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_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))