def action(args):
engine = create_engine(args.url, echo=args.verbosity > 2)
tax = Taxonomy(engine, schema=args.schema)
taxids = set()
if args.taxids:
if os.access(args.taxids, os.F_OK):
for line in getlines(args.taxids):
taxids.update(set(re.split(r'[\s,;]+', line)))
else:
taxids.update([x.strip()
for x in re.split(r'[\s,;]+', args.taxids)])
if args.seq_info:
with args.seq_info:
reader = csv.DictReader(args.seq_info)
taxids.update(frozenset(i['tax_id']
for i in reader if i['tax_id']))
writer = csv.writer(args.out)
for t in taxids:
try:
tax._node(t)
except ValueError:
# Check for merged
m = tax._get_merged(t)
if m and m != t:
writer.writerow([t, m])
else:
writer.writerow([t, None])
engine.dispose()
return 0
def action(args):
engine = create_engine(
'sqlite:///%s' % args.database_file, echo=args.verbosity > 2)
tax = Taxonomy(engine, ncbi.ranks)
taxids = set()
if args.taxids:
if os.access(args.taxids, os.F_OK):
for line in getlines(args.taxids):
taxids.update(set(re.split(r'[\s,;]+', line)))
else:
taxids.update([x.strip()
for x in re.split(r'[\s,;]+', args.taxids)])
if args.taxnames:
for taxname in getlines(args.taxnames):
for name in re.split(r'\s*[,;]\s*', taxname):
tax_id, primary_name, is_primary = tax.primary_from_name(
name.strip())
taxids.add(tax_id)
if args.seq_info:
with args.seq_info:
reader = csv.DictReader(args.seq_info)
taxids.update(frozenset(i['tax_id']
for i in reader if i['tax_id']))
# Before digging into lineages, make sure all the taxids exist in
# the taxonomy database.
valid_taxids = True
for t in taxids:
try:
tax._node(t)
except KeyError:
# Check for merged
m = tax._get_merged(t)
if m and m != t:
msg = ("Taxid {0} has been replaced by {1}. "
"Please update your records").format(t, m)
print >> sys.stderr, msg
else:
print >>sys.stderr, "Taxid %s not found in taxonomy." % t
valid_taxids = False
if not(valid_taxids):
print >>sys.stderr, "Some taxids were invalid. Exiting."
return 1 # exits with code 1
# Extract all the taxids to be exported in the CSV file.
taxids_to_export = set()
for t in taxids:
taxids_to_export.update([y for (x, y) in tax._get_lineage(t)])
tax.write_table(taxids_to_export, csvfile=args.out_file, full=args.full)
engine.dispose()
return 0
def action(args):
engine = sqlalchemy.create_engine(args.url, echo=False)
tax = Taxonomy(engine, schema=args.schema)
names = []
if args.infile:
names += [line.split('#', 1)[0].strip()
for line in args.infile
if line.strip() and not line.startswith('#')]
if args.names:
names += [x.strip() for x in args.names.split(',')]
writer = csv.writer(args.outfile)
writer.writerow(['input', 'tax_name', 'tax_id', 'rank'])
found = 0
for name in names:
try:
tax_id, tax_name, is_primary = tax.primary_from_name(name)
except ValueError:
if args.include_unmatched:
writer.writerow([name, None, None, None])
else:
found += 1
parent, rank = tax._node(tax_id)
writer.writerow([name, tax_name, tax_id, rank])
log.warning('found {} of {} names'.format(found, len(names)))
def test_species_below():
engine = create_engine('sqlite:///../testfiles/taxonomy.db', echo=False)
tax = Taxonomy(engine, taxtastic.ncbi.RANKS)
t = tax.species_below('1239')
parent_id, rank = tax._node(t)
for t in [None, '1239', '186801', '1117']:
s = tax.species_below(t)
assert t is None or s is None or tax.is_ancestor_of(s, t)
assert s is None or tax.rank(s) == 'species'
def action(args):
engine = create_engine('sqlite:///%s' %
args.database_file, echo=args.verbosity > 2)
tax = Taxonomy(engine, ncbi.RANKS)
taxids = set()
if args.taxids:
if os.access(args.taxids, os.F_OK):
for line in getlines(args.taxids):
taxids.update(set(re.split(r'[\s,;]+', line)))
else:
taxids.update([x.strip()
for x in re.split(r'[\s,;]+', args.taxids)])
if args.seq_info:
with args.seq_info:
reader = csv.DictReader(args.seq_info)
taxids.update(frozenset(i['tax_id']
for i in reader if i['tax_id']))
writer = csv.writer(args.out_file)
for t in taxids:
try:
tax._node(t)
except ValueError:
# Check for merged
m = tax._get_merged(t)
if m and m != t:
writer.writerow([t, m])
else:
writer.writerow([t, None])
engine.dispose()
return 0
def action(args):
dbfile = args.dbfile
taxnames_file = args.taxnames_file
taxnames = args.taxnames
outfile = args.outfile
engine = create_engine('sqlite:///%s' % dbfile, echo=False)
tax = Taxonomy(engine, ncbi.RANKS)
names = []
if taxnames_file:
names += [line.split('#', 1)[0].strip()
for line in taxnames_file
if line.strip() and not line.startswith('#')]
if taxnames:
names += [x.strip() for x in taxnames.split(',')]
taxa = {}
for name in set(names):
tax_id, tax_name, is_primary, rank, note = '', '', '', '', ''
try:
tax_id, tax_name, is_primary = tax.primary_from_name(name)
except ValueError:
note = 'not found'
else:
parent, rank = tax._node(tax_id)
note = '' if is_primary else 'not primary'
if note:
log.warning(
'%(name)20s | %(tax_id)7s %(tax_name)20s %(note)s' % locals())
if rank == 'species':
taxa[tax_id] = dict(tax_id=tax_id, tax_name=tax_name, rank=rank)
else:
keys, rows = get_children(engine, [tax_id])
taxa.update(dict((row['tax_id'], row) for row in rows))
for d in sorted(taxa.values(), key=lambda x: x['tax_name']):
outfile.write('%(tax_id)s # %(tax_name)s\n' % d)
def test__node():
engine = create_engine(
'sqlite:///../testfiles/small_taxonomy.db', echo=False)
tax = Taxonomy(engine, taxtastic.ncbi.RANKS)
assert tax._node(None) is None
assert tax._node('91061') == (u'1239', u'class')