Loading deepchem/feat/__init__.py +2 −1 Original line number Diff line number Diff line Loading @@ -37,6 +37,7 @@ from deepchem.feat.molecule_featurizers import SmilesToSeq, create_char_to_idx from deepchem.feat.complex_featurizers import RdkitGridFeaturizer from deepchem.feat.complex_featurizers import NeighborListAtomicCoordinates from deepchem.feat.complex_featurizers import NeighborListComplexAtomicCoordinates from deepchem.feat.complex_featurizers import AtomicConvFeaturizer from deepchem.feat.complex_featurizers import ( ComplexNeighborListFragmentAtomicCoordinates,) from deepchem.feat.complex_featurizers import ContactCircularFingerprint Loading deepchem/feat/complex_featurizers/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -5,6 +5,7 @@ Featurizers for complex. from deepchem.feat.complex_featurizers.rdkit_grid_featurizer import RdkitGridFeaturizer from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListAtomicCoordinates from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListComplexAtomicCoordinates from deepchem.feat.complex_featurizers.complex_atomic_coordinates import AtomicConvFeaturizer from deepchem.feat.complex_featurizers.complex_atomic_coordinates import ComplexNeighborListFragmentAtomicCoordinates from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularFingerprint from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularVoxelizer Loading deepchem/feat/complex_featurizers/complex_atomic_coordinates.py +58 −13 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ Atomic coordinate featurizer. """ import logging import warnings import numpy as np Loading Loading @@ -134,23 +135,26 @@ class NeighborListComplexAtomicCoordinates(ComplexFeaturizer): return (system_coords, system_neighbor_list) class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): class AtomicConvFeaturizer(ComplexFeaturizer): """This class computes the featurization that corresponds to AtomicConvModel. This class computes featurizations needed for AtomicConvModel. Given a two molecular structures, it computes a number of useful geometric features. In particular, for each molecule and the global complex, it computes a coordinates matrix of size (N_atoms, 3) where N_atoms is the number of atoms. It also computes a neighbor-list, a dictionary with N_atoms elements where neighbor-list[i] is a list of the atoms the i-th atom has as neighbors. In addition, it computes a z-matrix for the molecule which is an array of shape (N_atoms,) that contains the atomic This class computes featurizations needed for AtomicConvModel. Given two molecular structures, it computes a number of useful geometric features. In particular, for each molecule and the global complex, it computes a coordinates matrix of size (N_atoms, 3) where N_atoms is the number of atoms. It also computes a neighbor-list, a dictionary with N_atoms elements where neighbor-list[i] is a list of the atoms the i-th atom has as neighbors. In addition, it computes a z-matrix for the molecule which is an array of shape (N_atoms,) that contains the atomic number of that atom. Since the featurization computes these three quantities for each of the two molecules and the complex, a total of 9 quantities are returned for each complex. Note that for efficiency, fragments of the molecules can be provided rather than the full molecules themselves. Since the featurization computes these three quantities for each of the two molecules and the complex, a total of 9 quantities are returned for each complex. Note that for efficiency, fragments of the molecules can be provided rather than the full molecules themselves. """ def __init__(self, Loading @@ -160,6 +164,27 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): max_num_neighbors, neighbor_cutoff, strip_hydrogens=True): """ Parameters ---------- frag1_num_atoms: int Maximum number of atoms in fragment 1. frag2_num_atoms: int Maximum number of atoms in fragment 2. complex_num_atoms: int Maximum number of atoms in complex of frag1/frag2 together. max_num_neighbors: int Maximum number of atoms considered