def main(args, parser):
"""
Build the protein database.
@param args: The namespace of command-line arguments returned by
argparse.parse_args()
@param parser: An C{argparse.ArgumentParser} instance.
"""
if (args.minGenomeLength is not None and args.maxGenomeLength is not None
and args.minGenomeLength > args.maxGenomeLength):
raise ValueError(
'--minGenomeLength cannot be larger than --maxGenomeLength')
if args.excludeExclusiveHost:
excludeExclusiveHosts = set(
chain.from_iterable(args.excludeExclusiveHost))
else:
excludeExclusiveHosts = None
taxonomyDatabase = parseTaxonomyDatabaseCommandLineOptions(args, parser)
progress = args.progress
if progress:
overallStart = time()
totalGenomeCount = totalProteinCount = 0
with SqliteIndexWriter(args.databaseFile) as db:
for fileCount, (filename, addFunc,
type_) in enumerate(filenamesAndAdders(args, db),
start=1):
if args.logFile:
print("\n>>> Indexing '%s'." % filename,
end='\n\n',
file=args.logFile)
if progress:
start = time()
examinedGenomeCount, genomeCount, proteinCount = addFunc(
filename,
dnaOnly=args.dnaOnly,
rnaOnly=args.rnaOnly,
minGenomeLength=args.minGenomeLength,
maxGenomeLength=args.maxGenomeLength,
excludeExclusiveHosts=excludeExclusiveHosts,
excludeFungusOnlyViruses=args.excludeFungusOnlyViruses,
excludePlantOnlyViruses=args.excludePlantOnlyViruses,
databaseName=args.databaseName,
taxonomyDatabase=taxonomyDatabase,
proteinSource=args.proteinSource,
genomeSource=args.genomeSource,
duplicationPolicy=args.duplicationPolicy,
logfp=args.logFile)
if examinedGenomeCount == 0:
if type_ == 'gb':
print('WARNING: No genomes found in %r. Did the GenBank '
'download fail on that file?' % filename,
file=sys.stderr)
else:
assert type_ == 'json'
print('WARNING: no genomes found in JSON file %r.' %
filename,
file=sys.stderr)
if progress:
elapsed = time() - start
totalGenomeCount += genomeCount
totalProteinCount += proteinCount
print('Processed %r: added %3d of %3d genome%s (%5d '
'protein%s) in %.2f seconds.' %
(filename, genomeCount, examinedGenomeCount,
' ' if examinedGenomeCount == 1 else 's', proteinCount,
'' if proteinCount == 1 else 's', elapsed),
file=sys.stderr)
if progress:
elapsed = time() - overallStart
print('%d files (containing %d genomes and %d proteins) '
'indexed in %.2f seconds (%.2f mins).' %
(fileCount, totalGenomeCount, totalProteinCount, elapsed,
elapsed / 60),
file=sys.stderr)
'--database',
required=True,
help=('The file holding the sqlite3 taxonomy database. See '
'https://github.com/acorg/ncbi-taxonomy-database for how to '
'build one.'))
parser.add_argument('--printId',
default=False,
action='store_true',
help='If specified, also print the id.')
addTaxonomyDatabaseCommandLineOptions(parser)
args = parser.parse_args()
db = parseTaxonomyDatabaseCommandLineOptions(args, parser)
if args.ids:
ids = args.ids
else:
ids = (line[:-1] for line in sys.stdin)
for id_ in ids:
if args.printId:
print(id_ + ':')
hosts = hosts(id_, db)
if hosts:
print(', '.join(sorted(hosts)))
else:
print(
'No host information for %r found in the taxonomy database.' %