Research
Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
arXiv:2604.25244v1 Announce Type: cross Abstract: Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics sim
arXiv:2604.25244v1 Announce Type: cross Abstract: Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics simulations and the scarcity of dynamic structural data. This survey reviews recent advances in artificial intelligence for protein dynamics from three perspectives: learning from structural ensembles and trajectories, learning from physical energy signals, and learning to accelerate molecular simulations. We summarize representative methods for conformation ensemble generation, trajectory generation, Boltzmann generators, physics-aware adaptation, machine learning potentials, coarse-grained modeling, and collective variable discovery. We further discuss available datasets and key open challenges, such as scalability, thermodynamic consistency, kinetic fidelity, and integration with experimental constraints.
Related
- Learning residue level protein dynamics with multiscale Gaussians
- Enhancing molecular dynamics with equivariant machine-learned densities
- ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
- Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
Source: arXiv cs.LG | 2026-04-29