Mercurial > repos > proteore > proteore_data_manager

comparison data_manager/resource_building.py @ 36:b18cb0d11971 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit ba867b8fa3352695fbda1ae764407f363ee79a50-dirty"
author proteore
date Wed, 08 Jan 2020 10:34:07 +0000
parents 06103d45814d
children 807ecb8c3867
comparison
equal deleted inserted replaced
35:06103d45814d 36:b18cb0d11971
134 def id_mapping_sources (data_manager_dict, species, target_directory, tool_data_path) : 134 def id_mapping_sources (data_manager_dict, species, target_directory, tool_data_path) :
135 135
136 human = species == "Human" 136 human = species == "Human"
137 species_dict = { "Human" : "HUMAN_9606", "Mouse" : "MOUSE_10090", "Rat" : "RAT_10116" } 137 species_dict = { "Human" : "HUMAN_9606", "Mouse" : "MOUSE_10090", "Rat" : "RAT_10116" }
138 files=["idmapping_selected.tab.gz","idmapping.dat.gz"] 138 files=["idmapping_selected.tab.gz","idmapping.dat.gz"]
139 archive = os.path.join(tool_data_path, "ID_mapping_archive_"+species+"_"+str(time.strftime("%Y%m%d"))) 139 archive = os.path.join(tool_data_path, "id_mapping/ID_mapping_archive_"+species+"_"+str(time.strftime("%Y%m%d")))
140 if os.path.isfile is False : os.mkdir(archive) 140 if os.path.isfile is False : os.mkdir(archive)
141 141
142 #header 142 #header
143 if human : tab = [["UniProt-AC","UniProt-AC_reviewed","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG",'Gene_Name']] 143 if human : tab = [["UniProt-AC","UniProt-AC_reviewed","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG",'Gene_Name']]
144 else : tab = [["UniProt-AC","UniProt-AC_reviewed","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG",'Gene_Name']] 144 else : tab = [["UniProt-AC","UniProt-AC_reviewed","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG",'Gene_Name']]
250 250
251 with open(path,"w") as out : 251 with open(path,"w") as out :
252 w = csv.writer(out,delimiter='\t') 252 w = csv.writer(out,delimiter='\t')
253 w.writerows(tab) 253 w.writerows(tab)
254 254
255 subprocess.call(['tar', '-zczf', archive+".tar.gz", archive]) 255 subprocess.call(['tar', '-czvf', archive+".tar.gz", archive])
256 os.remove(archive)
256 257
257 name_dict={"Human" : "Homo sapiens", "Mouse" : "Mus musculus", "Rat" : "Rattus norvegicus"} 258 name_dict={"Human" : "Homo sapiens", "Mouse" : "Mus musculus", "Rat" : "Rattus norvegicus"}
258 name = species +" (" + name_dict[species]+" "+time.strftime("%d/%m/%Y")+")" 259 name = species +" (" + name_dict[species]+" "+time.strftime("%d/%m/%Y")+")"
259 release = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") 260 release = species+"_id_mapping_"+ time.strftime("%d-%m-%Y")
260 id = str(10000000000 - int(time.strftime("%Y%m%d"))) #new ids must be inferior to previous id -> sort by <filter> in xml only in descending order 261 id = str(10000000000 - int(time.strftime("%Y%m%d"))) #new ids must be inferior to previous id -> sort by <filter> in xml only in descending order