def test_parser_uniprotkb_decoydb(self):
header = (
'sp|P27748|ACOX_RALEH Acetoin catabolism protein X OS=Ralstonia'
' eutropha (strain ATCC 17699 / H16 / DSM 428 / Stanier 337)'
' GN=acoX PE=4 SV=2')
sequence = 'SEQUENCE'
with tempfile.TemporaryFile(mode='r+') as db:
fasta.write([(header, sequence)], db)
db.seek(0)
entries = list(
fasta.decoy_db(db,
prefix='PREFIX_',
parser=fasta.parse,
decoy_only=True))
parsed = {
'GN': 'acoX',
'OS': 'Ralstonia eutropha '
'(strain ATCC 17699 / H16 / DSM 428 / Stanier 337)',
'PE': 4,
'SV': 2,
'db': 'PREFIX_sp',
'entry': 'ACOX_RALEH',
'id': 'P27748',
'gene_id': 'ACOX',
'name': 'Acetoin catabolism protein X',
'taxon': 'RALEH'
}
self.assertEqual(entries[0][0], parsed)
self.assertEqual(entries[0][1], 'SEQUENCE'[::-1])
self.assertEqual(len(entries), 1)
def test_read_and_write_fasta_short(self):
with tempfile.TemporaryFile(mode='r+') as new_fasta_file:
fasta.write(fasta.read(self.fasta_file, ignore_comments=True),
new_fasta_file)
new_fasta_file.seek(0)
new_entries = list(fasta.read(new_fasta_file,
ignore_comments=True))
self.assertEqual(new_entries, self.fasta_entries_short)
def make_reverse_fasta(input_file, output_file):
'''
Takes as input fasta file, drops all _REVERSED proteins and creates a new _REVERSED decoy proteins.
'''
prots = []
for prot_desc, prot_seq in fasta.read(input_file):
if not prot_desc.endswith('_REVERSED'):
prots.append((prot_desc, prot_seq))
prots.append((prot_desc + '_REVERSED', smart_reverse(prot_seq)))
fasta.write(prots, output_file, file_mode='w')
def main(): # pragma: no cover
"""
Execute pytrapment.
Returns:
None
"""
today = date.today().strftime("%Y%m%d")
parser = arg_parser()
try:
args = parser.parse_args(sys.argv[1:])
except TypeError:
parser.print_usage()
# create dir if not there
if not os.path.exists(args.out_dir):
os.makedirs(args.out_dir)
start_time = time.time()
print("Starting pytrapment.")
fasta_df = entrapment.get_nearest_neighbor_proteins(
args.fasta_host, args.fasta_trap)
print("Found neighbors.")
print("Write fasta.")
_ = fasta.write(zip(fasta_df.index, fasta_df.sequence),
os.path.join(args.out_dir, f"entrapment_{today}.fasta"),
file_mode="w")
end_time = time.time()
print(f"Took {(end_time-start_time)/60.:.2f} minutes")
# doing qc
print("Perform qc.")
host_peptides = entrapment.digest_protein_df(
fasta_df[fasta_df["db_type"] == "host"])
trap_peptides = entrapment.digest_protein_df(
fasta_df[fasta_df["db_type"] == "trap"])
features_df_host = qc.compute_sequence_features(host_peptides)
features_df_host["Type"] = "host"
features_df_trap = qc.compute_sequence_features(trap_peptides)
features_df_trap["Type"] = "trap"
qc.qc_peptides(features_df_host, features_df_trap, args.out_dir)
print("Done.")
