Merge pull request #2136 from nd-02110114/fix-docs-2 (28d0e19b) · Commits · 钟慕尧 / deepchem

deepchem/feat/adjacency_fingerprints.py→contrib/torch/adjacency_fingerprint.py

+0 −0

File moved.

deepchem/feat/init.py

+10 −9

Original line number	Diff line number	Diff line
		@@ -13,22 +13,23 @@ 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

		# molecule featurizers
		from deepchem.feat.molecule_featurizers import MolGraphConvFeaturizer
		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 MordredDescriptors
		from deepchem.feat.molecule_featurizers import Mol2VecFingerprint
		from deepchem.feat.molecule_featurizers import OneHotFeaturizer
		from deepchem.feat.molecule_featurizers import RawFeaturizer
		from deepchem.feat.molecule_featurizers import RDKitDescriptors
		from deepchem.feat.molecule_featurizers import SmilesToImage
		from deepchem.feat.molecule_featurizers import SmilesToSeq, create_char_to_idx

		# material featurizers
		from deepchem.feat.material_featurizers import ElementPropertyFingerprint

deepchem/feat/atomic_coordinates.py

+5 −6

Original line number	Diff line number	Diff line
		@@ -133,7 +133,6 @@ class NeighborListAtomicCoordinates(Featurizer):
		mol: rdkit Mol
		To be featurized.
		"""
		N = mol.GetNumAtoms()
		# TODO(rbharath): Should this return a list?
		bohr_coords = self.coordinates_featurizer._featurize(mol)[0]
		coords = get_coords(mol)
		@@ -168,9 +167,9 @@ class NeighborListComplexAtomicCoordinates(ComplexFeaturizer):

		Parameters
		----------
		mol_pdb_file: Str
		mol_pdb_file: str
		Filename for ligand pdb file.
		protein_pdb_file: Str
		protein_pdb_file: str
		Filename for protein pdb file.
		"""
		mol_coords, ob_mol = load_molecule(mol_pdb_file)
		@@ -245,7 +244,7 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer):

		system_coords, system_neighbor_list, system_z = self.featurize_mol(
		system_coords, system_mol, self.complex_num_atoms)
		except ValueError as e:
		except ValueError:
		logging.warning(
		"max_atoms was set too low. Some complexes too large and skipped")
		return None

deepchem/feat/base_classes.py

+19 −1

Original line number	Diff line number	Diff line
		@@ -7,6 +7,7 @@ import numpy as np
		import multiprocessing
		from typing import Any, Dict, List, Iterable, Sequence, Tuple, Union

		from deepchem.utils import get_print_threshold
		from deepchem.utils.typing import PymatgenStructure

		logger = logging.getLogger(__name__)
		@@ -96,7 +97,15 @@ class Featurizer(object):
		args_names = [arg for arg in args_spec.args if arg != 'self']
		args_info = ''
		for arg_name in args_names:
		args_info += arg_name + '=' + str(self.__dict__[arg_name]) + ', '
		value = self.__dict__[arg_name]
		# for str
		if isinstance(value, str):
		value = "'" + value + "'"
		# for list
		if isinstance(value, list):
		threshold = get_print_threshold()
		value = np.array2string(np.array(value), threshold=threshold)
		args_info += arg_name + '=' + str(value) + ', '
		return self.__class__.__name__ + '[' + args_info[:-2] + ']'

		def __str__(self) -> str:
		@@ -126,6 +135,15 @@ class Featurizer(object):
		override_args_info = ''
		for arg_name, default in zip(args_names, args_default_values):
		arg_value = self.__dict__[arg_name]
		# validation
		# skip list
		if isinstance(arg_value, list):
		continue
		if isinstance(arg_value, str):
		# skip path string
		if "\\/." in arg_value or "/" in arg_value or '.' in arg_value:
		continue
		# main logic
		if default != arg_value:
		override_args_info += '_' + arg_name + '_' + str(arg_value)
		return self.__class__.__name__ + override_args_info

deepchem/feat/binding_pocket_features.py

+23 −9

Original line number	Diff line number	Diff line
		@@ -3,14 +3,17 @@ Featurizes proposed binding pockets.
		"""
		import numpy as np
		import logging
		from typing import Dict, List

		from deepchem.feat import Featurizer
		from deepchem.utils.coordinate_box_utils import CoordinateBox
		from deepchem.utils.rdkit_utils import load_molecule

		logger = logging.getLogger(__name__)


		def boxes_to_atoms(coords, boxes):
		def boxes_to_atoms(coords: np.ndarray, boxes: List[CoordinateBox]
		) -> Dict[CoordinateBox, List[int]]:
		"""Maps each box to a list of atoms in that box.

		Given the coordinates of a macromolecule, and a collection of boxes,
		@@ -20,13 +23,14 @@ def boxes_to_atoms(coords, boxes):
		Parameters
		----------
		coords: np.ndarray
		Of shape `(N, 3)
		A numpy array of shape `(N, 3)`
		boxes: list
		list of `CoordinateBox` objects.
		List of `CoordinateBox` objects.

		Returns
		-------
		dictionary mapping `CoordinateBox` objects to lists of atom coordinates
		Dict[CoordinateBox, List[int]]
		A dictionary mapping `CoordinateBox` objects to lists of atom indices.
		"""
		mapping = {}
		for box_ind, box in enumerate(boxes):
		@@ -57,6 +61,10 @@ class BindingPocketFeaturizer(Featurizer):
		implementation for more sophisticated downstream usecases. Note that
		this class's implementation will only work for proteins and not for
		other macromolecules

		Notes
		-----
		This class requires mdtraj to be installed.
		"""

		residues = [
		@@ -67,7 +75,9 @@ class BindingPocketFeaturizer(Featurizer):

		n_features = len(residues)

		def featurize(self, protein_file, pockets):
		# FIXME: Signature of "featurize" incompatible with supertype "Featurizer"
		def featurize( # type: ignore[override]
		self, protein_file: str, pockets: List[CoordinateBox]) -> np.ndarray:
		"""
		Calculate atomic coodinates.

		@@ -75,14 +85,19 @@ class BindingPocketFeaturizer(Featurizer):
		----------
		protein_file: str
		Location of PDB file. Will be loaded by MDTraj
		pockets: list[CoordinateBox]
		pockets: List[CoordinateBox]
		List of `dc.utils.CoordinateBox` objects.

		Returns
		-------
		np.ndarray
		A numpy array of shale `(len(pockets), n_residues)`
		"""
		try:
		import mdtraj
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		protein_coords = load_molecule(
		protein_file, add_hydrogens=False, calc_charges=False)[0]
		mapping = boxes_to_atoms(protein_coords, pockets)
		@@ -101,6 +116,5 @@ class BindingPocketFeaturizer(Featurizer):
		if residue not in res_map:
		logger.info("Warning: Non-standard residue in PDB file")
		continue
		atomtype = atom_name.split("-")[1]
		all_features[pocket_num, res_map[residue]] += 1
		return all_features

Admin message