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_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 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 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)