Ligand Iterative Sampling for Affinity Refinement and Drug Discovery (LISARDD)

ICML 2025 Workshop FM4LS Submission50 Authors

Keywords: Reinforcement Learning, Drug Generation, Drug Discovery, Molecular Generation, Binding Affinity Prediction, Multi-objective Optimization

TL;DR: Modular RL framework for target-specific small molecule ligand generation and optimization.

Abstract: *De novo* drug generation is a challenging task that aims to generate novel molecules with specific properties from scratch. Deep learning can accelerate this process by efficiently exploring the drug-like chemical space. Here, we introduce LISARDD, a Reinforcement Learning framework to optimize sampling in the latent space of a pretrained target-agnostic generative model. We demonstrate that our approach can generate candidate molecules that simultaneously optimize multiple drug properties, including target-specific binding affinity, drug-likeness, and synthetic accessibility. This fully modular framework can leverage any molecular generative model, binding affinity scoring model, or optimization algorithm to identify novel drug candidates for future experimental validation.

Submission Number: 50