def test_write_gnina_conf(self):
docking_utils.write_gnina_conf(
'protein.pdb',
'ligand.sdf',
'conf.txt',
)
assert os.path.exists('conf.txt')
os.remove('conf.txt')
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 = True,
**kwargs) -> Union[Tuple[DOCKED_POSES, np.ndarray], 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).
centroid: np.ndarray, optional (default None)
The centroid to dock against. Is computed if not specified.
box_dims: np.ndarray, optional (default None)
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 4 angstroms.
exhaustiveness: int (default 8)
Tells GNINA how exhaustive it should be with pose
generation.
num_modes: int (default 9)
Tells GNINA how many binding modes it should generate at
each invocation.
out_dir: str, optional
If specified, write generated poses to this directory.
generate_scores: bool, optional (default True)
If `True`, the pose generator will return scores for complexes.
This is used typically when invoking external docking programs
that compute scores.
kwargs:
Any args supported by GNINA as documented
https://github.com/gnina/gnina#usage
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 an array of binding affinities (kcal/mol),
CNN pose scores, and CNN affinities predicted by GNINA.
"""
if out_dir is None:
out_dir = tempfile.mkdtemp()
if not os.path.exists(out_dir):
os.makedirs(out_dir)
# Parse complex
if len(molecular_complex) > 2:
raise ValueError(
"GNINA can only dock protein-ligand complexes and not more general molecular complexes."
)
(protein_file, ligand_file) = molecular_complex
# check filetypes
if not protein_file.endswith('.pdb'):
raise ValueError('Protein file must be in .pdb format.')
if not ligand_file.endswith('.sdf'):
raise ValueError('Ligand file must be in .sdf format.')
protein_mol = load_molecule(protein_file,
calc_charges=True,
add_hydrogens=True)
ligand_name = os.path.basename(ligand_file).split(".")[0]
# Define locations of log and output files
log_file = os.path.join(out_dir, "%s_log.txt" % ligand_name)
out_file = os.path.join(out_dir, "%s_docked.pdbqt" % ligand_name)
logger.info("About to call GNINA.")
# Write GNINA conf file
conf_file = os.path.join(out_dir, "conf.txt")
write_gnina_conf(protein_filename=protein_file,
ligand_filename=ligand_file,
conf_filename=conf_file,
num_modes=num_modes,
exhaustiveness=exhaustiveness,
**kwargs)
# Run GNINA
args = [
self.gnina_cmd, "--config", conf_file, "--log", log_file, "--out",
out_file
]
process = Popen(args, stdout=PIPE, stderr=PIPE)
stdout, stderr = process.communicate()
# read output and log
ligands, _ = load_docked_ligands(out_file)
docked_complexes = [(protein_mol[1], ligand) for ligand in ligands]
scores = read_gnina_log(log_file)
if generate_scores:
return docked_complexes, scores
else:
return docked_complexes