Loading contrib/autoencoder_models/one_hot_featurizer.pydeleted 100644 → 0 +0 −158 Original line number Diff line number Diff line import numpy as np from deepchem.feat.base_classes import MolecularFeaturizer zinc_charset = [ ' ', '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8', '=', '@', 'C', 'B', 'F', 'I', 'H', 'O', 'N', 'S', '[', ']', '\\', 'c', 'l', 'o', 'n', 'p', 's', 'r' ] class OneHotFeaturizer(MolecularFeaturizer): """Encodes a molecule as a one-hot array. This featurizer takes a molecule and encodes its Smiles string as a one-hot array. Note ---- This class requires RDKit to be installed. Note that this featurizer is not Thread Safe in initialization of charset """ def __init__(self, charset=None, padlength=120): """Initialize featurizer. Parameters ---------- charset: list of str, optional (default None) A list of strings, where each string is length 1. padlength: int, optional (default 120) length to pad the smile strings to. """ try: from rdkit import Chem except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") self.charset = charset self.pad_length = padlength def _featurize(self, mol): """Compute one-hot featurization of this molecule. Parameters ---------- mol : RDKit Mol Molecule. Returns ------- rval: np.ndarray Vector of RDKit descriptors for `mol` """ from rdkit import Chem smiles = Chem.MolToSmiles(mol) if self.charset is None: self.charset = self._create_charset(smiles) return np.array([self.one_hot_encoded(smile) for smile in smiles]) def one_hot_array(self, i): """Create a one hot array with bit i set to 1 Parameters ---------- i: int bit to set to 1 Returns ------- obj:`list` of obj:`int` length len(self.charset) """ return [int(x) for x in [ix == i for ix in range(len(self.charset))]] def one_hot_index(self, c): """Compute one-hot index of charater. Parameters ---------- c: char character whose index we want Returns ------- index of c in self.charset """ return self.charset.index(c) def pad_smile(self, smile): """Pad a smile string to `self.pad_length` Parameters ---------- smile: str The smiles string to be padded. Returns ------- str smile string space padded to self.pad_length """ return smile.ljust(self.pad_length) def one_hot_encoded(self, smile): """One Hot Encode an entire SMILE string Parameters ---------- smile: str smile string to encode Returns ------- np.array of one hot encoded arrays for each character in smile """ return np.array([ self.one_hot_array(self.one_hot_index(x)) for x in self.pad_smile(smile) ]) def untransform(self, z): """Convert from one hot representation back to SMILE Parameters ---------- z: obj:`list` list of one hot encoded features Returns ------- Smile Strings picking MAX for each one hot encoded array """ z1 = [] for i in range(len(z)): s = "" for j in range(len(z[i])): oh = np.argmax(z[i][j]) s += self.charset[oh] z1.append([s.strip()]) return z1 def _create_charset(self, smiles): """Create the charset from smiles Parameters ---------- smiles: obj:`list` of obj:`str` list of smile strings Returns ------- obj:`list` of obj:`str` List of length one strings that are characters in smiles. No duplicates """ s = set() for smile in smiles: for c in smile: s.add(c) return [' '] + sorted(list(s)) deepchem/feat/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -25,6 +25,7 @@ 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 Loading deepchem/feat/molecule_featurizers/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -5,6 +5,7 @@ from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrix from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrixEig from deepchem.feat.molecule_featurizers.mordred_descriptors import MordredDescriptors from deepchem.feat.molecule_featurizers.mol2vec_fingerprint import Mol2VecFingerprint 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 from deepchem.feat.molecule_featurizers.smiles_to_image import SmilesToImage Loading deepchem/feat/molecule_featurizers/one_hot_featurizer.py 0 → 100644 +113 −0 Original line number Diff line number Diff line import logging from typing import List import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.utils.molecule_feature_utils import one_hot_encode