Zero-shot protein stability prediction by inverse folding models: a free energy interpretation

TL;DR

This paper explores the theoretical foundations of inverse folding models for protein stability prediction, linking them to free-energy principles and proposing improvements for zero-shot accuracy.

Contribution

It clarifies the free-energy basis of inverse folding models and introduces methods to enhance their zero-shot stability prediction performance.

Findings

Likelihood ratios are a simplistic approximation of free-energy considerations.

Simple methodological improvements can significantly boost zero-shot prediction accuracy.

Empirical results show notable performance gains with proposed approaches.

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.