Loading .travis.yml +3 −1 Original line number Diff line number Diff line Loading @@ -33,10 +33,11 @@ install: - bash scripts/install_deepchem_conda.sh deepchem - conda activate deepchem - python setup.py install - pip install coveralls mypy yapf==0.22.0 - pip install coveralls mypy flake8 yapf==0.22.0 script: - bash devtools/run_yapf.sh - bash devtools/run_flake8.sh - mypy -p deepchem - pytest -m "not slow" --cov=deepchem deepchem - if [ $TRAVIS_PYTHON_VERSION == '3.7' ]; then Loading @@ -47,6 +48,7 @@ script: find ./deepchem -name "*.py" ! -name '*load_dataset_template.py' | xargs python -m doctest -v; fi after_success: - echo $TRAVIS_SECURE_ENV_VARS - coveralls Loading deepchem/dock/__init__.py +1 −3 Original line number Diff line number Diff line """ Imports all submodules """ # flake8: noqa from deepchem.dock.pose_generation import PoseGenerator from deepchem.dock.pose_generation import VinaPoseGenerator from deepchem.dock.docking import Docker Loading deepchem/dock/binding_pocket.py +36 −28 Original line number Diff line number Diff line """ Computes putative binding pockets on protein. """ import os import logging import tempfile import numpy as np from subprocess import call from deepchem.feat.fingerprints import CircularFingerprint from deepchem.models.sklearn_models import SklearnModel from deepchem.utils import rdkit_util from deepchem.utils import coordinate_box_utils as box_utils from typing import Any, List, Optional, Tuple from deepchem.models import Model from deepchem.utils.rdkit_util import load_molecule from deepchem.utils.coordinate_box_utils \ import CoordinateBox, get_face_boxes, merge_overlapping_boxes from deepchem.utils.fragment_util import get_contact_atom_indices logger = logging.getLogger(__name__) def extract_active_site(protein_file, ligand_file, cutoff=4): def extract_active_site(protein_file: str, ligand_file: str, cutoff: float = 4.0 ) -> Tuple[CoordinateBox, np.ndarray]: """Extracts a box for the active site. Parameters Loading @@ -24,18 +26,18 @@ def extract_active_site(protein_file, ligand_file, cutoff=4): Location of protein PDB ligand_file: str Location of ligand input file cutoff: int, optional cutoff: float, optional (default 4.0) The distance in angstroms from the protein pocket to consider for featurization. Returns ------- Tuple[CoordinateBox, np.ndarray] A tuple of `(CoordinateBox, np.ndarray)` where the second entry is of shape `(N, 3)` with `N` the number of atoms in the active site. """ protein = rdkit_util.load_molecule(protein_file, add_hydrogens=False) ligand = rdkit_util.load_molecule( ligand_file, add_hydrogens=True, calc_charges=True) protein = load_molecule(protein_file, add_hydrogens=False) ligand = load_molecule(ligand_file, add_hydrogens=True, calc_charges=True) protein_contacts, ligand_contacts = get_contact_atom_indices( [protein, ligand], cutoff=cutoff) protein_coords = protein[0] Loading @@ -47,7 +49,7 @@ def extract_active_site(protein_file, ligand_file, cutoff=4): y_max = int(np.ceil(np.amax(pocket_coords[:, 1]))) z_min = int(np.floor(np.amin(pocket_coords[:, 2]))) z_max = int(np.ceil(np.amax(pocket_coords[:, 2]))) box = box_utils.CoordinateBox((x_min, x_max), (y_min, y_max), (z_min, z_max)) box = CoordinateBox((x_min, x_max), (y_min, y_max), (z_min, z_max)) return (box, pocket_coords) Loading @@ -66,7 +68,7 @@ class BindingPocketFinder(object): technique to be used. """ def find_pockets(self, molecule): def find_pockets(self, molecule: Any): """Finds potential binding pockets in proteins. Parameters Loading @@ -83,32 +85,37 @@ class ConvexHullPocketFinder(BindingPocketFinder): Based on https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4112621/pdf/1472-6807-14-18.pdf """ def __init__(self, scoring_model=None, pad=5): def __init__(self, scoring_model: Optional[Model] = None, pad: float = 5.0): """Initialize the pocket finder. Parameters ---------- scoring_model: `dc.models.Model`, optional If specified, use this model to prune pockets. pad: float, optional pad: float, optional (default 5.0) The number of angstroms to pad around a binding pocket's atoms to get a binding pocket box. """ self.scoring_model = scoring_model self.pad = pad def find_all_pockets(self, protein_file): def find_all_pockets(self, protein_file: str) -> List[CoordinateBox]: """Find list of binding pockets on protein. Parameters ---------- protein_file: str Protein to load in. Returns ------- List[CoordinateBox] List of binding pockets on protein. Each pocket is a `CoordinateBox` """ coords, _ = rdkit_util.load_molecule(protein_file) return box_utils.get_face_boxes(coords, self.pad) coords, _ = load_molecule(protein_file) return get_face_boxes(coords, self.pad) def find_pockets(self, macromolecule_file): def find_pockets(self, macromolecule_file: str) -> List[CoordinateBox]: """Find list of suitable binding pockets on protein. This function computes putative binding pockets on this protein. Loading @@ -123,10 +130,11 @@ class ConvexHullPocketFinder(BindingPocketFinder): Returns ------- List[CoordinateBox] List of pockets. Each pocket is a `CoordinateBox` """ coords = rdkit_util.load_molecule( macromolecule_file, add_hydrogens=False, calc_charges=False)[0] boxes = box_utils.get_face_boxes(coords, self.pad) boxes = box_utils.merge_overlapping_boxes(boxes) coords, _ = load_molecule( macromolecule_file, add_hydrogens=False, calc_charges=False) boxes = get_face_boxes(coords, self.pad) boxes = merge_overlapping_boxes(boxes) return boxes deepchem/dock/docking.py +39 −21 Original line number Diff line number Diff line Loading @@ -2,11 +2,14 @@ Docks Molecular Complexes """ import logging import numpy as np import os import tempfile from subprocess import call from typing import cast, Optional, Tuple import numpy as np from deepchem.models import Model from deepchem.feat import ComplexFeaturizer from deepchem.data import NumpyDataset from deepchem.dock import PoseGenerator logger = logging.getLogger(__name__) Loading @@ -25,16 +28,19 @@ class Docker(object): generation and scoring classes that are provided to this class. """ def __init__(self, pose_generator, featurizer=None, scoring_model=None): def __init__(self, pose_generator: PoseGenerator, featurizer: Optional[ComplexFeaturizer] = None, scoring_model: Optional[Model] = None): """Builds model. Parameters ---------- pose_generator: `PoseGenerator` The pose generator to use for this model featurizer: `ComplexFeaturizer` featurizer: `ComplexFeaturizer`, optional (default None) Featurizer associated with `scoring_model` scoring_model: `Model` scoring_model: `Model`, optional (default None) Should make predictions on molecular complex. """ if ((featurizer is not None and scoring_model is None) or Loading @@ -47,14 +53,14 @@ class Docker(object): self.scoring_model = scoring_model def dock(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, use_pose_generator_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, use_pose_generator_scores: bool = False): """Generic docking function. This docking function uses this object's featurizer, pose Loading @@ -63,8 +69,14 @@ class Docker(object): Parameters ---------- molecular_complex: Object Some representation of a molecular complex. molecular_complex: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional (default None) The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional (default None) Of shape `(3,)` holding the size of the box to dock. If not specified is set to size of molecular complex plus 5 angstroms. exhaustiveness: int, optional (default 10) Tells pose generator how exhaustive it should be with pose generation. Loading @@ -90,8 +102,10 @@ class Docker(object): """ if self.scoring_model is not None and use_pose_generator_scores: raise ValueError( "Cannot set use_pose_generator_scores=True when self.scoring_model is set (since both generator scores for complexes)." "Cannot set use_pose_generator_scores=True " "when self.scoring_model is set (since both generator scores for complexes)." ) outputs = self.pose_generator.generate_poses( molecular_complex, centroid=centroid, Loading @@ -105,11 +119,15 @@ class Docker(object): complexes, scores = outputs else: complexes = outputs # We know use_pose_generator_scores == False in this case if self.scoring_model is not None: for posed_complex in complexes: # NOTE: this casting is workaround. This line doesn't effect anything to the runtime self.featurizer = cast(ComplexFeaturizer, self.featurizer) # TODO: How to handle the failure here? features, _ = self.featurizer.featurize([molecular_complex]) (protein_file, ligand_file) = molecular_complex