def main(args):
server = BioSeqDatabase.open_database(driver=args.driver, db=args.database, user=args.user, host=args.host, passwd=args.password)
seqfeature_ids = get_seqfeature_ids_from_qv(server, args.qualifier, args.value, args.database_name)
if args.output_format == 'feat-prot':
extract_feature_sql(server, seqfeature_ids, type=['CDS'], translate=True )
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, seqfeature_ids )
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver, db=args.database, user=args.user, host=args.host, passwd=args.password)
seqfeature_ids = get_seqfeature_ids_from_qv(server, args.qualifier, args.value, args.database_name, fuzzy=args.fuzzy)
if args.feature_type is not None:
types = args.feature_type
elif args.output_format == 'feat-prot':
types = ['CDS']
elif args.output_format == 'feat-nucl':
types = ['CDS', 'rRNA', 'tRNA']
if args.output_format == 'feat-prot':
extract_feature_sql(server, seqfeature_ids, type=types, translate=True )
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, seqfeature_ids, type=types)
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver, db=args.database, user=args.user, host=args.host, passwd=args.password)
if args.output_format == 'fasta':
from Bio import SeqIO
db = server[args.database_name]
for rec in db.values():
SeqIO.write(rec, sys.stdout, args.output_format)
else:
seqfeature_ids = get_seqfeature_for_db(server, args.database_name)
if args.output_format == 'feat-prot':
extract_feature_sql(server, seqfeature_ids, type=['CDS'], translate=True )
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, seqfeature_ids )
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver,
db=args.database,
user=args.user,
host=args.host,
passwd=args.password)
seqfeature_ids = []
with open(args.infile) as fp:
for line in fp:
seqfeature_ids.append(int(line.rstrip()))
if args.output_format == 'feat-prot':
extract_feature_sql(server,
seqfeature_ids,
type=['CDS'],
translate=True)
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, seqfeature_ids)
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver,
db=args.database,
user=args.user,
host=args.host,
passwd=args.password)
if args.output_format == 'fasta':
from Bio import SeqIO
db = server[args.database_name]
for rec in db.values():
SeqIO.write(rec, sys.stdout, args.output_format)
else:
seqfeature_ids = get_seqfeature_for_db(server, args.database_name)
if args.output_format == 'feat-prot':
extract_feature_sql(server,
seqfeature_ids,
type=['CDS'],
translate=True)
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, seqfeature_ids)
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver, db=args.database, user=args.user, host=args.host, passwd=args.password)
tax_name = False
try:
ncbi_tax = int(args.taxid)
except ValueError:
tax_name = True
if not tax_name:
print("interpreting as an NCBI taxon ID...", file=sys.stderr)
taxon_id_lookup_sql = "SELECT bioentry_id, taxon_id, biodatabase.name FROM bioentry JOIN "\
"biodatabase USING(biodatabase_id) WHERE taxon_id IN "\
"(SELECT DISTINCT include.taxon_id FROM taxon "\
"INNER JOIN taxon as include ON (include.left_value "\
"BETWEEN taxon.left_value AND taxon.right_value) "\
"WHERE taxon.ncbi_taxon_id = %s AND include.right_value = include.left_value + 1)"
rows = server.adaptor.execute_and_fetchall(taxon_id_lookup_sql, (ncbi_tax,))
else:
print("interpreting as a taxon name...", file=sys.stderr)
taxon_name_lookup_sql = "SELECT bioentry_id, taxon_id, biodatabase.name FROM bioentry JOIN "\
"biodatabase USING(biodatabase_id) WHERE taxon_id IN "\
"(SELECT DISTINCT include.taxon_id FROM taxon "\
"INNER JOIN taxon as include ON (include.left_value "\
"BETWEEN taxon.left_value AND taxon.right_value) "\
"WHERE taxon.taxon_id IN (SELECT taxon_id FROM taxon_name "\
"WHERE name like %s) AND include.right_value = include.left_value + 1)"
rows = server.adaptor.execute_and_fetchall(taxon_name_lookup_sql, (args.taxid,))
dbids = {}
for row in rows:
dbids[(row[0], row[2])] = row[1]
files = {}
taxid_to_dbids = {}
if args.split_species:
taxon_file_mapping = {}
for k, v in dbids.items():
tname = server.adaptor.execute_and_fetch_col0("SELECT name from taxon_name where taxon_id = %s and name_class = %s", (v,'scientific name'))[0]
tname = tname.replace(' ', '_')
if args.output_format == 'gb':
tname += '.gb'
elif args.output_format == 'feat-prot':
tname += '.faa'
else:
tname += '.fna'
files[v] = tname
taxid_to_dbids.setdefault(v, []).append(k)
if args.split_species:
# got to save all of the records before printing them out
outdata = {}
for taxid, dbid_list in taxid_to_dbids.items():
for dbid, dbname in dbid_list:
db = server[dbname]
seq_rec = db[dbid]
