liveBook · Manning

Representative data split

As explained in Build AI Drug Discovery Pipelines

A representative data split partitions a dataset into subsets whose distributions and variability reflect those of the full dataset.

A representative data split partitions a dataset into training and test sets whose distributions, extremes, and intermediate variability reflect the full dataset. This is especially important for small QSAR datasets, where the split affects evaluation of unseen-sample performance and the model’s applicability domain. section 6.2.2

A useful representative split should:

  • Cover the full range of binding activity rather than omitting an entire ligand class or response region. section 6.2.2
  • Preserve gradual changes in ligand properties so the model can interpolate between known compounds with similar but nonidentical structures. section 6.2.2
  • Use the Kennard-Stone algorithm to select a diverse training subset that captures variability across the dataset. section 6.2.2

Small-molecule binding dataset

For 48 ligands spanning five classes, a random split could place all aminoglycosides outside training, reducing observed kₒₙ coverage from [100,107] to [103,107]. Kennard-Stone selection instead uses pairwise sample distances to align training and test distributions and broaden the QSAR applicability domain. section 6.2.2

Figure 6.7 KSA ensures representative sampling from each cluster in this arbitrarily created data set, rather than sampling that is biased towards only one or two clusters.

Visualizes how Kennard-Stone sampling covers multiple clusters instead of concentrating selected samples in only one or two regions. section 6.2.2

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains representativeness, variability, interpolation, and distance-based Kennard-Stone selection, but does not provide full implementation details.
Examples
Uses 48 ligands in five classes, aminoglycoside coverage, binding-activity landscapes, and a clustered toy dataset.
What it assumes
Requires a dataset with ligand features and responses; introduces representative splitting before model development.
What you can do after
Apply it via the Kennard-Stone algorithm to select diverse training samples and evaluate QSAR generalization.
How it connects
Connects dataset splitting with QSAR models, applicability domains, ligand diversity, dimensionality reduction, and data refinement.

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.