def main(argv = None):
# Setup argument parser
parser = ArgumentParser(description = '%s -- create actual bacteria databases from NCBI Sources' %
(os.path.basename(sys.argv[0])),
epilog = 'created by Philipp Sehnert',
add_help = True)
parser.add_argument('--version', action = 'version', version = '%s 1.0' %
(os.path.basename(sys.argv[0])))
parser.add_argument("-type", dest = "type", default = 'nucl',
choices = {'nucl','prot'}, help = "set type of blastdb")
parser.add_argument('-metacv', dest = 'metacv', action = 'store_true',
default = False, help = 'create metacv database')
parser.add_argument('-exe', dest = 'exe',
help = "if not installed, specify path to executable of 'makeblastdb' or 'metacv'")
parser.add_argument('-name', dest = 'name', default = 'bacterial', required = True,
help = 'outname for the databases')
parser.add_argument('-parse_seqids', dest = 'parse_seqids', action = 'store_false', default = True,
help = 'Remove duplicated GI numbers from downloaded files and run "makeblastdb" with -parse_seqids statement ')
# Process arguments
args = parser.parse_args()
DB_TYPE = args.type
METACV = args.metacv
DB_NAME = args.name
EXECUTABLE = args.exe
PARSE_SEQIDS = args.parse_seqids
if __name__ == '__main__':
# check for protein or nucleotide database
DB_TYPE = check_db_type(METACV, DB_TYPE)
# verify executable for external scripts
EXECUTABLE = check_executable(EXECUTABLE, METACV)
# create dir for sources
create_folder(DOWNLOAD_FOLDER)
# init FTP functions
ftp = ftp_functions(FTP_SERVER, FTP_ROOT, DOWNLOAD_FOLDER, DEBUG)
# connect to Blast FTP Server
ftp.connect()
ftp.go_to_root()
# start Downloading
for ftp_folder in SOURCES:
sys.stdout.write("Downloading files from %s \n" % (ftp_folder))
ftp.download_folder(ftp_folder, DB_TYPE)
# close ftp connection
ftp.close()
# run external database creation scripts
DBCreate = DBCreation(DB_OUT, DOWNLOAD_FOLDER, DB_TYPE, PARSE_SEQIDS, DEBUG, EXECUTABLE)
if METACV:
DBCreate.set_METACV(True)
# select the subfolder for MetaCV database
DBCreate.createMetaCVDB(DB_NAME, ['Bacteria', 'Bacteria_DRAFT'])
else:
DBCreate.set_METACV(False)
DBCreate.createBlastDB(DB_NAME)
def get_functional_annotation(self):
'''checks if functional annotation if function annotion exists and is actual
if not the annotation will be downloaded from uniprot ftp server'''
# FTP Server information
uniprotFTP = 'ftp.uniprot.org'
functional = 'pub/databases/uniprot/current_release/knowledgebase/idmapping'
idmapping = 'idmapping.dat.gz'
# establish connection
uniprot = ftp_functions(uniprotFTP, functional, DOWNLOAD_FOLDER, self.DEBUG)
uniprot.connect()
# go to functional dir
uniprot.go_down(functional)
# download file and extract it
idmapping = uniprot.get_idmapping(idmapping)
# close connection
uniprot.close()
return idmapping
def get_taxonomy(self):
'''checks if taxonomical annotation for metacv database is existing and actual
if not the files will be downloaded from ncbi ftp server'''
# FTP Server information
ncbiFTP = 'ftp.ncbi.nih.gov'
taxonomy = '/pub/taxonomy/'
ncbi_files = ['gi_taxid_prot.dmp.gz', 'taxdump.tar.gz']
files = []
# establish connection
ncbi = ftp_functions(ncbiFTP, taxonomy, self.DOWNLOAD_FOLDER, self.DEBUG)
ncbi.connect()
# go to taxonomy dir
ncbi.go_down(taxonomy)
for item in ncbi_files:
# download actual files and extract needed files
if item in ncbi_files[0]:
files.append(ncbi.get_gi_map(item))
else:
[files.append(x) for x in ncbi.get_taxdump(item)]
# close connection
ncbi.close()
return files