Mercurial > repos > dchristiany > data_manager_proteore

comparison data_manager/resource_building.py @ 28:d235909789ca draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit e694c4b0df30a4286ba09721696e8ec3af25fd97-dirty
author dchristiany
date Fri, 25 Jan 2019 09:38:35 -0500
parents 592c59530c32
children 871a7347ca24
comparison
equal deleted inserted replaced
27:592c59530c32 28:d235909789ca
121 import ftplib, gzip 121 import ftplib, gzip
122 csv.field_size_limit(sys.maxsize) # to handle big files 122 csv.field_size_limit(sys.maxsize) # to handle big files
123 123
124 def id_mapping_sources (data_manager_dict, species, target_directory) : 124 def id_mapping_sources (data_manager_dict, species, target_directory) :
125 125
126 human = species == "human" 126 human = species == "Human"
127 species_dict = { "human" : "HUMAN_9606", "mouse" : "MOUSE_10090", "rat" : "RAT_10116" } 127 species_dict = { "Human" : "HUMAN_9606", "Mouse" : "MOUSE_10090", "Rat" : "RAT_10116" }
128 files=["idmapping_selected.tab.gz","idmapping.dat.gz"] 128 files=["idmapping_selected.tab.gz","idmapping.dat.gz"]
129 129
130 #header 130 #header
131 if human : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG"]] 131 if human : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG"]]
132 else : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"]] 132 else : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"]]
216 216
217 with open(path,"w") as out : 217 with open(path,"w") as out :
218 w = csv.writer(out,delimiter='\t') 218 w = csv.writer(out,delimiter='\t')
219 w.writerows(tab) 219 w.writerows(tab)
220 220
221 name_dict={"human" : "Homo sapiens", "mouse" : "Mus musculus", "rat" : "Rattus norvegicus"} 221 name_dict={"Human" : "Homo sapiens", "Mouse" : "Mus musculus", "Rat" : "Rattus norvegicus"}
222 name = name_dict[species]+" "+time.strftime("%d/%m/%Y") 222 name = species +" (" + name_dict[species]+" "+time.strftime("%d/%m/%Y")+")"
223 id = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") 223 id = species+"_id_mapping_"+ time.strftime("%d-%m-%Y")
224 224
225 data_table_entry = dict(id=id, name = name, value = species, path = path) 225 data_table_entry = dict(id=id, name = name, value = species, path = path)
226 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_id_mapping") 226 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_id_mapping")
227 227
274 # 4. Build protein interaction maps files 274 # 4. Build protein interaction maps files
275 ####################################################################################################### 275 #######################################################################################################
276 276
277 def PPI_ref_files(data_manager_dict, species, interactome, target_directory): 277 def PPI_ref_files(data_manager_dict, species, interactome, target_directory):
278 278
279 species_dict={'human':'Homo sapiens',"mouse":"Mus musculus","rat":"Rattus norvegicus"} 279 species_dict={'Human':'Homo sapiens',"Mouse":"Mus musculus","Rat":"Rattus norvegicus"}
280 280
281 ##BioGRID 281 ##BioGRID
282 if interactome=="biogrid": 282 if interactome=="biogrid":
283 283
284 tab2_link="https://downloads.thebiogrid.org/Download/BioGRID/Release-Archive/BIOGRID-3.5.167/BIOGRID-ORGANISM-3.5.167.tab2.zip" 284 tab2_link="https://downloads.thebiogrid.org/Download/BioGRID/Release-Archive/BIOGRID-3.5.167/BIOGRID-ORGANISM-3.5.167.tab2.zip"