSON
from xml.dom.minidom import parse, parseString
ot = OpenTargetsClient()
cancer_strings = ("cancer", "melanoma", "carcinoma", "leukemia", "sarcoma", "lymphoma", "Hodgkin", "tumor")
def getCancerGeneCensusData():
csv_file = 'data/cancer_gene_census.csv'
return pd.read_csv(csv_file)
def getInvertedEntrezNamesMap():
inverted_file = "data/gene_names/entrez_names_inverted"
if not os.path.isfile(inverted_file + ".npy"):
entrez_labels_map = np.load("data/gene_names/entrez_names.npy").item()
inverted_entrez_labels_map = {v: k for k, v in entrez_labels_map.items()}
np.save(inverted_file, inverted_entrez_labels_map)
return np.load(inverted_file+ ".npy").item()
def lookupDisgenet(gene):
entrez_file = "data/gene_names/entrez_names.npy"
entrez_labels_map = np.load(entrez_file).item()
import requests
import pprint
import urllib2
from opentargets import OpenTargetsClient
STRING_API_URL = "https://string-db.org/api"
ot = OpenTargetsClient()
res = ot.search('BRAF')
def getAssociationsForDisease(disease='cancer'):
return ot.get_associations_for_disease(disease)[0]
def getAssociationsForTarget(target="BRAF"):
return ot.get_associations_for_target(target)
def getAssociationByID(gene, disease):
assocs = ot.get_association('{gene}-{disease}'.format(gene=gene,
disease=disease)[0])
return assocs
# STRING DATA
class StringData:
def __init__(self, url):
self.url = url
def getStringIDs(self, lsgenes=[], limit=1):
def setUp(self):
self.client = OpenTargetsClient()
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)
import argparse
import sys
import numpy as np
from opentargets import OpenTargetsClient
ot = OpenTargetsClient()
#This script queries the Open Targets REST API using either a target id or disease id.
#This returns the maximum, minimum, mean and standard deviations of the association scores.
__version__ = '0.1'
__date__ = '23Aug2019'
__author__ = '*****@*****.**'
Description = 'version %s, date %s, author %s' % (__version__, __date__,
__author__)
Parser = argparse.ArgumentParser(description=Description)
Parser.add_argument(
'-t',
'--target_id',
metavar='STRING',
dest='target_id',
#required=True,
help='Please supply gene target id')
Parser.add_argument(
'-d',
'--disease_id',
metavar='STRING',
dest='disease_id',
}
disease_id = datadict_disease.get("disease")
#First, print an error message if no argument is provided.
#Then, run appropriat code depending on input argument (target or disase)
if target_id == None and disease_id == None:
print(
"Error: target_id or disease_id must be provided. Provide a target_id such as ENSG00000197386 or disease_id such as Orphanet_399."
)
elif target_id != None and disease_id != None:
print(
"Error: One argument should be provided at a time. Provide either a target_id such as ENSG00000197386 or disease_id such as Orphanet_399."
)
else:
#get associations
client = OpenTargetsClient()
response = client.filter_associations()
#filter, calculate and print required information for a target or disease
if target_id != None:
#filter for target_id. Print target_id, disease_id & association_score.overall.
filtered = response.filter(target=target_id)
target_filtered = filtered.to_dataframe()
target_fin = target_filtered[[
"target.id", "disease.id", "association_score.overall"
]]
print(target_fin)
#calculate and print maximum, minimum and average and standard deviation values of association_score.overall
maximum = target_fin["association_score.overall"].max()
minimum = target_fin["association_score.overall"].min()
average = target_fin["association_score.overall"].mean()
def ot_version():
ot = OpenTargetsClient()
stats = ot.get_stats()
return str(stats.info['data_version'])
