:bug: fix some bugs (d8ec6061) · Commits · 钟慕尧 / deepchem

deepchem/feat/molecule_featurizers/init.py

+0 −1

Original line number	Diff line number	Diff line
		@@ -4,7 +4,6 @@ from deepchem.feat.molecule_featurizers.bp_symmetry_function_input import BPSymm
		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.atom_coordinates import NeighborListAtomicCoordinates
		from deepchem.feat.molecule_featurizers.one_hot_featurizer import OneHotFeaturizer
		from deepchem.feat.molecule_featurizers.raw_featurizer import RawFeaturizer
		from deepchem.feat.molecule_featurizers.rdkit_descriptors import RDKitDescriptors

+3 −2

Original line number	Diff line number	Diff line
		import numpy as np

		from deepchem.utils.typing import RDKitMol
		from deepchem.utils.rdkit_utils import get_coordinates_from_mol
		from deepchem.feat.base_classes import MolecularFeaturizer
		from deepchem.feat.atomic_coordinates import AtomicCoordinates


		class BPSymmetryFunctionInput(MolecularFeaturizer):
		@@ -33,7 +33,8 @@ class BPSymmetryFunctionInput(MolecularFeaturizer):
		self.max_atoms = max_atoms

		def _featurize(self, mol: RDKitMol) -> np.ndarray:
		coordinates = get_coordinates_from_mol(mol, unit='bohr')
		coordfeat = AtomicCoordinates()
		coordinates = coordfeat._featurize(mol)[0]
		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]

+2 −1

Original line number	Diff line number	Diff line
		"""
		Topological fingerprints.
		"""
		from typing import Dict

		from deepchem.utils.typing import RDKitMol
		from deepchem.feat.base_classes import MolecularFeaturizer
		@@ -74,7 +75,7 @@ class CircularFingerprint(MolecularFeaturizer):
		raise ValueError("This class requires RDKit to be installed.")

		if self.sparse:
		info = {}
		info: Dict = {}
		fp = rdMolDescriptors.GetMorganFingerprint(
		mol,
		self.radius,

+4 −4

Original line number	Diff line number	Diff line
		import numpy as np
		from typing import List, Optional
		from typing import List

		from deepchem.utils.typing import RDKitMol
		from deepchem.feat.base_classes import MolecularFeaturizer
		@@ -23,12 +23,12 @@ class OneHotFeaturizer(MolecularFeaturizer):
		Note that this featurizer is not thread Safe in initialization of charset
		"""

		def __init__(self, charset: Optional[List[str]] = None, padlength: int = 120):
		def __init__(self, charset: List[str] = ZINC_CHARSET, padlength: int = 120):
		"""Initialize featurizer.

		Parameters
		----------
		charset: List[str], optional (default None)
		charset: List[str]
		A list of strings, where each string is length 1.
		padlength: int, optional (default 120)
		length to pad the smile strings to.
		@@ -141,7 +141,7 @@ class OneHotFeaturizer(MolecularFeaturizer):
		for j in range(len(one_hot[i])):
		char_bit = np.argmax(one_hot[i][j])
		smiles += self.charset[char_bit]
		smiles_list.append([smiles.strip()])
		smiles_list.append(smiles.strip())
		return smiles_list

		def _create_charset(self, smiles: List[str]) -> List[str]:

+1 −1

Original line number	Diff line number	Diff line
		@@ -97,7 +97,7 @@ class SmilesToSeq(MolecularFeaturizer):
		self.idx_to_char = {idx: letter for letter, idx in self.char_to_idx.items()}
		self.pad_len = pad_len

		def to_seq(self, smile: str) -> np.ndarray:
		def to_seq(self, smile: List[str]) -> np.ndarray:
		"""Turns list of smiles characters into array of indices"""
		out_of_vocab_idx = self.char_to_idx[OUT_OF_VOCAB_TOKEN]
		seq = [