用于鲁棒分子跃迁路径采样的随机控制策略
Stochastic Control Policies for Robust Molecular Transition Path Sampling
浏览论文内容
中文总结 AI 辅助
本研究针对现有基于滚动的分子跃迁路径采样（TPS）控制方法不稳定且依赖随机种子的问题，提出FS-TPS和LaS-TPS两种随机策略，在三种生物分子系统上验证其可提升跃迁成功率与路径质量并降低初始化敏感性。
中文摘要 AI 辅助
跃迁路径采样（TPS）旨在高效生成亚稳态之间罕见的分子跃迁轨迹，对理解生物分子机制至关重要。除了传统的基于分子动力学（MD）的采样方法外，机器学习已成为当前最先进TPS的核心。一类主要方法在显式MD滚动过程中学习控制力，由于保留了底层分子动力学，这些方法往往比直接构建路径的端点条件生成器产生更符合物理规律的轨迹。然而，据报道，基于滚动的控制方法存在性能不稳定且严重依赖随机种子的问题。我们将基于滚动的控制重新表述为学习路径空间提议分布，并研究将随机性作为设计选择以提升探索能力和优化鲁棒性。我们开发了两种随机策略：FS-TPS，直接对控制策略输出上的状态依赖高斯分布进行参数化；LaS-TPS，对紧凑的潜在控制变量进行采样并将其解码为结构化的跨原子相关力变化。我们在三个规模递增的生物分子系统上进行了广泛的多种子实验：丙氨酸二肽、芝蛋白（chignolin）以及快速折叠蛋白BBL。与确定性策略基线相比，随机策略始终提高了跃迁成功率和路径质量，同时大幅降低了对随机初始化的敏感性。
英文摘要
Transition path sampling (TPS) aims to efficiently generate rare molecular transition trajectories between metastable states and is essential for understanding biomolecular mechanisms. Beyond traditional molecular dynamics (MD)-based sampling, machine learning has become central to state-of-the-art TPS. One major class of methods learns control forces during explicit MD rollouts. By preserving the underlying molecular dynamics, these methods tend to produce more physically plausible trajectories than endpoint-conditioned generators that construct paths directly. However, rollout-based control methods have been reported to exhibit unstable and strongly seed-dependent performance. We recast rollout-based control as learning a path-space proposal distribution and investigate stochasticity placement as a design choice for improving exploration and optimization robustness. We develop two stochastic policies: FS-TPS, which directly parameterizes a state-dependent Gaussian distribution over the control policy output, and LaS-TPS, which samples a compact latent control variable and decodes it into structured, cross-atom-correlated force variation. We conduct extensive multi-seed experiments on three biomolecular systems of increasing size: alanine dipeptide, chignolin, and BBL, a fast-folding protein. Stochastic policies consistently improve transition success and path quality over deterministic-policy baselines while substantially reducing sensitivity to random initialization.
