Mercurial > repos > proteore > proteore_data_manager

comparison data_manager/resource_building.py @ 7:b8565596bb25 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 7afd4b3ee25f024257ccbac6e51076d25b2a04e7"
author proteore
date Thu, 20 Aug 2020 03:33:35 -0400
parents 8f33a6e6e36c
children
comparison
equal deleted inserted replaced
6:8f33a6e6e36c 7:b8565596bb25
552 output_file = 'nextprot_ref_'+ time.strftime("%d-%m-%Y") + ".tsv" 552 output_file = 'nextprot_ref_'+ time.strftime("%d-%m-%Y") + ".tsv"
553 path = os.path.join(target_directory,output_file) 553 path = os.path.join(target_directory,output_file)
554 name = "neXtProt release "+time.strftime("%d-%m-%Y") 554 name = "neXtProt release "+time.strftime("%d-%m-%Y")
555 release_id = "nextprot_ref_"+time.strftime("%d-%m-%Y") 555 release_id = "nextprot_ref_"+time.strftime("%d-%m-%Y")
556 556
557 output = open(path, 'w') 557 output = open('test.csv', 'w')
558 writer = csv.writer(output,delimiter="\t") 558 writer = csv.writer(output,delimiter="\t")
559 559
560 nextprot_file=[["NextprotID","MW","SeqLength","IsoPoint","Chr","SubcellLocations","Diseases","TMDomains","ProteinExistence"]] 560 nextprot_file=[["NextprotID","ProteinName","SeqLength","MW","IsoPoint","TMDomains","SubcellLocations","Diseases","Function","PostTranslationalModifications","ProteinFamily","Pathway","ProteinExistence","Chr"]]
561 writer.writerows(nextprot_file) 561 writer.writerows(nextprot_file)
562 562
563 for id in ids : 563 for id in ids :
564 query="https://api.nextprot.org/entry/"+id+".json" 564 query="https://api.nextprot.org/entry/"+id+".json"
565 try: 565 try:
566 resp = requests.get(url=query) 566 resp = requests.get(url=query)
567 except : 567 except :
568 print ("wainting 1 hour before trying again") 568 print ("waiting 15 minutes before trying again")
569 time.sleep(3600) 569 time.sleep(900)
570 resp = requests.get(url=query) 570 resp = requests.get(url=query)
571 data = resp.json() 571 data = resp.json()
572 572
573 #get info from json dictionary 573 #get info from json dictionary
574 mass_mol = data["entry"]["isoforms"][0]["massAsString"] 574 mass_mol = data["entry"]["isoforms"][0]["massAsString"]
575 seq_length = data['entry']["isoforms"][0]["sequenceLength"] 575 seq_length = data['entry']["isoforms"][0]["sequenceLength"]
576 iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"] 576 iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"]
577 chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"] 577 chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"]
578 protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level']) 578 protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level'])
579 protein_name = data['entry']["overview"]['proteinNames'][0]['name']
580
581 #get families description
582 if 'families' in data['entry']["overview"] and len(data['entry']["overview"]['families']) > 0:
583 families = data['entry']["overview"]['families']
584 families = [entry['description'] for entry in families]
585 protein_family = ";".join(families)
586 else:
587 protein_family = 'NA'
588
589 #get Protein function
590 if 'function-info' in data['entry']['annotationsByCategory'].keys():
591 function_info = data['entry']['annotationsByCategory']['function-info']
592 function_info = [entry['description'] for entry in function_info if entry['qualityQualifier'] == 'GOLD']
593 function = ';'.join(function_info)
594 else :
595 function = 'NA'
596
597 #Get ptm-info
598 post_trans_mod = 'NA'
599 if 'ptm-info' in data['entry']['annotationsByCategory'].keys():
600 ptm_info = data['entry']['annotationsByCategory']['ptm-info']
601 infos = [entry['description'] for entry in ptm_info if entry['qualityQualifier'] == 'GOLD']
602 post_trans_mod = ";".join(infos)
603
604 #Get pathway(s)
605 if 'pathway' in data['entry']['annotationsByCategory'].keys():
606 pathways = data['entry']['annotationsByCategory']['pathway']
607 pathways = [entry['description'] for entry in pathways if entry['qualityQualifier'] == 'GOLD']
608 pathway = ";".join(pathways)
609 else :
610 pathway = 'NA'
579 611
580 #put all subcell loc in a set 612 #put all subcell loc in a set
581 if "subcellular-location" in data['entry']["annotationsByCategory"].keys() : 613 if "subcellular-location" in data['entry']["annotationsByCategory"].keys() :
582 subcell_locs = data['entry']["annotationsByCategory"]["subcellular-location"] 614 subcell_locs = data['entry']["annotationsByCategory"]["subcellular-location"]
583 all_subcell_locs = set() 615 all_subcell_locs = set()
608 for tm in tm_domains : 640 for tm in tm_domains :
609 all_tm_domains.add(tm['cvTermName']) 641 all_tm_domains.add(tm['cvTermName'])
610 nb_domains+=1 642 nb_domains+=1
611 #print "nb domains ++" 643 #print "nb domains ++"
612 #print (nb_domains) 644 #print (nb_domains)
645
613 nextprot_file[:] = [] 646 nextprot_file[:] = []
614 nextprot_file.append([id,mass_mol,str(seq_length),iso_elec_point,chr_loc,all_subcell_locs,all_diseases,str(nb_domains),protein_existence]) 647 nextprot_file.append([id,protein_name,str(seq_length),mass_mol,iso_elec_point,str(nb_domains),all_subcell_locs,all_diseases,function,post_trans_mod,protein_family,pathway,protein_existence,chr_loc])
615 writer.writerows(nextprot_file) 648 writer.writerows(nextprot_file)
616 649
617 id = str(10000000000 - int(time.strftime("%Y%m%d"))) 650 id = str(10000000000 - int(time.strftime("%Y%m%d")))
618 651
619 data_table_entry = dict(id=id, release=release_id, name = name, value = path) 652 data_table_entry = dict(id=id, release=release_id, name = name, value = path)
620 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref") 653 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref")
621 654
622 ####################################################################################################### 655 #######################################################################################################