Modeling conformational states of proteins with AlphaFold

Many proteins exert their function by switching among different structures. Knowing the conformational ensembles affiliated with these states is critical to elucidate key mechanistic aspects that govern protein function. While experimental determination efforts are still bottlenecked by cost, time, and technical challenges, the machine-learning technology AlphaFold showed near experimental accuracy in predicting the three-dimensional structure of monomeric proteins. However, an AlphaFold ensemble of models usually represents a single conformational state with minimal structural heterogeneity. Consequently, several pipelines have been proposed to either expand the structural breadth of an ensemble or bias the prediction toward a desired conformational state. Here, we analyze how those pipelines work, what they can and cannot predict, and future directions.

Automated summary

Many proteins switch among different structures to exert their function, and understanding these conformational ensembles is crucial for unraveling key mechanistic aspects of protein function. Experimental determination of these structures is limited by cost, time, and technical challenges, but the machine-learning technology AlphaFold has shown promising accuracy in predicting the three-dimensional structure of monomeric proteins. However, AlphaFold typically represents a single conformational state with minimal structural heterogeneity, leading to the development of pipelines to expand the diversity or bias the prediction towards desired conformational states. In this study, we analyze the functionality, limitations, and future directions of these pipelines.