A large language model-type architecture for high-dimensional molecular potential energy surfaces
This work addresses a key problem in computational chemistry for predicting reaction rates, but it appears incremental as it adapts existing AI methods to a new domain.
The authors tackled the challenge of computing high-dimensional potential energy surfaces for molecular systems by designing a graph-based neural network architecture inspired by large language models, achieving sub-kcal/mol accuracy for a 186-dimensional surface.
Computing high dimensional potential surfaces for molecular and materials systems is considered to be a great challenge in computational chemistry with potential impact in a range of areas including fundamental prediction of reaction rates. In this paper we design and discuss an algorithm that has similarities to large language models in generative AI and natural language processing. Specifically, we represent a molecular system as a graph which contains a set of nodes, edges, faces etc. Interactions between these sets, which represent molecular subsystems in our case, are used to construct the potential energy surface for a reasonably sized chemical system with 51 dimensions. Essentially a family of neural networks that pertain to the graph-based subsystems, get the job done for this 51 dimensional system. We then ask if this same family of lower-dimensional neural networks can be transformed to provide accurate predictions for a 186 dimensional potential surface. We find that our algorithm does provide reasonably accurate results for this larger dimensional problem with sub-kcal/mol accuracy for the higher dimensional potential surface problem.