from deepchem.feat.base_classes import MolecularFeaturizer logger = logging.getLogger(__name__) ZINC_CHARSET = [ '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8', '=', '@', 'C', 'B', 'F', 'I', 'H', 'O', 'N', 'S', '[', ']', '\\', 'c', 'l', 'o', 'n', 'p', 's', 'r' ] class OneHotFeaturizer(MolecularFeaturizer): """Encodes SMILES as a one-hot array. This featurizer encodes its SMILES string as a one-hot array. Notes ---- This class requires RDKit to be installed. """ def __init__(self, charset: List[str] = ZINC_CHARSET, max_length: int = 100): """Initialize featurizer. Parameters ---------- charset: List[str], optional (default ZINC_CHARSET) A list of strings, where each string is length 1 and unique. max_length: int, optional (default 100) length to pad the SMILES strings to. """ if len(charset) != len(set(charset)): raise ValueError("All values in charset must be unique.") self.charset = charset self.max_length = max_length def _featurize(self, mol: RDKitMol) -> np.ndarray: """Compute one-hot featurization of this molecule. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray An one hot vector encoded from SMILES. The shape is `(max_length, len(charset) + 1)`. The index of unknown character is `len(charset)`. """ try: from rdkit import Chem except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") smiles = Chem.MolToSmiles(mol) # validation if len(smiles) > self.max_length: logger.info( "The length of {} is longer than `max_length`. So we return an empty array." ) return np.array([]) smiles = self.pad_smile(smiles) return np.array([ one_hot_encode(val, self.charset, include_unknown_set=True) for val in smiles ]) def pad_smile(self, smiles: str) -> str: """Pad SMILES string to `self.pad_length` Parameters ---------- smiles: str The smiles string to be padded. Returns ------- str SMILES string space padded to self.pad_length """ return smiles.ljust(self.max_length) def untransform(self, one_hot_vectors: np.ndarray) -> str: """Convert from one hot representation back to SMILES Parameters ---------- one_hot_vectors: np.ndarray An array of one hot encoded features. Returns ------- str SMILES string for an one hot encoded array. """ smiles = "" for one_hot in one_hot_vectors: try: idx = np.argmax(one_hot) smiles += self.charset[idx] except IndexError: smiles += "" return smiles deepchem/feat/tests/test_one_hot_featurizer.py 0 → 100644 +64 −0 Original line number Diff line number Diff line import unittest import numpy as np from deepchem.feat import OneHotFeaturizer from deepchem.feat.molecule_featurizers.one_hot_featurizer import ZINC_CHARSET class TestOneHotFeaturizert(unittest.TestCase): """ Test OneHotFeaturizer. """ def test_onehot_featurizer(self): """ Test simple one hot encoding. """ from rdkit import Chem length = len(ZINC_CHARSET) + 1 smiles = 'CC(=O)Oc1ccccc1C(=O)O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer() feature = featurizer([mol]) assert feature.shape == (1, 100, length) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles def test_onehot_featurizer_with_max_length(self): """ Test one hot encoding with max_length. """ from rdkit import Chem length = len(ZINC_CHARSET) + 1 smiles = 'CC(=O)Oc1ccccc1C(=O)O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer(max_length=120) feature = featurizer([mol]) assert feature.shape == (1, 120, length) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles def test_correct_transformation(self): """ Test correct one hot encoding. """ from rdkit import Chem charset = ['C', 'N', '=', ')', '(', 'O'] smiles = 'CN=C=O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer(charset=charset, max_length=100) feature = featurizer([mol]) assert np.allclose(feature[0][0], np.array([1, 0, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][1], np.array([0, 1, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][2], np.array([0, 0, 1, 0, 0, 0, 0])) assert np.allclose(feature[0][3], np.array([1, 0, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][4], np.array([0, 0, 1, 0, 0, 0, 0])) assert np.allclose(feature[0][5], np.array([0, 0, 0, 0, 0, 1, 0])) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles Loading