features, _ = self.featurizer.featurize([protein_file], [ligand_file]) dataset = NumpyDataset(X=features) score = self.scoring_model.predict(dataset) yield (posed_complex, score) Loading deepchem/dock/pose_generation.py +51 −43 Original line number Diff line number Diff line Loading @@ -2,19 +2,21 @@ Generates protein-ligand docked poses. """ import platform import deepchem import logging import numpy as np import os import tempfile import tarfile import numpy as np from subprocess import call from subprocess import check_output from deepchem.utils import rdkit_util from deepchem.utils import mol_xyz_util from deepchem.utils import geometry_utils from deepchem.utils import vina_utils from deepchem.utils import download_url from typing import Optional, Tuple from deepchem.dock.binding_pocket import BindingPocketFinder from deepchem.utils import download_url, get_data_dir from deepchem.utils.mol_xyz_util import get_molecule_range from deepchem.utils.geometry_utils import compute_centroid from deepchem.utils.rdkit_util import load_molecule, write_molecule from deepchem.utils.vina_utils import load_docked_ligands, write_vina_conf logger = logging.getLogger(__name__) Loading @@ -32,23 +34,24 @@ class PoseGenerator(object): """ def generate_poses(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, generate_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, generate_scores: bool = False): """Generates a list of low energy poses for molecular complex Parameters ---------- molecular_complexes: list A representation of a molecular complex. centroid: np.ndarray, optional molecular_complexes: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional (default None) The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional box_dims: np.ndarray, optional (default None) Of shape `(3,)` holding the size of the box to dock. If not specified is set to size of molecular complex plus 5 angstroms. exhaustiveness: int, optional (default 10) Loading @@ -61,7 +64,7 @@ class PoseGenerator(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. generate_score: bool, optional (default False) If `True`, the pose generator will return scores for complexes. Loading Loading @@ -89,7 +92,9 @@ class VinaPoseGenerator(PoseGenerator): This class requires RDKit to be installed. """ def __init__(self, sixty_four_bits=True, pocket_finder=None): def __init__(self, sixty_four_bits: bool = True, pocket_finder: Optional[BindingPocketFinder] = None): """Initializes Vina Pose Generator Parameters Loading @@ -101,7 +106,7 @@ class VinaPoseGenerator(PoseGenerator): If specified should be an instance of `dc.dock.BindingPocketFinder`. """ data_dir = deepchem.utils.get_data_dir() data_dir = get_data_dir() if platform.system() == 'Linux': url = "http://vina.scripps.edu/download/autodock_vina_1_1_2_linux_x86.tgz" filename = "autodock_vina_1_1_2_linux_x86.tgz" Loading Loading @@ -144,22 +149,23 @@ class VinaPoseGenerator(PoseGenerator): os.remove(downloaded_file) def generate_poses(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, generate_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, generate_scores: bool = False): """Generates the docked complex and outputs files for docked complex. TODO: How can this work on Windows? We need to install a .msi file and invoke it correctly from Python for this to work. Parameters ---------- molecular_complexes: list A representation of a molecular complex. molecular_complexes: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional Loading Loading @@ -213,10 +219,10 @@ class VinaPoseGenerator(PoseGenerator): protein_name = os.path.basename(protein_file).split(".")[0] protein_hyd = os.path.join(out_dir, "%s_hyd.pdb" % protein_name) protein_pdbqt = os.path.join(out_dir, "%s.pdbqt" % protein_name) protein_mol = rdkit_util.load_molecule( protein_mol = load_molecule( protein_file, calc_charges=True, add_hydrogens=True) rdkit_util.write_molecule(protein_mol[1], protein_hyd, is_protein=True) rdkit_util.write_molecule(protein_mol[1], protein_pdbqt, is_protein=True) write_molecule(protein_mol[1], protein_hyd, is_protein=True) write_molecule(protein_mol[1], protein_pdbqt, is_protein=True) # Get protein centroid and range if centroid is not None and box_dims is not None: Loading @@ -225,8 +231,8 @@ class VinaPoseGenerator(PoseGenerator): else: if self.pocket_finder is None: logger.info("Pockets not specified. Will use whole protein to dock") protein_centroid = geometry_utils.compute_centroid(protein_mol[0]) protein_range = mol_xyz_util.get_molecule_range(protein_mol[0]) protein_centroid = compute_centroid(protein_mol[0]) protein_range = get_molecule_range(protein_mol[0]) box_dims = protein_range + 5.0 centroids, dimensions = [protein_centroid], [box_dims] else: Loading Loading @@ -257,9 +263,9 @@ class VinaPoseGenerator(PoseGenerator): ligand_name = os.path.basename(ligand_file).split(".")