def test_CallableFeaturizer():
from sklearn.preprocessing import scale
systems = (
LigandSystem([RDKitLigand.from_smiles("C")]),
LigandSystem([RDKitLigand.from_smiles("CC")]),
LigandSystem([RDKitLigand.from_smiles("CCC")]),
)
HashFeaturizer(getter=lambda s: s.ligand.to_smiles(), normalize=False).featurize(systems)
CallableFeaturizer(lambda s: scale(s.featurizations["last"].reshape((1,)))).featurize(systems)
for s in systems:
assert s.featurizations["last"].shape
def test_ClearFeaturizations_removeall():
from kinoml.features.ligand import OneHotSMILESFeaturizer
systems = (
System([RDKitLigand.from_smiles("C")]),
System([RDKitLigand.from_smiles("CC")]),
System([RDKitLigand.from_smiles("CCC")]),
)
OneHotSMILESFeaturizer().featurize(systems)
PadFeaturizer().featurize(systems)
ClearFeaturizations(keys=tuple(), style="keep").featurize(systems)
for s in systems:
assert not s.featurizations
def test_PadFeaturizer():
from kinoml.features.ligand import OneHotSMILESFeaturizer
systems = (
System([RDKitLigand.from_smiles("C")]),
System([RDKitLigand.from_smiles("CC")]),
System([RDKitLigand.from_smiles("CCC")]),
)
OneHotSMILESFeaturizer().featurize(systems)
PadFeaturizer().featurize(systems)
for s in systems:
assert s.featurizations["last"].shape == (53, 3)
return systems
def test_ClearFeaturizations_keeplast():
from kinoml.features.ligand import OneHotSMILESFeaturizer
systems = (
System([RDKitLigand.from_smiles("C")]),
System([RDKitLigand.from_smiles("CC")]),
System([RDKitLigand.from_smiles("CCC")]),
)
OneHotSMILESFeaturizer().featurize(systems)
PadFeaturizer().featurize(systems)
ClearFeaturizations().featurize(systems)
for s in systems:
assert len(s.featurizations) == 1
assert "last" in s.featurizations
def test_SmilesToLigandFeaturizer_fails():
ligand = RDKitLigand.from_smiles("CCCCC")
system = System([ligand])
featurizer = SmilesToLigandFeaturizer(ligand_type="openforcefield")
with pytest.raises(ValueError):
featurizer.featurize([system])
molecule = system.featurizations[featurizer.name]
assert type(molecule) == OpenForceFieldLigand
def test_Concatenated():
from kinoml.features.ligand import MorganFingerprintFeaturizer
ligand = RDKitLigand.from_smiles("CCCC")
system = System([ligand])
featurizer1 = MorganFingerprintFeaturizer(radius=2, nbits=512)
featurizer2 = MorganFingerprintFeaturizer(radius=2, nbits=512)
concatenated = Concatenated([featurizer1, featurizer2], axis=1)
concatenated.featurize([system])
assert system.featurizations["last"].shape[0] == 1024
def test_datasetprovider_awkward_exporter_single_tensor_same_shape():
"""
The core assumption for simplest cases is that one
system will be featurized as a single tensor, and that
all the tensors will be of the same shape across systems.
If that's the case:
- DatasetProvider.to_numpy() will work and will return
a X, y tuple of arrays
- DatasetProvider.to_dict_of_arrays() will work and will
return a dict of arrays with X, y keys.
Note that `.to_numpy()` won't work if the core assumptions
are broken. For those cases, `.to_dict_of_arrays()` is
recommended instead.
