Merge branch 'master' into refactor-complex-feat (40b2ff42) · Commits · 钟慕尧 / deepchem

deepchem/feat/init.py

+1 −0

Original line number	Diff line number	Diff line
		@@ -17,6 +17,7 @@ from deepchem.feat.binding_pocket_features import BindingPocketFeaturizer

		# molecule featurizers
		from deepchem.feat.molecule_featurizers import AtomicCoordinates
		from deepchem.feat.molecule_featurizers import BPSymmetryFunctionInput
		from deepchem.feat.molecule_featurizers import CircularFingerprint
		from deepchem.feat.molecule_featurizers import CoulombMatrix
		from deepchem.feat.molecule_featurizers import CoulombMatrixEig

+6 −8

Original line number	Diff line number	Diff line
		@@ -50,8 +50,13 @@ class ElementPropertyFingerprint(MaterialCompositionFeaturizer):
		data_source: str of "matminer", "magpie" or "deml" (default "matminer")
		Source for element property data.
		"""
		try:
		from matminer.featurizers.composition import ElementProperty
		except ModuleNotFoundError:
		raise ValueError("This class requires matminer to be installed.")

		self.data_source = data_source
		self.ep_featurizer = ElementProperty.from_preset(self.data_source)

		def _featurize(self, composition: PymatgenComposition) -> np.ndarray:
		"""
		@@ -69,14 +74,7 @@ class ElementPropertyFingerprint(MaterialCompositionFeaturizer):
		stoichiometry. Some values may be NaN.
		"""
		try:
		from matminer.featurizers.composition import ElementProperty
		except ModuleNotFoundError:
		raise ValueError("This class requires matminer to be installed.")

		ep = ElementProperty.from_preset(self.data_source)

		try:
		feats = ep.featurize(composition)
		feats = self.ep_featurizer.featurize(composition)
		except:
		feats = []

+6 −8

Original line number	Diff line number	Diff line
		@@ -54,9 +54,14 @@ class SineCoulombMatrix(MaterialStructureFeaturizer):
		flatten: bool (default True)
		Return flattened vector of matrix eigenvalues.
		"""
		try:
		from matminer.featurizers.structure import SineCoulombMatrix as SCM
		except ModuleNotFoundError:
		raise ValueError("This class requires matminer to be installed.")

		self.max_atoms = max_atoms
		self.flatten = flatten
		self.scm = SCM(flatten=False)

		def _featurize(self, struct: PymatgenStructure) -> np.ndarray:
		"""
		@@ -74,15 +79,8 @@ class SineCoulombMatrix(MaterialStructureFeaturizer):
		2D sine Coulomb matrix with shape (max_atoms, max_atoms),
		or 1D matrix eigenvalues with shape (max_atoms,).
		"""

		try:
		from matminer.featurizers.structure import SineCoulombMatrix as SCM
		except ModuleNotFoundError:
		raise ValueError("This class requires matminer to be installed.")

		# Get full N x N SCM
		scm = SCM(flatten=False)
		sine_mat = scm.featurize(struct)
		sine_mat = self.scm.featurize(struct)

		if self.flatten:
		eigs, _ = np.linalg.eig(sine_mat)

+8 −5

Original line number	Diff line number	Diff line
		@@ -55,6 +55,12 @@ class CircularFingerprint(MolecularFeaturizer):
		Whether to calculate SMILES strings for fragment IDs (only applicable
		when calculating sparse fingerprints).
		"""
		try:
		from rdkit import Chem # noqa
		from rdkit.Chem import rdMolDescriptors # noqa
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		self.radius = radius
		self.size = size
		self.chiral = chiral
		@@ -76,11 +82,8 @@ class CircularFingerprint(MolecularFeaturizer):
		np.ndarray
		A numpy array of circular fingerprint.
		"""
		try:
		from rdkit import Chem
		from rdkit.Chem import rdMolDescriptors
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		if self.sparse:
		info: Dict = {}

+8 −5

Original line number	Diff line number	Diff line
		@@ -63,6 +63,12 @@ class CoulombMatrix(MolecularFeaturizer):
		seed: int, optional (default None)
		Random seed to use.
		"""
		try:
		from rdkit import Chem # noqa
		from rdkit.Chem import AllChem # noqa
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		self.max_atoms = int(max_atoms)
		self.remove_hydrogens = remove_hydrogens
		self.randomize = randomize
		@@ -116,11 +122,8 @@ class CoulombMatrix(MolecularFeaturizer):
		np.ndarray
		The coulomb matrices of the given molecule
		"""
		try:
		from rdkit import Chem
		from rdkit.Chem import AllChem
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		# Check whether num_confs >=1 or not
		num_confs = len(mol.GetConformers())