def test_VEA():
calc = Calculator([AdjacencyMatrix, DistanceMatrix])
for line in data:
line = line.strip().split()
smi = line[0]
mol = Chem.MolFromSmiles(smi)
desireds = dict(zip(descs, map(parse_reference, line[1:])))
actuals = {str(k): v for k, v in zip(calc.descriptors, calc(mol))}
for desc in descs:
actual = actuals[desc]
decimal, desired = desireds[desc]
if desired is None:
continue
assert not is_missing(actual), actual
yield (
assert_almost_equal,
actual,
desired,
decimal,
"{} of {}".format(desc, smi),
)
def mordred_fingerprint2d(mols):
result = np.zeros((len(mols), len(descriptors2d)), dtype=np.float32)
calc = Calculator(descriptors2d)
for i, m in enumerate(tqdm.tqdm(mols)):
for j, v in enumerate(calc(m)):
result[i, j] = v if not is_missing(v) else np.nan
header = np.array([str(d) for d in descriptors2d])
return result, header
def mordred_fingerprint3d(mols):
result = np.zeros((len(mols), len(descriptors3d)), dtype=np.float32)
calc = Calculator(descriptors3d)
for i, m in enumerate(tqdm.tqdm(mols)):
if m.GetNumConformers() == 1:
for j, v in enumerate(calc(m)):
result[i, j] = v if not is_missing(v) else np.nan
elif m.GetNumConformers() == 0:
result[i] = np.nan
else:
raise ValueError("every molecule must have at most 1 conformer")
header = np.array([str(d) for d in descriptors3d])
return result, header
def test_getitem():
yield eq_, 1, result[0]
yield ok_, is_missing(result[1])
yield eq_, 1, result["Dummy1"]
yield ok_, is_missing(result["Dummy2"])
def test_name():
yield eq_, 1, result.name["Dummy1"]
yield ok_, is_missing(result.name["Dummy2"])
def test_ix():
yield eq_, 1, result.ix[0]
yield ok_, is_missing(result.ix[1])
result = calc1(benzene)
print(result)
# >>> [0.0, 1, 0, 0, 0, 1, (snip)
# Calculator constructor can register descriptors
calc2 = Calculator(Chi.Chi)
# Descriptors module contains all descriptors
calc3 = Calculator(descriptors)
# User can access all descriptor instances by descriptors property
print(calc3.descriptors)
# >>> (mordred.EccentricConnectivityIndex.EccentricConnectivityIndex(), (snip)
# Calculate descriptors
result = calc3(benzene)
# get first missing value
na1 = next(r for r in result if is_missing(r))
# get reason
print(na1.error)
# >>> missing 3D coordinate
# Delete all missing value
result = result.drop_missing()
# convert to dict
print(result.asdict())