def prepare_decoy_db(args):
add_decoy = args['ad']
if add_decoy:
prefix = args['prefix']
db = args['d']
out1, out2 = os.path.splitext(db)
out_db = out1 + '_shuffled' + out2
logger.info('Creating decoy database: %s', out_db)
extra_check = False
if '{' in args['e']:
extra_check = True
if extra_check:
banned_pairs = set()
banned_aa = set()
for enzyme_local in args['e'].split(','):
if '{' in enzyme_local:
lpart, rpart = enzyme_local.split('|')
for aa_left, aa_right in itertools.product(
lpart[1:-1], rpart[1:-1]):
banned_aa.add(aa_left)
banned_aa.add(aa_right)
banned_pairs.add(aa_left + aa_right)
logger.debug(banned_aa)
logger.debug(banned_pairs)
enzyme = get_enzyme(args['e'])
cleave_rule_custom = enzyme + '|' + '([BXZUO])'
# cleave_rule_custom = '([RKBXZUO])'
logger.debug(cleave_rule_custom)
shuf_map = dict()
prots = []
for p in fasta.read(db):
if not p[0].startswith(prefix):
target_peptides = [
x[1] for x in parser.icleave(p[1], cleave_rule_custom, 0)
]
checked_peptides = set()
sample_list = []
for idx, pep in enumerate(target_peptides):
if len(pep) > 2:
pep_tmp = pep[1:-1]
if extra_check:
for bp in banned_pairs:
if bp in pep_tmp:
pep_tmp = pep_tmp.replace(bp, '')
checked_peptides.add(idx)
sample_list.extend(pep_tmp)
random.shuffle(sample_list)
idx_for_shuffle = 0
decoy_peptides = []
for idx, pep in enumerate(target_peptides):
if len(pep) > 2:
if pep in shuf_map:
tmp_seq = shuf_map[pep]
else:
if not extra_check or idx not in checked_peptides:
tmp_seq = pep[0]
for pep_aa in pep[1:-1]:
tmp_seq += sample_list[idx_for_shuffle]
idx_for_shuffle += 1
tmp_seq += pep[-1]
else:
max_l = len(pep)
tmp_seq = ''
ii = 0
while ii < max_l - 1:
# for ii in range(max_l-1):
if pep[ii] in banned_aa and pep[
ii +
1] in banned_aa and pep[ii] + pep[
ii + 1] in banned_pairs:
tmp_seq += pep[ii] + pep[ii + 1]
ii += 1
else:
if ii == 0:
tmp_seq += pep[ii]
else:
tmp_seq += sample_list[
idx_for_shuffle]
idx_for_shuffle += 1
ii += 1
tmp_seq += pep[max_l - 1]
shuf_map[pep] = tmp_seq
else:
tmp_seq = pep
decoy_peptides.append(tmp_seq)
assert len(target_peptides) == len(decoy_peptides)
prots.append((p[0], ''.join(target_peptides)))
prots.append(('DECOY_' + p[0], ''.join(decoy_peptides)))
fasta.write(prots, open(out_db, 'w')).close()
args['d'] = out_db
args['ad'] = 0
return args
def test_read_and_write_long(self):
with tempfile.TemporaryFile(mode='r+') as new_fasta_file:
fasta.write(fasta.read(self.fasta_file), new_fasta_file)
new_fasta_file.seek(0)
new_entries = list(fasta.read(new_fasta_file))
self.assertEqual(new_entries, self.fasta_entries_long)
description was replaced by the gene name.
'''
descr, seq = e
m = GN_PATTERN.search(descr)
new_descr = m.group('gene') or descr
return Protein(new_descr, seq)
parser = argparse.ArgumentParser()
parser.add_argument('files', type=str, nargs='+',
help='.fasta files containing plink output')
parser.add_argument('-o', '--output', type=str, default=None,
help='file to write output to.')
parser.add_argument('--gname', action='store_true',
help='only leave gene name (GN) in the output fasta header')
parser.add_argument('-v', '--verbosity', action='count',
help='increase output verbosity')
args = parser.parse_args()
unique_entries = set()
for filename in args.files:
if args.verbosity > 0:
print 'Processing {0}...'.format(filename)
for entry in fasta.read(open(filename)):
if args.gname:
entry = get_gene_name(entry)
unique_entries.update({entry,})
if args.verbosity > 1:
print '\t... found {0} unique entries so far'.format(len(unique_entries))
fasta.write(unique_entries, output=args.output)