def generate_poses(
self,
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
) -> Union[Tuple[DOCKED_POSES, List[float]], DOCKED_POSES]:
"""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: Tuple[str, 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
A numpy array 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 Autodock Vina how exhaustive it should be with pose
generation.
num_modes: int, optional (default 9)
Tells Autodock Vina how many binding modes it should generate at
each invocation.
num_pockets: int, optional (default None)
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
If specified, write generated poses to this directory.
generate_score: bool, optional (default False)
If `True`, the pose generator will return scores for complexes.
This is used typically when invoking external docking programs
that compute scores.
Returns
-------
Tuple[`docked_poses`, `scores`] or `docked_poses`
Tuple of `(docked_poses, scores)` or `docked_poses`. `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
------
`ValueError` if `num_pockets` is set but `self.pocket_finder is None`.
"""
if out_dir is None:
out_dir = tempfile.mkdtemp()
if num_pockets is not None and self.pocket_finder is None:
raise ValueError(
"If num_pockets is specified, pocket_finder must have been provided at construction time."
)
# Parse complex
if len(molecular_complex) > 2:
raise ValueError(
"Autodock Vina can only dock protein-ligand complexes and not more general molecular complexes."
)
(protein_file, ligand_file) = molecular_complex
# Prepare protein
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 = load_molecule(protein_file,
calc_charges=True,
add_hydrogens=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:
centroids = [centroid]
dimensions = [box_dims]
else:
if self.pocket_finder is None:
logger.info(
"Pockets not specified. Will use whole protein to dock")
protein_centroid = compute_centroid(protein_mol[0])
protein_range = compute_protein_range(protein_mol[0])
box_dims = protein_range + 5.0
centroids, dimensions = [protein_centroid], [box_dims]
else:
logger.info("About to find putative binding pockets")
pockets = self.pocket_finder.find_pockets(protein_file)
logger.info("%d pockets found in total" % len(pockets))
logger.info("Computing centroid and size of proposed pockets.")
centroids, dimensions = [], []
for pocket in pockets:
protein_centroid = pocket.center()
(x_min, x_max), (y_min, y_max), (
z_min,
z_max) = pocket.x_range, pocket.y_range, pocket.z_range
# TODO(rbharath: Does vina divide box dimensions by 2?
x_box = (x_max - x_min) / 2.
y_box = (y_max - y_min) / 2.
z_box = (z_max - z_min) / 2.
box_dims = (x_box, y_box, z_box)
centroids.append(protein_centroid)
dimensions.append(box_dims)
if num_pockets is not None:
logger.info(
"num_pockets = %d so selecting this many pockets for docking."
% num_pockets)
centroids = centroids[:num_pockets]
dimensions = dimensions[:num_pockets]
# Prepare protein
ligand_name = os.path.basename(ligand_file).split(".")[0]
ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name)
ligand_mol = load_molecule(ligand_file,
calc_charges=True,
add_hydrogens=True)
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 + 1, len(centroids)))
logger.info("Docking with center: %s" % str(protein_centroid))
logger.info("Box dimensions: %s" % str(box_dims))
# Write Vina conf file
conf_file = os.path.join(out_dir, "conf.txt")
write_vina_conf(protein_pdbqt,
ligand_pdbqt,
protein_centroid,
box_dims,
conf_file,
num_modes=num_modes,
exhaustiveness=exhaustiveness)
# Define locations of log and output files
log_file = os.path.join(out_dir, "%s_log.txt" % ligand_name)
out_pdbqt = os.path.join(out_dir, "%s_docked.pdbqt" % ligand_name)
logger.info("About to call Vina")
if platform.system() == 'Windows':
args = [
self.vina_cmd, "--config", conf_file, "--log", log_file,
"--out", out_pdbqt
]
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.
# 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 = load_docked_ligands(out_pdbqt)
docked_complexes += [(protein_mol[1], ligand)
for ligand in ligands]
all_scores += scores
if generate_scores:
return docked_complexes, all_scores
else:
return docked_complexes
def generate_poses(
self,
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: Optional[bool] = False,
**kwargs) -> Union[Tuple[DOCKED_POSES, List[float]], DOCKED_POSES]:
"""Generates the docked complex and outputs files for docked complex.
Parameters
----------
molecular_complexes: Tuple[str, str]
A representation of a molecular complex. This tuple is
(protein_file, ligand_file). The protein should be a pdb file
and the ligand should be an sdf file.
centroid: np.ndarray, optional
The centroid to dock against. Is computed if not specified.
box_dims: np.ndarray, optional
A numpy array 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 Autodock Vina how exhaustive it should be with pose generation. A
higher value of exhaustiveness implies more computation effort for the
docking experiment.
num_modes: int, optional (default 9)
Tells Autodock Vina how many binding modes it should generate at
each invocation.
num_pockets: int, optional (default None)
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
If specified, write generated poses to this directory.
generate_score: bool, optional (default False)
If `True`, the pose generator will return scores for complexes.
