Mercurial > repos > dchristiany > data_manager_proteore
comparison data_manager/resource_building.py @ 40:fddf4a3847f4 draft
planemo upload commit 43e2a01d7519104c2c16510e4dbdc023e65c49c7-dirty
| author | dchristiany |
|---|---|
| date | Tue, 29 Jan 2019 10:50:31 -0500 |
| parents | ec6252ad1a8e |
| children | 4062484f2cee |
comparison
equal
deleted
inserted
replaced
| 39:ec6252ad1a8e | 40:fddf4a3847f4 |
|---|---|
| 310 shutil.rmtree("tmp_BioGRID", ignore_errors=True) | 310 shutil.rmtree("tmp_BioGRID", ignore_errors=True) |
| 311 | 311 |
| 312 #download NCBI2Reactome.txt file and build dictionary | 312 #download NCBI2Reactome.txt file and build dictionary |
| 313 with requests.Session() as s: | 313 with requests.Session() as s: |
| 314 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt') | 314 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt') |
| 315 r.encoding = r.apparent_encoding | 315 r.encoding ="utf-8" |
| 316 tab_file = csv.reader(r.text.splitlines(), delimiter='\t') | 316 tab_file = csv.reader(r.content.splitlines(), delimiter='\t') |
| 317 | 317 |
| 318 dico_nodes = {} | 318 dico_nodes = {} |
| 319 uniProt_index=0 | 319 uniProt_index=0 |
| 320 pathway_description_index=3 | 320 pathway_description_index=3 |
| 321 species_index=5 | 321 species_index=5 |
| 354 else: | 354 else: |
| 355 dico_network["UniProt-AC"][line[2]].append([line[i] for i in network_uniprot_cols]) | 355 dico_network["UniProt-AC"][line[2]].append([line[i] for i in network_uniprot_cols]) |
| 356 dico_GeneID_to_UniProt[line[0]]=line[2] | 356 dico_GeneID_to_UniProt[line[0]]=line[2] |
| 357 | 357 |
| 358 with requests.Session() as s: | 358 with requests.Session() as s: |
| 359 download = s.get('https://reactome.org/download/current/UniProt2Reactome.txt') | 359 r = s.get('https://reactome.org/download/current/UniProt2Reactome.txt') |
| 360 decoded_content = download.content.decode('utf-8') | 360 r.encoding ="utf-8" |
| 361 tab_file = csv.reader(decoded_content.splitlines(), delimiter='\t') | 361 tab_file = csv.reader(r.content.splitlines(), delimiter='\t') |
| 362 | 362 |
| 363 dico_nodes_uniprot = {} | 363 dico_nodes_uniprot = {} |
| 364 uniProt_index=0 | 364 uniProt_index=0 |
| 365 pathway_description_index=3 | 365 pathway_description_index=3 |
| 366 species_index=5 | 366 species_index=5 |
| 371 else : | 371 else : |
| 372 dico_nodes_uniprot[line[uniProt_index]] = [line[pathway_description_index]] | 372 dico_nodes_uniprot[line[uniProt_index]] = [line[pathway_description_index]] |
| 373 | 373 |
| 374 with requests.Session() as s: | 374 with requests.Session() as s: |
| 375 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt') | 375 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt') |
| 376 r.encoding = r.apparent_encoding | 376 r.encoding ="utf-8" |
| 377 tab_file = csv.reader(r.text.splitlines(), delimiter='\t') | 377 tab_file = csv.reader(r.content.splitlines(), delimiter='\t') |
| 378 | 378 |
| 379 dico_nodes_geneid = {} | 379 dico_nodes_geneid = {} |
| 380 uniProt_index=0 | 380 uniProt_index=0 |
| 381 pathway_description_index=3 | 381 pathway_description_index=3 |
| 382 species_index=5 | 382 species_index=5 |