Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search
This work addresses the challenge of generating pharmacologically viable molecules for drug discovery, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of inefficient and limited molecular design in drug discovery by introducing Trio, a framework that integrates language modeling, reinforcement learning, and Monte Carlo tree search, resulting in improved binding affinity (+7.85%), drug-likeness (+11.10%), synthetic accessibility (+12.05%), and a fourfold increase in molecular diversity compared to state-of-the-art methods.
Drug discovery is a time-consuming and expensive process, with traditional high-throughput and docking-based virtual screening hampered by low success rates and limited scalability. Recent advances in generative modelling, including autoregressive, diffusion, and flow-based approaches, have enabled de novo ligand design beyond the limits of enumerative screening. Yet these models often suffer from inadequate generalization, limited interpretability, and an overemphasis on binding affinity at the expense of key pharmacological properties, thereby restricting their translational utility. Here we present Trio, a molecular generation framework integrating fragment-based molecular language modeling, reinforcement learning, and Monte Carlo tree search, for effective and interpretable closed-loop targeted molecular design. Through the three key components, Trio enables context-aware fragment assembly, enforces physicochemical and synthetic feasibility, and guides a balanced search between the exploration of novel chemotypes and the exploitation of promising intermediates within protein binding pockets. Experimental results show that Trio reliably achieves chemically valid and pharmacologically enhanced ligands, outperforming state-of-the-art approaches with improved binding affinity (+7.85%), drug-likeness (+11.10%) and synthetic accessibility (+12.05%), while expanding molecular diversity more than fourfold.