Differentiable Rotamer Sampling with Molecular Force Fields
This provides a faster alternative to molecular dynamics for structural biology, enabling more efficient exploration of molecular energy landscapes.
The paper tackled the computational inefficiency and theoretical gaps of Boltzmann generators for molecular dynamics by developing a mathematical foundation, demonstrating that the approach can replace traditional MD for proteins with sufficient speed.
Molecular dynamics is the primary computational method by which modern structural biology explores macromolecule structure and function. Boltzmann generators have been proposed as an alternative to molecular dynamics, by replacing the integration of molecular systems over time with the training of generative neural networks. This neural network approach to MD samples rare events at a higher rate than traditional MD, however critical gaps in the theory and computational feasibility of Boltzmann generators significantly reduce their usability. Here, we develop a mathematical foundation to overcome these barriers; we demonstrate that the Boltzmann generator approach is sufficiently rapid to replace traditional MD for complex macromolecules, such as proteins in specific applications, and we provide a comprehensive toolkit for the exploration of molecular energy landscapes with neural networks.