as neighbors. neighbor_cutoff: float Maximum distance (angstroms) for two atoms to be considered as neighbors. If more than `max_num_neighbors` atoms fall within this cutoff, the closest `max_num_neighbors` will be used. strip_hydrogens: bool (default True) Remove hydrogens before computing featurization. """ self.frag1_num_atoms = frag1_num_atoms self.frag2_num_atoms = frag2_num_atoms self.complex_num_atoms = complex_num_atoms Loading @@ -176,6 +201,7 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): mol_pdb_file, is_protein=False, sanitize=True, add_hydrogens=False) frag2_coords, frag2_mol = load_molecule( protein_pdb_file, is_protein=True, sanitize=True, add_hydrogens=False) except MoleculeLoadException: # Currently handles loading failures by returning None # TODO: Is there a better handling procedure? Loading Loading @@ -216,6 +242,7 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): logging.info("Featurizing molecule of size: %d", len(mol.GetAtoms())) neighbor_list = compute_neighbor_list(coords, self.neighbor_cutoff, self.max_num_neighbors, None) # pad outputs z = self.get_Z_matrix(mol, max_num_atoms) z = pad_array(z, max_num_atoms) coords = pad_array(coords, (max_num_atoms, 3)) Loading Loading @@ -253,3 +280,21 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): mol = MoleculeShim(atomic_numbers) coords = coords[indexes_to_keep] return coords, mol # Deprecation warnings for old atomic conv featurizer name # ATOMICCONV_DEPRECATION = "{} is deprecated and has been renamed to {} and will be removed in DeepChem 3.0." class ComplexNeighborListFragmentAtomicCoordinates(AtomicConvFeaturizer): def __init__(self, *args, **kwargs): warnings.warn( ATOMICCONV_DEPRECATION.format( "ComplexNeighorListFragmentAtomicCoordinates", "AtomicConvFeaturizer"), FutureWarning) super(ComplexNeighborListFragmentAtomicCoordinates, self).__init__( *args, **kwargs) deepchem/feat/tests/data/3zso_protein_noH.pdb 0 → 100644 +2876 −0 File added.Preview size limit exceeded, changes collapsed. Show changes deepchem/feat/tests/test_atomic_conv_feat.py 0 → 100644 +58 −0 Original line number Diff line number Diff line """ Test atomic conv featurizer. """ import os import logging import numpy as np from deepchem.feat import AtomicConvFeaturizer logger = logging.getLogger(__name__) def test_atomic_conv_featurization(): """Unit test for AtomicConvFeaturizer.""" dir_path = os.path.dirname(os.path.realpath(__file__)) ligand_file = os.path.join(dir_path, "data/3zso_ligand_hyd.pdb") protein_file = os.path.join(dir_path, "data/3zso_protein_noH.pdb") # Pulled from PDB files. For larger datasets with more PDBs, would use # max num atoms instead of exact. frag1_num_atoms = 44 # for ligand atoms frag2_num_atoms = 2334 # for protein atoms complex_num_atoms = 2378 # in total max_num_neighbors = 4 # Cutoff in angstroms neighbor_cutoff = 4 complex_featurizer = AtomicConvFeaturizer(frag1_num_atoms, frag2_num_atoms, complex_num_atoms, max_num_neighbors, neighbor_cutoff) (frag1_coords, frag1_neighbor_list, frag1_z, frag2_coords, frag2_neighbor_list, frag2_z, complex_coords, complex_neighbor_list, complex_z) = complex_featurizer._featurize((ligand_file, protein_file)) # Coords are padded, neighbor list and Z are not assert frag1_coords.shape == (frag1_num_atoms, 3) assert (sorted(list(frag1_neighbor_list.keys())) == list( range(frag1_num_atoms))) assert frag1_neighbor_list[0] == [1, 2, 14, 3] assert frag1_z.shape == (frag1_num_atoms,) assert np.array_equal( frag1_z, np.array([ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 8, 8, 8, 8, 8, 8, 8 ])) assert frag2_coords.shape == (frag2_num_atoms, 3) assert (sorted(list(frag2_neighbor_list.keys())) == list( range(frag2_num_atoms))) assert frag2_neighbor_list[0] == [1, 2, 4, 3] assert frag2_z.shape == (frag2_num_atoms,) assert complex_coords.shape == (complex_num_atoms, 3) assert (sorted(list(complex_neighbor_list.keys())) == list( range(complex_num_atoms))) assert complex_neighbor_list[0] == [1, 2, 14, 3] assert (complex_z.shape == (complex_num_atoms,)) Loading
