Towards experiment-guided AlphaFold

Summary

Researchers at ISTA and international collaborators have developed a method to guide AlphaFold with experimental data, enabling the modeling of protein structure ensembles that better reflect physical and biological reality. Although AlphaFold predicts protein 3D structures with remarkable accuracy, it tends to reduce heterogeneous structures to a single dominant conformation and overlooks experimental conditions affecting local structure. Published in Nature Biotechnology, the approach highlights the functional importance of protein motions and paves the way for improved predictive models. The team, led by Alex Bronstein, emphasizes that proteins are highly dynamic molecules, and modeling this dynamism is crucial for understanding their functions.