3 papers
cs.LG2025
Hierarchical geometric deep learning enables scalable analysis of molecular dynamics
Zihan Pengmei, Spencer C. Guo, Chatipat Lorpaiboon +1
Molecular dynamics simulations can generate atomically detailed trajectories of complex systems, but analyzing these dynamics can be challenging when systems lack well-established…
cs.LG2024
Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamics
Zihan Pengmei, Chatipat Lorpaiboon, Spencer C. Guo +2
Identifying informative low-dimensional features that characterize dynamics in molecular simulations remains a challenge, often requiring extensive manual tuning and system-specifi…
physics.comp-ph2023
Accurate estimates of dynamical statistics using memory
Chatipat Lorpaiboon, Spencer C. Guo, John Strahan +2
Many chemical reactions and molecular processes occur on timescales that are significantly longer than those accessible by direct simulation. One successful approach to estimating…