def generate_rdDescriptors(mol, Normalized=True):
smiles = Chem.MolToSmiles(
mol, isomericSmiles=True) if type(mol) != str else mol
from descriptastorus.descriptors import rdDescriptors, rdNormalizedDescriptors
if Normalized:
generator = rdNormalizedDescriptors.RDKit2DNormalized()
tors = generator.process(smiles)
else:
generator = rdDescriptors.RDKit2D()
tors = generator.process(smiles)
return tors[1:]
def rdkit_2d_features_generator(mol: Molecule) -> np.ndarray:
"""
Generates RDKit 2D features for a molecule.
:param mol: A molecule (i.e., either a SMILES or an RDKit molecule).
:return: A 1D numpy array containing the RDKit 2D features.
"""
smiles = Chem.MolToSmiles(mol, isomericSmiles=True) if type(mol) != str else mol
generator = rdDescriptors.RDKit2D()
features = generator.process(smiles)[1:]
return features
def generate_rdDescriptorsSets(mols, Normalized=True):
from descriptastorus.descriptors import rdDescriptors, rdNormalizedDescriptors
if Normalized:
generator = rdNormalizedDescriptors.RDKit2DNormalized()
else:
generator = rdDescriptors.RDKit2D()
tors = []
for mol in mols:
smiles = Chem.MolToSmiles(
mol, isomericSmiles=True) if type(mol) != str else mol
tors.append(generator.process(smiles)[1:])
return np.asarray(tors)
def rdkit_functional_group_label_features_generator(
mol: Molecule) -> np.ndarray:
"""
Generates functional group label for a molecule using RDKit.
:param mol: A molecule (i.e. either a SMILES string or an RDKit molecule).
:return: A 1D numpy array containing the RDKit 2D features.
"""
smiles = Chem.MolToSmiles(mol,
isomericSmiles=True) if type(mol) != str else mol
generator = rdDescriptors.RDKit2D(RDKIT_PROPS)
features = generator.process(smiles)[1:]
features = np.array(features)
features[features != 0] = 1
return features
calc = Calculator(descriptors, ignore_3D=True)
descriptors = calc.pandas(mols)
descriptors = descriptors.astype(str)
masks = descriptors.apply(lambda d: d.str.contains('[a-zA-Z]', na=False))
descriptors = descriptors[~masks]
descriptors = descriptors.astype(float)
y = pd.DataFrame(y, index=smiles, columns=[y_name])
if dataset_type == 3:
from descriptastorus.descriptors.DescriptorGenerator import MakeGenerator
from descriptastorus.descriptors import rdDescriptors
from descriptastorus.descriptors import rdNormalizedDescriptors
gen1 = MakeGenerator(('rdkit2d', 'Morgan3counts'))
gen2 = rdDescriptors.RDKit2D()
gen3 = rdNormalizedDescriptors.RDKit2DNormalized()
data1 = gen1.process(smiles)
data2 = gen2.process(smiles)
data3 = gen3.process(smiles)
for col in gen1.GetColumns():
y_name.append(col)
y = pd.DataFrame(y, index=smiles, columns=[y_name])
if dataset_type == 4: #3D Descriptors
from e3fp.fingerprint.generate import fp, fprints_dict_from_mol
from e3fp.conformer.generate import generate_conformers
mols = [Chem.MolFromSmiles(smile) for smile in smiles]
optimize_mols = []
for mol in mols: