liveBook · Manning

KIBA dataset

As explained in Build AI Drug Discovery Pipelines

A KIBA score is a unified bioactivity metric derived by integrating heterogeneous measurements of drug-target binding strength.

The KIBA dataset supports drug-target affinity prediction by representing each drug-protein pair with a KIBA score: a normalized combination of Ki, Kd, and IC50 measurements. Unlike a bind/no-bind label, the score supports regression over continuous binding strength. section 11.1 section 11.5.5

A practical KIBA workflow uses the dataset as follows:

  • Train a model on 118,254 measured interactions covering 2,111 compounds and 229 proteins. section 11.5.5
  • Represent drugs and proteins as graph inputs when using graph neural networks, then predict one affinity score for each pair. section 11.5.5
  • Interpret warm-start results carefully: test compounds and proteins may have appeared during training, although their tested combinations were held out. section 11.5.5
  • Use cold-drug, cold-target, or cold-drug/cold-target splits to test generalization to unseen chemistry, targets, or both. section 11.5.5

Affinity prediction for a new pair

A model can learn from known drug-target interactions and estimate the KIBA score for a held-out combination, such as a known compound paired with a known protein. This warm-start task mirrors screening known drugs against new targets, but its results can overstate performance on genuinely new compounds or proteins. section 11.5.5

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines the score composition, dataset scale, graph inputs, and warm- versus cold-start evaluation, but does not detail score derivation.
Examples
Uses 2,111 compounds, 229 proteins, 118,254 interactions, and held-out drug-protein combinations as evaluation examples.
What it assumes
Assumes basic drug-target affinity and regression concepts, while introducing KIBA scores and graph-based dataset preparation.
What you can do after
Evaluate drug-target affinity models while distinguishing memorization of familiar partners from generalization to unseen drugs or proteins.
How it connects
Links drug-target affinity prediction, virtual screening, graph neural networks, and the DAVIS benchmark.

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.