def generate_poses(self,
protein_file,
ligand_file,
centroid=None,
box_dims=None,
dry_run=False,
out_dir=None):
"""Generates the docked complex and outputs files for docked complex."""
if out_dir is None:
out_dir = tempfile.mkdtemp()
# Prepare receptor
receptor_name = os.path.basename(protein_file).split(".")[0]
protein_hyd = os.path.join(out_dir, "%s.pdb" % receptor_name)
protein_pdbqt = os.path.join(out_dir, "%s.pdbqt" % receptor_name)
hydrogenate_and_compute_partial_charges(protein_file,
"pdb",
hyd_output=protein_hyd,
pdbqt_output=protein_pdbqt,
protein=True)
# Get protein centroid and range
# TODO(rbharath): Need to add some way to identify binding pocket, or this is
# going to be extremely slow!
if centroid is not None and box_dims is not None:
protein_centroid = centroid
else:
if not self.detect_pockets:
receptor_mol = rdkit_util.load_molecule(protein_hyd,
calc_charges=False,
add_hydrogens=False)
protein_centroid = mol_xyz_util.get_molecule_centroid(
receptor_mol[0])
protein_range = mol_xyz_util.get_molecule_range(
receptor_mol[0])
box_dims = protein_range + 5.0
else:
logger.info("About to find putative binding pockets")
pockets, pocket_atoms_maps, pocket_coords = self.pocket_finder.find_pockets(
protein_file, ligand_file)
# TODO(rbharath): Handle multiple pockets instead of arbitrarily selecting
# first pocket.
logger.info("Computing centroid and size of proposed pocket.")
pocket_coord = pocket_coords[0]
protein_centroid = np.mean(pocket_coord, axis=1)
pocket = pockets[0]
(x_min, x_max), (y_min, y_max), (z_min, z_max) = pocket
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)
# Prepare receptor
ligand_name = os.path.basename(ligand_file).split(".")[0]
ligand_hyd = os.path.join(out_dir, "%s.pdb" % ligand_name)
ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name)
# TODO(rbharath): Generalize this so can support mol2 files as well.
hydrogenate_and_compute_partial_charges(ligand_file,
"sdf",
hyd_output=ligand_hyd,
pdbqt_output=ligand_pdbqt,
protein=False)
# Write Vina conf file
conf_file = os.path.join(out_dir, "conf.txt")
write_conf(protein_pdbqt,
ligand_pdbqt,
protein_centroid,
box_dims,
conf_file,
exhaustiveness=self.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)
# TODO(rbharath): Let user specify the number of poses required.
if not dry_run:
logger.info("About to call Vina")
call("%s --config %s --log %s --out %s" %
(self.vina_cmd, conf_file, log_file, out_pdbqt),
shell=True)
# TODO(rbharath): Convert the output pdbqt to a pdb file.
# Return docked files
return protein_hyd, out_pdbqt
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):
"""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.
centroid: np.ndarray, optional
The centroid to dock against. Is computed if not specified.
