def _featurize(self, mol_pdb_file, protein_pdb_file):
try:
frag1_coords, frag1_mol = load_molecule(
mol_pdb_file, is_protein=False, sanitize=True, add_hydrogens=False)
frag2_coords, frag2_mol = load_molecule(
protein_pdb_file, is_protein=True, sanitize=True, add_hydrogens=False)
except MoleculeLoadException:
# Currently handles loading failures by returning None
# TODO: Is there a better handling procedure?
logging.warning("Some molecules cannot be loaded by Rdkit. Skipping")
return None
system_mol = merge_molecules([frag1_mol, frag2_mol])
system_coords = get_xyz_from_mol(system_mol)
frag1_coords, frag1_mol = self._strip_hydrogens(frag1_coords, frag1_mol)
frag2_coords, frag2_mol = self._strip_hydrogens(frag2_coords, frag2_mol)
system_coords, system_mol = self._strip_hydrogens(system_coords, system_mol)
try:
frag1_coords, frag1_neighbor_list, frag1_z = self.featurize_mol(
frag1_coords, frag1_mol, self.frag1_num_atoms)
frag2_coords, frag2_neighbor_list, frag2_z = self.featurize_mol(
frag2_coords, frag2_mol, self.frag2_num_atoms)
system_coords, system_neighbor_list, system_z = self.featurize_mol(
system_coords, system_mol, self.complex_num_atoms)
except ValueError:
logging.warning(
"max_atoms was set too low. Some complexes too large and skipped")
return None
return frag1_coords, frag1_neighbor_list, frag1_z, frag2_coords, frag2_neighbor_list, frag2_z, \
system_coords, system_neighbor_list, system_z
def test_merge_molecules(self):
current_dir = os.path.dirname(os.path.realpath(__file__))
ligand_file = os.path.join(current_dir, "../../dock/tests/1jld_ligand.sdf")
xyz, mol = rdkit_utils.load_molecule(
ligand_file, calc_charges=False, add_hydrogens=False)
num_mol_atoms = mol.GetNumAtoms()
# self.ligand_file is for 3ws9_ligand.sdf
oth_xyz, oth_mol = rdkit_utils.load_molecule(
self.ligand_file, calc_charges=False, add_hydrogens=False)
num_oth_mol_atoms = oth_mol.GetNumAtoms()
merged = rdkit_utils.merge_molecules([mol, oth_mol])
merged_num_atoms = merged.GetNumAtoms()
assert merged_num_atoms == num_mol_atoms + num_oth_mol_atoms
