def mset_to_smiles(max_atoms, filename):
mset = MSet()
try:
mset.load(filename)
except json.JSONDecodeError:
print("json decode error")
return (None, None)
if mset.n_atoms > max_atoms:
return (None, None)
geom = mset.get_min_geom
try:
charges = [
float(atom.labels['wB97X-D.6-311g**.charges'])
for atom in geom.atoms
]
except KeyError:
charges = [
float(atom.labels['wb97x-d.6-311gss.mulliken_charges'])
for atom in geom.atoms
]
charge = sum(charges) / len(charges)
try:
mol = xyz2mol(geom.at_nums, [atom.xyz for atom in geom.atoms], charge)
except Chem.AtomValenceException:
print("atom valence exception")
return (None, None)
smiles = Chem.MolToSmiles(mol, isomericSmiles=False)
m = Chem.MolFromSmiles(smiles)
smiles = Chem.MolToSmiles(m, isomericSmiles=False)
mset.identifiers.update({"smiles": smiles})
mset.save(filename)
return (filename, smiles)
def mset_to_smiles(filename):
mset = MSet()
try:
mset.load(filename)
except json.JSONDecodeError:
print("json decode error")
return None
geom = get_min_geom(mset.geometries)
charge = 0
try:
smiles = geom_to_smiles(geom, charge)
except:
return None
mset.identifiers.update({"smiles": smiles})
mset.save(filename)
return filename
def mset_to_smiles(filename):
mset = MSet()
mset.load(filename)
geom = mset.get_min_geom
try:
cm5_charges = [
float(atom.labels['wb97x_dz.cm5_charges']) for atom in geom.atoms
]
hirshfeld_charges = [
float(atom.labels['wb97x_dz.hirshfeld_charges'])
for atom in geom.atoms
]
charge = ((sum(cm5_charges) / len(cm5_charges)) +
(sum(hirshfeld_charges) / len(hirshfeld_charges))) / 2
except:
charge = 0
try:
smiles = geom_to_smiles(geom, charge)
except:
return None
mset.identifiers.update({"smiles": smiles})
mset.save(filename)
return filename
else:
opt_natoms[len(opt_mol_data['atoms'])] = [opt_mol]
with open(
"/mnt/sdb1/jeherr/chemspider_data/chno_msets/chno_opt_natoms.txt",
"w") as f:
json.dump(opt_natoms, f)
opt_matches = {}
meta_matches = {}
for n_atoms, meta_mols in meta_natoms.items():
opt_mols = opt_natoms[n_atoms]
opt_msets = []
meta_msets = []
for opt_mol in opt_mols:
opt_mset = MoleculeSet()
opt_mset.load(opt_mol)
opt_mset.filename = opt_mol
opt_msets.append(opt_mset)
for meta_mol in meta_mols:
meta_mset = MoleculeSet()
meta_mset.load(meta_mol)
meta_mset.filename = meta_mol
meta_msets.append(meta_mset)
for meta_mset in meta_msets:
matches = []
for opt_mset in opt_msets:
if meta_mset.compare_hash(opt_mset):
matches.append(opt_mset.filename)
meta_matches[meta_mset.filename] = matches
for opt_mset in opt_msets:
matches = []