load_chembl4005_ki#

skfp.datasets.moleculeace.load_chembl4005_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 ChEMBL4005 Ki dataset.

The task is to predict the inhibitor constant (Ki) of molecules against the Phosphatidylinositol 4,5-bisphosphate 3-kinase catalytic subunit alpha isoform target [1] [2].

Tasks

1

Task type

regression

Total samples

960

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_chembl4005_ki
>>> dataset = load_chembl4005_ki()
>>> dataset  
(['COC[C@H]1OC(=O)c2coc3c2[C@@]1(C)C1=C(C3=O)[C@@H]2CCC(=O)[C@@]2(C)C[C@H]1OC(C)=O, ..., 'CC(C)n1nc(-c2ccc3oc(N)nc3c2)c2c(N)ncnc21'], \
array([-2.079, ..., -1.447]))

>>> dataset = load_chembl4005_ki(as_frame=True)
>>> dataset.head() 
                                              SMILES        Ki
0  COC[C@H]1OC(=O)c2coc3c2[C@@]1(C)C1=C(C3=O)[C@@... -2.079181
1              O=c1cc(N2CCOCC2)oc2c(-c3ccccc3)cccc12 -3.778151
2  CS(=O)(=O)N1CCN(Cc2cc3nc(-c4cccc5[nH]ncc45)nc(... -0.806180
3          COc1ccc(NC(=O)c2c(C)ccc3c(N)nc(C)nc23)cn1 -2.000000
4          COc1ccc(NC(=O)c2cc(C)cc3c(N)nc(C)nc23)cn1  0.301030