def get_pubmed_id_for_pubchem_id(pubchem_id):
"""
This takes a PubChem id and then gets the PMIDs for articles on PubMed from PubChem which include this entity.
"""
if not isinstance(pubchem_id, str):
return None
requests = CacheControlHelper()
url = 'https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/' + str(pubchem_id) + '/xrefs/PubMedID/JSON'
try:
r = requests.get(url, timeout=10)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryPubChem for URL: ' + url, file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryPubChem for URL: %s' % (e, url), file=sys.stderr)
return None
if r is not None:
if 'Fault' in r.json().keys():
return None
else:
ans = [str(x) + '[uid]' for x in r.json()['InformationList']['Information'][0]['PubMedID']]
return ans
else:
return None
def query_oxo(uid):
"""
This takes a curie id and send that id to EMBL-EBI OXO to convert to cui
"""
url_str = 'https://www.ebi.ac.uk/spot/oxo/api/mappings?fromId=' + str(uid)
requests = CacheControlHelper()
try:
res = requests.get(url_str, headers={'accept': 'application/json'}, timeout=120)
except requests.exceptions.Timeout:
print('HTTP timeout in SemMedInterface.py; URL: ' + url_str, file=sys.stderr)
time.sleep(1) ## take a timeout because NCBI rate-limits connections
return None
except requests.exceptions.ConnectionError:
print('HTTP connection error in SemMedInterface.py; URL: ' + url_str, file=sys.stderr)
time.sleep(1) ## take a timeout because NCBI rate-limits connections
return None
except sqlite3.OperationalError:
print('Error reading sqlite cache; URL: ' + url_str, file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print('HTTP response status code: ' + str(status_code) + ' for URL:\n' + url_str, file=sys.stderr)
res = None
return res
def get_reactome_names(id):
'''
Takes a reactome id then return a string containing all synonyms listed on reactome seperated by the deliminator |
However, If it finds a MeSH terms in the list it will return the search term as a mesh term serach
e.g. it will return something like '(IGF1R)[MeSH Terms]'
This can be inputed into the google function as a non mesh term and will search as a mesh term.
This is so that we do not need to handle the output of this function any differently it can all be input as non mesh terms
Parameters:
id - a string containing the reactome id
Output:
search - a string containing all synonyms of the reactome id or a mesh term formatted for the google distance function
'''
# We want the actual reactome name R-HSA..., not the curie REACT:R-HSA...
if "REACT:" in id:
id = ":".join(id.split(":")[1:])
url = 'https://reactome.org/ContentService/data/query/' + id + '/name' # hardcoded url for reactiome names
requests = CacheControlHelper()
r = requests.get(url,
headers={'User-Agent': 'Mozilla/5.0'
}) # sends get request that returns a string
if r.status_code != 200:
print('HTTP response status code: ' + str(r.status_code) +
' for URL:\n' + url,
file=sys.stderr)
return None
nameList = r.text.split('\n') # splits returned string by line
search = '' # initializes search term variable
for name in nameList:
if len(
name
) > 0: # removes blank lines at beginning and end of response
if len(re.compile("[()]").split(
name)) > 1: # check for parenthesis
for n in re.compile("[()]").split(
name): # splits on either "(" or ")"
if len(n) > 0: # removes banks generated by split
if QueryNCBIeUtils.is_mesh_term(
n): # check for mesh term
search += '|' + n + '[MeSH Terms]'
else:
search += '|' + n
elif len(name.split('ecNumber')) > 1: # checks for ec number
if QueryNCBIeUtils.is_mesh_term(name.split('ecNumber')[0]):
search += '|' + name.split(
'ecNumber')[0] + '[MeSH Terms]'
else:
search += '|' + name.split('ecNumber')[0]
search += '|' + name.split(
'ecNumber'
)[1][:-1] + '[EC/RN Number]' # removes trailing "/" and formats as ec search term
else:
if QueryNCBIeUtils.is_mesh_term(name):
search += '|' + name + '[MeSH Terms]'
else:
search += '|' + name
search = search[1:] # removes leading |
return search
def get_cui(chemical_substance_id):
if chemical_substance_id[:7].upper() == "CHEMBL:":
chemical_substance_id = "CHEMBL" + chemical_substance_id[7:]
handler = 'chem/' + chemical_substance_id + '?fields=drugcentral.xref.umlscui'
requests = CacheControlHelper()
url = QueryMyChem.API_BASE_URL + '/' + handler
try:
