Parallel path sampling method learns reaction steps without prior knowledge
Correlation-Free Transition Path Sampling through Shooting Point Generation Guided by Committor Learning
Machine Learning
Summary
Studying how systems change from one stable state to another is hard because these changes happen rarely. Traditional methods to sample these changes one by one are slow and produce related examples. The authors created a new approach that uses machine learning to understand and guide the sampling process, generating many independent transition paths in parallel without knowing the system's details beforehand. They tested this approach on simple and complex models and found it works better than standard methods.
What this means in practice
- •For computational chemists: Simulate rare molecular transitions more efficiently without predefined reaction details by using learned reaction coordinates in parallel.
- •For materials simulation teams: Generate diverse transition paths for complex materials to study transformations faster with reduced path correlations.
Authors
Maximilian Negedly, Sebastian Falkner, Alessandro Coretti, Christoph Dellago
Abstract
Studying the dynamical behavior of a system often depends on characterizing how it transitions between long-lived states. Because such transitions are rare, observing them usually requires specialized enhanced sampling techniques. Transition Path Sampling (TPS) is a well-established method for generating reactive trajectories, which is simple to implement and does not require the definition of a preconceived reaction coordinate. However, its efficiency is limited by its sequential nature and the resulting correlations between sampled paths. Previous work addressed this limitation by combining TPS with a sampling scheme based on conditioned Boltzmann Generators, a generative machine learning model capable of sampling a given target probability distribution. This approach produces uncorrelated transition paths but relies on an accurate reaction coordinate, which is rarely known in advance. Building on recent advances in committor learning, specifically on the Artificial Intelligence for Molecular Mechanism Discovery (AIMMD) method, in this work we introduce GenAIMMD, an iterative algorithm that actively and self-consistently learns the ideal reaction coordinate (the committor) and trains a conditioned Boltzmann Generator to sample from arbitrary bias windows along it. GenAIMMD thereby provides a correlation-free and fully parallelizable path sampling scheme that does not require prior knowledge of the system's transition mechanism. We apply GenAIMMD to a two-dimensional toy model and a higher-dimensional polymer system. In both cases, GenAIMMD succeeds in training the Boltzmann Generator and learning the committor. Benchmark results show a substantial increase in performance compared to standard TPS.