Mercurial > repos > galaxyp > unipept

comparison unipept.py @ 1:b65ee881ca64 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository http://unipept.ugent.be/apidocs commit e91b0fe16bf468b34884508652359b91847d1f95
author galaxyp
date Tue, 22 Jan 2019 20:58:28 -0500
parents b33376bf2290
children dca8a1fe0bf3
comparison
equal deleted inserted replaced
0:b33376bf2290 1:b65ee881ca64
181 def best_match(peptide,matches): 181 def best_match(peptide,matches):
182 if not matches: 182 if not matches:
183 return None 183 return None
184 elif len(matches) == 1: 184 elif len(matches) == 1:
185 return matches[0].copy() 185 return matches[0].copy()
186 else: 186 elif 'taxon_rank' in matches[0]:
187 # find the most specific match (peptide is always the first column order field) 187 # find the most specific match (peptide is always the first column order field)
188 for col in reversed(pept2lca_extra_column_order[1:]): 188 for col in reversed(pept2lca_extra_column_order[1:]):
189 col_id = col+"_id" if options.extra else col 189 col_id = col+"_id" if options.extra else col
190 for match in matches: 190 for match in matches:
191 if 'taxon_rank' in match and match['taxon_rank'] == col: 191 if 'taxon_rank' in match and match['taxon_rank'] == col:
192 return match.copy() 192 return match.copy()
193 if col_id in match and match[col_id]: 193 if col_id in match and match[col_id]:
194 return match.copy() 194 return match.copy()
195 else:
196 return sorted(matches, key=lambda x: len(x['peptide']))[-1].copy()
195 return None 197 return None
196 198
197 def get_taxon_json(resp): 199 def get_taxon_json(resp):
198 found_keys = set() 200 found_keys = set()
199 for i,pdict in enumerate(resp): 201 for i,pdict in enumerate(resp):
278 for ec in pdict['ec']: 280 for ec in pdict['ec']:
279 child = None 281 child = None
280 protein_count = ec['protein_count'] 282 protein_count = ec['protein_count']
281 ec_number = ec['ec_number'] 283 ec_number = ec['ec_number']
282 for ec_id in get_ids(ec_number): 284 for ec_id in get_ids(ec_number):
283 child = get_node(ec_id,ec_id,child,seq) 285 ec_name = str(ec_id)
286 ## if len(ec_id) == 3:
287 ## ec_name = '%s\n%s\n%s' %(str(ec_id), ec_name_dict[str(ec_id[0])], ec_name_dict[str(ec_id)])
288 child = get_node(ec_id,ec_name,child,seq)
284 seq = None 289 seq = None
285 if child: 290 if child:
286 get_node(0,'-.-.-.-',child,None) 291 get_node(0,'-.-.-.-',child,None)
287 return root 292 return root
288 293
497 post_data.append(("extra","true")) 502 post_data.append(("extra","true"))
498 if options.domains: 503 if options.domains:
499 post_data.append(("domains","true")) 504 post_data.append(("domains","true"))
500 post_data += [('input[]', x) for x in trypticPeptides[idx[i]:idx[i+1]]] 505 post_data += [('input[]', x) for x in trypticPeptides[idx[i]:idx[i+1]]]
501 if options.debug: print >> sys.stdout, "post_data: %s\n" % (str(post_data)) 506 if options.debug: print >> sys.stdout, "post_data: %s\n" % (str(post_data))
502 params = '&'.join(['%s=%s' % (i[0],i[1]) for i in post_data]) 507 headers = {'Content-Type': 'application/x-www-form-urlencoded', 'Accept': 'application/json'}
503 #headers = {'Content-Type': 'application/x-www-form-urlencoded', 'Accept': 'application/json'} 508 ## headers = {'Accept': 'application/json'}
504 headers = {'Accept': 'application/json'}
505 url = '%s/%s' % (options.url.rstrip('/'),options.unipept) 509 url = '%s/%s' % (options.url.rstrip('/'),options.unipept)
506 if options.get: 510 if options.get:
511 params = '&'.join(['%s=%s' % (i[0],i[1]) for i in post_data])
507 url = '%s.json?%s' % (url,params) 512 url = '%s.json?%s' % (url,params)
508 req = urllib2.Request( url ) 513 req = urllib2.Request( url )
509 else: 514 else:
510 url = '%s.json' % (url) 515 url = '%s.json' % (url)
511 req = urllib2.Request( url, headers = headers, data = urllib.urlencode(post_data) ) 516 req = urllib2.Request( url, headers = headers, data = urllib.urlencode(post_data) )
544 else: 549 else:
545 for key,match in keyToMatch.iteritems(): 550 for key,match in keyToMatch.iteritems():
546 match['tryptic_peptide'] = match['peptide'] 551 match['tryptic_peptide'] = match['peptide']
547 match['peptide'] = peptide 552 match['peptide'] = peptide
548 peptideMatches.append(match) 553 peptideMatches.append(match)
549 elif options.unipept in ['pept2lca']: 554 elif options.unipept in ['pept2lca', 'peptinfo']:
550 ## should be one response per trypticPeptide for pep2lca 555 ## should be one response per trypticPeptide for pep2lca
551 respMap = {v['peptide']:v for v in unipept_resp} 556 respMap = {v['peptide']:v for v in unipept_resp}
552 ## map resp back to peptides 557 ## map resp back to peptides
553 for peptide in peptides: 558 for peptide in peptides:
554 matches = list() 559 matches = list()