hkmztrk / smilesvecproteinrepresentation Goto Github PK

When fetching interactions if any connection error occurs fetch process is ended. It might be good if there is a --max-try parameter to continue trying after this error.

Error message is below;

('Fetching interactions for', 'P63092', 'CHEMBL4377')
Traceback (most recent call last):
File "getligprotvec.py", line 104, in
getProteinVec(proteins_path)
File "getligprotvec.py", line 78, in getProteinVec
PLIlist = getLigandInteractions(proteins_path)
File "getligprotvec.py", line 63, in getLigandInteractions
compounds = activity_parser(activities)
File "getligprotvec.py", line 38, in activity_parser
for activity in activities:
File "/home/srb/.local/lib/python2.7/site-packages/chembl_webresource_client/query_set.py", line 116, in next
self.chunk = self.query.next_page()
File "/home/srb/.local/lib/python2.7/site-packages/chembl_webresource_client/url_query.py", line 435, in next_page
return self.get_page()
File "/home/srb/.local/lib/python2.7/site-packages/chembl_webresource_client/url_query.py", line 390, in get_page
res = session.post(self.base_url + '.' + self.frmt, json=data, timeout=self.timeout)
File "/home/srb/.local/lib/python2.7/site-packages/requests/sessions.py", line 581, in post
return self.request('POST', url, data=data, json=json, **kwargs)
File "/home/srb/.local/lib/python2.7/site-packages/requests_cache/core.py", line 132, in request
**kwargs
File "/home/srb/.local/lib/python2.7/site-packages/requests/sessions.py", line 533, in request
resp = self.send(prep, **send_kwargs)
File "/home/srb/.local/lib/python2.7/site-packages/requests_cache/core.py", line 105, in send
return send_request_and_cache_response()
File "/home/srb/.local/lib/python2.7/site-packages/requests_cache/core.py", line 97, in send_request_and_cache_response
response = super(CachedSession, self).send(request, **kwargs)
File "/home/srb/.local/lib/python2.7/site-packages/requests/sessions.py", line 646, in send
r = adapter.send(request, **kwargs)
File "/home/srb/.local/lib/python2.7/site-packages/requests/adapters.py", line 498, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', BadStatusLine("''",))

When I try to generate protein vectors with;

python getligprotvec.py drug.l8.chembl23.canon.ws20.txt

command, same vector is written to protein.vec file. I'm attaching prots_sample.txt and protein.vec files.

prots_sample.txt

protein.vec.zip

When I try to get vectors of human proteins using;

python getligprotvec.py drug.pubchem.canon.l8.ws20.txt

or

python getligprotvec.py drug.l8.chembl23.canon.ws20.txt

I got error as;

('Fetching interactions for', 'Q9HAV4', 'none')
Traceback (most recent call last):
  File "getligprotvec.py", line 103, in <module>
    getProteinVec(proteins_path)
  File "getligprotvec.py", line 94, in getProteinVec
    sumVec = [sumVec[i]/len(ligands) for i in range(len(sumVec))]
ZeroDivisionError: float division by zero

If you need any further info I can happy to supply it.

Created protein vectors saved in a list by the getligprotvec.py in order to protein names in smiles_sample.txt. For big files it creates a readability problem. A dictionary might help for this issue such as ['protname1':[vectorvalue1, vectorvalue2], ['protname2':[vectorvalue1, vectorvalue2] ... ]

The created protein vector can be opened with python2 but can not be opened with python3.

>>> import pickle
>>> pickle.load(open("protein.vec"))
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: a bytes-like object is required, not 'str'