def filter_and_write(mol2_files, ids, output_dir, includelist_filter, verbose):
for mol2_file in mol2_files:
if verbose:
sys.stdout.write('Processing %s' % os.path.basename(mol2_file))
sys.stdout.flush()
if not os.path.exists(output_dir):
os.mkdir(output_dir)
mol2_outpath = os.path.join(output_dir, os.path.basename(mol2_file))
if mol2_outpath.endswith('.gz'):
write_mode = 'wb'
open_file = gzip.open
else:
write_mode = 'w'
open_file = open
with open_file(mol2_outpath, write_mode) as f:
if verbose:
start = time.time()
if includelist_filter:
if write_mode == 'w':
for idx, mol2 in enumerate(split_multimol2(mol2_file)):
if mol2[0] in ids:
f.write(''.join(mol2[1]))
else:
for idx, mol2 in enumerate(split_multimol2(mol2_file)):
if mol2[0].decode('utf-8') in ids:
f.write(b''.join(mol2[1]))
else:
if write_mode == 'w':
for idx, mol2 in enumerate(split_multimol2(mol2_file)):
if mol2[0] not in ids:
f.write(''.join(mol2[1]))
else:
for idx, mol2 in enumerate(split_multimol2(mol2_file)):
if mol2[0].decode('utf-8') not in ids:
f.write(b''.join(mol2[1]))
if verbose:
elapsed = time.time() - start
n_molecules = idx + 1
sys.stdout.write(' | scanned %d molecules | %d mol/sec\n' %
(n_molecules, n_molecules / elapsed))
sys.stdout.flush()
def test_split_multimol2_gz():
all_mol2 = []
for i in split_multimol2(os.path.join(this_dir,
'data', '40_mol2_files.mol2.gz')):
all_mol2.append(i[0])
assert(all_mol2[1].decode() == 'ZINC04084113')
assert(len(all_mol2) == 40)
def run_rocs(source_file, target_file, n_processes, settings):
prefix = ''.join(target_file.split('.mol2')[:-1])
sys.stdout.write('Processing %s\n' % os.path.basename(source_file))
sys.stdout.flush()
for idx, mol2 in enumerate(split_multimol2(QUERY_FILE)):
if idx >= 1:
mcquery = 'true'
break
if not idx:
mcquery = 'false'
cmd = [EXECUTABLE,
'-ref', QUERY_FILE,
'-dbase', source_file,
'-outputquery', 'false',
'-prefix', prefix,
'-mcquery', mcquery,
'-mpi_np', str(n_processes),
'-oformat', 'mol2']
if settings:
for s in settings.split():
s = s.strip()
if s:
cmd.append(s)
subprocess.call(cmd, stdout=subprocess.PIPE, bufsize=1)
def test_read_mol2_from_list():
data_path = os.path.join(this_dir, 'data', '40_mol2_files.mol2')
mol2 = next(split_multimol2(data_path))
pdmol = PandasMol2().read_mol2_from_list(mol2_lines=mol2[1],
mol2_code=mol2[0])
assert pdmol.df.shape == (65, 9)
assert pdmol.code == 'ZINC38611810'
def check_query(query_path):
ids = [mol2[0] for mol2 in split_multimol2(query_path)]
n_ids = len(ids)
if n_ids > 1:
n_unique_ids = len(set(ids))
if n_unique_ids > 1:
raise ValueError('Please Make sure that you only submit one'
' molecule or, if you submit a multi-conformer'
' query, that conformers of the molecule'
' have all the same molecule ID labels.'
' Found %d molecules and %d unique labels' %
(n_ids, n_unique_ids))
def mol2_to_idfile(mol2_files, id_file_path, verbose=0):
with open(id_file_path, 'w') as f:
for mol2_file in mol2_files:
if verbose:
sys.stdout.write('Processing %s' % os.path.basename(mol2_file))
sys.stdout.flush()
start = time.time()
for idx, mol2 in enumerate(split_multimol2(mol2_file)):
f.write(mol2[0] + '\n')
if verbose:
elapsed = time.time() - start
n_molecules = idx + 1
sys.stdout.write(' | scanned %d molecules | %d mol/sec\n' %
(n_molecules, n_molecules / elapsed))
sys.stdout.flush()
def read_mol2(self, path, columns=None):
mol2_code, mol2_lines = next(split_multimol2(path))
self._load_mol2(mol2_lines, mol2_code, columns)
self.mol2_path = path
return self
def run_code():
next(split_multimol2('40_mol2_files.pdb'))
