Loading deepchem/dock/docking.py +17 −8 Original line number Diff line number Diff line Loading @@ -68,16 +68,25 @@ class Docker(object): If specified, `self.pocket_finder` must be set. Will only generate poses for the first `num_pockets` returned by `self.pocket_finder`. out_dir: str, optional out_dir: str, optional (default None) If specified, write generated poses to this directory. use_pose_generator_scores: bool, optional (default False) If `True`, ask pose generator to generate scores. This cannot be `True` if `self.featurizer` and `self.scoring_model` are set since those will be used to generate scores in that case. """ complexes = self.pose_generator.generate_poses(molecular_complex, outputs = self.pose_generator.generate_poses(molecular_complex, centroid=centroid, box_dims=box_dims, exhaustiveness=exhaustiveness, num_modes=num_modes, num_pockets=num_pockets, out_dir=out_dir) out_dir=out_dir, generate_scores=use_pose_generator_scores) if use_pose_generator_scores: complexes, scores = outputs else: complexes = outputs for posed_complex in complexes: if self.featurizer is not None: # TODO: How to handle the failure here? Loading deepchem/dock/pose_generation.py +9 −6 Original line number Diff line number Diff line Loading @@ -140,8 +140,6 @@ class VinaPoseGenerator(PoseGenerator): TODO: How can this work on Windows? We need to install a .msi file and invoke it correctly from Python for this to work. TODO: Can we extract the autodock vina computed binding free energy? Need to parse the output from Autodock vina. Parameters ---------- molecular_complexes: list Loading @@ -166,7 +164,10 @@ class VinaPoseGenerator(PoseGenerator): Returns ------- List of docked molecular complexes. Each entry in this list contains a `(protein_mol, ligand_mol)` pair of RDKit molecules. Tuple of `(docked_poses, scores)`. `docked_poses` is a list of docked molecular complexes. Each entry in this list contains a `(protein_mol, ligand_mol)` pair of RDKit molecules. `scores` is a list of binding free energies predicted by Vina. Raises ------ Loading Loading @@ -237,8 +238,9 @@ class VinaPoseGenerator(PoseGenerator): rdkit_util.write_molecule(ligand_mol[1], ligand_pdbqt) docked_complexes = [] all_scores = [] for i, (protein_centroid, box_dims) in enumerate(zip(centroids, dimensions)): logger.info("Docking in pocket %d/%d" % (i, len(centroids))) logger.info("Docking in pocket %d/%d" % (i+1, len(centroids))) logger.info("Docking with center: %s" % str(protein_centroid)) logger.info("Box dimensions: %s" % str(box_dims)) # Write Vina conf file Loading @@ -260,7 +262,8 @@ class VinaPoseGenerator(PoseGenerator): "%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file, log_file, out_pdbqt), shell=True) ligands = vina_utils.load_docked_ligands(out_pdbqt) ligands, scores = vina_utils.load_docked_ligands(out_pdbqt) docked_complexes += [(protein_mol[1], ligand) for ligand in ligands] all_scores += scores return docked_complexes return docked_complexes, all_scores deepchem/dock/tests/test_pose_generation.py +6 −3 Original line number Diff line number Diff line Loading @@ -41,13 +41,14 @@ class TestPoseGeneration(unittest.TestCase): ligand_file = os.path.join(current_dir, "1jld_ligand.sdf") vpg = dc.dock.VinaPoseGenerator(pocket_finder=None) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), exhaustiveness=1, num_modes=1, out_dir="/tmp") assert len(poses) == 1 assert len(scores) == 1 protein, ligand = poses[0] from rdkit import Chem assert isinstance(protein, Chem.Mol) Loading @@ -69,7 +70,7 @@ class TestPoseGeneration(unittest.TestCase): centroid = np.array([56.21891368, 25.95862964, 3.58950065]) box_dims = np.array([51.354, 51.243, 55.608]) vpg = dc.dock.VinaPoseGenerator(pocket_finder=None) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), centroid=centroid, box_dims=box_dims, Loading @@ -78,6 +79,7 @@ class TestPoseGeneration(unittest.TestCase): out_dir="/tmp") assert len(poses) == 1 assert len(scores) == 1 protein, ligand = poses[0] from rdkit import Chem assert isinstance(protein, Chem.Mol) Loading @@ -99,7 +101,7 @@ class TestPoseGeneration(unittest.TestCase): # Note this may download autodock Vina... convex_finder = dc.dock.ConvexHullPocketFinder() vpg = dc.dock.VinaPoseGenerator(pocket_finder=convex_finder) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), exhaustiveness=1, num_modes=1, Loading @@ -107,6 +109,7 @@ class TestPoseGeneration(unittest.TestCase): out_dir="/tmp") assert len(poses) == 2 assert len(scores) == 2 from rdkit import Chem for pose in poses: protein, ligand = pose Loading deepchem/utils/rdkit_util.py +6 −3 Original line number Diff line number Diff line Loading @@ -52,7 +52,7 @@ def get_xyz_from_mol(mol): xyz[i, 2] = position.z return (xyz) def add_hydrogens_to_mol(mol): def add_hydrogens_to_mol(mol, is_protein=False): """ Add hydrogens to a molecule object Loading @@ -60,6 +60,9 @@ def add_hydrogens_to_mol(mol): ---------- mol: Rdkit Mol Molecule to hydrogenate is_protein: bool, optional (default False) Whether this molecule is a protein. Returns ------- Loading @@ -69,7 +72,7 @@ def add_hydrogens_to_mol(mol): ---- This function requires RDKit and PDBFixer to be installed. """ return apply_pdbfixer(mol, hydrogenate=True) return apply_pdbfixer(mol, hydrogenate=True, is_protein=is_protein) def apply_pdbfixer(mol, add_missing=True, hydrogenate=True, pH=7.4, Loading @@ -80,7 +83,7 @@ def apply_pdbfixer(mol, add_missing=True, hydrogenate=True, pH=7.4, Parameters ---------- mol: Rdkit Mol Molecule to hydrogenate Molecule to clean up. add_missing: bool, optional If true, add in missing residues and atoms hydrogenate: bool, optional Loading deepchem/utils/test/test_geometry_utils.py +19 −0 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ import unittest import numpy as np from deepchem.utils.geometry_utils import unit_vector from deepchem.utils.geometry_utils import angle_between from deepchem.utils.geometry_utils import compute_pairwise_distances from deepchem.utils.geometry_utils import generate_random_unit_vector from deepchem.utils.geometry_utils import generate_random_rotation_matrix from deepchem.utils.geometry_utils import is_angle_within_cutoff Loading Loading @@ -43,3 +44,21 @@ class TestGeometryUtils(unittest.TestCase): v2 = np.array([-1, 0, 0]) angle_cutoff = 10 assert is_angle_within_cutoff(v1, v2, angle_cutoff) def test_compute_pairwise_distances(self): n1 = 10 n2 = 50 coords1 = np.random.rand(n1, 3) coords2 = np.random.rand(n2, 3) distance = compute_pairwise_distances(coords1, coords2) self.assertEqual(distance.shape, (n1, n2)) self.assertTrue((distance >= 0).all()) # random coords between 0 and 1, so the max possible distance in sqrt(2) self.assertTrue((distance <= 2.0**0.5).all()) # check if correct distance metric was used coords1 = np.array([[0, 0, 0], [1, 0, 0]]) coords2 = np.array([[1, 0, 0], [2, 0, 0], [3, 0, 0]]) distance = compute_pairwise_distances(coords1, coords2) self.assertTrue((distance == [[1, 2, 3], [0, 1, 2]]).all()) Loading