res = requests.get(url, timeout=QueryMyChem.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryMyChem for URL: ' + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryMyChem for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
# print(url, file=sys.stderr)
# print('Status code ' + str(status_code) + ' for url: ' + url, file=sys.stderr)
return None
id_json = res.json()
res = None
if 'drugcentral' in id_json.keys():
if 'xref' in id_json['drugcentral'].keys():
if 'umlscui' in id_json['drugcentral']['xref'].keys():
res = id_json['drugcentral']['xref']['umlscui']
return res
def send_query_get(handler, url_suffix):
requests = CacheControlHelper()
url = QueryChEMBL.API_BASE_URL + '/' + handler + '?' + url_suffix
# print(url)
try:
res = requests.get(url, timeout=QueryChEMBL.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryChEMBL for URL: ' + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryChEMBL for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url,
file=sys.stderr)
return None
return res.json()
def send_query_get(entity, url_suffix):
requests = CacheControlHelper()
url_str = QueryPharos.API_BASE_URL + "/" + entity + url_suffix
#print(url_str)
try:
res = requests.get(url_str)
except requests.exceptions.Timeout:
print(url_str, file=sys.stderr)
print('Timeout in QueryMiRBase for URL: ' + url_str,
file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryMiRBase for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
#print("Status code="+str(status_code))
assert status_code in [200, 404]
if status_code == 404:
res = None
return res
def send_query_post(handler, params, retmax=1000):
requests = CacheControlHelper()
url_str = QueryNCBIeUtils.API_BASE_URL + '/' + handler
params['retmax'] = str(retmax)
params['retmode'] = 'json'
# print(url_str)
try:
res = requests.post(url_str,
data=params,
timeout=QueryNCBIeUtils.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print('HTTP timeout in QueryNCBIeUtils.py; URL: ' + url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
except requests.exceptions.ConnectionError:
print('HTTP connection error in QueryNCBIeUtils.py; URL: ' +
url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
status_code = res.status_code
if status_code != 200:
print('HTTP response status code: ' + str(status_code) +
' for URL:\n' + url_str,
file=sys.stderr)
res = None
return res
def __access_api(handler, url_suffix, params=None, return_raw=False):
requests = CacheControlHelper()
if url_suffix:
url = QueryMyGeneExtended.API_BASE_URL + '/' + handler + '?' + url_suffix
else:
url = QueryMyGeneExtended.API_BASE_URL + '/' + handler
headers = {'user-agent': "mygene.py/%s python-requests/%s" % ("1.0.0", "1.0.0"), 'Accept': 'application/json'}
try:
res = requests.get(url, params=params, timeout=QueryMyGeneExtended.TIMEOUT_SEC, headers=headers)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryMyGeneExtended for URL: ' + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryMyGeneExtended for URL: %s' % (e, url), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url, file=sys.stderr)
return None
if return_raw:
return res.text
else:
return res.json()
def send_query_get(handler, url_suffix):
requests = CacheControlHelper()
url_str = QueryEBIOLS.API_BASE_URL + '/' + handler + "/" + url_suffix
# print(url_str)
try:
res = requests.get(url_str, timeout=QueryEBIOLS.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print('HTTP timeout in QueryNCBIeUtils.py; URL: ' + url_str, file=sys.stderr)
time.sleep(1) # take a timeout because NCBI rate-limits connections
return None
except requests.exceptions.ConnectionError:
print('HTTP connection error in QueryNCBIeUtils.py; URL: ' + url_str, file=sys.stderr)
time.sleep(1) # take a timeout because NCBI rate-limits connections
return None
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryEBIOLS for URL: %s' % (e, url_str), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print('HTTP response status code: ' + str(status_code) + ' for URL:\n' + url_str, file=sys.stderr)
res = None
return res
def send_query_get(handler, url_suffix):
requests = CacheControlHelper()
url_str = QueryMiRGate.API_BASE_URL + "/" + handler + "/" + url_suffix
# print(url_str)
try:
res = requests.get(url_str, timeout=QueryMiRGate.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url_str, file=sys.stderr)
print("Timeout in QueryMiRGate for URL: " + url_str, file=sys.stderr)
return None
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryMiRGate for URL: %s' % (e, url_str), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url_str, file=sys.stderr)