[0] ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name) ligand_mol = rdkit_util.load_molecule( ligand_mol = load_molecule( ligand_file, calc_charges=True, add_hydrogens=True) rdkit_util.write_molecule(ligand_mol[1], ligand_pdbqt) write_molecule(ligand_mol[1], ligand_pdbqt) docked_complexes = [] all_scores = [] Loading @@ -270,7 +276,7 @@ class VinaPoseGenerator(PoseGenerator): logger.info("Box dimensions: %s" % str(box_dims)) # Write Vina conf file conf_file = os.path.join(out_dir, "conf.txt") vina_utils.write_vina_conf( write_vina_conf( protein_pdbqt, ligand_pdbqt, protein_centroid, Loading @@ -291,10 +297,12 @@ class VinaPoseGenerator(PoseGenerator): else: # I'm not sure why specifying the args as a list fails on other platforms, # but for some reason it only works if I pass it as a string. args = "%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file, log_file, out_pdbqt) # FIXME: Incompatible types in assignment args = "%s --config %s --log %s --out %s" % ( # type: ignore self.vina_cmd, conf_file, log_file, out_pdbqt) # FIXME: We should use `subprocess.run` instead of `call` call(args, shell=True) ligands, scores = vina_utils.load_docked_ligands(out_pdbqt) ligands, scores = load_docked_ligands(out_pdbqt) docked_complexes += [(protein_mol[1], ligand) for ligand in ligands] all_scores += scores Loading Loading
.travis.yml +3 −1 Original line number Diff line number Diff line Loading @@ -33,10 +33,11 @@ install: - bash scripts/install_deepchem_conda.sh deepchem - conda activate deepchem - python setup.py install - pip install coveralls mypy yapf==0.22.0 - pip install coveralls mypy flake8 yapf==0.22.0 script: - bash devtools/run_yapf.sh - bash devtools/run_flake8.sh - mypy -p deepchem - pytest -m "not slow" --cov=deepchem deepchem - if [ $TRAVIS_PYTHON_VERSION == '3.7' ]; then Loading @@ -47,6 +48,7 @@ script: find ./deepchem -name "*.py" ! -name '*load_dataset_template.py' | xargs python -m doctest -v; fi after_success: - echo $TRAVIS_SECURE_ENV_VARS - coveralls Loading
deepchem/dock/__init__.py +1 −3 Original line number Diff line number Diff line """ Imports all submodules """ # flake8: noqa from deepchem.dock.pose_generation import PoseGenerator from deepchem.dock.pose_generation import VinaPoseGenerator from deepchem.dock.docking import Docker Loading
deepchem/dock/binding_pocket.py +36 −28 Original line number Diff line number Diff line """ Computes putative binding pockets on protein. """ import os import logging import tempfile import numpy as np from subprocess import call from deepchem.feat.fingerprints import CircularFingerprint from deepchem.models.sklearn_models import SklearnModel from deepchem.utils import rdkit_util from deepchem.utils import coordinate_box_utils as box_utils from typing import Any, List, Optional, Tuple from deepchem.models import Model from deepchem.utils.rdkit_util import load_molecule from deepchem.utils.coordinate_box_utils \ import CoordinateBox, get_face_boxes, merge_overlapping_boxes from deepchem.utils.fragment_util import get_contact_atom_indices logger = logging.getLogger(__name__) def extract_active_site(protein_file, ligand_file, cutoff=4): def extract_active_site(protein_file: str, ligand_file: str, cutoff: float = 4.0 ) -> Tuple[CoordinateBox, np.ndarray]: """Extracts a box for the active site. Parameters Loading @@ -24,18 +26,18 @@ def extract_active_site(protein_file, ligand_file, cutoff=4): Location of protein PDB ligand_file: str Location of ligand input file cutoff: int, optional cutoff: float, optional (default 4.0) The distance in angstroms from the protein pocket to consider for featurization. Returns ------- Tuple[CoordinateBox, np.ndarray] A tuple of `(CoordinateBox, np.ndarray)` where the second entry is of shape `(N, 3)` with `N` the number of atoms in the active site. """ protein = rdkit_util.load_molecule(protein_file, add_hydrogens=False) ligand = rdkit_util.load_molecule( ligand_file, add_hydrogens=True, calc_charges=True) protein = load_molecule(protein_file, add_hydrogens=False) ligand = load_molecule(ligand_file, add_hydrogens=True, calc_charges=True) protein_contacts, ligand_contacts = get_contact_atom_indices( [protein, ligand], cutoff=cutoff) protein_coords = protein[0] Loading @@ -47,7 +49,7 @@ def extract_active_site(protein_file, ligand_file, cutoff=4): y_max = int(np.ceil(np.amax(pocket_coords[:, 1]))) z_min = int(np.floor(np.amin(pocket_coords[:, 2]))) z_max = int(np.ceil(np.amax(pocket_coords[:, 2]))) box = box_utils.CoordinateBox((x_min, x_max), (y_min, y_max), (z_min, z_max)) box = CoordinateBox((x_min, x_max), (y_min, y_max), (z_min, z_max)) return (box, pocket_coords) Loading @@ -66,7 +68,7 @@ class BindingPocketFinder(object): technique to be used. """ def find_pockets(self, molecule): def find_pockets(self, molecule: Any): """Finds potential binding pockets in proteins. Parameters Loading @@ -83,32 +85,37 @@ class ConvexHullPocketFinder(BindingPocketFinder): Based on https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4112621/pdf/1472-6807-14-18.pdf """ def __init__(self, scoring_model=None, pad=5): def __init__(self, scoring_model: Optional[Model] = None, pad: float = 5.0): """Initialize the pocket finder. Parameters ---------- scoring_model: `dc.models.Model`, optional If specified, use this model to prune pockets. pad: float, optional pad: float, optional (default 5.0) The number of angstroms to pad around a binding pocket's atoms to get a binding pocket box. """ self.scoring_model = scoring_model self.pad = pad def find_all_pockets(self, protein_file): def find_all_pockets(self, protein_file: str) -> List[CoordinateBox]: """Find list of binding pockets on protein. Parameters ---------- protein_file: str Protein to load in. Returns ------- List[CoordinateBox] List of binding pockets on protein. Each pocket is a `CoordinateBox` """ coords, _ = rdkit_util.load_molecule(protein_file) return box_utils.get_face_boxes(coords, self.pad) coords, _ = load_molecule(protein_file) return get_face_boxes(coords, self.pad) def find_pockets(self, macromolecule_file): def find_pockets(self, macromolecule_file: str) -> List[CoordinateBox]: """Find list of suitable binding pockets on protein. This function computes putative binding pockets on this protein. Loading @@ -123,10 +130,11 @@ class ConvexHullPocketFinder(BindingPocketFinder): Returns ------- List[CoordinateBox] List of pockets. Each pocket is a `CoordinateBox` """ coords = rdkit_util.load_molecule( macromolecule_file, add_hydrogens=False, calc_charges=False)[0] boxes = box_utils.get_face_boxes(coords, self.pad) boxes = box_utils.merge_overlapping_boxes(boxes) coords, _ = load_molecule( macromolecule_file, add_hydrogens=False, calc_charges=False) boxes = get_face_boxes(coords, self.pad) boxes = merge_overlapping_boxes(boxes) return boxes
deepchem/dock/docking.py +39 −21 Original line number Diff line number Diff line Loading @@ -2,11 +2,14 @@ Docks Molecular Complexes """ import logging import numpy as np import os import tempfile from subprocess import call from typing import cast, Optional, Tuple import numpy as np from deepchem.models import Model from deepchem.feat import ComplexFeaturizer from deepchem.data import NumpyDataset from deepchem.dock import PoseGenerator logger = logging.getLogger(__name__) Loading @@ -25,16 +28,19 @@ class Docker(object): generation and scoring classes that are provided to this class. """ def __init__(self, pose_generator, featurizer=None, scoring_model=None): def __init__(self, pose_generator: PoseGenerator, featurizer: Optional[ComplexFeaturizer] = None, scoring_model: Optional[Model] = None): """Builds model. Parameters ---------- pose_generator: `PoseGenerator` The pose generator to use for this model featurizer: `ComplexFeaturizer` featurizer: `ComplexFeaturizer`, optional (default None) Featurizer associated with `scoring_model` scoring_model: `Model` scoring_model: `Model`, optional (default None) Should make predictions on molecular complex. """ if ((featurizer is not None and scoring_model is None) or Loading @@ -47,14 +53,14 @@ class Docker(object): self.scoring_model = scoring_model def dock(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, use_pose_generator_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, use_pose_generator_scores: bool = False): """Generic docking function. This docking function uses this object's featurizer, pose Loading @@ -63,8 +69,14 @@ class Docker(object): Parameters ---------- molecular_complex: Object Some representation of a molecular complex. molecular_complex: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional (default None) The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional (default None) Of shape `(3,)` holding the size of the box to dock. If not specified is set to size of molecular complex plus 5 angstroms. exhaustiveness: int, optional (default 10) Tells pose generator how exhaustive it should be with pose generation. Loading @@ -90,8 +102,10 @@ class Docker(object): """ if self.scoring_model is not None and use_pose_generator_scores: raise ValueError( "Cannot set use_pose_generator_scores=True when self.scoring_model is set (since both generator scores for complexes)." "Cannot set use_pose_generator_scores=True " "when self.scoring_model is set (since both generator scores for complexes)." ) outputs = self.pose_generator.generate_poses( molecular_complex, centroid=centroid, Loading @@ -105,11 +119,15 @@ class Docker(object): complexes, scores = outputs else: complexes = outputs # We know use_pose_generator_scores == False in this case if self.scoring_model is not None: for posed_complex in complexes: # NOTE: this casting is workaround. This line doesn't effect anything to the runtime self.featurizer = cast(ComplexFeaturizer, self.featurizer) # TODO: How to handle the failure here? features, _ = self.featurizer.featurize([molecular_complex]) (protein_file, ligand_file) = molecular_complex features, _ = self.featurizer.featurize([protein_file], [ligand_file]) dataset = NumpyDataset(X=features) score = self.scoring_model.predict(dataset) yield (posed_complex, score) Loading
deepchem/dock/pose_generation.py +51 −43 Original line number Diff line number Diff line Loading @@ -2,19 +2,21 @@ Generates protein-ligand docked poses. """ import platform import deepchem import logging import numpy as np import os import tempfile import tarfile import numpy as np from subprocess import call from subprocess import check_output from deepchem.utils import rdkit_util from deepchem.utils import mol_xyz_util from deepchem.utils import geometry_utils from deepchem.utils import vina_utils from deepchem.utils import download_url from typing import Optional, Tuple from deepchem.dock.binding_pocket import BindingPocketFinder from deepchem.utils import download_url, get_data_dir from deepchem.utils.mol_xyz_util import get_molecule_range from deepchem.utils.geometry_utils import compute_centroid from deepchem.utils.rdkit_util import load_molecule, write_molecule from deepchem.utils.vina_utils import load_docked_ligands, write_vina_conf logger = logging.getLogger(__name__) Loading @@ -32,23 +34,24 @@ class PoseGenerator(object): """ def generate_poses(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, generate_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, generate_scores: bool = False): """Generates a list of low energy poses for molecular complex Parameters ---------- molecular_complexes: list A representation of a molecular complex. centroid: np.ndarray, optional molecular_complexes: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional (default None) The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional box_dims: np.ndarray, optional (default None) Of shape `(3,)` holding the size of the box to dock. If not specified is set to size of molecular complex plus 5 angstroms. exhaustiveness: int, optional (default 10) Loading @@ -61,7 +64,7 @@ class PoseGenerator(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. generate_score: bool, optional (default False) If `True`, the pose generator will return scores for complexes. Loading Loading @@ -89,7 +92,9 @@ class VinaPoseGenerator(PoseGenerator): This class requires RDKit to be installed. """ def __init__(self, sixty_four_bits=True, pocket_finder=None): def __init__(self, sixty_four_bits: bool = True, pocket_finder: Optional[BindingPocketFinder] = None): """Initializes Vina Pose Generator Parameters Loading @@ -101,7 +106,7 @@ class VinaPoseGenerator(PoseGenerator): If specified should be an instance of `dc.dock.BindingPocketFinder`. """ data_dir = deepchem.utils.get_data_dir() data_dir = get_data_dir() if platform.system() == 'Linux': url = "http://vina.scripps.edu/download/autodock_vina_1_1_2_linux_x86.tgz" filename = "autodock_vina_1_1_2_linux_x86.tgz" Loading Loading @@ -144,22 +149,23 @@ class VinaPoseGenerator(PoseGenerator): os.remove(downloaded_file) def generate_poses(self, molecular_complex, centroid=None, box_dims=None, exhaustiveness=10, num_modes=9, num_pockets=None, out_dir=None, generate_scores=False): molecular_complex: Tuple[str, str], centroid: Optional[np.ndarray] = None, box_dims: Optional[np.ndarray] = None, exhaustiveness: int = 10, num_modes: int = 9, num_pockets: Optional[int] = None, out_dir: Optional[str] = None, generate_scores: bool = False): """Generates the docked complex and outputs files for docked complex. TODO: How can this work on Windows? We need to install a .msi file and invoke it correctly from Python for this to work. Parameters ---------- molecular_complexes: list A representation of a molecular complex. molecular_complexes: Tuple[str] A representation of a molecular complex. This tuple is (protein_file, ligand_file). centroid: np.ndarray, optional The centroid to dock against. Is computed if not specified. box_dims: np.ndarray, optional Loading Loading @@ -213,10 +219,10 @@ class VinaPoseGenerator(PoseGenerator): protein_name = os.path.basename(protein_file).split(".")[0] protein_hyd = os.path.join(out_dir, "%s_hyd.pdb" % protein_name) protein_pdbqt = os.path.join(out_dir, "%s.pdbqt" % protein_name) protein_mol = rdkit_util.load_molecule( protein_mol = load_molecule( protein_file, calc_charges=True, add_hydrogens=True) rdkit_util.write_molecule(protein_mol[1], protein_hyd, is_protein=True) rdkit_util.write_molecule(protein_mol[1], protein_pdbqt, is_protein=True) write_molecule(protein_mol[1], protein_hyd, is_protein=True) write_molecule(protein_mol[1], protein_pdbqt, is_protein=True) # Get protein centroid and range if centroid is not None and box_dims is not None: Loading @@ -225,8 +231,8 @@ class VinaPoseGenerator(PoseGenerator): else: if self.pocket_finder is None: logger.info("Pockets not specified. Will use whole protein to dock") protein_centroid = geometry_utils.compute_centroid(protein_mol[0]) protein_range = mol_xyz_util.get_molecule_range(protein_mol[0]) protein_centroid = compute_centroid(protein_mol[0]) protein_range = get_molecule_range(protein_mol[0]) box_dims = protein_range + 5.0 centroids, dimensions = [protein_centroid], [box_dims] else: Loading Loading @@ -257,9 +263,9 @@ class VinaPoseGenerator(PoseGenerator): ligand_name = os.path.basename(ligand_file).split(".")[0] ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name) ligand_mol = rdkit_util.load_molecule( ligand_mol = load_molecule( ligand_file, calc_charges=True, add_hydrogens=True) rdkit_util.write_molecule(ligand_mol[1], ligand_pdbqt) write_molecule(ligand_mol[1], ligand_pdbqt) docked_complexes = [] all_scores = [] Loading @@ -270,7 +276,7 @@ class VinaPoseGenerator(PoseGenerator): logger.info("Box dimensions: %s" % str(box_dims)) # Write Vina conf file conf_file = os.path.join(out_dir, "conf.txt") vina_utils.write_vina_conf( write_vina_conf( protein_pdbqt, ligand_pdbqt, protein_centroid, Loading @@ -291,10 +297,12 @@ class VinaPoseGenerator(PoseGenerator): else: # I'm not sure why specifying the args as a list fails on other platforms, # but for some reason it only works if I pass it as a string. args = "%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file, log_file, out_pdbqt) # FIXME: Incompatible types in assignment args = "%s --config %s --log %s --out %s" % ( # type: ignore self.vina_cmd, conf_file, log_file, out_pdbqt) # FIXME: We should use `subprocess.run` instead of `call` call(args, shell=True) ligands, scores = vina_utils.load_docked_ligands(out_pdbqt) ligands, scores = load_docked_ligands(out_pdbqt) docked_complexes += [(protein_mol[1], ligand) for ligand in ligands] all_scores += scores Loading
