def featurize_mol(self, coords, mol, max_num_atoms):
logging.info("Featurizing molecule of size: %d", len(mol.GetAtoms()))
neighbor_list = compute_neighbor_list(coords, self.neighbor_cutoff,
self.max_num_neighbors, None)
z = self.get_Z_matrix(mol, max_num_atoms)
z = pad_array(z, max_num_atoms)
coords = pad_array(coords, (max_num_atoms, 3))
return coords, neighbor_list, z
def _featurize(self, mol: RDKitMol) -> np.ndarray:
"""
Calculate eigenvalues of Coulomb matrix for molecules. Eigenvalues
are returned sorted by absolute value in descending order and padded
by max_atoms.
Parameters
----------
mol: rdkit.Chem.rdchem.Mol
RDKit Mol object
Returns
-------
np.ndarray
The eigenvalues of Coulomb matrix for molecules.
The default shape is `(num_confs, max_atoms)`.
If num_confs == 1, the shape is `(max_atoms,)`.
"""
cmat = self.coulomb_matrix(mol)
features_list = []
for f in cmat:
w, v = np.linalg.eig(f)
w_abs = np.abs(w)
sortidx = np.argsort(w_abs)
sortidx = sortidx[::-1]
w = w[sortidx]
f = pad_array(w, self.max_atoms)
features_list.append(f)
features = np.asarray(features_list)
if features.shape[0] == 1:
# `(1, max_atoms)` -> `(max_atoms,)`
features = np.squeeze(features, axis=0)
return features
def _featurize(self, struct: PymatgenStructure) -> np.ndarray:
"""
Calculate sine Coulomb matrix from pymatgen structure.
Parameters
----------
struct: pymatgen.Structure
A periodic crystal composed of a lattice and a sequence of atomic
sites with 3D coordinates and elements.
Returns
-------
features: np.ndarray
2D sine Coulomb matrix with shape (max_atoms, max_atoms),
or 1D matrix eigenvalues with shape (max_atoms,).
"""
# Get full N x N SCM
sine_mat = self.scm.featurize(struct)
if self.flatten:
eigs, _ = np.linalg.eig(sine_mat)
zeros = np.zeros(self.max_atoms)
zeros[:len(eigs[0])] = eigs[0]
features = zeros
else:
features = pad_array(sine_mat, self.max_atoms)
features = np.asarray(features)
return features
def _featurize(self, datapoint: RDKitMol, **kwargs) -> np.ndarray:
"""Calculate symmetry function.
Parameters
----------
datapoint: rdkit.Chem.rdchem.Mol
RDKit Mol object
Returns
-------
np.ndarray
A numpy array of symmetry function. The shape is `(max_atoms, 4)`.
"""
if 'mol' in kwargs:
datapoint = kwargs.get("mol")
raise DeprecationWarning(
'Mol is being phased out as a parameter, please pass "datapoint" instead.'
)
coordinates = self.coordfeat._featurize(datapoint)
atom_numbers = np.array(
[atom.GetAtomicNum() for atom in datapoint.GetAtoms()])
atom_numbers = np.expand_dims(atom_numbers, axis=1)
assert atom_numbers.shape[0] == coordinates.shape[0]
features = np.concatenate([atom_numbers, coordinates], axis=1)
return pad_array(features, (self.max_atoms, 4))
def get_Z_matrix(self, mol, max_atoms):
if len(mol.GetAtoms()) > max_atoms:
raise ValueError(
"A molecule is larger than permitted by max_atoms. "
"Increase max_atoms and try again.")
return pad_array(
np.array([atom.GetAtomicNum() for atom in mol.GetAtoms()]),
max_atoms)
def coulomb_matrix(self, mol: RDKitMol) -> np.ndarray:
"""
Generate Coulomb matrices for each conformer of the given molecule.
Parameters
----------
mol: rdkit.Chem.rdchem.Mol
RDKit Mol object
Returns
-------
np.ndarray
The coulomb matrices of the given molecule
"""
try:
from rdkit import Chem
from rdkit.Chem import AllChem
except ModuleNotFoundError:
raise ImportError("This class requires RDKit to be installed.")
# Check whether num_confs >=1 or not
num_confs = len(mol.GetConformers())
if num_confs == 0:
mol = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol, AllChem.ETKDG())
if self.remove_hydrogens:
mol = Chem.RemoveHs(mol)
n_atoms = mol.GetNumAtoms()
z = [atom.GetAtomicNum() for atom in mol.GetAtoms()]
rval = []
for conf in mol.GetConformers():
d = self.get_interatomic_distances(conf)
m = np.outer(z, z) / d
m[range(n_atoms), range(n_atoms)] = 0.5 * np.array(z)**2.4
if self.randomize:
for random_m in self.randomize_coulomb_matrix(m):
random_m = pad_array(random_m, self.max_atoms)
rval.append(random_m)
else:
m = pad_array(m, self.max_atoms)
rval.append(m)
rval = np.asarray(rval)
return rval
def _featurize(self, datapoint: PymatgenStructure, **kwargs) -> np.ndarray:
"""
Calculate sine Coulomb matrix from pymatgen structure.
