skfp.model_selection.scaffold_train_test_split#

skfp.model_selection.scaffold_train_test_split(data: Sequence[str | Mol], *additional_data: Sequence, train_size: float | None = None, test_size: float | None = None, use_csk: bool = False, return_indices: bool = False) → tuple[Sequence[str | Mol], Sequence[str | Mol], Sequence[Sequence[Any]]] | tuple[Sequence, ...] | tuple[Sequence[int], Sequence[int]]#

Split using groups of Bemis-Murcko scaffolds.

This split uses deterministically partitioned groups of Bemis-Murcko molecular scaffolds [1] for splitting, as introduced in the MoleculeNet [2] paper. It aims to verify the model generalization to new and rare scaffolds, as an approximation to the time split.

By default, core structure scaffolds are used (following RDKit), which include atom types. Original Bemis-Murcko approach uses the cyclic skeleton of a molecule, replacing all atoms by carbons. It is also known as CSK (Cyclic SKeleton) [3], and can be used with use_csk parameter.

This approach is known to have certain limitations. In particular, molecules with no rings will not get a scaffold, resulting in them being grouped together regardless of their structure.

The split is fully deterministic, with the smallest scaffold sets assigned to the test subset and the rest to the training subset.

The split fractions (train_size, test_size) must sum to 1.

Parameters:

  • data (sequence) – A sequence representing either SMILES strings or RDKit Mol objects.

  • additional_data (list[sequence]) – Additional sequences to be split alongside the main data (e.g., labels or feature vectors).

  • train_size (float, default=None) – The fraction of data to be used for the train subset. If None, it is set to 1 - test_size. If test_size is also None, it will be set to 0.8.

  • test_size (float, default=None) – The fraction of data to be used for the test subset. If None, it is set to 1 - train_size. If train_size is also None, it will be set to 0.2.

  • use_csk (bool, default=False) – Whether to use molecule’s skeleton or the core structure scaffold (including atom types).

  • return_indices (bool, default=False) – Whether the method should return the input object subsets, i.e. SMILES strings or RDKit Mol objects, or only the indices of the subsets instead of the data.

Returns:

  • subsets (tuple[list, list, …])

  • Tuple with train-test subsets of provided arrays. First two are lists of SMILES strings or RDKit Mol objects,

  • depending on the input type. If return_indices is True, lists of indices are returned instead of actual data.

References

On this page
Show Source