deepchem/dock/docking.py +17 −8 Original line number Diff line number Diff line Loading @@ -68,16 +68,25 @@ class Docker(object): If specified, `self.pocket_finder` must be set. Will only generate poses for the first `num_pockets` returned by `self.pocket_finder`. out_dir: str, optional out_dir: str, optional (default None) If specified, write generated poses to this directory. use_pose_generator_scores: bool, optional (default False) If `True`, ask pose generator to generate scores. This cannot be `True` if `self.featurizer` and `self.scoring_model` are set since those will be used to generate scores in that case. """ complexes = self.pose_generator.generate_poses(molecular_complex, outputs = self.pose_generator.generate_poses(molecular_complex, centroid=centroid, box_dims=box_dims, exhaustiveness=exhaustiveness, num_modes=num_modes, num_pockets=num_pockets, out_dir=out_dir) out_dir=out_dir, generate_scores=use_pose_generator_scores) if use_pose_generator_scores: complexes, scores = outputs else: complexes = outputs for posed_complex in complexes: if self.featurizer is not None: # TODO: How to handle the failure here? Loading
deepchem/dock/pose_generation.py +9 −6 Original line number Diff line number Diff line Loading @@ -140,8 +140,6 @@ class VinaPoseGenerator(PoseGenerator): TODO: How can this work on Windows? We need to install a .msi file and invoke it correctly from Python for this to work. TODO: Can we extract the autodock vina computed binding free energy? Need to parse the output from Autodock vina. Parameters ---------- molecular_complexes: list Loading @@ -166,7 +164,10 @@ class VinaPoseGenerator(PoseGenerator): Returns ------- List of docked molecular complexes. Each entry in this list contains a `(protein_mol, ligand_mol)` pair of RDKit molecules. Tuple of `(docked_poses, scores)`. `docked_poses` is a list of docked molecular complexes. Each entry in this list contains a `(protein_mol, ligand_mol)` pair of RDKit molecules. `scores` is a list of binding free energies predicted by Vina. Raises ------ Loading Loading @@ -237,8 +238,9 @@ class VinaPoseGenerator(PoseGenerator): rdkit_util.write_molecule(ligand_mol[1], ligand_pdbqt) docked_complexes = [] all_scores = [] for i, (protein_centroid, box_dims) in enumerate(zip(centroids, dimensions)): logger.info("Docking in pocket %d/%d" % (i, len(centroids))) logger.info("Docking in pocket %d/%d" % (i+1, len(centroids))) logger.info("Docking with center: %s" % str(protein_centroid)) logger.info("Box dimensions: %s" % str(box_dims)) # Write Vina conf file Loading @@ -260,7 +262,8 @@ class VinaPoseGenerator(PoseGenerator): "%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file, log_file, out_pdbqt), shell=True) ligands = vina_utils.load_docked_ligands(out_pdbqt) ligands, scores = vina_utils.load_docked_ligands(out_pdbqt) docked_complexes += [(protein_mol[1], ligand) for ligand in ligands] all_scores += scores return docked_complexes return docked_complexes, all_scores
deepchem/dock/tests/test_pose_generation.py +6 −3 Original line number Diff line number Diff line Loading @@ -41,13 +41,14 @@ class TestPoseGeneration(unittest.TestCase): ligand_file = os.path.join(current_dir, "1jld_ligand.sdf") vpg = dc.dock.VinaPoseGenerator(pocket_finder=None) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), exhaustiveness=1, num_modes=1, out_dir="/tmp") assert len(poses) == 1 assert len(scores) == 1 protein, ligand = poses[0] from rdkit import Chem assert isinstance(protein, Chem.Mol) Loading @@ -69,7 +70,7 @@ class