AlphaFold2 can predict single-mutation effects

TL;DR

This study evaluates AlphaFold2's ability to predict the effects of single mutations on protein structure and phenotype, demonstrating its potential and proposing methods to enhance prediction accuracy and reliability.

Contribution

The paper shows that AlphaFold2 can predict single-mutation effects and introduces a method to improve and assess the precision of these predictions.

Findings

AF predictions correlate with experimental structures for single mutations.

Local structural changes relate to phenotypic variations.

Proposed method enhances prediction reliability.

Abstract

AlphaFold2 (AF) is a promising tool, but is it accurate enough to predict single mutation effects? Here, we report that the localized structural deformation between protein pairs differing by only 1-3 mutations -- as measured by the effective strain -- is correlated across \num{3901} experimental and AF-predicted structures. Furthermore, analysis of ${\sim} 11000$ proteins shows that the local structural change correlates with various phenotypic changes. These findings suggest that AF can predict the range and magnitude of single-mutation effects on average, and we propose a method to improve precision of AF predictions and to indicate when predictions are unreliable.