:construction: wip molecule featurizer (ad62142f) · Commits · 钟慕尧 / deepchem

deepchem/feat/adjacency_fingerprints.py→deepchem/feat/molecule_featurizers/adjacency_fingerprint.py

+0 −11

Original line number	Diff line number	Diff line
		from collections import deque

		import sys
		import tensorflow as tf
		import pickle

		import os
		import fnmatch
		import numpy as np
		from scipy.spatial.distance import pdist, squareform
		import pandas as pd

		from deepchem.feat.base_classes import Featurizer
		from deepchem.feat.graph_features import atom_features
		from scipy.sparse import csr_matrix


		def get_atom_type(atom):

deepchem/feat/coulomb_matrices.py→deepchem/feat/molecule_featurizers/coulomb_matrices.py

+11 −50

Original line number	Diff line number	Diff line
		@@ -4,7 +4,6 @@ Generate coulomb matrices for molecules.
		See Montavon et al., _New Journal of Physics_ __15__ (2013) 095003.
		"""
		import numpy as np
		import deepchem as dc
		from deepchem.feat.base_classes import MolecularFeaturizer
		from deepchem.utils import pad_array
		from deepchem.feat.atomic_coordinates import AtomicCoordinates
		@@ -54,23 +53,6 @@ class CoulombMatrix(MolecularFeaturizer):
		Coulomb matrices provide a representation of the electronic structure of a
		molecule. This method is described in [1]_.

		Parameters
		----------
		max_atoms : int
		Maximum number of atoms for any molecule in the dataset. Used to
		pad the Coulomb matrix.
		remove_hydrogens : bool, optional (default False)
		Whether to remove hydrogens before constructing Coulomb matrix.
		randomize : bool, optional (default False)
		Whether to randomize Coulomb matrices to remove dependence on atom
		index order.
		upper_tri : bool, optional (default False)
		Whether to return the upper triangular portion of the Coulomb matrix.
		n_samples : int, optional (default 1)
		Number of random Coulomb matrices to generate if randomize is True.
		seed : int, optional
		Random seed.

		Example
		-------
		>>> featurizers = dc.feat.CoulombMatrix(max_atoms=23)
		@@ -90,8 +72,6 @@ class CoulombMatrix(MolecularFeaturizer):
		----
		This class requires RDKit to be installed.
		"""
		conformers = True
		name = 'coulomb_matrix'

		def __init__(self,
		max_atoms,
		@@ -118,10 +98,6 @@ class CoulombMatrix(MolecularFeaturizer):
		seed: int, optional (default None)
		Random seed to use.
		"""
		try:
		from rdkit import Chem
		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
		@@ -142,8 +118,8 @@ class CoulombMatrix(MolecularFeaturizer):

		Parameters
		----------
		mol : RDKit Mol
		Molecule.
		mol: rdkit.Chem.rdchem.Mol
		RDKit Mol object
		"""
		features = self.coulomb_matrix(mol)
		if self.upper_tri:
		@@ -157,10 +133,14 @@ class CoulombMatrix(MolecularFeaturizer):

		Parameters
		----------
		mol : RDKit Mol
		Molecule.
		mol: rdkit.Chem.rdchem.Mol
		RDKit Mol object
		"""
		try:
		from rdkit import Chem
		except ModuleNotFoundError:
		raise ValueError("This class requires RDKit to be installed.")

		if self.remove_hydrogens:
		mol = Chem.RemoveHs(mol)
		n_atoms = mol.GetNumAtoms()
		@@ -191,12 +171,8 @@ class CoulombMatrix(MolecularFeaturizer):

		Parameters
		----------
		m : ndarray
		m: np.ndarray
		Coulomb matrix.
		n_samples : int, optional (default 1)
		Number of random matrices to generate.
		seed : int, optional
		Random seed.

		References
		----------
		@@ -240,21 +216,6 @@ class CoulombMatrixEig(CoulombMatrix):
		This featurizer computes the eigenvalues of the Coulomb matrices for provided
		molecules. Coulomb matrices are described in [1]_.

		Parameters
		----------
		max_atoms : int
		Maximum number of atoms for any molecule in the dataset. Used to
		pad the Coulomb matrix.
		remove_hydrogens : bool, optional (default False)
		Whether to remove hydrogens before constructing Coulomb matrix.
		randomize : bool, optional (default False)
		Whether to randomize Coulomb matrices to remove dependence on atom
		index order.
		n_samples : int, optional (default 1)
		Number of random Coulomb matrices to generate if randomize is True.
		seed : int, optional
		Random seed.

		Example
		-------
		>>> featurizers = dc.feat.CoulombMatrixEig(max_atoms=23)
		@@ -311,8 +272,8 @@ class CoulombMatrixEig(CoulombMatrix):

		Parameters
		----------
		mol : RDKit Mol
		Molecule.
		mol: rdkit.Chem.rdchem.Mol
		RDKit Mol object
		"""
		cmat = self.coulomb_matrix(mol)
		features = []

deepchem/feat/fingerprints.py→deepchem/feat/molecule_featurizers/morgan_fingerprints.py

+0 −1

Original line number	Diff line number	Diff line
		@@ -40,7 +40,6 @@ class CircularFingerprint(MolecularFeaturizer):
		----
		This class requires RDKit to be installed.
		"""
		name = 'circular'

		def __init__(self,
		radius=2,

Admin message