:construction: create molecule featurizer directory (7ccc4d59) · Commits · 钟慕尧 / deepchem

deepchem/feat/init.py

+10 −6

Original line number	Diff line number	Diff line
		"""
		Making it easy to import in classes.
		"""
		# flake8: noqa
		from deepchem.feat.base_classes import Featurizer
		from deepchem.feat.base_classes import MolecularFeaturizer
		from deepchem.feat.base_classes import MaterialStructureFeaturizer
		from deepchem.feat.base_classes import MaterialCompositionFeaturizer
		from deepchem.feat.base_classes import ComplexFeaturizer
		from deepchem.feat.base_classes import UserDefinedFeaturizer

		from deepchem.feat.graph_features import ConvMolFeaturizer
		from deepchem.feat.graph_features import WeaveFeaturizer
		from deepchem.feat.fingerprints import CircularFingerprint
		from deepchem.feat.rdkit_descriptors import RDKitDescriptors
		from deepchem.feat.coulomb_matrices import CoulombMatrix
		from deepchem.feat.coulomb_matrices import CoulombMatrixEig
		from deepchem.feat.coulomb_matrices import BPSymmetryFunctionInput
		from deepchem.feat.rdkit_grid_featurizer import RdkitGridFeaturizer
		from deepchem.feat.binding_pocket_features import BindingPocketFeaturizer
		from deepchem.feat.one_hot import OneHotFeaturizer
		from deepchem.feat.raw_featurizer import RawFeaturizer
		from deepchem.feat.atomic_coordinates import AtomicCoordinates
		from deepchem.feat.atomic_coordinates import NeighborListComplexAtomicCoordinates
		from deepchem.feat.adjacency_fingerprints import AdjacencyFingerprint
		from deepchem.feat.smiles_featurizers import SmilesToSeq, SmilesToImage

		from deepchem.feat.molecule_featurizers import AdjacencyFingerprint
		from deepchem.feat.molecule_featurizers import CircularFingerprint
		from deepchem.feat.molecule_featurizers import CoulombMatrix
		from deepchem.feat.molecule_featurizers import CoulombMatrixEig
		from deepchem.feat.molecule_featurizers import OneHotFeaturizer
		from deepchem.feat.molecule_featurizers import RDKitDescriptors

		from deepchem.feat.material_featurizers import ElementPropertyFingerprint
		from deepchem.feat.material_featurizers import SineCoulombMatrix
		from deepchem.feat.material_featurizers import CGCNNFeaturizer

deepchem/feat/base_classes.py

+13 −13

Original line number	Diff line number	Diff line
		@@ -2,10 +2,9 @@
		Feature calculations.
		"""
		import logging
		import types
		import numpy as np
		import multiprocessing
		from typing import Any, Dict, List, Iterable, Sequence, Tuple, Union
		from typing import Any, Dict, List, Iterable, Sequence, Tuple

		logger = logging.getLogger(__name__)

		@@ -169,7 +168,7 @@ class MolecularFeaturizer(Featurizer):
		In general, subclasses of this class will require RDKit to be installed.
		"""

		def featurize(self, molecules, log_every_n=1000):
		def featurize(self, molecules, log_every_n=1000, canonical=False):
		"""Calculate features for molecules.

		Parameters
		@@ -177,6 +176,10 @@ class MolecularFeaturizer(Featurizer):
		molecules: RDKit Mol / SMILES string / iterable
		RDKit Mol, or SMILES string or iterable sequence of RDKit mols/SMILES
		strings.
		log_every_n: int, default 1000
		Logging messages reported every `log_every_n` samples.
		canonical: bool, default False
		Whether to use a canonical order of atoms returned by RDKit

		Returns
		-------
		@@ -185,33 +188,30 @@ class MolecularFeaturizer(Featurizer):
		"""
		try:
		from rdkit import Chem
		from rdkit.Chem import rdmolfiles
		from rdkit.Chem import rdmolops
		from rdkit.Chem.rdchem import Mol
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		# Special case handling of single molecule
		if isinstance(molecules, str) or isinstance(molecules, Mol):
		molecules = [molecules]
		else:
		# Convert iterables to list
		molecules = list(molecules)

		features = []
		for i, mol in enumerate(molecules):
		if i % log_every_n == 0:
		logger.info("Featurizing datapoint %i" % i)
		try:
		# Process only case of SMILES strings.
		if isinstance(mol, str):
		# mol must be a SMILES string so parse
		mol = Chem.MolFromSmiles(mol)
		# TODO (ytz) this is a bandage solution to reorder the atoms
		# so that they're always in the same canonical order.
		# Presumably this should be correctly implemented in the
		# future for graph mols.
		if mol:
		new_order = rdmolfiles.CanonicalRankAtoms(mol)
		mol = rdmolops.RenumberAtoms(mol, new_order)
		# canonicalize
		if canonical:
		canonical_smiles = Chem.MolToSmiles(mol, isomericSmiles=False, canonical=True)
		mol = Chem.MolFromSmiles(canonical_smiles)

		features.append(self._featurize(mol))
		except:
		logger.warning(

deepchem/feat/graph_data.py

+3 −4

Original line number	Diff line number	Diff line
		@@ -109,8 +109,7 @@ class GraphData:
		return Data(
		x=torch.from_numpy(self.node_features),
		edge_index=torch.from_numpy(self.edge_index).long(),
		edge_attr=None if self.edge_features is None \
		else torch.from_numpy(self.edge_features),
		edge_attr=None if self.edge_features is None else torch.from_numpy(self.edge_features),
		)

		def to_dgl_graph(self):
		@@ -194,8 +193,8 @@ class BatchGraphData(GraphData):
		# create new edge index
		num_nodes_list = [graph.num_nodes for graph in graph_list]
		batch_edge_index = np.hstack(
		[graph.edge_index + prev_num_node for prev_num_node, graph \
		in zip([0] + num_nodes_list[:-1], graph_list)]
		[graph.edge_index + prev_num_node
		for prev_num_node, graph in zip([0] + num_nodes_list[:-1], graph_list)]
		)

		# graph_index indicates which nodes belong to which graph

deepchem/feat/material_featurizers/init.py

+1 −0

Original line number	Diff line number	Diff line
		"""
		Featurizers for inorganic crystals.
		"""
		# flake8: noqa
		from deepchem.feat.material_featurizers.element_property_fingerprint import ElementPropertyFingerprint
		from deepchem.feat.material_featurizers.sine_coulomb_matrix import SineCoulombMatrix
		from deepchem.feat.material_featurizers.cgcnn_featurizer import CGCNNFeaturizer

deepchem/feat/molecule_featurizers/init.py

0 → 100644

+7 −0

Original line number	Diff line number	Diff line
		# flake8: noqa
		from deepchem.feat.molecule_featurizers.adjacency_fingerprint import AdjacencyFingerprint
		from deepchem.feat.molecule_featurizers.morgan_fingerprint import CircularFingerprint
		from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrix
		from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrixEig
		from deepchem.feat.molecule_featurizers.one_hot_featurizer import OneHotFeaturizer
		from deepchem.feat.molecule_featurizers.rdkit_descriptors import RDKitDescriptors

Admin message