load_chembl237_ki#

skfp.datasets.moleculeace.load_chembl237_ki(data_dir: str | PathLike | None = None, as_frame: bool = False, verbose: bool = False, force_update: bool = False) → DataFrame | tuple[list[str], ndarray]#

Load the ChEMBL237 Ki dataset.

The task is to predict the inhibitor constant (Ki) of molecules against the Kappa-type opioid receptor target [1] [2].

Tasks

1

Task type

regression

Total samples

2603

Recommended split

activity_cliff

Recommended metric

RMSE
Parameters:

  • data_dir ({None, str, path-like}, default=None) – Path to the root data directory. If None, currently set scikit-learn directory is used, by default $HOME/scikit_learn_data.

  • as_frame (bool, default=False) – If True, returns the raw DataFrame with columns: “SMILES”, “label”. Otherwise, returns SMILES as list of strings, and labels as a NumPy array (1D integer binary vector).

  • verbose (bool, default=False) – If True, progress bar will be shown for downloading or loading files.

  • force_update (bool, default=False) – If True, always re-download the dataset from HuggingFace Hub, even if it is already present locally. If False, the dataset is downloaded only if it is not yet available locally.

Returns:

data – Depending on the as_frame argument, one of: - Pandas DataFrame with columns: “SMILES”, “label” - tuple of: list of strings (SMILES), NumPy array (labels)

Return type:

pd.DataFrame or tuple(list[str], np.ndarray)

References

Examples

>>> from skfp.datasets.moleculeace import load_chembl237_ki
>>> dataset = load_chembl237_ki()
>>> dataset  
(['CC(c1ccccc1)N1CC[C@H]1[C@@H](N)c1cccc(Cl)c1, ..., 'CCO[C@@]12Cc3cc(-c4ccccc4)cnc3[C@@H]3Oc4c(O)ccc5c4[C@@]31CCN(CC1CC1)[C@@H]2C5'], \
array([-3.613, ..., -2.401]))

>>> dataset = load_chembl237_ki(as_frame=True)
>>> dataset.head() 
                                              SMILES        Ki
0        CC(c1ccccc1)N1CC[C@H]1[C@@H](N)c1cccc(Cl)c1 -3.612678
1  Cc1ccc(C(c2ccc(C)cc2)N2CC[C@H]2[C@H](N)c2cccc(... -3.265054
2  COc1ccc([C@H](N)[C@@H]2CCN2C(c2ccccc2)c2ccccc2... -3.127429
3  N[C@H](c1cccc(Cl)c1)[C@@H]1CCN1C(c1ccc(F)cc1)c... -3.350248
4  N[C@H](c1cccc(Cl)c1)[C@@H]1CCN1C(c1cccc(Cl)c1)... -3.780821