liveBook · Manning

Scaffold split

As explained in Build AI Drug Discovery Pipelines

A scaffold split partitions molecular data according to shared chemical scaffolds so that related scaffold families are separated between subsets.

A scaffold split keeps molecules sharing a core chemical structure in the same subset. Training and test compounds therefore come from structurally different scaffold families, making validation more challenging than a random split. section 4.1.1

Randomly separating related molecules can produce overly optimistic results because similar compounds often have similar properties. Scaffold splitting better tests whether a model generalizes to unfamiliar chemical structures. section 4.1.1

A practical scaffold-split workflow is:

  • Choose a dataset containing molecular structures and measured targets. section 4.1.1
  • Request scaffold-based train, validation, and test partitions rather than random partitions. section 4.1.1
  • Compare model performance against random-split results, recognizing that scaffold-based testing is more demanding. section 4.1.1
Listing 4.1 Load AqSolDB with Scaffold-based Splits
from tdc.single_pred import ADME
data = ADME(name = 'Solubility_AqSolDB')
split = data.get_split(method = 'scaffold')
train_df, valid_df, test_df = split['train'], split['valid'], split['test']

Load AqSolDB through TDC and obtain train, validation, and test data using method='scaffold'. section 4.1.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines scaffolds, explains optimistic random-split validation, and demonstrates loading predefined partitions without detailing scaffold-generation algorithms.
Examples
Demonstrates scaffold partitions for AqSolDB solubility data and identifies a scaffold split column in a hERG blocker dataset.
What it assumes
Assumes molecular datasets and model-validation basics, while defining chemical scaffolds and contrasting them with random splits.
What you can do after
Apply scaffold splitting through the TDC API and obtain train, validation, and test data for molecular modeling.
How it connects
Connects molecular scaffolds with random splitting, model validation, structural similarity, and generalization.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.