load_chembl3979_ec50#

skfp.datasets.moleculeace.load_chembl3979_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 ChEMBL3979 EC50 dataset.

The task is to predict the half maximal effective concentration (EC50) of molecules against the Peroxisome proliferator-activated receptor delta target [1] [2].

Tasks

1

Task type

regression

Total samples

1125

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_chembl3979_ec50
>>> dataset = load_chembl3979_ec50()
>>> dataset  
(['CCC(Cc1ccc(OC)c(C(=O)NCCc2ccc(C(F)(F)F)cc2)c1)C(=O)O, ..., 'CC(C)c1onc(-c2c(Cl)cccc2Cl)c1COc1ccc(CNc2ccc(CC(=O)O)cc2)c(Cl)c1'], \
array([-3.176, ..., -3.176]))

>>> dataset = load_chembl3979_ec50(as_frame=True)
>>> dataset.head() 
                                              SMILES      EC50
0  CCC(Cc1ccc(OC)c(C(=O)NCCc2ccc(C(F)(F)F)cc2)c1)... -3.176091
1  CCC(Cc1ccc(OC)c(C(=O)NCc2ccc(OC(F)(F)F)cc2)c1)... -2.954243
2    CCC(Cc1ccc(OC)c(CCCc2ccc(C(F)(F)F)cc2)c1)C(=O)O -2.806180
3  CCSC(Cc1ccc(OC)c(C(=O)NCc2ccc(C(F)(F)F)cc2)c1)... -3.477121
4  CCOC(Cc1ccc(OC)c(C(=O)NCc2ccc(C(F)(F)F)cc2)c1)... -3.477121