Parameters
----------
datapoint: pymatgen.core.Structure
A periodic crystal composed of a lattice and a sequence of atomic
sites with 3D coordinates and elements.
Returns
-------
features: np.ndarray
2D sine Coulomb matrix with shape (max_atoms, max_atoms),
or 1D matrix eigenvalues with shape (max_atoms,).
"""
if 'struct' in kwargs and datapoint is None:
datapoint = kwargs.get("struct")
raise DeprecationWarning(
'Struct is being phased out as a parameter, please pass "datapoint" instead.'
)
if self.scm is None:
try:
from matminer.featurizers.structure import SineCoulombMatrix as SCM
self.scm = SCM(flatten=False)
except ModuleNotFoundError:
raise ImportError(
"This class requires matminer to be installed.")
# Get full N x N SCM
sine_mat = self.scm.featurize(datapoint)
if self.flatten:
eigs, _ = np.linalg.eig(sine_mat)
zeros = np.zeros(self.max_atoms)
zeros[:len(eigs[0])] = eigs[0]
features = zeros
else:
features = pad_array(sine_mat, self.max_atoms)
features = np.asarray(features)
return features
def _featurize(self, mol: RDKitMol) -> np.ndarray:
"""Calculate symmetry function.
Parameters
----------
mol: rdkit.Chem.rdchem.Mol
RDKit Mol object
Returns
-------
np.ndarray
A numpy array of symmetry function. The shape is `(max_atoms, 4)`.
"""
coordinates = self.coordfeat._featurize(mol)
atom_numbers = np.array([atom.GetAtomicNum() for atom in mol.GetAtoms()])
atom_numbers = np.expand_dims(atom_numbers, axis=1)
assert atom_numbers.shape[0] == coordinates.shape[0]
features = np.concatenate([atom_numbers, coordinates], axis=1)
return pad_array(features, (self.max_atoms, 4))
def _featurize(self, datapoint: RDKitMol, **kwargs) -> np.ndarray:
"""
Calculate eigenvalues of Coulomb matrix for molecules. Eigenvalues
are returned sorted by absolute value in descending order and padded
by max_atoms.
Parameters
----------
datapoint: rdkit.Chem.rdchem.Mol
RDKit Mol object
Returns
-------
np.ndarray
The eigenvalues of Coulomb matrix for molecules.
The default shape is `(num_confs, max_atoms)`.
If num_confs == 1, the shape is `(max_atoms,)`.
"""
if 'mol' in kwargs:
datapoint = kwargs.get("mol")
raise DeprecationWarning(
'Mol is being phased out as a parameter, please pass "datapoint" instead.'
)
cmat = self.coulomb_matrix(datapoint)
features_list = []
for f in cmat:
w, v = np.linalg.eig(f)
w_abs = np.abs(w)
sortidx = np.argsort(w_abs)
sortidx = sortidx[::-1]
w = w[sortidx]
f = pad_array(w, self.max_atoms)
features_list.append(f)
features = np.asarray(features_list)
if features.shape[0] == 1:
# `(1, max_atoms)` -> `(max_atoms,)`
features = np.squeeze(features, axis=0)
return features
def _featurize(self, struct: PymatgenStructure) -> np.ndarray:
"""
Calculate sine Coulomb matrix from pymatgen structure.
Parameters
----------
struct: pymatgen.core.Structure
A periodic crystal composed of a lattice and a sequence of atomic
sites with 3D coordinates and elements.
Returns
-------
features: np.ndarray
2D sine Coulomb matrix with shape (max_atoms, max_atoms),
or 1D matrix eigenvalues with shape (max_atoms,).
"""
if self.scm is None:
try:
from matminer.featurizers.structure import SineCoulombMatrix as SCM
self.scm = SCM(flatten=False)
except ModuleNotFoundError:
raise ImportError(
"This class requires matminer to be installed.")
# Get full N x N SCM
sine_mat = self.scm.featurize(struct)
if self.flatten:
eigs, _ = np.linalg.eig(sine_mat)
zeros = np.zeros(self.max_atoms)
zeros[:len(eigs[0])] = eigs[0]
features = zeros
else:
features = pad_array(sine_mat, self.max_atoms)
features = np.asarray(features)
return features
