load_b3db_regression

skfp.datasets.tdc.adme.load_b3db_regression(data_dir: str | PathLike | None = None, as_frame: bool = False, verbose: bool = False) → DataFrame | tuple[list[str]] | ndarray

Load the regression subset of Blood-Brain-Barrier dataset.

The task is to predict the BBB permeability [1] [2]. The BBB permeability is measured by the logarithm of the brain-plasma concentration ratio:

\[\log BB = \log \frac{C_{brain}}{C_{blood}}\]

Where \(C_{brain}\) and \(C_{blood}\) are concentrations in brain and blood, respectively. This dataset should not be confused with BBBP dataset from MoleculeNet.

See also load_b3db_classification()

This dataset is a part of “distribution” subset of ADME tasks.

Tasks	1
Task type	regression
Total samples	942
Recommended split	scaffold
Recommended metric	MAE

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.

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

[1]

Meng, F., Xi, Y., Huang, J. & Ayers, P. W. “A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors” Sci Data 8, 289 (2021).

[2]

Huang, Kexin, et al. “Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development” Proceedings of Neural Information Processing Systems, NeurIPS Datasets and Benchmarks, 2021