Merge pull request #2571 from arunppsg/master (692a2ed7) · Commits · 钟慕尧 / deepchem

deepchem/feat/atomic_conformation.py

+22 −0

Original line number	Diff line number	Diff line
		@@ -125,6 +125,28 @@ class AtomicConformationFeaturizer(Featurizer):

		Otherwise, it is assumed to be a SMILES string. RDKit is used to generate a
		3D conformation and to compute formal and partial charges.

		Examples
		--------
		>>> import deepchem as dc
		>>> smiles = ['CCC']
		>>> featurizer = dc.feat.AtomicConformationFeaturizer()
		>>> features = featurizer.featurize(smiles)
		>>> features[0].num_atoms
		11
		>>> sum(features[0].atomic_number == 6)
		3
		>>> sum(features[0].atomic_number == 1)
		8
		>>> type(features[0].formal_charge)
		<class 'numpy.ndarray'>
		>>> features[0].formal_charge.shape
		(11,)
		>>> type(features[0].partial_charge)
		<class 'numpy.ndarray'>
		>>> features[0].partial_charge.shape
		(11,)

		"""

		def _featurize(self, datapoint: str) -> AtomicConformation:

deepchem/feat/graph_features.py

+74 −11

Original line number	Diff line number	Diff line
		@@ -54,6 +54,7 @@ def one_of_k_encoding_unk(x, allowable_set):
		--------
		>>> dc.feat.graph_features.one_of_k_encoding_unk("s", ["a", "b", "c"])
		[False, False, True]

		"""
		if x not in allowable_set:
		x = allowable_set[-1]
		@@ -78,6 +79,7 @@ def get_intervals(l):

		>>> dc.feat.graph_features.get_intervals([[1], [], [1, 2], [1, 2, 3]])
		[1, 1, 3, 12]

		"""
		intervals = len(l) * [0]
		# Initalize with 1
		@@ -104,10 +106,11 @@ def safe_index(l, e):
		0
		>>> dc.feat.graph_features.safe_index([1, 2, 3], 7)
		3

		"""
		try:
		return l.index(e)
		except:
		except ValueError:
		return len(l)


		@@ -149,7 +152,7 @@ def get_feature_list(atom):

		Parameters
		----------
		atom: RDKit.rdchem.Atom
		atom: RDKit.Chem.rdchem.Atom
		Atom to get features for

		Examples
		@@ -157,8 +160,11 @@ def get_feature_list(atom):
		>>> from rdkit import Chem
		>>> mol = Chem.MolFromSmiles("C")
		>>> atom = mol.GetAtoms()[0]
		>>> dc.feat.graph_features.get_feature_list(atom)
		[0, 4, 4, 3, 0, 2]
		>>> features = dc.feat.graph_features.get_feature_list(atom)
		>>> type(features)
		<class 'list'>
		>>> len(features)
		6

		Note
		----
		@@ -259,7 +265,7 @@ def atom_to_id(atom):

		Parameters
		----------
		atom: RDKit.rdchem.Atom
		atom: RDKit.Chem.rdchem.Atom
		Atom to convert to ids.

		Returns
		@@ -281,6 +287,8 @@ def atom_features(atom,

		Parameters
		----------
		atom: RDKit.Chem.rdchem.Atom
		Atom to compute features on.
		bool_id_feat: bool, optional
		Return an array of unique identifiers corresponding to atom type.
		explicit_H: bool, optional
		@@ -290,7 +298,20 @@ def atom_features(atom,

		Returns
		-------
		np.ndarray of per-atom features.
		features: np.ndarray
		An array of per-atom features.

		Examples
		--------
		>>> from rdkit import Chem
		>>> mol = Chem.MolFromSmiles('CCC')
		>>> atom = mol.GetAtoms()[0]
		>>> features = dc.feat.graph_features.atom_features(atom)
		>>> type(features)
		<class 'numpy.ndarray'>
		>>> features.shape
		(75,)

		"""
		if bool_id_feat:
		return np.array([atom_to_id(atom)])
		@@ -376,6 +397,8 @@ def bond_features(bond, use_chirality=False):

		Parameters
		----------
		bond: rdkit.Chem.rdchem.Bond
		Bond to compute features on.
		use_chirality: bool, optional
		If true, use chirality information.

		@@ -388,6 +411,22 @@ def bond_features(bond, use_chirality=False):
		bond_feats: np.ndarray
		Array of bond features. This is a 1-D array of length 6 if `use_chirality`
		is `False` else of length 10 with chirality encoded.

		Examples
		--------
		>>> from rdkit import Chem
		>>> mol = Chem.MolFromSmiles('CCC')
		>>> bond = mol.GetBonds()[0]
		>>> bond_features = dc.feat.graph_features.bond_features(bond)
		>>> type(bond_features)
		<class 'numpy.ndarray'>
		>>> bond_features.shape
		(6,)

		Note
		----
		This method requires RDKit to be installed.

		"""
		try:
		from rdkit import Chem
		@@ -406,8 +445,8 @@ def bond_features(bond, use_chirality=False):
		return np.array(bond_feats)


		def max_pair_distance_pairs(mol: RDKitMol,
		max_pair_distance: Optional[int]) -> np.ndarray:
		def max_pair_distance_pairs(
		mol: RDKitMol, max_pair_distance: Optional[int] = None) -> np.ndarray:
		"""Helper method which finds atom pairs within max_pair_distance graph distance.