print("Status code " + str(status_code) + " for url: " + url_str, file=sys.stderr)
return None
if len(res.content) == 0:
print(url_str, file=sys.stderr)
print("Empty response from URL!", file=sys.stderr)
res = None
return res
def __access_api(handler):
requests = CacheControlHelper()
url = QueryEBIOLSExtended.API_BASE_URL + '/' + handler
# print(url)
try:
res = requests.get(url, timeout=QueryEBIOLSExtended.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryEBIOLSExtended for URL: ' + url,
file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryEBIOLSExtended for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url,
file=sys.stderr)
return None
return res.text
def __access_api(url):
requests = CacheControlHelper()
url = url + '.xml'
try:
res = requests.get(url, timeout=QueryHMDB.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryHMDB for URL: ' + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryHMDB for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url,
file=sys.stderr)
return None
return res.text
def __retrieve_entries_from_url():
# network request
requests = CacheControlHelper()
try:
res = requests.get(GenerateMetabolitesTSV.URL)
except requests.exceptions.Timeout:
print(GenerateMetabolitesTSV.URL, file=sys.stderr)
print("Timeout for URL: " + GenerateMetabolitesTSV.URL,
file=sys.stderr)
return False
except BaseException as e:
print(GenerateMetabolitesTSV.URL, file=sys.stderr)
print('%s received in GenerateMetabolitesTSV for URL: %s' %
(e, GenerateMetabolitesTSV.URL),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(GenerateMetabolitesTSV.URL, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' +
GenerateMetabolitesTSV.URL,
file=sys.stderr)
return False
# save content to file
with open(GenerateMetabolitesTSV.FILE_NAME, 'wb') as fd:
for chunk in res.iter_content(1024):
fd.write(chunk)
return True
def __access_api(handler):
api_base_url = 'http://www.uniprot.org'
url = api_base_url + '/' + handler
#print(url)
contact = "*****@*****.**"
header = {'User-Agent': 'Python %s' % contact}
requests = CacheControlHelper()
try:
res = requests.get(url,
timeout=QueryUniprot.TIMEOUT_SEC,
headers=header)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryUniprot for URL: ' + url, file=sys.stderr)
return None
except requests.exceptions.ChunkedEncodingError:
print(url, file=sys.stderr)
print('ChunkedEncodingError for URL: ' + url, file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryUniprot for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url,
file=sys.stderr)
return None
return res.text
def get_request_with_cookie(url):
API_KEY = '1YCxuN7PRHyrpuZnO7F5gQ'
API_BASE_URL = 'https://api.omim.org/api'
session_data = {'apiKey': API_KEY,
'format': 'json'}
requests = CacheControlHelper()
r = requests.sess.post(API_BASE_URL + "/apiKey", data=session_data)
assert 200 == r.status_code
cookie = r.cookies
try:
res = requests.get(url, cookies=cookie)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print("Timeout in QueryOMIM for URL: " + url, file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryOMIM for URL: %s' % (e, url), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print("Status code " + str(status_code) + " for URL: " + url, file=sys.stderr)
return None
return res.json()
def send_query_get(self, omim_handler, url_suffix):
requests = CacheControlHelper()
url = "{api_base_url}/{omim_handler}?{url_suffix}&format=json".format(
api_base_url=QueryOMIM.API_BASE_URL,
omim_handler=omim_handler,
url_suffix=url_suffix)
# print(url)
try:
res = requests.get(url, cookies=self.cookie)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print("Timeout in QueryOMIM for URL: " + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryOMIM for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print("Status code " + str(status_code) + " for URL: " + url,
file=sys.stderr)
return None
return res
def __init__(self):
requests = CacheControlHelper()
url = QueryOMIMExtended.API_BASE_URL + "/apiKey"
session_data = {'apiKey': QueryOMIMExtended.API_KEY, 'format': 'json'}
r = requests.post(url, data=session_data)
assert 200 == r.status_code
self.cookie = r.cookies
def send_query_get(handler, st):
url_str = QueryUMLS.API_BASE_URL + '/' + handler + '&ticket=' + st
requests = CacheControlHelper()
try:
res = requests.get(url_str,
