liveBook · Manning

DAVIS dataset

As explained in Build AI Drug Discovery Pipelines

DAVIS is a benchmark dataset of drug-target pairs with measured binding-affinity values, commonly used to evaluate affinity-prediction models.

The DAVIS dataset is a benchmark for drug-target affinity prediction. It records experimentally measured binding strengths between kinase inhibitors and protein kinases, supporting regression models that predict continuous affinity rather than only bind/no-bind labels. section 11.1 section 11.1.1

Use these properties when preparing or evaluating DAVIS data:

  • Represents 68 unique compounds, 442 protein targets, and 30,056 measured drug-target pairs; a commonly curated version contains 433 kinases after removing nine records. section 11.1.1
  • Focuses on kinase selectivity, where conserved ATP-binding sites make cross-reactivity and off-target effects important modeling concerns. section 11.1.1
  • Stores affinity as pKd, calculated from Kd in molar units with pKd = -log10(Kd); higher pKd indicates stronger binding. section 11.1.1 section 11.5.5
  • Creates repeated exposure because most compounds are tested against many proteins, making memorization and test-set leakage important evaluation risks. section 11.5.5
  • Supports warm-start evaluation on unseen pairings, while cold-drug, cold-target, and cold-drug/cold-target splits measure generalization to unseen partners. section 11.5.5

Graph-based training record

A training example pairs a molecular graph with a protein representation and assigns the measured pKd as its target value. PyTorch Geometric stores graph features, edges, and the affinity label in a Data object, then batches variable-sized molecular and protein graphs with Batch.from_data_list. section 11.5.5

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines dataset composition, pKd preprocessing, graph preparation, and warm- versus cold-start evaluation, but not model architecture.
Examples
Uses kinase inhibitor screens, pKd distributions, molecular graph records, and variable-sized PyTorch Geometric batches.
What it assumes
Assumes basic drug-target affinity and machine-learning terminology, while defining Kd, pKd, kinase selectivity, and evaluation splits.
What you can do after
Evaluate affinity-prediction models while distinguishing memorization of known compounds or proteins from generalization to new partners.
How it connects
Connects drug-target affinity prediction, virtual screening, kinase selectivity, pKd, KIBA, and warm-start or cold-start evaluation.

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.