		This helper method is used to find atoms which are within max_pair_distance
		@@ -434,6 +473,15 @@ def max_pair_distance_pairs(mol: RDKitMol,
		distance 2 apart. If `max_pair_distance` is `None`, all pairs are
		considered (effectively infinite `max_pair_distance`)

		Examples
		--------
		>>> from rdkit import Chem
		>>> mol = Chem.MolFromSmiles('CCC')
		>>> features = dc.feat.graph_features.max_pair_distance_pairs(mol, 1)
		>>> type(features)
		<class 'numpy.ndarray'>
		>>> features.shape # (2, num_pairs)
		(2, 7)

		Returns
		-------
		@@ -862,9 +910,24 @@ class WeaveFeaturizer(MolecularFeaturizer):
		Examples
		--------
		>>> import deepchem as dc
		>>> mols = ["C", "CCC"]
		>>> mols = ["CCC"]
		>>> featurizer = dc.feat.WeaveFeaturizer()
		>>> X = featurizer.featurize(mols)
		>>> features = featurizer.featurize(mols)
		>>> type(features[0])
		<class 'deepchem.feat.mol_graphs.WeaveMol'>
		>>> features[0].get_num_atoms() # 3 atoms in compound
		3
		>>> features[0].get_num_features() # feature size
		75
		>>> type(features[0].get_atom_features())
		<class 'numpy.ndarray'>
		>>> features[0].get_atom_features().shape
		(3, 75)
		>>> type(features[0].get_pair_features())
		<class 'numpy.ndarray'>
		>>> features[0].get_pair_features().shape
		(9, 14)


		References
		----------

deepchem/feat/molecule_featurizers/atomic_coordinates.py

+16 −0

Original line number	Diff line number	Diff line
		@@ -10,6 +10,22 @@ from deepchem.utils.typing import RDKitMol
		class AtomicCoordinates(MolecularFeaturizer):
		"""Calculate atomic coordinates.

		Examples
		--------
		>>> import deepchem as dc
		>>> from rdkit import Chem
		>>> mol = Chem.MolFromSmiles('C1C=CC=CC=1')
		>>> n_atoms = len(mol.GetAtoms())
		>>> n_atoms
		6
		>>> featurizer = dc.feat.AtomicCoordinates(use_bohr=False)
		>>> features = featurizer.featurize([mol])
		>>> type(features[0])
		<class 'numpy.ndarray'>
		>>> features[0].shape # (n_atoms, 3)
		(6, 3)


		Note
		----
		This class requires RDKit to be installed.

deepchem/feat/molecule_featurizers/bp_symmetry_function_input.py

+12 −1

Original line number	Diff line number	Diff line
		@@ -9,7 +9,18 @@ from deepchem.feat.molecule_featurizers.atomic_coordinates import AtomicCoordina
		class BPSymmetryFunctionInput(MolecularFeaturizer):
		"""Calculate symmetry function for each atom in the molecules

		This method is described in [1]_
		This method is described in [1]_.

		Examples
		--------
		>>> import deepchem as dc
		>>> smiles = ['C1C=CC=CC=1']
		>>> featurizer = dc.feat.BPSymmetryFunctionInput(max_atoms=10)
		>>> features = featurizer.featurize(smiles)
		>>> type(features[0])
		<class 'numpy.ndarray'>
		>>> features[0].shape # (max_atoms, 4)
		(10, 4)

		References
		----------

deepchem/feat/molecule_featurizers/circular_fingerprint.py

+23 −1

Original line number	Diff line number	Diff line
		@@ -14,7 +14,8 @@ class CircularFingerprint(MolecularFeaturizer):

		Extended Connectivity Circular Fingerprints compute a bag-of-words style
		representation of a molecule by breaking it into local neighborhoods and
		hashing into a bit vector of the specified size. See [1]_ for more details.
		hashing into a bit vector of the specified size. It is used specifically
		for structure-activity modelling. See [1]_ for more details.

		References
		----------
		@@ -24,6 +25,27 @@ class CircularFingerprint(MolecularFeaturizer):
		Note
		----
		This class requires RDKit to be installed.

		Examples
		--------
		>>> import deepchem as dc
		>>> from rdkit import Chem
		>>> smiles = ['C1=CC=CC=C1']
		>>> # Example 1: (size = 2048, radius = 4)
		>>> featurizer = dc.feat.CircularFingerprint(size=2048, radius=4)
		>>> features = featurizer.featurize(smiles)
		>>> type(features[0])
		<class 'numpy.ndarray'>
		>>> features[0].shape
		(2048,)

		>>> # Example 2: (size = 2048, radius = 4, sparse = True, smiles = True)
		>>> featurizer = dc.feat.CircularFingerprint(size=2048, radius=8,
		... sparse=True, smiles=True)
		>>> features = featurizer.featurize(smiles)
		>>> type(features[0]) # dict containing fingerprints
		<class 'dict'>

		"""

		def __init__(self,

Admin message