def test_load_xyzfile(xyz_path):
path = os.path.join(xyz_path, '1_opt.xyz')
m = Molecule(path, 'xyz')
assert m.creator == ('XYZ', path)
assert isinstance(m.pybel_molecule, pybel.Molecule)
assert m.xyz.geometry.shape == (28, 3)
m.to_smiles()
assert m.smiles == 'c1ccc(CC2CCCC2)cc1'
m.to_smarts()
assert m.smarts == '[#6]1-[#6]-[#6]-[#6](-[#6]-1)-[#6]-[#6]1:[#6]:[#6]:[#6]:[#6]:[#6]:1'
m.to_inchi()
assert m.inchi == 'InChI=1S/C12H16/c1-2-6-11(7-3-1)10-12-8-4-5-9-12/h1-3,6-7,12H,4-5,8-10H2'
def load_xyz_polarizability():
"""Load and return xyz files and polarizability (Bohr^3).
The xyz coordinates of small organic molecules are optimized with BP86/def2svp level of theory.
Polarizability of the molecules are also calcualted in the same level of thoery.
================= ======================
rows 50
Columns 1
header polarizability
molecules rep. xyz
Features 0
Returns 1 dataframe and 1 dict
================= ======================
Returns
-------
molecules : list
The list of molecule objects with xyz coordinates.
pol : pandas dataframe
The polarizability of each molecule as a column of dataframe.
Examples
--------
>>> from chemml.datasets import load_xyz_polarizability
>>> molecules, polarizabilities = load_xyz_polarizability()
>>> print(len(molecules))
50
>>> print(polarizabilities.shape)
(50, 1)
"""
DATA_PATH = pkg_resources.resource_filename('chemml', os.path.join('datasets','data','organic_xyz'))
# from chemml.initialization import XYZreader
# reader = XYZreader(path_pattern=['[1-9]_opt.xyz', '[1-9][0-9]_opt.xyz'],
# path_root=DATA_PATH,
# reader='manual',
# skip_lines=[2, 0])
# molecules = reader.read()
molecules = []
for i in range(1,51):
molecule = Molecule(os.path.join(DATA_PATH,"%i_opt.xyz"%i), "xyz")
molecule.to_smiles()
molecule.pybel_molecule = None
molecules.append(molecule)
df = pd.read_csv(os.path.join(DATA_PATH,'pol.csv'))
return molecules, df
def test_hydrogens(caffeine_smiles, caffeine_canonical, caffeine_inchi):
m = Molecule(caffeine_smiles, 'smiles')
m.to_smiles()
assert isinstance(m.rdkit_molecule, Chem.Mol)
assert m.smiles == caffeine_canonical
# add hydrogens
m.hydrogens('add', explicitOnly=False)
# canonical smiles with hydrogens
m.to_smiles()
assert m.smiles == "[H]c1nc2c(c(=O)n(C([H])([H])[H])c(=O)n2C([H])([H])[H])n1C([H])([H])[H]"
# test inchi
m = Molecule(caffeine_inchi, 'inchi')
m.to_inchi()
assert m.inchi == caffeine_inchi
# add hydrogens
m.hydrogens('add')
m.to_inchi()
assert m.inchi == caffeine_inchi
def test_mol2smiles(caffeine_smiles, caffeine_canonical, caffeine_kekulize):
m = Molecule(caffeine_smiles, 'smiles')
m.to_smiles()
assert isinstance(m.rdkit_molecule, Chem.Mol)
assert m.smiles == caffeine_canonical
m.to_smiles(kekuleSmiles=True)
assert m.smiles == caffeine_kekulize
# kekulize takes priority over canonical
m.to_smiles(kekuleSmiles=True)
assert m.smiles == caffeine_kekulize
# if kekule is False, everything is OK
m.to_smiles(canonical=True)
assert m.smiles == caffeine_canonical
def test_mol2smiles_defaultargs(caffeine_smiles):
m = Molecule(caffeine_smiles, 'smiles')
m.to_smiles()
m.to_smiles(**m._default_rdkit_smiles_args)
# all the args & canonical=False
args = m._default_rdkit_smiles_args
args['canonical'] = False
m.to_smiles(**args)
assert m.smiles_args['canonical'] is False