python/dgllife/utils/complex_to_graph.py [76:141]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - strip_hydrogens=False): """Graph construction and featurization for `PotentialNet for Molecular Property Prediction `__. Parameters ---------- ligand_mol : rdkit.Chem.rdchem.Mol RDKit molecule instance. protein_mol : rdkit.Chem.rdchem.Mol RDKit molecule instance. ligand_coordinates : Float Tensor of shape (V1, 3) Atom coordinates in a ligand. protein_coordinates : Float Tensor of shape (V2, 3) Atom coordinates in a protein. max_num_ligand_atoms : int or None Maximum number of atoms in ligands for zero padding, which should be no smaller than ligand_mol.GetNumAtoms() if not None. If None, no zero padding will be performed. Default to None. max_num_protein_atoms : int or None Maximum number of atoms in proteins for zero padding, which should be no smaller than protein_mol.GetNumAtoms() if not None. If None, no zero padding will be performed. Default to None. max_num_neighbors : int Maximum number of neighbors allowed for each atom when constructing KNN graph. Default to 4. distance_bins : list of float Distance bins to determine the edge types. Edges of the first edge type are added between pairs of atoms whose distances are less than `distance_bins[0]`. The length matches the number of edge types to be constructed. Default `[1.5, 2.5, 3.5, 4.5]`. strip_hydrogens : bool Whether to exclude hydrogen atoms. Default to False. Returns ------- complex_bigraph : DGLGraph Bigraph with the ligand and the protein (pocket) combined and canonical features extracted. The atom features are stored as DGLGraph.ndata['h']. The edge types are stored as DGLGraph.edata['e']. The bigraphs of the ligand and the protein are batched together as one complex graph. complex_knn_graph : DGLGraph K-nearest-neighbor graph with the ligand and the protein (pocket) combined and edge features extracted based on distances. The edge types are stored as DGLGraph.edata['e']. The knn graphs of the ligand and the protein are batched together as one complex graph. """ assert ligand_coordinates is not None, 'Expect ligand_coordinates to be provided.' assert protein_coordinates is not None, 'Expect protein_coordinates to be provided.' if max_num_ligand_atoms is not None: assert max_num_ligand_atoms >= ligand_mol.GetNumAtoms(), \ 'Expect max_num_ligand_atoms to be no smaller than ligand_mol.GetNumAtoms(), ' \ 'got {:d} and {:d}'.format(max_num_ligand_atoms, ligand_mol.GetNumAtoms()) if max_num_protein_atoms is not None: assert max_num_protein_atoms >= protein_mol.GetNumAtoms(), \ 'Expect max_num_protein_atoms to be no smaller than protein_mol.GetNumAtoms(), ' \ 'got {:d} and {:d}'.format(max_num_protein_atoms, protein_mol.GetNumAtoms()) if strip_hydrogens: # Remove hydrogen atoms and their corresponding coordinates ligand_atom_indices_left = filter_out_hydrogens(ligand_mol) protein_atom_indices_left = filter_out_hydrogens(protein_mol) ligand_coordinates = ligand_coordinates.take(ligand_atom_indices_left, axis=0) protein_coordinates = protein_coordinates.take(protein_atom_indices_left, axis=0) else: ligand_atom_indices_left = list(range(ligand_mol.GetNumAtoms())) protein_atom_indices_left = list(range(protein_mol.GetNumAtoms())) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - python/dgllife/utils/complex_to_graph.py [207:255]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - strip_hydrogens=False): """Graph construction and featurization for `Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity `__. Parameters ---------- ligand_mol : rdkit.Chem.rdchem.Mol RDKit molecule instance. protein_mol : rdkit.Chem.rdchem.Mol RDKit molecule instance. ligand_coordinates : Float Tensor of shape (V1, 3) Atom coordinates in a ligand. protein_coordinates : Float Tensor of shape (V2, 3) Atom coordinates in a protein. max_num_ligand_atoms : int or None Maximum number of atoms in ligands for zero padding, which should be no smaller than ligand_mol.GetNumAtoms() if not None. If None, no zero padding will be performed. Default to None. max_num_protein_atoms : int or None Maximum number of atoms in proteins for zero padding, which should be no smaller than protein_mol.GetNumAtoms() if not None. If None, no zero padding will be performed. Default to None. neighbor_cutoff : float Distance cutoff to define 'neighboring'. Default to 12. max_num_neighbors : int Maximum number of neighbors allowed for each atom. Default to 12. strip_hydrogens : bool Whether to exclude hydrogen atoms. Default to False. """ assert ligand_coordinates is not None, 'Expect ligand_coordinates to be provided.' assert protein_coordinates is not None, 'Expect protein_coordinates to be provided.' if max_num_ligand_atoms is not None: assert max_num_ligand_atoms >= ligand_mol.GetNumAtoms(), \ 'Expect max_num_ligand_atoms to be no smaller than ligand_mol.GetNumAtoms(), ' \ 'got {:d} and {:d}'.format(max_num_ligand_atoms, ligand_mol.GetNumAtoms()) if max_num_protein_atoms is not None: assert max_num_protein_atoms >= protein_mol.GetNumAtoms(), \ 'Expect max_num_protein_atoms to be no smaller than protein_mol.GetNumAtoms(), ' \ 'got {:d} and {:d}'.format(max_num_protein_atoms, protein_mol.GetNumAtoms()) if strip_hydrogens: # Remove hydrogen atoms and their corresponding coordinates ligand_atom_indices_left = filter_out_hydrogens(ligand_mol) protein_atom_indices_left = filter_out_hydrogens(protein_mol) ligand_coordinates = ligand_coordinates.take(ligand_atom_indices_left, axis=0) protein_coordinates = protein_coordinates.take(protein_atom_indices_left, axis=0) else: ligand_atom_indices_left = list(range(ligand_mol.GetNumAtoms())) protein_atom_indices_left = list(range(protein_mol.GetNumAtoms())) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -