Generative design of therapeutics that bind and modulate protein states

Numerous therapeutic approaches have been developed to enable interrogation and modulation of protein isoforms, but often require laborious experimental development or screening of binders to targets of interest. In this article, we focus on efficient, state-of-the-art computational methods to design both small molecule and protein-based binders to target proteins, and highlight recent generative artificial intelligence approaches to binder design, which represents the most promising direction to enable targeting and modulation of any protein state. Integrated with advances in protein-modifying architectures, the strategies described here may serve as the foundation for therapeutic development in the near future.

Duke Scholars

Author Pranam D. Chatterjee Biomedical Engineering