Loading deepchem/feat/__init__.py +2 −0 Original line number Diff line number Diff line Loading @@ -21,10 +21,12 @@ from deepchem.feat.molecule_featurizers import BPSymmetryFunctionInput 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 MACCSKeysFingerprint from deepchem.feat.molecule_featurizers import MordredDescriptors from deepchem.feat.molecule_featurizers import Mol2VecFingerprint from deepchem.feat.molecule_featurizers import MolGraphConvFeaturizer from deepchem.feat.molecule_featurizers import OneHotFeaturizer from deepchem.feat.molecule_featurizers import PubChemFingerprint 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 +2 −0 Original line number Diff line number Diff line Loading @@ -4,9 +4,11 @@ from deepchem.feat.molecule_featurizers.bp_symmetry_function_input import BPSymm from deepchem.feat.molecule_featurizers.circular_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.maccs_keys_fingerprint import MACCSKeysFingerprint 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.pubchem_fingerprint import PubChemFingerprint 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/maccs_keys_fingerprint.py 0 → 100644 +47 −0 Original line number Diff line number Diff line import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.feat.base_classes import MolecularFeaturizer class MACCSKeysFingerprint(MolecularFeaturizer): """MACCS Keys Fingerprint. The MACCS (Molecular ACCess System) keys are one of the most commonly used structural keys. Please confirm the details in [1]_, [2]_. References ---------- .. [1] Durant, Joseph L., et al. "Reoptimization of MDL keys for use in drug discovery." Journal of chemical information and computer sciences 42.6 (2002): 1273-1280. .. [2] https://github.com/rdkit/rdkit/blob/master/rdkit/Chem/MACCSkeys.py Notes ----- This class requires RDKit to be installed. """ def __init__(self): """Initialize this featurizer.""" try: from rdkit.Chem.AllChem import GetMACCSKeysFingerprint # noqa except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") self.calculator = GetMACCSKeysFingerprint def _featurize(self, mol: RDKitMol) -> np.ndarray: """ Calculate MACCS keys fingerprint. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray 1D array of RDKit descriptors for `mol`. The length is 167. """ return self.calculator(mol) deepchem/feat/molecule_featurizers/mol2vec_fingerprint.py +2 −15 Original line number Diff line number Diff line Loading @@ -42,8 +42,7 @@ class Mol2VecFingerprint(MolecularFeaturizer): def __init__(self, pretrain_model_path: Optional[str] = None, radius: int = 1, unseen: str = 'UNK', gather_method: str = 'sum'): unseen: str = 'UNK'): """ Parameters ---------- Loading @@ -56,9 +55,6 @@ class Mol2VecFingerprint(MolecularFeaturizer): github repository. unseen: str, optional (default 'UNK') The string to used to replace uncommon words/identifiers while training. gather_method: str, optional (default 'sum') How to aggregate vectors of identifiers are extracted from Mol2vec. 'sum' or 'mean' is supported. """ try: from gensim.models import word2vec Loading @@ -68,7 +64,6 @@ class Mol2VecFingerprint(MolecularFeaturizer): self.radius = radius self.unseen = unseen self.gather_method = gather_method self.sentences2vec = sentences2vec self.mol2alt_sentence = mol2alt_sentence if pretrain_model_path is None: Loading Loading @@ -98,13 +93,5 @@ class Mol2VecFingerprint(MolecularFeaturizer): 1D array of mol2vec fingerprint. The default length is 300. """ sentence = self.mol2alt_sentence(mol, self.radius) vec_identifiers = self.sentences2vec( sentence, self.model, unseen=self.unseen) if self.gather_method == 'sum': feature = np.sum(vec_identifiers, axis=0) elif self.gather_method == 'mean': feature = np.mean(vec_identifiers, axis=0) else: raise ValueError( 'Not supported gather_method type. Please set "sum" or "mean"') feature = self.sentences2vec([sentence], self.model, unseen=self.unseen)[0] return feature deepchem/feat/molecule_featurizers/pubchem_fingerprint.py 0 → 100644 +52 −0 Original line number Diff line number Diff line import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.feat.base_classes import MolecularFeaturizer class PubChemFingerprint(MolecularFeaturizer): """PubChem Fingerprint. The PubChem fingerprint is a 881 bit structural key, which is used by PubChem for similarity searching. Please confirm the details in [1]_. References ---------- .. [1] ftp://ftp.ncbi.nlm.nih.gov/pubchem/specifications/pubchem_fingerprints.pdf Notes ----- This class requires RDKit and PubChemPy to be installed. PubChemPy use REST API to get the fingerprint, so you need the internet access. """ def __init__(self): """Initialize this featurizer.""" try: from rdkit import Chem # noqa import pubchempy as pcp # noqa except ModuleNotFoundError: raise ValueError("This class requires PubChemPy to be installed.") self.get_pubchem_compounds = pcp.get_compounds def _featurize(self, mol: RDKitMol) -> np.ndarray: """ Calculate PubChem fingerprint. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray 1D array of RDKit descriptors for `mol`. The length is 881. """ from rdkit import Chem smiles = Chem.MolToSmiles(mol) pubchem_compound = self.get_pubchem_compounds(smiles, 'smiles')[0] feature = [int(bit) for bit in pubchem_compound.cactvs_fingerprint] return np.asarray(feature) Loading
