High-dimensional near-optimal experiment design for drug discovery via Bayesian sparse sampling

TL;DR

This paper introduces a high-dimensional, near-optimal experiment design method for drug discovery using Bayesian inference, highlighting the advantages of sparse tree search over traditional exploration techniques.

Contribution

It develops a novel high-dimensional experiment design framework employing Bayesian sparse sampling, demonstrating its superiority in drug screening tasks.

Findings

Sparse tree search outperforms Thompson sampling and UCB in drug screening.

The approach significantly improves drug toxicity prediction accuracy.

Method shows strong results on synthetic and real datasets.

Abstract

We study the problem of performing automated experiment design for drug screening through Bayesian inference and optimisation. In particular, we compare and contrast the behaviour of linear-Gaussian models and Gaussian processes, when used in conjunction with upper confidence bound algorithms, Thompson sampling, or bounded horizon tree search. We show that non-myopic sophisticated exploration techniques using sparse tree search have a distinct advantage over methods such as Thompson sampling or upper confidence bounds in this setting. We demonstrate the significant superiority of the approach over existing and synthetic datasets of drug toxicity.