Mercurial > repos > dchristiany > data_manager_proteore
comparison data_manager/resource_building.py @ 47:7b486b0fba4e draft
planemo upload commit cb633de1f04ef7b7133728909716b6c6594533d1-dirty
| author | dchristiany |
|---|---|
| date | Fri, 01 Feb 2019 10:30:00 -0500 |
| parents | 80fc0b28e227 |
| children | 4b6c6f9b4de0 |
comparison
equal
deleted
inserted
replaced
| 46:80fc0b28e227 | 47:7b486b0fba4e |
|---|---|
| 277 | 277 |
| 278 ####################################################################################################### | 278 ####################################################################################################### |
| 279 # 4. Build protein interaction maps files | 279 # 4. Build protein interaction maps files |
| 280 ####################################################################################################### | 280 ####################################################################################################### |
| 281 | 281 |
| 282 def get_interactant_name(line): | 282 def get_interactant_name(line,dico): |
| 283 | 283 |
| 284 if line[0] in dico_geneid_to_gene_name : | 284 if line[0] in dico : |
| 285 print line[0] | 285 interactant_A = dico[line[0]] |
| 286 interactant_A = dico_geneid_to_gene_name[line[0]] | |
| 287 else : | 286 else : |
| 288 interactant_A = "NA" | 287 interactant_A = "NA" |
| 289 | 288 |
| 290 if line[1] in dico_geneid_to_gene_name : | 289 if line[1] in dico : |
| 291 interactant_B = dico_geneid_to_gene_name[line[1]] | 290 interactant_B = dico[line[1]] |
| 292 else : | 291 else : |
| 293 interactant_B = "NA" | 292 interactant_B = "NA" |
| 294 | 293 |
| 295 return interactant_A, interactant_B | 294 return interactant_A, interactant_B |
| 296 | 295 |
| 424 r = r.content.decode('utf-8') | 423 r = r.content.decode('utf-8') |
| 425 humap_nodes = csv.reader(r.splitlines(), delimiter=',') | 424 humap_nodes = csv.reader(r.splitlines(), delimiter=',') |
| 426 | 425 |
| 427 dico_geneid_to_gene_name={} | 426 dico_geneid_to_gene_name={} |
| 428 for line in humap_nodes : | 427 for line in humap_nodes : |
| 429 if check_entrez_geneid(line[5]): | 428 if check_entrez_geneid(line[4]): |
| 430 if line[5] not in dico_geneid_to_gene_name: | 429 if line[4] not in dico_geneid_to_gene_name: |
| 431 dico_geneid_to_gene_name[line[5]]=[line[4]] | 430 dico_geneid_to_gene_name[line[4]]=line[3] |
| 432 else : | |
| 433 if line[4] not in dico_geneid_to_gene_name[line[5]] : | |
| 434 dico_geneid_to_gene_name[line[5]].append(line[4]) | |
| 435 | 431 |
| 436 with requests.Session() as s: | 432 with requests.Session() as s: |
| 437 r = s.get('http://proteincomplexes.org/static/downloads/pairsWprob.txt') | 433 r = s.get('http://proteincomplexes.org/static/downloads/pairsWprob.txt') |
| 438 r = r.content.decode('utf-8') | 434 r = r.content.decode('utf-8') |
| 439 humap = csv.reader(r.splitlines(), delimiter='\t') | 435 humap = csv.reader(r.splitlines(), delimiter='\t') |