Understanding transition pathways between meta-stable states in molecular systems is crucial to advance material design and drug discovery. However, unbiased molecular dynamics simulations are computationally infeasible due to the high energy barriers separating these states. Although recent machine learning techniques offer potential solutions, they are often limited to simple systems or rely on collective variables (CVs) derived from costly domain expertise. In this paper, we introduce a novel approach that trains diffusion path samplers (DPS) for transition path sampling (TPS) without the need for CVs. We recast the problem as an amortized sampling of the target path measure, minimizing the log-variance divergence between the path measure induced by our DPS and the target path measure. To ensure scalability for high-dimensional tasks, we introduce (1) a new off-policy training objective based on learning control variates with replay buffers and (2) a scale-based equivariant parameterization of the bias forces. We evaluate our approach, coined TPS-DPS, on a synthetic double-well potential and three peptides: Alanine Dipeptide, Polyproline Helix, and Chignolin. Results show that our approach produces more realistic and diverse transition pathways compared to existing baselines.

翻译：理解分子系统中亚稳态之间的过渡路径对于推进材料设计和药物发现至关重要。然而，由于分隔这些状态的高能垒，无偏分子动力学模拟在计算上不可行。尽管最近的机器学习技术提供了潜在的解决方案，但它们通常仅限于简单系统，或依赖于从昂贵的领域专业知识中推导出的集体变量（CVs）。本文提出了一种无需CVs即可训练用于过渡路径采样（TPS）的扩散路径采样器（DPS）的新方法。我们将该问题重新表述为目标路径测度的摊销采样，最小化由我们的DPS诱导的路径测度与目标路径测度之间的对数方差散度。为确保高维任务的可扩展性，我们引入了（1）基于学习控制变量与回放缓冲区的新的离策略训练目标，以及（2）偏置力的尺度等变参数化。我们在一个合成双势阱和三种肽（丙氨酸二肽、脯氨酸螺旋和Chignolin）上评估了我们的方法（命名为TPS-DPS）。结果表明，与现有基线相比，我们的方法能产生更真实且更多样化的过渡路径。