Diffusion-based protein structure prediction methods double as energy methods comparable to traditional force fields

Summary

Diffusion-based protein structure prediction methods double as energy functions comparable in performance to traditional methods like Rosetta (1). This was observed by computing the energy at $t=0.1$, which was a hyperparameter (see below)

Figures

Ref (1)

1.

Roney JP, Ou C, Ovchinnikov S. Protein Diffusion Models as Statistical Potentials. openRxiv; 2025. Available from: https://doi.org/10.64898/2025.12.09.693073