deepchem/feat/__init__.py +2 −0 Original line number Diff line number Diff line Loading @@ -21,10 +21,12 @@ from deepchem.feat.molecule_featurizers import BPSymmetryFunctionInput 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 MACCSKeysFingerprint from deepchem.feat.molecule_featurizers import MordredDescriptors from deepchem.feat.molecule_featurizers import Mol2VecFingerprint from deepchem.feat.molecule_featurizers import MolGraphConvFeaturizer from deepchem.feat.molecule_featurizers import OneHotFeaturizer from deepchem.feat.molecule_featurizers import PubChemFingerprint 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 +2 −0 Original line number Diff line number Diff line Loading @@ -4,9 +4,11 @@ from deepchem.feat.molecule_featurizers.bp_symmetry_function_input import BPSymm from deepchem.feat.molecule_featurizers.circular_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.maccs_keys_fingerprint import MACCSKeysFingerprint 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.pubchem_fingerprint import PubChemFingerprint 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/maccs_keys_fingerprint.py 0 → 100644 +47 −0 Original line number Diff line number Diff line import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.feat.base_classes import MolecularFeaturizer class MACCSKeysFingerprint(MolecularFeaturizer): """MACCS Keys Fingerprint. The MACCS (Molecular ACCess System) keys are one of the most commonly used structural keys. Please confirm the details in [1]_, [2]_. References ---------- .. [1] Durant, Joseph L., et al. "Reoptimization of MDL keys for use in drug discovery." Journal of chemical information and computer sciences 42.6 (2002): 1273-1280. .. [2] https://github.com/rdkit/rdkit/blob/master/rdkit/Chem/MACCSkeys.py Notes ----- This class requires RDKit to be installed. """ def __init__(self): """Initialize this featurizer.""" try: from rdkit.Chem.AllChem import GetMACCSKeysFingerprint # noqa except ModuleNotFoundError: raise ValueError("This class requires RDKit to be installed.") self.calculator = GetMACCSKeysFingerprint def _featurize(self, mol: RDKitMol) -> np.ndarray: """ Calculate MACCS keys fingerprint. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray 1D array of RDKit descriptors for `mol`. The length is 167. """ return self.calculator(mol)
deepchem/feat/molecule_featurizers/mol2vec_fingerprint.py +2 −15 Original line number Diff line number Diff line Loading @@ -42,8 +42,7 @@ class Mol2VecFingerprint(MolecularFeaturizer): def __init__(self, pretrain_model_path: Optional[str] = None, radius: int = 1, unseen: str = 'UNK', gather_method: str = 'sum'): unseen: str = 'UNK'): """ Parameters ---------- Loading @@ -56,9 +55,6 @@ class Mol2VecFingerprint(MolecularFeaturizer): github repository. unseen: str, optional (default 'UNK') The string to used to replace uncommon words/identifiers while training. gather_method: str, optional (default 'sum') How to aggregate vectors of identifiers are extracted from Mol2vec. 'sum' or 'mean' is supported. """ try: from gensim.models import word2vec Loading @@ -68,7 +64,6 @@ class Mol2VecFingerprint(MolecularFeaturizer): self.radius = radius self.unseen = unseen self.gather_method = gather_method self.sentences2vec = sentences2vec self.mol2alt_sentence = mol2alt_sentence if pretrain_model_path is None: Loading Loading @@ -98,13 +93,5 @@ class Mol2VecFingerprint(MolecularFeaturizer): 1D array of mol2vec fingerprint. The default length is 300. """ sentence = self.mol2alt_sentence(mol, self.radius) vec_identifiers = self.sentences2vec( sentence, self.model, unseen=self.unseen) if self.gather_method == 'sum': feature = np.sum(vec_identifiers, axis=0) elif self.gather_method == 'mean': feature = np.mean(vec_identifiers, axis=0) else: raise ValueError( 'Not supported gather_method type. Please set "sum" or "mean"') feature = self.sentences2vec([sentence], self.model, unseen=self.unseen)[0] return feature
deepchem/feat/molecule_featurizers/pubchem_fingerprint.py 0 → 100644 +52 −0 Original line number Diff line number Diff line import numpy as np from deepchem.utils.typing import RDKitMol from deepchem.feat.base_classes import MolecularFeaturizer class PubChemFingerprint(MolecularFeaturizer): """PubChem Fingerprint. The PubChem fingerprint is a 881 bit structural key, which is used by PubChem for similarity searching. Please confirm the details in [1]_. References ---------- .. [1] ftp://ftp.ncbi.nlm.nih.gov/pubchem/specifications/pubchem_fingerprints.pdf Notes ----- This class requires RDKit and PubChemPy to be installed. PubChemPy use REST API to get the fingerprint, so you need the internet access. """ def __init__(self): """Initialize this featurizer.""" try: from rdkit import Chem # noqa import pubchempy as pcp # noqa except ModuleNotFoundError: raise ValueError("This class requires PubChemPy to be installed.") self.get_pubchem_compounds = pcp.get_compounds def _featurize(self, mol: RDKitMol) -> np.ndarray: """ Calculate PubChem fingerprint. Parameters ---------- mol: rdkit.Chem.rdchem.Mol RDKit Mol object Returns ------- np.ndarray 1D array of RDKit descriptors for `mol`. The length is 881. """ from rdkit import Chem smiles = Chem.MolToSmiles(mol) pubchem_compound = self.get_pubchem_compounds(smiles, 'smiles')[0] feature = [int(bit) for bit in pubchem_compound.cactvs_fingerprint] return np.asarray(feature)
