def _basta_taxonomy(self, args):
if not os.path.exists(args.output):
os.makedirs(args.output)
self.logger.info(
"\n#### Downloading and processing NCBI taxonomy files\n")
self.logger.info("\n# [BASTA STATUS] Download taxonomy files")
dutils.down_and_check("ftp://ftp.ncbi.nih.gov/pub/taxonomy/",
"taxdump.tar.gz", args.output)
call([
"tar", "-xzvf",
os.path.join(args.output, "taxdump.tar.gz"), "-C", args.output
])
self.logger.info(
"\n# [BASTA STATUS] Creating complete taxonomy file\n")
tax_creator = ntc.Creator(os.path.join(args.output, "names.dmp"),
os.path.join(args.output, "nodes.dmp"))
tax_creator._write(os.path.join(args.output, "complete_taxa"))
self.logger.info("\n# [BASTA STATUS] Creating taxonomy database")
dbutils.create_db(args.output, "complete_taxa.gz", "complete_taxa.db",
0, 1)
self.logger.info(
"\n### Done! NCBI taxonomy database created in %s ####" %
(args.output))
def _fetch_mapping(args,logger):
logger.info("\n# [STATUS] Initializing mapping database")
db_file = db.get_db_name(args.directory,args.dbtype)
map_lookup = db._init_db(os.path.abspath(os.path.join(args.directory,db_file)))
with open(args.mapout,"w") as f:
for k,v in map_lookup:
f.write("%s\t%s\n" % (k,v))
def run_basta(self,args):
if args.subparser_name == 'sequence':
self._check_dir(args)
if not dbutils._check_complete(args.directory):
self.logger.error("\n[BASTA ERROR] Couldn't find complete_taxa.db in %s. Did you run initial \'basta download\'?" % (args.directory))
sys.exit()
self._basta_sequence(args)
elif args.subparser_name == 'single':
self._check_dir(args)
if not dbutils._check_complete(args.directory):
self.logger.error("\n[BASTA ERROR] Couldn't find complete_taxa.db in %s. Did you run initial \'basta download\'?" % (args.directory))
sys.exit()
self._basta_single(args)
elif args.subparser_name == 'multiple':
self._check_dir(args)
if not dbutils._check_complete(args.directory):
self.logger.error("\n[BASTA ERROR] Couldn't find complete_taxa.db in %s. Did you run initial \'basta download\'?" % (args.directory))
sys.exit()
self._basta_multiple(args)
elif args.subparser_name == 'download':
self._check_dir(args)
self._basta_download(args)
elif args.subparser_name == 'create_db':
self._check_dir(args)
self._basta_create_db(args)
elif args.subparser_name == 'taxonomy':
self._check_dir(args)
self._basta_taxonomy(args)
def _basta_create_db(self, args):
if not os.path.exists(args.directory):
os.makedirs(args.directory)
self.logger.info("\n#### Creating database\n")
dbutils.create_db(args.directory, args.input, args.output, args.key,
args.value)
self.logger.info("\n#### Done. Processed file %s\n" % (args.input))
def _basta_download(self, args):
if not os.path.exists(args.directory):
os.makedirs(args.directory)
self.logger.info(
"\n##### Downloading and processing mapping file(s) from NCBI ###\n"
)
#db_file = dbutils.get_db_name(args.directory,args.type)
if args.type == "prot":
map_file = "prot.accession2taxid.gz"
db_file = "prot_mapping.db"
elif args.type == "wgs":
map_file = "nucl_wgs.accession2taxid.gz"
db_file = "wgs_mapping.db"
elif args.type == "gss":
map_file = "nucl_gss.accession2taxid.gz"
db_file = "gss_mapping.db"
elif args.type == "est":
map_file = "nucl_est.accession2taxid.gz"
db_file = "est_mapping.db"
elif args.type == "pdb":
map_file = "pdb.accession2taxid.gz"
db_file = "pdb_mapping.db"
else:
map_file = "nucl_gb.accession2taxid.gz"
db_file = "gb_mapping.db"
self.logger.info("\n# [BASTA STATUS] Downloading mapping files\n")
dutils.down_and_check(args.ftp, map_file, args.directory)
self.logger.info("\n# [BASTA STATUS] Creating mapping database\n")
dbutils.create_db(args.directory, map_file, db_file, 0, 2)
self.logger.info("\n##### Done. Downloaded and processed file %s\n" %
(map_file))
def _get_lookups(self, db_file):
self.logger.info("\n# [BASTA STATUS] Initializing taxonomy database")
tax_lookup = db._init_db(
os.path.join(self.directory, "complete_taxa.db"))
self.logger.info("\n# [BASTA STATUS] Initializing mapping database")
map_lookup = db._init_db(
os.path.abspath(os.path.join(self.directory, db_file)))
return (tax_lookup, map_lookup)
def _basta_sequence(self,args):
self.logger.info("\n#### Assigning taxonomy to each sequence ###\n")
db_file = dbutils.get_db_name(args.directory,args.type)
assigner = AssignTaxonomy.Assigner(args.evalue,args.alen,args.identity,args.number,args.minimum,args.maj_perc,args.directory,args.config_path,args.output,args.hit_count)
if args.verbose:
assigner.info_file = args.verbose
assigner._assign_sequence(args.blast,db_file,args.best_hit)
self.logger.info("\n#### Done. Output written to %s" % (args.output))
def _basta_download(self, args):
if not os.path.exists(args.directory):
os.makedirs(args.directory)
self.logger.info(
"\n##### Downloading and processing mapping file(s) from NCBI ###\n"
)
#db_file = dbutils.get_db_name(args.directory,args.type)
if args.type == "prot":
map_file = "prot.accession2taxid.gz"
db_file = "prot_mapping.db"
elif args.type == "uni":