contrib/autoencoder_models/one_hot_featurizer.pydeleted 100644 → 0 +0 −158 Original line number Diff line number Diff line import numpy as np from deepchem.feat.base_classes import MolecularFeaturizer zinc_charset = [ ' ', '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8', '=', '@', 'C', 'B', 'F', 'I', 'H', 'O', 'N', 'S', '[', ']', '\\', 'c', 'l', 'o', 'n', 'p', 's', 'r' ] class OneHotFeaturizer(MolecularFeaturizer): """Encodes a molecule as a one-hot array. This featurizer takes a molecule and encodes its Smiles string as a one-hot array. Note ---- This class requires RDKit to be installed. Note that this featurizer is not Thread Safe in initialization of charset """ def __init__(self, charset=None, padlength=120): """Initialize featurizer. Parameters ---------- charset: list of str, optional (default None) A list of strings, where each string is length 1. padlength: int, optional (default 120) length to pad the smile strings to. """ try: from rdkit import Chem except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") self.charset = charset self.pad_length = padlength def _featurize(self, mol): """Compute one-hot featurization of this molecule. Parameters ---------- mol : RDKit Mol Molecule. Returns ------- rval: np.ndarray Vector of RDKit descriptors for `mol` """ from rdkit import Chem smiles = Chem.MolToSmiles(mol) if self.charset is None: self.charset = self._create_charset(smiles) return np.array([self.one_hot_encoded(smile) for smile in smiles]) def one_hot_array(self, i): """Create a one hot array with bit i set to 1 Parameters ---------- i: int bit to set to 1 Returns ------- obj:`list` of obj:`int` length len(self.charset) """ return [int(x) for x in [ix == i for ix in range(len(self.charset))]] def one_hot_index(self, c): """Compute one-hot index of charater. Parameters ---------- c: char character whose index we want Returns ------- index of c in self.charset """ return self.charset.index(c) def pad_smile(self, smile): """Pad a smile string to `self.pad_length` Parameters ---------- smile: str The smiles string to be padded. Returns ------- str smile string space padded to self.pad_length """ return smile.ljust(self.pad_length) def one_hot_encoded(self, smile): """One Hot Encode an entire SMILE string Parameters ---------- smile: str smile string to encode Returns ------- np.array of one hot encoded arrays for each character in smile """ return np.array([ self.one_hot_array(self.one_hot_index(x)) for x in self.pad_smile(smile) ]) def untransform(self, z): """Convert from one hot representation back to SMILE Parameters ---------- z: obj:`list` list of one hot encoded features Returns ------- Smile Strings picking MAX for each one hot encoded array """ z1 = [] for i in range(len(z)): s = "" for j in range(len(z[i])): oh = np.argmax(z[i][j]) s += self.charset[oh] z1.append([s.strip()]) return z1 def _create_charset(self, smiles): """Create the charset from smiles Parameters ---------- smiles: obj:`list` of obj:`str` list of smile strings Returns ------- obj:`list` of obj:`str` List of length one strings that are characters in smiles. No duplicates """ s = set() for smile in smiles: for c in smile: s.add(c) return [' '] + sorted(list(s))
deepchem/feat/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -25,6 +25,7 @@ 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 Loading
deepchem/feat/molecule_featurizers/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -5,6 +5,7 @@ from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrix from deepchem.feat.molecule_featurizers.coulomb_matrices import CoulombMatrixEig from deepchem.feat.molecule_featurizers.mordred_descriptors import MordredDescriptors from deepchem.feat.molecule_featurizers.mol2vec_fingerprint import Mol2VecFingerprint 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 from deepchem.feat.molecule_featurizers.smiles_to_image import SmilesToImage Loading
