Breaking through AlphaFold's limits to predict how proteins change shape
Researchers have developed a method to improve AlphaFold3's ability to predict multiple protein conformational states by introducing a repulsive force. This advancement helps overcome the AI's tendency to predict only a single structure, which is often insufficient for understanding protein function.
Why it matters
Enhancing protein structure prediction accuracy is critical for drug discovery and understanding biological mechanisms at the molecular level.
by The Graduate University for Advanced Studies, SOKENDAI
edited by Sadie Harley , reviewed by Robert Egan
This article has been reviewed according to Science X's editorial process and policies . Editors have highlighted the following attributes while ensuring the content's credibility:
Add as preferred source AlphaFold3 diffusion model. (A) Conformational sampling by the diffusion generative model of AlphaFold3. (B) The method developed in this study enhances conformational sampling with AlphaFold3 by introducing a bias. Credit: Jun Ohnuki and Kei-ichi Okazaki, Institute for Molecular Science Conformational changes in proteins are vital to their function yet remain challenging for state-of-the-art artificial intelligence, such as AlphaFold3, to predict. Researchers at the Institute for Molecular Science (IMS), and the Graduate University for Advanced Studies, SOKENDAI introduced a repulsive force between predicted structures, allowing AlphaFold3 to sample the multiple conformational states that its default settings rarely capture.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in