TestPoseGeneration(unittest.TestCase): centroid = np.array([56.21891368, 25.95862964, 3.58950065]) box_dims = np.array([51.354, 51.243, 55.608]) vpg = dc.dock.VinaPoseGenerator(pocket_finder=None) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), centroid=centroid, box_dims=box_dims, Loading @@ -78,6 +79,7 @@ class TestPoseGeneration(unittest.TestCase): out_dir="/tmp") assert len(poses) == 1 assert len(scores) == 1 protein, ligand = poses[0] from rdkit import Chem assert isinstance(protein, Chem.Mol) Loading @@ -99,7 +101,7 @@ class TestPoseGeneration(unittest.TestCase): # Note this may download autodock Vina... convex_finder = dc.dock.ConvexHullPocketFinder() vpg = dc.dock.VinaPoseGenerator(pocket_finder=convex_finder) poses = vpg.generate_poses( poses, scores = vpg.generate_poses( (protein_file, ligand_file), exhaustiveness=1, num_modes=1, Loading @@ -107,6 +109,7 @@ class TestPoseGeneration(unittest.TestCase): out_dir="/tmp") assert len(poses) == 2 assert len(scores) == 2 from rdkit import Chem for pose in poses: protein, ligand = pose Loading
deepchem/utils/rdkit_util.py +6 −3 Original line number Diff line number Diff line Loading @@ -52,7 +52,7 @@ def get_xyz_from_mol(mol): xyz[i, 2] = position.z return (xyz) def add_hydrogens_to_mol(mol): def add_hydrogens_to_mol(mol, is_protein=False): """ Add hydrogens to a molecule object Loading @@ -60,6 +60,9 @@ def add_hydrogens_to_mol(mol): ---------- mol: Rdkit Mol Molecule to hydrogenate is_protein: bool, optional (default False) Whether this molecule is a protein. Returns ------- Loading @@ -69,7 +72,7 @@ def add_hydrogens_to_mol(mol): ---- This function requires RDKit and PDBFixer to be installed. """ return apply_pdbfixer(mol, hydrogenate=True) return apply_pdbfixer(mol, hydrogenate=True, is_protein=is_protein) def apply_pdbfixer(mol, add_missing=True, hydrogenate=True, pH=7.4, Loading @@ -80,7 +83,7 @@ def apply_pdbfixer(mol, add_missing=True, hydrogenate=True, pH=7.4, Parameters ---------- mol: Rdkit Mol Molecule to hydrogenate Molecule to clean up. add_missing: bool, optional If true, add in missing residues and atoms hydrogenate: bool, optional Loading
deepchem/utils/test/test_geometry_utils.py +19 −0 Original line number Diff line number Diff line Loading @@ -2,6 +2,7 @@ import unittest import numpy as np from deepchem.utils.geometry_utils import unit_vector from deepchem.utils.geometry_utils import angle_between from deepchem.utils.geometry_utils import compute_pairwise_distances from deepchem.utils.geometry_utils import generate_random_unit_vector from deepchem.utils.geometry_utils import generate_random_rotation_matrix from deepchem.utils.geometry_utils import is_angle_within_cutoff Loading Loading @@ -43,3 +44,21 @@ class TestGeometryUtils(unittest.TestCase): v2 = np.array([-1, 0, 0]) angle_cutoff = 10 assert is_angle_within_cutoff(v1, v2, angle_cutoff) def test_compute_pairwise_distances(self): n1 = 10 n2 = 50 coords1 = np.random.rand(n1, 3) coords2 = np.random.rand(n2, 3) distance = compute_pairwise_distances(coords1, coords2) self.assertEqual(distance.shape, (n1, n2)) self.assertTrue((distance >= 0).all()) # random coords between 0 and 1, so the max possible distance in sqrt(2) self.assertTrue((distance <= 2.0**0.5).all()) # check if correct distance metric was used coords1 = np.array([[0, 0, 0], [1, 0, 0]]) coords2 = np.array([[1, 0, 0], [2, 0, 0], [3, 0, 0]]) distance = compute_pairwise_distances(coords1, coords2) self.assertTrue((distance == [[1, 2, 3], [0, 1, 2]]).all())
