load_chembl2835_ki#

skfp.datasets.moleculeace.load_chembl2835_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 ChEMBL2835 Ki dataset.

The task is to predict the inhibitor constant (Ki) of molecules against the Tyrosine-protein kinase jak1 target [1] [2].

Tasks

1

Task type

regression

Total samples

615

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_chembl2835_ki
>>> dataset = load_chembl2835_ki()
>>> dataset  
(['C[C@@H]1CCN(C(=O)CC#N)C[C@@H]1N(C)c1ncnc2[nH]ccc12, ..., 'Cc1cnc(Nc2ccc(OCCN3CCCC3)cc2)nc1Nc1cccc(S(=O)(=O)NC(C)(C)C)c1'], \
array([0.1549, ..., -2.021]))

>>> dataset = load_chembl2835_ki(as_frame=True)
>>> dataset.head() 
                                              SMILES        Ki
0  C[C@@H]1CCN(C(=O)CC#N)C[C@@H]1N(C)c1ncnc2[nH]c...  0.154902
1  C[C@@H]1CCN(C(=O)CC#N)C[C@@H]1n1cnc2cnc3[nH]cc...  0.301030
2  C[C@@H]1CCN(Cc2ccccc2)C[C@@H]1N(C)c1ncnc2[nH]c... -2.785330
3  C[C@@H]1CCN(Cc2ccccc2)C[C@@H]1n1cnc2cnc3[nH]cc... -1.079181
4      N#CCC(=O)N1CCC[C@@H](n2cnc3cnc4[nH]ccc4c32)C1  0.397940