deepchem/feat/__init__.py +2 −1 Original line number Diff line number Diff line Loading @@ -37,6 +37,7 @@ from deepchem.feat.molecule_featurizers import SmilesToSeq, create_char_to_idx from deepchem.feat.complex_featurizers import RdkitGridFeaturizer from deepchem.feat.complex_featurizers import NeighborListAtomicCoordinates from deepchem.feat.complex_featurizers import NeighborListComplexAtomicCoordinates from deepchem.feat.complex_featurizers import AtomicConvFeaturizer from deepchem.feat.complex_featurizers import ( ComplexNeighborListFragmentAtomicCoordinates,) from deepchem.feat.complex_featurizers import ContactCircularFingerprint Loading
deepchem/feat/complex_featurizers/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -5,6 +5,7 @@ Featurizers for complex. from deepchem.feat.complex_featurizers.rdkit_grid_featurizer import RdkitGridFeaturizer from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListAtomicCoordinates from deepchem.feat.complex_featurizers.complex_atomic_coordinates import NeighborListComplexAtomicCoordinates from deepchem.feat.complex_featurizers.complex_atomic_coordinates import AtomicConvFeaturizer from deepchem.feat.complex_featurizers.complex_atomic_coordinates import ComplexNeighborListFragmentAtomicCoordinates from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularFingerprint from deepchem.feat.complex_featurizers.contact_fingerprints import ContactCircularVoxelizer Loading
deepchem/feat/complex_featurizers/complex_atomic_coordinates.py +58 −13 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ Atomic coordinate featurizer. """ import logging import warnings import numpy as np Loading Loading @@ -134,23 +135,26 @@ class NeighborListComplexAtomicCoordinates(ComplexFeaturizer): return (system_coords, system_neighbor_list) class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): class AtomicConvFeaturizer(ComplexFeaturizer): """This class computes the featurization that corresponds to AtomicConvModel. This class computes featurizations needed for AtomicConvModel. Given a two molecular structures, it computes a number of useful geometric features. In particular, for each molecule and the global complex, it computes a coordinates matrix of size (N_atoms, 3) where N_atoms is the number of atoms. It also computes a neighbor-list, a dictionary with N_atoms elements where neighbor-list[i] is a list of the atoms the i-th atom has as neighbors. In addition, it computes a z-matrix for the molecule which is an array of shape (N_atoms,) that contains the atomic This class computes featurizations needed for AtomicConvModel. Given two molecular structures, it computes a number of useful geometric features. In particular, for each molecule and the global complex, it computes a coordinates matrix of size (N_atoms, 3) where N_atoms is the number of atoms. It also computes a neighbor-list, a dictionary with N_atoms elements where neighbor-list[i] is a list of the atoms the i-th atom has as neighbors. In addition, it computes a z-matrix for the molecule which is an array of shape (N_atoms,) that contains the atomic number of that atom. Since the featurization computes these three quantities for each of the two molecules and the complex, a total of 9 quantities are returned for each complex. Note that for efficiency, fragments of the molecules can be provided rather than the full molecules themselves. Since the featurization computes these three quantities for each of the two molecules and the complex, a total of 9 quantities are returned for each complex. Note that for efficiency, fragments of the molecules can be provided rather than the full molecules themselves. """ def __init__(self, Loading @@ -160,6 +164,27 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): max_num_neighbors, neighbor_cutoff, strip_hydrogens=True): """ Parameters ---------- frag1_num_atoms: int Maximum number of atoms in fragment 1. frag2_num_atoms: int Maximum number of atoms in fragment 2. complex_num_atoms: int Maximum number of atoms in complex of frag1/frag2 together. max_num_neighbors: int Maximum number of atoms