Bayes optimal informer sets for early-stage drug discovery

An important experimental design problem in early-stage drug discovery is how to prioritize available compounds for testing when very little is known about the target protein. Informer-based ranking (IBR) methods address the prioritization problem when the compounds have provided bioactivity data on other potentially relevant targets. An IBR method selects an informer set of compounds, and then prioritizes the remaining compounds on the basis of new bioactivity experiments performed with the informer set on the target. We formalize the problem as a two-stage decision problem and introduce the Bayes Optimal Informer SEt (BOISE) method for its solution. BOISE leverages a flexible model of the initial bioactivity data, a relevant loss function, and effective computational schemes to resolve the two-step design problem. We evaluate BOISE and compare it to other IBR strategies in two retrospective studies, one on protein-kinase inhibition and the other on anticancer drug sensitivity. In both empirical settings BOISE exhibits better predictive performance than available methods. It also behaves well with missing data, where methods that use matrix completion show worse predictive performance.

Automated summary

This study addresses an important experimental design problem in early-stage drug discovery, focusing on prioritizing compounds for testing when little is known about the target protein. The Informer-based ranking (IBR) method is introduced as a solution, which selects a set of informer compounds and prioritizes the remaining compounds based on new bioactivity experiments. The Bayes Optimal Informer SEt (BOISE) method is proposed to efficiently solve this two-stage decision problem and outperforms other available methods in predicting protein-kinase inhibition and anticancer drug sensitivity.