Zero-shot protein stability prediction by inverse folding models: a free energy interpretation
This work addresses a theoretical gap for researchers in computational biology, but it is incremental as it builds on existing inverse folding models.
The paper tackled the problem of understanding the link between inverse folding models and free-energy considerations for protein stability prediction, and demonstrated that simple improvements to likelihood ratio approximations yield considerable gains in zero-shot performance.
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.