# Another quick'n dirty hardcoded thing do add uniprot to
# db type prot ...
map_file = "idmapping_selected.tab.gz"
db_file = "prot_mapping.db"
self.logger.info("\n# [BASTA STATUS] Downloading mapping file\n")
dutils.down(
"ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/idmapping/",
map_file, args.directory)
self.logger.info("\n# [BASTA STATUS] Creating mapping database\n")
dbutils.create_db(args.directory, map_file, db_file, 0, 12)
return
elif args.type == "wgs":
map_file = "nucl_wgs.accession2taxid.gz"
db_file = "wgs_mapping.db"
elif args.type == "gss":
map_file = "nucl_gss.accession2taxid.gz"
db_file = "gss_mapping.db"
elif args.type == "est":
map_file = "nucl_est.accession2taxid.gz"
db_file = "est_mapping.db"
elif args.type == "pdb":
map_file = "pdb.accession2taxid.gz"
db_file = "pdb_mapping.db"
else:
map_file = "nucl_gb.accession2taxid.gz"
db_file = "gb_mapping.db"
self.logger.info("\n# [BASTA STATUS] Downloading mapping files\n")
dutils.down_and_check(args.ftp, map_file, args.directory)
self.logger.info("\n# [BASTA STATUS] Creating mapping database\n")
dbutils.create_db(args.directory, map_file, db_file, 0, 2)
self.logger.info("\n##### Done. Downloaded and processed file %s\n" %
(map_file))
def _basta_single(self,args):
self.logger.info("\n#### Assigning one taxonomy based on all sequences ###\n")
db_file = dbutils.get_db_name(args.directory,args.type)
assigner = AssignTaxonomy.Assigner(args.evalue,args.alen,args.identity,args.number,args.minimum,args.maj_perc,args.directory,args.config_path,args.output,args.hit_count)
if args.verbose:
assigner.info_file = args.verbose
lca = assigner._assign_single(args.blast,db_file,args.best_hit)
self.logger.info("\n##### Results #####\n")
self.logger.info("Last Common Ancestor: %s\n" % (lca))
self.logger.info("\n###################\n")
def _basta_multiple(self,args):
self.logger.info("\n#### Assigning one taxonomy for each file ###\n")
db_file = ""
db_file = dbutils.get_db_name(args.directory,args.type)
assigner = AssignTaxonomy.Assigner(args.evalue,args.alen,args.identity,args.number,args.minimum,args.maj_perc,args.directory,args.config_path,args.output,args.hit_count,args.quiet)
if args.verbose:
if os.path.exists(args.verbose):
os.remove(args.verbose)
assigner.info_file = args.verbose
assigner._assign_multiple(args.blast,db_file,args.best_hit)
self.logger.info("\n###### Done. Output written to %s" % (args.output))
def _fetch_taxonomies(args,logger):
tax_dict = {}
logger.info("\n# [STATUS] Initializing taxonomy database")
db_file = db.get_db_name(args.directory,args.dbtype)
map_lookup = db._init_db(os.path.abspath(os.path.join(args.directory,db_file)))
tax_lookup = db._init_db(os.path.join(args.directory,"complete_taxa.db"))
not_found = {}
with open(args.dbout,"w") as f:
for k,v in map_lookup:
tax_string = tax_lookup.get(v)
if not tax_string:
if v in not_found:
continue
else:
logger.warning("\n# [WARNING] No taxon found for %d " % (int(v)))
not_found[v] = 1
continue
f.write("%s\t%s\n" % (v,tax_string))
def _basta_multiple(self, args):
self.logger.info("\n#### Assigning one taxonomy for each file ###\n")
db_file = ""
db_file = dbutils.get_db_name(args.directory, args.type)
assigner = AssignTaxonomy.Assigner(args.evalue, args.alen,
args.identity, args.number,
args.minimum, args.lazy,
args.tax_method, args.directory,
args.config_path, args.output)
if args.verbose:
assigner.info_file = args.verbose
assigner._assign_multiple(args.blast, db_file, args.best_hit)
self.logger.info("\n###### Done. Output written to %s" % (args.output))
def _fetch_taxonomies(seqs, args, logger):
tax_dict = {}
logger.info("\n# [STATUS] Initializing taxonomy database")
tax_lookup = db._init_db(os.path.join(args.directory, "complete_taxa.db"))
logger.info("\n# [STATUS] Initializing mapping database")
db_file = db.get_db_name(args.directory, args.dbtype)
map_lookup = db._init_db(
os.path.abspath(os.path.join(args.directory, db_file)))
for s in seqs:
taxon_id = map_lookup.get(s)
if not taxon_id:
logger.warning("\n# [WARNING] No mapping found for %s " % (s))
continue
tax_string = tax_lookup.get(taxon_id)
if not tax_string:
logger.warning("\n# [WARNING] No taxon found for %d " %
(int(taxon_id)))
continue
tax_dict[s] = tax_string
return tax_dict
def test_check_complete(self):
os.mkdir(os.path.join(self.pwd, "complete_taxa.db"))
self.assertTrue(db._check_complete(self.pwd))
os.rmdir(os.path.join(self.pwd, "complete_taxa.db"))
def test_get_db_name(self):
os.mkdir(os.path.join(self.pwd, "test_mapping.db"))
self.assertEqual(db.get_db_name(self.pwd, "test"), "test_mapping.db")
os.rmdir(os.path.join(self.pwd, "test_mapping.db"))
def test_check_file_name(self):
self.assertEqual(db._check_file_name("test"), "test.db")
self.assertEqual(db._check_file_name("test.db"), "test.db")