Zero-Shot Protein Stability Prediction by Inverse Folding Models: A Free Energy Interpretation
Abstract
Inverse folding models have proven to be highly effective zero-shot predictors of protein stability. Despite this success, the link between the amino acid preferences of an inverse folding model and the free-energy considerations underlying thermodynamic stability remains incompletely understood. A better understanding would be of interest not only from a theoretical perspective, but also potentially provide the basis for stronger zero-shot stability prediction. In this paper, we take steps to clarify the free-energy foundations of inverse folding models. Our derivation reveals the standard practice of likelihood ratios as a simplistic approximation and suggests several paths towards better estimates of the relative stability. We empirically assess these approaches and demonstrate that considerable gains in zero-shot performance can be achieved with fairly simple means.
Cite
Text
Frellsen et al. "Zero-Shot Protein Stability Prediction by Inverse Folding Models: A Free Energy Interpretation." Advances in Neural Information Processing Systems, 2025.Markdown
[Frellsen et al. "Zero-Shot Protein Stability Prediction by Inverse Folding Models: A Free Energy Interpretation." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/frellsen2025neurips-zeroshot/)BibTeX
@inproceedings{frellsen2025neurips-zeroshot,
title = {{Zero-Shot Protein Stability Prediction by Inverse Folding Models: A Free Energy Interpretation}},
author = {Frellsen, Jes and Kassem, Maher M. and Bengtsen, Tone and Olsen, Lars and Lindorff-Larsen, Kresten and Ferkinghoff-Borg, Jesper and Boomsma, Wouter},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/frellsen2025neurips-zeroshot/}
}