outdata.setdefault(taxid, []).append(seq_rec)
for taxid, dbrecs in outdata.items():
with open(files[taxid], 'w') as fp:
if 'feat' in args.output_format:
for dbrec in dbrecs:
extract_feature(dbrec, args.output_format, fp)
else:
SeqIO.write(dbrecs, fp, args.output_format)
else:
if args.output_format == 'feat-prot':
extract_feature_sql(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbids.keys()]),type=['CDS'], translate=True )
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbids.keys()]))
else:
for (dbid, dbname), taxid in dbids.items():
db = server[dbname]
try:
dbrec = db[dbid]
SeqIO.write(dbrec, sys.stdout, args.output_format)
except KeyError:
pass
def main(args):
server = BioSeqDatabase.open_database(driver=args.driver, db=args.database, user=args.user, host=args.host, passwd=args.password)
tax_name = False
try:
ncbi_tax = int(args.taxid)
except ValueError:
tax_name = True
if not tax_name:
print("interpreting as an NCBI taxon ID...", file=sys.stderr)
taxon_id_lookup_sql = "SELECT bioentry_id, taxon_id, biodatabase.name FROM bioentry JOIN "\
"biodatabase USING(biodatabase_id) WHERE taxon_id IN "\
"(SELECT DISTINCT include.taxon_id FROM taxon "\
"INNER JOIN taxon as include ON (include.left_value "\
"BETWEEN taxon.left_value AND taxon.right_value) "\
"WHERE taxon.ncbi_taxon_id = %s AND include.right_value = include.left_value + 1)"
rows = server.adaptor.execute_and_fetchall(taxon_id_lookup_sql, (ncbi_tax,))
else:
print("interpreting as a taxon name...", file=sys.stderr)
taxon_name_lookup_sql = "SELECT bioentry_id, taxon_id, biodatabase.name FROM bioentry JOIN "\
"biodatabase USING(biodatabase_id) WHERE taxon_id IN "\
"(SELECT DISTINCT include.taxon_id FROM taxon "\
"INNER JOIN taxon as include ON (include.left_value "\
"BETWEEN taxon.left_value AND taxon.right_value) "\
"WHERE taxon.taxon_id IN (SELECT taxon_id FROM taxon_name "\
"WHERE name like %s) AND include.right_value = include.left_value + 1)"
rows = server.adaptor.execute_and_fetchall(taxon_name_lookup_sql, (args.taxid,))
if args.feature_type is not None:
types = args.feature_type
elif args.output_format == 'feat-prot':
types = ['CDS']
elif args.output_format == 'feat-nucl':
types = ['CDS', 'rRNA', 'tRNA']
if len(rows) == 0:
print("\nThere does not appear to be any sequences associated with\n"
"the taxonomy provided. If you used a taxonomy name, make sure\n"
"it is spelled correctly. And remember that it must be the complete name\n"
"for a particular rank, for example 'Deltaproteo' will match nothing\n"
"it has to be 'Deltaproteobacteria'.\n"
"Don't forget to add 'Candidatus ' to the begining of some names\n"
"or the strain designation for a species. If you used an NCBI taxonomy ID, make\n"
"sure that it is correct by double checking on the NCBI taxonomy website.", file=sys.stderr)
sys.exit(1)
dbids = {}
for row in rows:
dbids[(row[0], row[2])] = row[1]
files = {}
taxid_to_dbids = {}
if args.split_species:
taxon_file_mapping = {}
for k, v in dbids.items():
tname = server.adaptor.execute_and_fetch_col0("SELECT name from taxon_name where taxon_id = %s and name_class = %s", (v,'scientific name'))[0]
tname = tname.replace(' ', '_')
if args.output_format == 'gb':
tname += '.gb'
elif args.output_format == 'feat-prot':
tname += '.faa'
elif args.output_format == 'csv':
tname += '.csv'
else:
tname += '.fna'
files[v] = tname
taxid_to_dbids.setdefault(v, []).append(k)
if args.split_species:
# got to save all of the records before printing them out
outdata = {}
for taxid, dbid_list in taxid_to_dbids.items():
if args.output_format == 'csv':
with open(files[taxid], 'w') as fp:
print_feature_qv_csv(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbid_list]), fp)
else:
for dbid, dbname in dbid_list:
db = server[dbname]
seq_rec = db[dbid]
outdata.setdefault(taxid, []).append(seq_rec)
for taxid, dbrecs in outdata.items():
with open(files[taxid], 'w') as fp:
if 'feat' in args.output_format:
for dbrec in dbrecs:
extract_feature(dbrec, args.output_format, fp)
elif 'csv' != args.output_format:
SeqIO.write(dbrecs, fp, args.output_format)
else:
if args.output_format == 'feat-prot':
extract_feature_sql(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbids.keys()]),type=types, translate=True )
elif args.output_format == 'feat-nucl':
extract_feature_sql(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbids.keys()]), type=types)
elif args.output_format == 'csv':
print_feature_qv_csv(server, get_seqfeature_ids_for_bioseqs(server, [x[0] for x in dbids.keys()]))
else:
for (dbid, dbname), taxid in dbids.items():
db = server[dbname]
try:
dbrec = db[dbid]
SeqIO.write(dbrec, sys.stdout, args.output_format)
except KeyError:
pass