deepchem/feat/molecule_featurizers/one_hot_featurizer.py 0 → 100644 +113 −0 Original line number Diff line number Diff line import logging from typing import List import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.utils.molecule_feature_utils import one_hot_encode from deepchem.feat.base_classes import MolecularFeaturizer logger = logging.getLogger(__name__) ZINC_CHARSET = [ '#', ')', '(', '+', '-', '/', '1', '3', '2', '5', '4', '7', '6', '8', '=', '@', 'C', 'B', 'F', 'I', 'H', 'O', 'N', 'S', '[', ']', '\\', 'c', 'l', 'o', 'n', 'p', 's', 'r' ] class OneHotFeaturizer(MolecularFeaturizer): """Encodes SMILES as a one-hot array. This featurizer encodes its SMILES string as a one-hot array. Notes ---- This class requires RDKit to be installed. """ def __init__(self, charset: List[str] = ZINC_CHARSET, max_length: int = 100): """Initialize featurizer. Parameters ---------- charset: List[str], optional (default ZINC_CHARSET) A list of strings, where each string is length 1 and unique. max_length: int, optional (default 100) length to pad the SMILES strings to. """ if len(charset) != len(set(charset)): raise ValueError("All values in charset must be unique.") self.charset = charset self.max_length = max_length def _featurize(self, mol: RDKitMol) -> np.ndarray: """Compute one-hot featurization of this molecule. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray An one hot vector encoded from SMILES. The shape is `(max_length, len(charset) + 1)`. The index of unknown character is `len(charset)`. """ try: from rdkit import Chem except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") smiles = Chem.MolToSmiles(mol) # validation if len(smiles) > self.max_length: logger.info( "The length of {} is longer than `max_length`. So we return an empty array." ) return np.array([]) smiles = self.pad_smile(smiles) return np.array([ one_hot_encode(val, self.charset, include_unknown_set=True) for val in smiles ]) def pad_smile(self, smiles: str) -> str: """Pad SMILES string to `self.pad_length` Parameters ---------- smiles: str The smiles string to be padded. Returns ------- str SMILES string space padded to self.pad_length """ return smiles.ljust(self.max_length) def untransform(self, one_hot_vectors: np.ndarray) -> str: """Convert from one hot representation back to SMILES Parameters ---------- one_hot_vectors: np.ndarray An array of one hot encoded features. Returns ------- str SMILES string for an one hot encoded array. """ smiles = "" for one_hot in one_hot_vectors: try: idx = np.argmax(one_hot) smiles += self.charset[idx] except IndexError: smiles += "" return smiles
deepchem/feat/tests/test_one_hot_featurizer.py 0 → 100644 +64 −0 Original line number Diff line number Diff line import unittest import numpy as np from deepchem.feat import OneHotFeaturizer from deepchem.feat.molecule_featurizers.one_hot_featurizer import ZINC_CHARSET class TestOneHotFeaturizert(unittest.TestCase): """ Test OneHotFeaturizer. """ def test_onehot_featurizer(self): """ Test simple one hot encoding. """ from rdkit import Chem length = len(ZINC_CHARSET) + 1 smiles = 'CC(=O)Oc1ccccc1C(=O)O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer() feature = featurizer([mol]) assert feature.shape == (1, 100, length) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles def test_onehot_featurizer_with_max_length(self): """ Test one hot encoding with max_length. """ from rdkit import Chem length = len(ZINC_CHARSET) + 1 smiles = 'CC(=O)Oc1ccccc1C(=O)O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer(max_length=120) feature = featurizer([mol]) assert feature.shape == (1, 120, length) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles def test_correct_transformation(self): """ Test correct one hot encoding. """ from rdkit import Chem charset = ['C', 'N', '=', ')', '(', 'O'] smiles = 'CN=C=O' mol = Chem.MolFromSmiles(smiles) featurizer = OneHotFeaturizer(charset=charset, max_length=100) feature = featurizer([mol]) assert np.allclose(feature[0][0], np.array([1, 0, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][1], np.array([0, 1, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][2], np.array([0, 0, 1, 0, 0, 0, 0])) assert np.allclose(feature[0][3], np.array([1, 0, 0, 0, 0, 0, 0])) assert np.allclose(feature[0][4], np.array([0, 0, 1, 0, 0, 0, 0])) assert np.allclose(feature[0][5], np.array([0, 0, 0, 0, 0, 1, 0])) # untranform undo_smiles = featurizer.untransform(feature[0]) assert smiles == undo_smiles