box_dims: np.ndarray, optional
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 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
------
`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 = rdkit_util.load_molecule(
protein_file, calc_charges=True, add_hydrogens=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")
rdkit_util.write_molecule(protein_mol[1], protein_hyd, is_protein=True)
rdkit_util.write_molecule(
protein_mol[1], protein_pdbqt, is_protein=True)
protein_centroid = geometry_utils.compute_centroid(protein_mol[0])
protein_range = mol_xyz_util.get_molecule_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 = rdkit_util.load_molecule(
ligand_file, calc_charges=True, add_hydrogens=True)
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 + 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")
vina_utils.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")
call(
"%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file,
log_file, out_pdbqt),
shell=True)
ligands, scores = vina_utils.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 dock_ligands_to_receptors(docking_dir,
worker_pool=None,
exhaustiveness=None,
chosen_receptor=None,
restrict_box=True):
subdirs = glob.glob(os.path.join(docking_dir, '*/'))
for subdir in subdirs:
subdir = subdir.rstrip('/')
receptor_name = os.path.basename(subdir)
if chosen_receptor is not None and chosen_receptor != receptor_name:
continue
print("receptor name = %s" % receptor_name)
receptor_filename = os.path.join(subdir, "%s.pdbqt" % receptor_name)
if not os.path.exists(receptor_filename):
continue
print("Examining %s" % receptor_filename)
receptor_mol = rdkit_util.load_molecule(
os.path.join(subdir, "%s.pdb" % receptor_name))
protein_centroid = mol_xyz_util.get_molecule_centroid(receptor_mol[0])
protein_range = mol_xyz_util.get_molecule_range(receptor_mol[0])
box_dims = protein_range + 5.0
ligands = sorted(glob.glob(os.path.join(subdir, '*_prepared.pdbqt')))
print("Num ligands = %d" % len(ligands))
dock_ligand_to_receptor_partial = partial(
dock_ligand_to_receptor,
receptor_filename=receptor_filename,
protein_centroid=protein_centroid,
box_dims=box_dims,
subdir=subdir,
exhaustiveness=exhaustiveness)
if restrict_box:
active_ligand = ""
for ligand in ligands:
if "CHEM" in ligand:
active_ligand = ligand
break
print("Docking to %s first to ascertain centroid and box dimensions" %
active_ligand)
out_pdb_qt = dock_ligand_to_receptor_partial(active_ligand)
ligand_pybel = rdkit_util.load_molecule(out_pdb_qt)
ligand_centroid = mol_xyz_util.get_molecule_centroid(ligand_pybel[0])
print("Protein centroid = %s" % (str(protein_centroid)))
print("Ligand centroid = %s" % (str(ligand_centroid)))
box_dims = np.array([20., 20., 20.])
dock_ligand_to_receptor_partial = partial(
dock_ligand_to_receptor,
receptor_filename=receptor_filename,
protein_centroid=ligand_centroid,
box_dims=box_dims,
subdir=subdir,
exhaustiveness=exhaustiveness)
print("Finished docking to %s, docking to remainder of ligands now." %
active_ligand)
if worker_pool is None:
for i, ligand_file in enumerate(ligands):
a = time.time()
dock_ligand_to_receptor_partial(ligand_file)
print("took %f seconds to dock single ligand." % (time.time() - a))
else:
print("parallelizing docking over worker pool")
worker_pool.map(dock_ligand_to_receptor_partial, ligands)
def generate_poses(self,
protein_file,
ligand_file,
centroid=None,
box_dims=None,
dry_run=False,
out_dir=None):
"""Generates the docked complex and outputs files for docked complex."""
if out_dir is None:
out_dir = tempfile.mkdtemp()
# Prepare receptor
receptor_name = os.path.basename(protein_file).split(".")[0]
protein_hyd = os.path.join(out_dir, "%s.pdb" % receptor_name)
protein_pdbqt = os.path.join(out_dir, "%s.pdbqt" % receptor_name)
hydrogenate_and_compute_partial_charges(
protein_file,
"pdb",
hyd_output=protein_hyd,
pdbqt_output=protein_pdbqt,
protein=True)
# Get protein centroid and range
# TODO(rbharath): Need to add some way to identify binding pocket, or this is
# going to be extremely slow!
if centroid is not None and box_dims is not None:
protein_centroid = centroid
else:
if not self.detect_pockets:
receptor_mol = rdkit_util.load_molecule(
protein_hyd, calc_charges=False, add_hydrogens=False)
protein_centroid = mol_xyz_util.get_molecule_centroid(receptor_mol[0])
protein_range = mol_xyz_util.get_molecule_range(receptor_mol[0])
box_dims = protein_range + 5.0
else:
logger.info("About to find putative binding pockets")
pockets, pocket_atoms_maps, pocket_coords = self.pocket_finder.find_pockets(
protein_file, ligand_file)
# TODO(rbharath): Handle multiple pockets instead of arbitrarily selecting
# first pocket.
logger.info("Computing centroid and size of proposed pocket.")
