def main():
parser = argparse.ArgumentParser(
description='Filter a Uniref FASTA file by taxonomy')
## output file to be written
parser.add_argument('-i',
'--input_fasta',
type=str,
required=True,
help='Path to an input file to be read')
parser.add_argument('-o',
'--output_fasta',
type=str,
required=True,
help='Path to an output file to be created')
parser.add_argument(
'-c',
'--clades',
type=str,
required=True,
help='Comma-separated string of clades to be included.')
parser.add_argument('-db',
'--taxadb',
type=str,
required=True,
help='Path to the taxadb sqlite3 file')
args = parser.parse_args()
if not os.path.exists(args.taxadb):
raise Exception("ERROR: Couldn't find taxadb specified")
taxid = TaxID(dbtype='sqlite', dbname=args.taxadb)
clades = args.clades.split(',')
record_count = 0
print_every = 1000
clade_counter = dict()
for clade in clades:
clade_counter[clade] = 0
# remembers for each ID if we're keeping it or not
id_cache = dict()
fout = open(args.output_fasta, 'wt')
keep_entry = False
for line in open(args.input_fasta):
if line[0] == '>':
record_count += 1
if record_count % print_every == 0:
print("{0} records processed ...".format(record_count),
flush=True)
m = re.search('TaxID=(\d+)', line)
if m:
tax_id = m.group(1)
if tax_id in id_cache:
if id_cache[tax_id] == True:
keep_entry = True
else:
keep_entry = False
else:
lineage = taxid.lineage_name(tax_id, reverse=True)
clade_found = False
if lineage is None:
keep_entry = False
continue
for clade in clades:
if clade in lineage:
clade_found = True
clade_counter[clade] += 1
break
if clade_found:
keep_entry = True
id_cache[tax_id] = True
else:
keep_entry = False
id_cache[tax_id] = False
else:
keep_entry = False
if keep_entry:
fout.write(line)
fout.close()
print("Number of entries exported by clade:")
for clade in clade_counter:
print("\t{0}: {1}".format(clade, clade_counter[clade]))
#!/usr/bin/env python3
import sys
from os.path import expanduser
from taxadb.taxid import TaxID
handler = TaxID(dbtype="sqlite", dbname=expanduser("~") + "/.taxadb/taxadb.sqlite")
for taxid in sys.stdin:
taxid = taxid.strip()
lineage = handler.lineage_name(taxid, reverse=True)
lineage_s = ""
if len(lineage) > 0:
lineage_s = "; ".join(lineage)
print("{}\t{}".format(taxid, lineage_s))
def main():
parser = argparse.ArgumentParser( description='Filter a Uniref FASTA file by taxonomy')
## output file to be written
parser.add_argument('-i', '--input_fasta', type=str, required=True, help='Path to an input file to be read' )
parser.add_argument('-o', '--output_fasta', type=str, required=True, help='Path to an output file to be created' )
parser.add_argument('-c', '--clades', type=str, required=True, help='Comma-separated string of clades to be included.' )
parser.add_argument('-db', '--taxadb', type=str, required=True, help='Path to the taxadb sqlite3 file' )
args = parser.parse_args()
if not os.path.exists(args.taxadb):
raise Exception("ERROR: Couldn't find taxadb specified")
taxid = TaxID(dbtype='sqlite', dbname=args.taxadb)
clades = args.clades.split(',')
record_count = 0
print_every = 1000
clade_counter = dict()
for clade in clades:
clade_counter[clade] = 0
# remembers for each ID if we're keeping it or not
id_cache = dict()
fout = open(args.output_fasta, 'wt')
keep_entry = False
for line in open(args.input_fasta):
if line[0] == '>':
record_count += 1
if record_count % print_every == 0:
print("{0} records processed ...".format(record_count), flush=True)
m = re.search('TaxID=(\d+)', line)
if m:
tax_id = m.group(1)
if tax_id in id_cache:
if id_cache[tax_id] == True:
keep_entry = True
else:
keep_entry = False
else:
lineage = taxid.lineage_name(tax_id, reverse=True)
clade_found = False
if lineage is None:
keep_entry = False
continue
for clade in clades:
if clade in lineage:
clade_found = True
clade_counter[clade] += 1
break
if clade_found:
keep_entry = True
id_cache[tax_id] = True
else:
keep_entry = False
id_cache[tax_id] = False
else:
keep_entry = False
if keep_entry:
fout.write(line)
fout.close()
print("Number of entries exported by clade:")
for clade in clade_counter:
print("\t{0}: {1}".format(clade, clade_counter[clade]))