considered as neighbors. neighbor_cutoff: float Maximum distance (angstroms) for two atoms to be considered as neighbors. If more than `max_num_neighbors` atoms fall within this cutoff, the closest `max_num_neighbors` will be used. strip_hydrogens: bool (default True) Remove hydrogens before computing featurization. """ self.frag1_num_atoms = frag1_num_atoms self.frag2_num_atoms = frag2_num_atoms self.complex_num_atoms = complex_num_atoms Loading @@ -176,6 +201,7 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): mol_pdb_file, is_protein=False, sanitize=True, add_hydrogens=False) frag2_coords, frag2_mol = load_molecule( protein_pdb_file, is_protein=True, sanitize=True, add_hydrogens=False) except MoleculeLoadException: # Currently handles loading failures by returning None # TODO: Is there a better handling procedure? Loading Loading @@ -216,6 +242,7 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): logging.info("Featurizing molecule of size: %d", len(mol.GetAtoms())) neighbor_list = compute_neighbor_list(coords, self.neighbor_cutoff, self.max_num_neighbors, None) # pad outputs z = self.get_Z_matrix(mol, max_num_atoms) z = pad_array(z, max_num_atoms) coords = pad_array(coords, (max_num_atoms, 3)) Loading Loading @@ -253,3 +280,21 @@ class ComplexNeighborListFragmentAtomicCoordinates(ComplexFeaturizer): mol = MoleculeShim(atomic_numbers) coords = coords[indexes_to_keep] return coords, mol # Deprecation warnings for old atomic conv featurizer name # ATOMICCONV_DEPRECATION = "{} is deprecated and has been renamed to {} and will be removed in DeepChem 3.0." class ComplexNeighborListFragmentAtomicCoordinates(AtomicConvFeaturizer): def __init__(self, *args, **kwargs): warnings.warn( ATOMICCONV_DEPRECATION.format( "ComplexNeighorListFragmentAtomicCoordinates", "AtomicConvFeaturizer"), FutureWarning) super(ComplexNeighborListFragmentAtomicCoordinates, self).__init__( *args, **kwargs)
deepchem/feat/tests/data/3zso_protein_noH.pdb 0 → 100644 +2876 −0 File added.Preview size limit exceeded, changes collapsed. Show changes
deepchem/feat/tests/test_atomic_conv_feat.py 0 → 100644 +58 −0 Original line number Diff line number Diff line """ Test atomic conv featurizer. """ import os import logging import numpy as np from deepchem.feat import AtomicConvFeaturizer logger = logging.getLogger(__name__) def test_atomic_conv_featurization(): """Unit test for AtomicConvFeaturizer.""" dir_path = os.path.dirname(os.path.realpath(__file__)) ligand_file = os.path.join(dir_path, "data/3zso_ligand_hyd.pdb") protein_file = os.path.join(dir_path, "data/3zso_protein_noH.pdb") # Pulled from PDB files. For larger datasets with more PDBs, would use # max num atoms instead of exact. frag1_num_atoms = 44 # for ligand atoms frag2_num_atoms = 2334 # for protein atoms complex_num_atoms = 2378 # in total max_num_neighbors = 4 # Cutoff in angstroms neighbor_cutoff = 4 complex_featurizer = AtomicConvFeaturizer(frag1_num_atoms, frag2_num_atoms, complex_num_atoms, max_num_neighbors, neighbor_cutoff) (frag1_coords, frag1_neighbor_list, frag1_z, frag2_coords, frag2_neighbor_list, frag2_z, complex_coords, complex_neighbor_list, complex_z) = complex_featurizer._featurize((ligand_file, protein_file)) # Coords are padded, neighbor list and Z are not assert frag1_coords.shape == (frag1_num_atoms, 3) assert (sorted(list(frag1_neighbor_list.keys())) == list( range(frag1_num_atoms))) assert frag1_neighbor_list[0] == [1, 2, 14, 3] assert frag1_z.shape == (frag1_num_atoms,) assert np.array_equal( frag1_z, np.array([ 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 8, 8, 8, 8, 8, 8, 8 ])) assert frag2_coords.shape == (frag2_num_atoms, 3) assert (sorted(list(frag2_neighbor_list.keys())) == list( range(frag2_num_atoms))) assert frag2_neighbor_list[0] == [1, 2, 4, 3] assert frag2_z.shape == (frag2_num_atoms,) assert complex_coords.shape == (complex_num_atoms, 3) assert (sorted(list(complex_neighbor_list.keys())) == list( range(complex_num_atoms))) assert complex_neighbor_list[0] == [1, 2, 14, 3] assert (complex_z.shape == (complex_num_atoms,))