headers={'accept': 'application/json'},
timeout=QueryUMLS.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print('HTTP timeout in QueryNCBIeUtils.py; URL: ' + url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
except requests.exceptions.ConnectionError:
print('HTTP connection error in QueryNCBIeUtils.py; URL: ' +
url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
status_code = res.status_code
if status_code != 200:
print('HTTP response status code: ' + str(status_code) +
' for URL:\n' + url_str,
file=sys.stderr)
res = None
return res
def get_single_ticket(tgt):
params = {'service': "http://umlsks.nlm.nih.gov"}
h = {
"Content-type": "application/x-www-form-urlencoded",
"Accept": "text/plain",
"User-Agent": "python"
}
requests = CacheControlHelper()
r = requests.post(tgt, data=params, headers=h)
st = r.text
return st
def uniprot_id_to_reactome_pathways(uniprot_id):
"""returns a ``set`` of reactome IDs of pathways associated with a given string uniprot ID
:param uniprot_id: a ``str`` uniprot ID, like ``"P68871"``
:returns: a ``set`` of string Reactome IDs
"""
payload = {
'from': 'ACC',
'to': 'REACTOME_ID',
'format': 'tab',
'query': uniprot_id
}
contact = "*****@*****.**"
header = {'User-Agent': 'Python %s' % contact}
requests = CacheControlHelper()
try:
url = QueryUniprot.API_BASE_URL
res = requests.post(QueryUniprot.API_BASE_URL,
data=payload,
headers=header)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryUniprot for URL: ' +
QueryUniprot.API_BASE_URL,
file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryUniprot for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(QueryUniprot.API_BASE_URL, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' +
QueryUniprot.API_BASE_URL,
file=sys.stderr)
return None
# assert 200 == res.status_code
res_set = set()
for line in res.text.splitlines():
field_str = line.split("\t")[1]
if field_str != "To":
res_set.add(field_str)
return res_set
def get_ticket_gen():
# params = {'username': self.username,'password': self.password}
params = {'apikey': QueryUMLS.api_key}
h = {
"Content-type": "application/x-www-form-urlencoded",
"Accept": "text/plain",
"User-Agent": "python"
}
requests = CacheControlHelper()
r = requests.post(QueryUMLS.Ticket_URL + QueryUMLS.auth_endpoint,
data=params,
headers=h)
response = fromstring(r.text)
## extract the entire URL needed from the HTML form (action attribute) returned - looks similar to https://utslogin.nlm.nih.gov/cas/v1/tickets/TGT-36471-aYqNLN2rFIJPXKzxwdTNC5ZT7z3B3cTAKfSc5ndHQcUxeaDOLN-cas
## we make a POST call to this URL in the getst method
tgt = response.xpath('//form/@action')[0]
return tgt
def send_query_get(handler, url_suffix, retmax=1000, retry_flag=True):
requests = CacheControlHelper()
url_str = QueryNCBIeUtils.API_BASE_URL + '/' + handler + '?' + url_suffix + '&retmode=json&retmax=' + str(
retmax)
# print(url_str)
try:
res = requests.get(url_str,
headers={
'accept': 'application/json',
'User-Agent': 'Mozilla/5.0'
},
timeout=QueryNCBIeUtils.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print('HTTP timeout in QueryNCBIeUtils.py; URL: ' + url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
except requests.exceptions.ConnectionError:
print('HTTP connection error in QueryNCBIeUtils.py; URL: ' +
url_str,
file=sys.stderr)
time.sleep(
1) ## take a timeout because NCBI rate-limits connections
return None
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryMiRGate for URL: %s' % (e, url_str),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
if status_code == 429 and retry_flag:
time.sleep(1)
res = QueryNCBIeUtils.send_query_get(handler, url_suffix,
retmax, False)
else:
print('HTTP response status code: ' + str(status_code) +
' for URL:\n' + url_str,
file=sys.stderr)
res = None
return res
def get_request(url):
requests = CacheControlHelper()
try:
res = requests.get(url, timeout=120)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout for URL: ' + url, file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url, file=sys.stderr)
print('%s received for URL: %s' % (e, url), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url, file=sys.stderr)
return None
return res.json()
def get_uniprot_names(id):
"""
Takes a uniprot id then return a string containing all synonyms listed on uniprot seperated by the deliminator |
:param id: a string containing the uniprot id
:returns: a string containing all synonyms uniprot lists for
"""
