load_chembl218_ec50#

skfp.datasets.moleculeace.load_chembl218_ec50(data_dir: str | PathLike | None = None, as_frame: bool = False, verbose: bool = False, force_update: bool = False) → DataFrame | tuple[list[str], ndarray]#

Load the ChEMBL218 EC50 dataset.

The task is to predict the half maximal effective concentration (EC50) of molecules against the Cannabinoid receptor 1 target [1] [2].

Tasks

1

Task type

regression

Total samples

1031

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_chembl218_ec50
>>> dataset = load_chembl218_ec50()
>>> dataset  
(['Cn1c(C(=O)NN2CCCCC2)nc(-c2ccc(Cl)cc2)c1-c1ccc(Cl)cc1, ..., 'CCCCCc1cccc(OCCCCCCCCCCC(=O)NC2CC2)c1'], \
array([-2.0, ..., -1.491]))

>>> dataset = load_chembl218_ec50(as_frame=True)
>>> dataset.head() 
                                              SMILES      EC50
0  Cn1c(C(=O)NN2CCCCC2)nc(-c2ccc(Cl)cc2)c1-c1ccc(... -2.000000
1  Cn1c(C(=O)NC2CCCCC2)nc(-c2ccc(Cl)cc2)c1-c1ccc(... -2.698970
2  Cn1c(C(=O)NN2CCCCC2)nc(-c2ccc(Cl)cc2Cl)c1-c1cc... -0.698970
3  Cn1c(C(=O)NC2CCCCC2)nc(-c2ccc(Cl)cc2Cl)c1-c1cc... -1.255273
4  N#Cc1cc(-c2ccc(Cl)cc2)c(-c2ccc(Cl)cc2Cl)nc1OCc... -0.903090