发表机构
Laboratoire de Physique et Chimie Theoriques, Universite de Lorraine and CNRS; University of Chicago; Theoretical and Computational Biophysics Group, Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign; University of Illinois Urbana-Champaign（洛林大学与法国国家科学研究中心理论与化学物理实验室; 芝加哥大学; 伊利诺伊大学厄巴纳-香槟分校贝克曼先进科学技术研究所理论与计算生物物理学组; 伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出变分多态承诺子网络（VMCN），结合分子模拟数据与边界条件训练，可恢复分子系统亚稳态结构、估计动力学，还能与Gen-COMPAS结合用于chignolin的多态跃迁网络采样。
AI 中文摘要
复杂分子系统的长时间动力学通常涉及亚稳态网络上的稀有跃迁。基于为描述两个亚稳态之间稀有跃迁提供严格框架的过渡路径理论，我们引入了变分多态承诺子网络（VMCN），这是一种直接从分子模拟数据中学习到达每个亚稳态概率的神经框架。从该表示出发，VMCN可识别特定状态的承诺、候选过渡区域和状态对之间与承诺子一致的路径，以及以跃迁速率为特征的有效动力学网络。该模型使用有限时间滞后轨迹数据以及在保守状态核上定义的边界条件进行训练。将其应用于三阱势、丙氨酸三肽异构化以及液泡ATP酶的V_o结构域中的c环旋转，结果显示VMCN可恢复亚稳态结构，提供与承诺子一致的过渡机制描述，并估计状态间动力学。VMCN还能为不完整的状态分解提供诊断，并支持对候选亚稳态及其连接区域的自适应探索。通过将VMCN与用于chignolin的生成式承诺子引导路径采样（Gen-COMPAS）相结合，我们从两个端点结构出发，识别出一个错误折叠状态和一个候选折叠中间体，并将后续采样导向所得的多态跃迁网络。
英文摘要
The long-time dynamics of complex molecular systems often involves rare transitions across networks of metastable states. Building on transition-path theory, which provides a rigorous framework for describing rare transitions between two metastable states, we introduce the variational multistate committor network (VMCN), a neural framework that learns the probabilities of reaching each metastable state directly from molecular simulation data. From this representation, VMCN identifies state-specific commitment, candidate transition regions and committor-consistent pathways between state pairs, and an effective kinetic network characterized by transition rates. The model is trained using finite time-lag trajectory data together with boundary conditions defined on conservative state cores. Applications to a triple-well potential, trialanine isomerization, and the $c$--ring rotation in the V$_{\rm o}$ domain of a vacuolar ATPase show that VMCN recovers metastable organization, provides committor-consistent descriptions of transition mechanisms, and estimates state-to-state kinetics. VMCN further provides diagnostics for incomplete state decompositions and enables adaptive exploration of candidate metastable states and their connecting regions. By integrating VMCN with generative committor-guided path sampling (Gen-COMPAS) for chignolin, we start from two end point structures, identify a misfolded state and a candidate folding intermediate, and we direct subsequent sampling toward the resulting multistate transition network.
