def test_mollist(mols2):
bob = BagofBonds(const=1.0, n_jobs=2, verbose=False)
for i in mols2:
i.hydrogens('remove')
features = bob.represent(mols2)
assert features.shape == (4, 80)
assert bob.header_.count((6.0, 6.0)) == 6
def test_h2o(mols):
bob = BagofBonds(const=1.0)
h2o = bob.represent(mols)
assert h2o.shape == (1, 6)
a = np.array([[0.66066557, 0.5, 0.5, 8.3593106, 8.35237809, 73.51669472]])
assert a[0][0] == pytest.approx(h2o.values[0][0])
assert a[0][1] == pytest.approx(h2o.values[0][1])
assert a[0][-1] == pytest.approx(h2o.values[0][-1])
def test_exception(mols):
# Value error: molecule object
bob = BagofBonds(n_jobs=10)
with pytest.raises(ValueError):
bob.represent('fake')
with pytest.raises(ValueError):
bob.represent(['fake'])
# Value error ndim>1
with pytest.raises(ValueError):
bob.represent(np.array([[mols], [mols]]))
def test_h2o(mols):
bob = BagofBonds(const=1.0)
h2o_df = bob.represent(mols)
assert h2o_df.shape == (1, 6)
a = np.array([[0.66066557, 0.5, 0.5, 8.3593106, 8.35237809, 73.51669472]])
# O
ind = bob.header_.index((8.0, ))
assert a[0][5] == pytest.approx(h2o_df.values[0][ind])
# OH
ind = bob.header_.index((8.0, 1.0))
assert a[0][3] == pytest.approx(h2o_df.values[0][ind])
# HH
ind = bob.header_.index((1.0, 1.0))
assert a[0][0] == pytest.approx(h2o_df.values[0][ind])
# H
ind = bob.header_.index((1.0, ))
assert a[0][1] == pytest.approx(h2o_df.values[0][ind])
def bagofbounds(mol2, maxentry):
from chemml.chem import Molecule
#caffeine_smiles = 'CN1C=NC2=C1C(=O)N(C(=O)N2C)C'
#caffeine_smarts = '[#6]-[#7]1:[#6]:[#7]:[#6]2:[#6]:1:[#6](=[#8]):[#7](:[#6](=[#8]):[#7]:2-[#6])-[#6]'
#caffeine_inchi = 'InChI=1S/C8H10N4O2/c1-10-4-9-6-5(10)7(13)12(3)8(14)11(6)2/h4H,1-3H3'
mol = Molecule(Chem.MolToSmiles(mol2), 'smiles')
mol.hydrogens('add')
mol.to_xyz(optimizer='MMFF', mmffVariant='MMFF94s', maxIters=300) # 'UFF'
print(mol)
mol.visualize()
#mol.visualize()
from chemml.datasets import load_xyz_polarizability
from chemml.chem import BagofBonds
#coordinates, y = load_xyz_polarizability(mol)
bob = BagofBonds(const=1.0)
features = bob.represent(mol)
print(features)
print("number of entry")
print(features.shape[1])
if features.shape[1] > maxentry:
maxentry = features.shape[1]
return features, maxentry
from chemml.chem import Molecule
caffeine_smiles = 'CN1C=NC2=C1C(=O)N(C(=O)N2C)C'
caffeine_smarts = '[#6]-[#7]1:[#6]:[#7]:[#6]2:[#6]:1:[#6](=[#8]):[#7](:[#6](=[#8]):[#7]:2-[#6])-[#6]'
caffeine_inchi = 'InChI=1S/C8H10N4O2/c1-10-4-9-6-5(10)7(13)12(3)8(14)11(6)2/h4H,1-3H3'
mol = Molecule(caffeine_smiles, input_type='smiles')
mol.hydrogens('add')
mol.to_xyz(optimizer='MMFF', mmffVariant='MMFF94s', maxIters=300) # 'UFF'
print(mol)
mol.visualize()
#mol.visualize()
from chemml.datasets import load_xyz_polarizability
from chemml.chem import BagofBonds
#coordinates, y = load_xyz_polarizability(mol)
bob = BagofBonds(const= 1.0)
features = bob.represent(mol)
print(features)
import chemml from chemml.datasets import load_xyz_polarizability from chemml.chem import BagofBonds coordinates, y = load_xyz_polarizability() bob = BagofBonds(const=1.0) features = bob.represent(coordinates)
def test_mollist(mols2):
bob = BagofBonds(const=1.0, n_jobs=2, verbose=False)
features = bob.represent(mols2)
assert features.shape == (4, 13)
assert bob.header_.count((6.0,6.0)) == 6