Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy Model

Zhen Wang (Northwestern Polytechnical University) · Dahao Xu (SUN YAT-SEN UNIVERSITY) · Jiahua Rao (Sun Yat-Sen University) · Yuedong Yang (SUN YAT-SEN UNIVERSITY) · Yicong Chen (SUN YAT-SEN UNIVERSITY) · Jiancong Xie (SUN YAT-SEN UNIVERSITY)

active learningactive moleculesadaptive drug discoverychemical spacescomputational constraintsdrugclipefficiency improvementenrichment factorsgroup relative policy optimization markov decision processmolecular diversityreinforced active learningselection accuracystate-of-the-art methodsvirtual screening

Virtual Screening (VS) is vital for drug discovery but struggles with low hit rates and high computational costs. While Active Learning (AL) has shown promise in improving the efficiency of VS, traditional methods rely on inflexible and handcrafted heuristics, limiting adaptability in complex chemical spaces, particularly in balancing molecular diversity and selection accuracy. To overcome these challenges, we propose GLARE, a reinforced active learning framework that reformulates VS as a Markov Decision Process (MDP). Using Group Relative Policy Optimization (GRPO), GLARE dynamically balances chemical diversity, biological relevance, and computational constraints, eliminating the need for inflexible heuristics. Experiments show GLARE outperforms state-of-the-art AL methods, with a 64.8% average improvement in Enrichment Factors (EF). Additionally, GLARE enhances the performance of VS foundation models like DrugCLIP, achieving up to an 8-fold improvement in EF$_{0.5\\%}$ with as few as 15 active molecules. These results highlight the transformative potential of GLARE for adaptive and efficient drug discovery.