def _featurize_ligand(self, ligand: rdkit.Chem.Mol) -> np.ndarray:
from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect as Morgan
# FIXME: Check whether OFF uses canonical smiles internally, or not
# otherwise, we should force that behaviour ourselves!
fp = Morgan(ligand, radius=self.radius, nBits=self.nbits)
return np.asarray(fp, dtype="uint8")
def fingerprint(smiles_or_mol,
fp_type='maccs',
dtype=None,
morgan__r=2,
morgan__n=1024,
*args,
**kwargs):
"""
Generates fingerprint for SMILES
If smiles is invalid, returns None
Returns numpy array of fingerprint bits
Parameters:
smiles: SMILES string
type: type of fingerprint: [MACCS|morgan]
dtype: if not None, specifies the dtype of returned array
"""
fp_type = fp_type.lower()
molecule = get_mol(smiles_or_mol, *args, **kwargs)
if molecule is None:
return None
if fp_type == 'maccs':
keys = MACCSkeys.GenMACCSKeys(molecule)
keys = np.array(keys.GetOnBits())
fingerprint = np.zeros(166, dtype='uint8')
if len(keys) != 0:
fingerprint[keys - 1] = 1 # We drop 0-th key that is always zero
elif fp_type == 'morgan':
fingerprint = np.asarray(Morgan(molecule, morgan__r, nBits=morgan__n),
dtype='uint8')
else:
raise ValueError("Unknown fingerprint type {}".format(fp_type))
if dtype is not None:
fingerprint = fingerprint.astype(dtype)
return fingerprint
def fingerprints(smiles):
"Calculates fingerprints of a list of SMILES strings"
fps = np.zeros((len(smiles), 1024))
for i, smi in enumerate(smiles):
mol = Chem.MolFromSmiles(smi)
fp = np.asarray(Morgan(mol, 2, 1024), dtype='uint8')
fps[i,:] = fp
return fps
def _featurize_one(self, system: System) -> np.ndarray:
"""
Parameters
----------
system : System
The System to be featurized.
options : dict
Unused
Returns
-------
array
"""
from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect as Morgan
# FIXME: Check whether OFF uses canonical smiles internally, or not
# otherwise, we should force that behaviour ourselves!
ligand = self._find_ligand(system).to_rdkit()
fp = Morgan(ligand, radius=self.radius, nBits=self.nbits)
return np.asarray(fp, dtype="int64")