pocket_coord = pocket_coords[0]
protein_centroid = np.mean(pocket_coord, axis=1)
pocket = pockets[0]
(x_min, x_max), (y_min, y_max), (z_min, z_max) = pocket
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)
# Prepare receptor
ligand_name = os.path.basename(ligand_file).split(".")[0]
ligand_hyd = os.path.join(out_dir, "%s.pdb" % ligand_name)
ligand_pdbqt = os.path.join(out_dir, "%s.pdbqt" % ligand_name)
# TODO(rbharath): Generalize this so can support mol2 files as well.
hydrogenate_and_compute_partial_charges(
ligand_file,
"sdf",
hyd_output=ligand_hyd,
pdbqt_output=ligand_pdbqt,
protein=False)
# Write Vina conf file
conf_file = os.path.join(out_dir, "conf.txt")
write_conf(
protein_pdbqt,
ligand_pdbqt,
protein_centroid,
box_dims,
conf_file,
exhaustiveness=self.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)
# TODO(rbharath): Let user specify the number of poses required.
if not dry_run:
logger.info("About to call Vina")
call(
"%s --config %s --log %s --out %s" % (self.vina_cmd, conf_file,
log_file, out_pdbqt),
shell=True)
# TODO(rbharath): Convert the output pdbqt to a pdb file.
# Return docked files
return protein_hyd, out_pdbqt
def dock_ligands_to_receptors(docking_dir,
worker_pool=None,
exhaustiveness=None,
chosen_receptor=None,
restrict_box=True):
subdirs = glob.glob(os.path.join(docking_dir, '*/'))
for subdir in subdirs:
subdir = subdir.rstrip('/')
receptor_name = os.path.basename(subdir)
if chosen_receptor is not None and chosen_receptor != receptor_name:
continue
print("receptor name = %s" % receptor_name)
receptor_filename = os.path.join(subdir, "%s.pdbqt" % receptor_name)
if not os.path.exists(receptor_filename):
continue
print("Examining %s" % receptor_filename)
receptor_mol = rdkit_util.load_molecule(
os.path.join(subdir, "%s.pdb" % receptor_name))
protein_centroid = mol_xyz_util.get_molecule_centroid(receptor_mol[0])
protein_range = mol_xyz_util.get_molecule_range(receptor_mol[0])
box_dims = protein_range + 5.0
ligands = sorted(glob.glob(os.path.join(subdir, '*_prepared.pdbqt')))
print("Num ligands = %d" % len(ligands))
dock_ligand_to_receptor_partial = partial(
dock_ligand_to_receptor,
receptor_filename=receptor_filename,
protein_centroid=protein_centroid,
box_dims=box_dims,
subdir=subdir,
exhaustiveness=exhaustiveness)
if restrict_box:
active_ligand = ""
for ligand in ligands:
if "CHEM" in ligand:
active_ligand = ligand
break
print(
"Docking to %s first to ascertain centroid and box dimensions"
% active_ligand)
out_pdb_qt = dock_ligand_to_receptor_partial(active_ligand)
ligand_pybel = rdkit_util.load_molecule(out_pdb_qt)
ligand_centroid = mol_xyz_util.get_molecule_centroid(
ligand_pybel[0])
print("Protein centroid = %s" % (str(protein_centroid)))
print("Ligand centroid = %s" % (str(ligand_centroid)))
box_dims = np.array([20., 20., 20.])
dock_ligand_to_receptor_partial = partial(
dock_ligand_to_receptor,
receptor_filename=receptor_filename,
protein_centroid=ligand_centroid,
box_dims=box_dims,
subdir=subdir,
exhaustiveness=exhaustiveness)
print(
"Finished docking to %s, docking to remainder of ligands now."
% active_ligand)
if worker_pool is None:
for i, ligand_file in enumerate(ligands):
a = time.time()
dock_ligand_to_receptor_partial(ligand_file)
print("took %f seconds to dock single ligand." %
(time.time() - a))
else:
print("parallelizing docking over worker pool")
worker_pool.map(dock_ligand_to_receptor_partial, ligands)