def _getSMILESStream(f, mols, delimiter=' ', nameHeader='Name', includeHeader=True, isomericSmiles=False,
kekuleSmiles=False):
w = SmilesWriter(f, delimiter=delimiter, nameHeader=nameHeader, includeHeader=includeHeader,
isomericSmiles=isomericSmiles, kekuleSmiles=kekuleSmiles)
for mol in mols:
w.write(mol)
w.flush()
def stream_smiles_results(operation, query, source, annotate=False):
buf = StringIO()
filtered = operation(query, source, annotate=annotate)
results = SmilesWriter(buf, isomericSmiles=True, includeHeader=False)
if annotate:
results.SetProps(['match'])
for result in filtered:
buf.truncate(0)
results.write(result)
results.flush()
yield buf.getvalue()
def write_smiles_results(operation, needles, haystack, dest, annotate=False, extra_props=0):
filtered = operation(needles, haystack, annotate=annotate)
results = SmilesWriter(dest, isomericSmiles=True, includeHeader=False)
props = []
if annotate:
props.append('match')
if extra_props:
props.extend('ExtraProp{0}'.format(i+1) for i in range(extra_props))
results.SetProps(props)
for result in filtered:
results.write(result)
return results.NumMols()
def preprocess_smi(self, smi):
norms = MolStandardize.normalize.NORMALIZATIONS
test_smiles = [smi]
test_label = [1] # dummy list
temp_dir = tempfile.mkdtemp()
df = pd.DataFrame(zip(test_smiles, test_label), columns=['SMILES', 'Label'])
df.to_csv(temp_dir+'/temp_file.csv', index=False)
try:
molReader = SmilesMolSupplier(temp_dir+'/temp_file.csv', delimiter=',', smilesColumn=0, nameColumn=1, titleLine=True, sanitize=True)
molWriter = SmilesWriter(temp_dir+'/temp_outfile.csv', delimiter=',', nameHeader='Name', includeHeader=True, isomericSmiles = (True), kekuleSmiles=False)
stdzr = self.MyStandardizer(norms)
stand_smiles = self.Standardize(stdzr, True, molReader, molWriter)
shutil.rmtree(temp_dir)
return stand_smiles
except:
print('No')
return ''
def _getSMILESStream(f,
mols,
delimiter=' ',
nameHeader='Name',
includeHeader=True,
isomericSmiles=False,
kekuleSmiles=False):
w = SmilesWriter(f,
delimiter=delimiter,
nameHeader=nameHeader,
includeHeader=includeHeader,
isomericSmiles=isomericSmiles,
kekuleSmiles=kekuleSmiles)
for mol in mols:
w.write(mol)
w.flush()
def _getSMILESStream(f, mols):
w = SmilesWriter(f, isomericSmiles=True)
for mol in mols:
w.write(mol)
w.flush()
def _getSMILESStream(f, mols):
w = SmilesWriter(f, isomericSmiles=True)
for mol in mols:
w.write(mol)
w.flush()
from sys import argv
from rdkit.Chem import SDMolSupplier, SmilesWriter
sdm = SDMolSupplier(argv[1])
sw = SmilesWriter(argv[2], includeHeader=False, nameHeader='_Name')
for mol in sdm:
sw.write(mol)
sw.close()