# We want the actual uniprot name P176..., not the curie UniProtKB:P176...
if "UniProtKB:" in id:
id = ":".join(id.split(":")[1:])
url = 'https://www.uniprot.org/uniprot/?query=id:' + id + '&sort=score&columns=entry name,protein names,genes&format=tab' # hardcoded url for uniprot data
requests = CacheControlHelper()
r = requests.get(url, headers={'User-Agent':
'Mozilla/5.0'}) # send get request
if r.status_code != 200: # checks for error
print('HTTP response status code: ' + str(r.status_code) +
' for URL:\n' + url,
file=sys.stderr)
return None
if r.content.decode('utf-8') == '':
return None
df = pandas.read_csv(StringIO(r.content.decode('utf-8')), sep='\t')
search = df.loc[0, 'Entry name'] # initializes search term variable
if type(df.loc[0, 'Protein names']) == str:
for name in re.compile("[()\[\]]").split(
df.loc[0, 'Protein names']): # checks for protein section
if len(name) > 1:
if QueryNCBIeUtils.is_mesh_term(name):
search += '|' + name + '[MeSH Terms]'
else:
search += '|' + name
if type(df.loc[0, 'Gene names']) == str:
for name in df.loc[0, 'Gene names'].split(' '):
if len(name) > 1:
if QueryNCBIeUtils.is_mesh_term(name):
search += '|' + name + '[MeSH Terms]'
else:
search += '|' + name
return search
def send_query_get(handler, url_suffix):
requests = CacheControlHelper()
url = QueryDisont.API_BASE_URL + "/" + handler + "/" + url_suffix
# print(url_str)
try:
res = requests.get(url, timeout=QueryDisont.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QueryDisont for URL: ' + url, file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QueryDisont for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print('Status code ' + str(status_code) + ' for url: ' + url,
file=sys.stderr)
return None
return res
def send_query_get(handler, url_suffix):
requests = CacheControlHelper()
url_str = QueryMiRBase.API_BASE_URL + "/" + handler + "?" + url_suffix
# print(url_str)
try:
res = requests.get(url_str)
except requests.exceptions.Timeout:
print(url_str, file=sys.stderr)
print('Timeout in QueryMiRBase for URL: ' + url_str,
file=sys.stderr)
return None
except KeyboardInterrupt:
sys.exit(0)
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryMiRBase for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
assert status_code == 200
return res
def __access_api(url, params=None, headers=None):
# print(url)
requests = CacheControlHelper()
try:
res = requests.get(url,
params=params,
timeout=QuerySciGraph.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url, file=sys.stderr)
print('Timeout in QuerySciGraph for URL: ' + url, file=sys.stderr)
return None
except BaseException as e:
print(url, file=sys.stderr)
print('%s received in QuerySciGraph for URL: %s' % (e, url),
file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url, file=sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + res.url,
file=sys.stderr)
return None
return res.json()
def send_query(query):
requests = CacheControlHelper()
res = requests.get(query, timeout=120)
return res.text
def query_mesh_id_to_uniprot_ids_desc(mesh_id):
ent = 'disease'
id = 'mesh'
STR = "c1.MESH = '"
intfield = mesh_id
seq = ( """
DEFINE
c0='/data/gene_disease_summary',
c1='/data/diseases',
c2='/data/genes',
c4='/data/sources'
ON
'http://www.disgenet.org/web/DisGeNET'
SELECT
c1 (diseaseId, name, diseaseClassName, STY, MESH, OMIM, type ),
c2 (geneId, symbol, uniprotId, description, pantherName ),
c0 (score, EI, Npmids, Nsnps)
FROM
c0
WHERE
(
""" + STR + mesh_id+"""'
AND
c4 = 'ALL'
)
ORDER BY
c0.score DESC""" ); #
binary_data = seq.encode('utf-8')
url_str = QueryDisGeNet.SPARQL_ENDPOINT_URL
requests = CacheControlHelper()
try:
res = requests.post(url_str, data=binary_data, timeout=QueryDisGeNet.TIMEOUT_SEC)
except requests.exceptions.Timeout:
print(url_str, sys.stderr)
print('Timeout in QueryDisGeNet for URL: ' + url_str, file=sys.stderr)
return dict()
except BaseException as e:
print(url_str, file=sys.stderr)
print('%s received in QueryDisGeNet for URL: %s' % (e, url_str), file=sys.stderr)
return None
status_code = res.status_code
if status_code != 200:
print(url_str, sys.stderr)
print('Status code ' + str(status_code) + ' for url: ' + url_str, file=sys.stderr)
return dict()
if len(res.content) == 0:
print(url_str, file=sys.stderr)
print('Empty response from URL!', file=sys.stderr)
return dict()
ret_data_df = pandas.read_csv(io.StringIO(res.content.decode('utf-8')), sep='\t').head(QueryDisGeNet.MAX_GENES_FOR_DISEASE)
uniprot_ids_list = ret_data_df['c2.uniprotId'].tolist()
gene_names_list = ret_data_df['c2.symbol'].tolist()
ret_dict = dict(list(zip(uniprot_ids_list, gene_names_list)))
for prot in ret_dict.copy().keys():
if type(prot)==str and prot != "null":
if '.' in prot or ';' in prot:
gene = ret_dict[prot]
del ret_dict[prot]
prot.replace('.', '')
prots_to_add = prot.split(';')
if len(prots_to_add) > QueryDisGeNet.MAX_PROTS_FOR_GENE:
prots_to_add = prots_to_add[0:QueryDisGeNet.MAX_PROTS_FOR_GENE]
dict_add = dict()
for prot_name in prots_to_add:
if type(prot_name) == str and prot_name != "null":
dict_add[prot_name] = gene
ret_dict.update(dict_add)
else: ## this is a math.nan
del ret_dict[prot]
return(ret_dict)