"""
from kinoml.core.ligands import RDKitLigand
from kinoml.features.ligand import MorganFingerprintFeaturizer
from kinoml.features.core import Concatenated, TupleOfArrays
import awkward as ak
conditions = AssayConditions()
systems = [
System([RDKitLigand.from_smiles(smi)]) for smi in ("CCCCC", "CCCCCCCC")
]
measurements = [
BaseMeasurement(50, conditions=conditions, system=systems[0]),
BaseMeasurement(30, conditions=conditions, system=systems[1]),
]
dataset = DatasetProvider(measurements=measurements)
featurizer1 = MorganFingerprintFeaturizer(radius=2, nbits=512)
featurizer2 = MorganFingerprintFeaturizer(radius=2, nbits=1024)
concatenate = Concatenated([featurizer1, featurizer2], axis=1)
aggregated = TupleOfArrays([concatenate])
aggregated.featurize(systems)
for system in systems:
assert system.featurizations["last"][0].shape[0] == (1024 + 512)
# With a single tensor per system, we build a unified X tensor
# First dimension in X and y must match
X, y = dataset.to_numpy()
# This extra dimension here V
# comes from the TupleOfArrays aggregation
assert X.shape[:3] == (2, 1, (1024 + 512))
assert X.shape[0] == y.shape[0]
# With dict_of_arrays and single tensor per system,
# the behavior is essentially the same
(Xa, ), ya = dataset.to_awkward()
assert ak.to_numpy(Xa).shape == (2, (1024 + 512))
assert ak.to_numpy(ya).shape == (2, )
def test_ligand_MorganFingerprintFeaturizer(smiles, solution):
"""
OFFTK _will_ add hydrogens to all ingested SMILES, and export a canonicalized output,
so the representation you get might not be the one you expect if you compute it directly.
"""
ligand = RDKitLigand.from_smiles(smiles)
system = System([ligand])
featurizer = MorganFingerprintFeaturizer(radius=2, nbits=512)
featurizer.featurize(system)
fingerprint = system.featurizations[featurizer.name]
solution_array = np.array(list(map(int, solution)), dtype="uint8")
assert (fingerprint == solution_array).all()
def test_ligand_GraphLigandFeaturizer_RDKit(smiles, solution):
"""
OFFTK _will_ add hydrogens to all ingested SMILES, and export a canonicalized output,
so the representation you get might not be the one you expect if you compute it directly.
That's why we use RDKitLigand here.
"""
ligand = RDKitLigand.from_smiles(smiles)
system = System([ligand])
GraphLigandFeaturizer().featurize([system])
connectivity, features = system.featurizations["last"]
assert (connectivity == solution[0]).all()
assert features == pytest.approx(solution[1])
def test_TupleOfArrays():
from kinoml.features.ligand import MorganFingerprintFeaturizer
ligand = RDKitLigand.from_smiles("CCCC")
system = System([ligand])
featurizer1 = MorganFingerprintFeaturizer(radius=2, nbits=512)
featurizer2 = MorganFingerprintFeaturizer(radius=2, nbits=1024)
aggregated = TupleOfArrays([featurizer1, featurizer2])
aggregated.featurize([system])
assert len(system.featurizations["last"]) == 2
assert system.featurizations["last"][0].shape[0] == 512
assert system.featurizations["last"][1].shape[0] == 1024
def test_ligand_OneHotSMILESFeaturizer(smiles, solution):
"""
OFFTK _will_ add hydrogens to all ingested SMILES, and export a canonicalized output,
so the representation you get might not be the one you expect if you compute it directly.
That's why we use RDKitLigand here.
"""
ligand = RDKitLigand.from_smiles(smiles)
system = System([ligand])
featurizer = OneHotSMILESFeaturizer()
featurizer.featurize(system)
matrix = system.featurizations[featurizer.name]
assert matrix.shape == solution.T.shape
assert (matrix == solution.T).all()
def test_ligand_GraphLigandFeaturizer(smiles, solution):
"""
OFFTK _will_ add hydrogens to all ingested SMILES, and export a canonicalized output,
so the representation you get might not be the one you expect if you compute it directly.
That's why we use RDKitLigand here.
"""
ligand = RDKitLigand.from_smiles(smiles)
system = System([ligand])
featurizer = GraphLigandFeaturizer()
featurizer.featurize(system)
graph = system.featurizations[featurizer.name]
assert (graph[0] == solution[0]).all() # connectivity
assert (graph[1] == solution[1]).all() # features
def test_datasetprovider_awkward_exporter_multiple_subtensors():
"""
When we use an aggregator like TupleOfArrays, which
breaks the one system -> one tensor assumption,
we need to use the `.dict_of_arrays()` exporter.
This creates a dictionary of arrays, where each key is
autogenerated like `X_s{int}_a{int}`, where `s` is the
system index and `a` is the array index.