This is used typically when invoking external docking programs
that compute scores.
kwargs:
The kwargs - cpu, min_rmsd, max_evals, energy_range supported by VINA
are as documented in https://autodock-vina.readthedocs.io/en/latest/vina.html
Returns
-------
Tuple[`docked_poses`, `scores`] or `docked_poses`
Tuple of `(docked_poses, scores)` or `docked_poses`. `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
------
`ValueError` if `num_pockets` is set but `self.pocket_finder is None`.
"""
if "cpu" in kwargs:
cpu = kwargs["cpu"]
else:
cpu = 0
if "min_rmsd" in kwargs:
min_rmsd = kwargs["min_rmsd"]
else:
min_rmsd = 1.0
if "max_evals" in kwargs:
max_evals = kwargs["max_evals"]
else:
max_evals = 0
if "energy_range" in kwargs:
energy_range = kwargs["energy_range"]
else:
energy_range = 3.0
try:
from vina import Vina
except ModuleNotFoundError:
raise ImportError("This function requires vina to be installed")
if out_dir is None:
out_dir = tempfile.mkdtemp()
if num_pockets is not None and self.pocket_finder is None:
raise ValueError(
"If num_pockets is specified, pocket_finder must have been provided at construction time."
)
# Parse complex
if len(molecular_complex) > 2:
raise ValueError(
"Autodock Vina can only dock protein-ligand complexes and not more general molecular complexes."
)
(protein_file, ligand_file) = molecular_complex
# Prepare protein
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 = load_molecule(protein_file,
calc_charges=True,
add_hydrogens=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:
centroids = [centroid]
dimensions = [box_dims]
else:
if self.pocket_finder is None:
logger.info(
"Pockets not specified. Will use whole protein to dock")
centroids = [compute_centroid(protein_mol[0])]
dimensions = [compute_protein_range(protein_mol[0]) + 5.0]
else:
logger.info("About to find putative binding pockets")
pockets = self.pocket_finder.find_pockets(protein_file)
logger.info("%d pockets found in total" % len(pockets))
logger.info("Computing centroid and size of proposed pockets.")
centroids, dimensions = [], []
for pocket in pockets:
(x_min, x_max), (y_min, y_max), (
z_min,
z_max) = pocket.x_range, pocket.y_range, pocket.z_range
# TODO(rbharath: Does vina divide box dimensions by 2?
x_box = (x_max - x_min) / 2.
y_box = (y_max - y_min) / 2.
z_box = (z_max - z_min) / 2.
centroids.append(pocket.center())
dimensions.append(np.array((x_box, y_box, z_box)))
if num_pockets is not None:
logger.info(
"num_pockets = %d so selecting this many pockets for docking."
% num_pockets)
centroids = centroids[:num_pockets]
dimensions = dimensions[:num_pockets]
# Prepare ligand
ligand_name = os.path.basename(ligand_file).split(".")[0]
ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name)
ligand_mol = load_molecule(ligand_file,
calc_charges=True,
add_hydrogens=True)
write_molecule(ligand_mol[1], ligand_pdbqt)
docked_complexes = []
all_scores = []
vpg = Vina(sf_name='vina',
cpu=cpu,
seed=0,
no_refine=False,
verbosity=1)
for i, (protein_centroid,
box_dims) in enumerate(zip(centroids, dimensions)):
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
conf_file = os.path.join(out_dir, "conf.txt")
write_vina_conf(protein_pdbqt,
ligand_pdbqt,
protein_centroid,
box_dims,
conf_file,
num_modes=num_modes,
exhaustiveness=exhaustiveness)
# Define locations of output files
out_pdbqt = os.path.join(out_dir, "%s_docked.pdbqt" % ligand_name)
logger.info("About to call Vina")
vpg.set_receptor(protein_pdbqt)
vpg.set_ligand_from_file(ligand_pdbqt)
vpg.compute_vina_maps(center=protein_centroid, box_size=box_dims)
vpg.dock(exhaustiveness=exhaustiveness,
n_poses=num_modes,
min_rmsd=min_rmsd,
max_evals=max_evals)
vpg.write_poses(out_pdbqt,
n_poses=num_modes,
energy_range=energy_range,
overwrite=True)
ligands, scores = load_docked_ligands(out_pdbqt)
docked_complexes += [(protein_mol[1], ligand)
for ligand in ligands]
all_scores += scores
if generate_scores:
return docked_complexes, all_scores
else:
return docked_complexes