Skip to yearly menu bar Skip to main content


Oral
in
Workshop: New Frontiers of AI for Drug Discovery and Development

Offline RL for generative design of protein binders

Denis Tarasov · Ulrich Armel Mbou Sob · Miguel ArbesĂș · Nima Siboni · Sebastien Boyer · Andries Smit · Oliver Bent · Arnu Pretorius · Marcin Skwark

Keywords: [ Drug Discovery ] [ offline reinforcement learning ]


Abstract:

Offline Reinforcement Learning (RL) offers a compelling avenue for solving RL problems without the need for interactions with an environment, which may be expensive or unsafe. While online RL methods have found success in various domains, such as de novo Structure-Based Drug Discovery (SBDD), they struggle when it comes to optimizing essential properties derived from protein-ligand docking. The high computational cost associated with the docking process makes it impractical for online RL, which typically requires hundreds of thousands of interactions during learning. In this study, we propose the application of offline RL to address the bottleneck posed by the docking process, leveraging RL's capability to optimize non-differentiable properties. Our preliminary investigation focuses on using offline RL to conditionally generate drugs with improved docking and chemical properties.

Chat is not available.