Adaptive CVgen: Leveraging reinforcement learning for advanced sampling in protein folding and chemical reactions

• 成果类型: Article
• 署名作者: Shen, Wenhui; Wan, Kaiwei; Li, Dechang; Gao, Huajian; Shi, Xinghua
• 署名单位: Chinese Academy of Sciences; National Center for Nanoscience & Technology, CAS; Chinese Academy of Sciences; University of Chinese Academy of Sciences, CAS; Zhejiang University; Tsinghua University
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-14373
• DOI: 10.1073/pnas.2414205121
• 发表日期: 2024-11-05
• 关键词: molecular-dynamics simulations; structure prediction; successes; binding

摘要

Enhanced sampling techniques have traditionally encountered two significant challenges: identifying suitable reaction coordinates and addressing the exploration-exploitation dilemma, particularly the difficulty of escaping local energy minima. Here, we introduce Adaptive CVgen, a universal adaptive sampling framework designed to tackle these issues. Our approach utilizes a set of collective variables (CVs) to comprehensively cover the system's potential evolutionary phase space, generating diverse reaction coordinates to address the first challenge. Moreover, we integrate reinforcement learning strategies to dynamically adjust the generated reaction coordinates, thereby effectively balancing the exploration- exploitation dilemma. We apply this framework to sample the conformational space of six proteins transitioning from completely disordered states to folded states, as well as to model the chemical synthesis process of C60, achieving minima, achieving both sampling efficiency and exploration accuracy. This framework holds potential for extending to various related challenges, including protein folding dynamics, drug targeting, and complex chemical reactions, thereby opening promising avenues for application in these fields.