"""
from kinoml.core.ligands import RDKitLigand
from kinoml.features.ligand import MorganFingerprintFeaturizer
from kinoml.features.core import TupleOfArrays
import awkward as ak
conditions = AssayConditions()
systems = [
System([RDKitLigand.from_smiles(smi)]) for smi in ("CCCCC", "CCCCCCCC")
]
measurements = [
BaseMeasurement(50, conditions=conditions, system=systems[0]),
BaseMeasurement(30, conditions=conditions, system=systems[1]),
]
dataset = DatasetProvider(measurements=measurements)
featurizer1 = MorganFingerprintFeaturizer(radius=2, nbits=512)
featurizer2 = MorganFingerprintFeaturizer(radius=2, nbits=1024)
aggregated = TupleOfArrays([featurizer1, featurizer2])
aggregated.featurize(dataset.systems)
for system in systems:
assert len(system.featurizations["last"]) == 2
assert system.featurizations["last"][0].shape[0] == 512
assert system.featurizations["last"][1].shape[0] == 1024
(x1, x2), y = dataset.to_awkward()
assert len(x1) == len(x2) == len(y)
assert ak.to_numpy(x1).shape == (2, 512)
assert ak.to_numpy(x2).shape == (2, 1024)
def test_datasetprovider_awkward_exporter_single_tensor_different_shapes():
"""
When a featurizer returns arrays of different shape for each
system, one can either choose between:
A. Pad them to the same dimension with PadFeaturizer,
and apply the Concatenated aggregator.
B. Keep them separate and export them with `.dict_of_arrays()`,
This creates a dictionary of arrays, where each key is
autogenerated like `X_s{int}`, where `s` is the
system index.
"""
from kinoml.core.ligands import RDKitLigand
from kinoml.features.ligand import OneHotSMILESFeaturizer
from kinoml.features.core import TupleOfArrays
import awkward as ak
conditions = AssayConditions()
smiles = ("CCCCC", "CCCCCCCC")
systems = [System([RDKitLigand.from_smiles(smi)]) for smi in smiles]
measurements = [
BaseMeasurement(50, conditions=conditions, system=systems[0]),
BaseMeasurement(30, conditions=conditions, system=systems[1]),
]
dataset = DatasetProvider(measurements=measurements)
featurizer = OneHotSMILESFeaturizer()
aggregated = TupleOfArrays([featurizer])
aggregated.featurize(dataset.systems)
for system, smi in zip(systems, smiles):
assert system.featurizations["last"][0].shape == (53, len(smi))
# X is returned as single-item list thanks to TupleOfArrays
(X, ), y = dataset.to_awkward()
assert X.type.length == len(y)
assert ak.to_numpy(X[0]).shape == (53, len(smiles[0]))
assert ak.to_numpy(X[1]).shape == (53, len(smiles[1]))
def test_datasetprovider_exporter_single_tensor_different_shapes():
"""
When a featurizer returns arrays of different shape for each
system, one can either choose between:
A. Pad them to the same dimension with PadFeaturizer,
and apply the Concatenated aggregator.
B. Keep them separate and export them with `.dict_of_arrays()`,
This creates a dictionary of arrays, where each key is
autogenerated like `X_s{int}`, where `s` is the
system index.
"""
from kinoml.core.ligands import RDKitLigand
from kinoml.features.ligand import OneHotSMILESFeaturizer
conditions = AssayConditions()
smiles = ("CCCCC", "CCCCCCCC")
systems = [System([RDKitLigand.from_smiles(smi)]) for smi in smiles]
measurements = [
BaseMeasurement(50, conditions=conditions, system=systems[0]),
BaseMeasurement(30, conditions=conditions, system=systems[1]),
]
dataset = DatasetProvider(measurements=measurements)
featurizer = OneHotSMILESFeaturizer()
featurizer.featurize(dataset.systems)
for system, smi in zip(systems, smiles):
assert system.featurizations["last"].shape == (53, len(smi))
arrays = dataset.to_dict_of_arrays()
X_keys = [k for k in arrays.keys() if k.startswith("X")]
assert sorted(X_keys) == ["X_s0_", "X_s1_"]
for X_key, smi in zip(X_keys, smiles):
assert arrays[X_key].shape == (53, len(smi))