AI Insight
Researchers at the Institute of Science and Technology Austria and international collaborators have developed a method to enhance AlphaFold's protein structure predictions by incorporating experimental data. While AlphaFold accurately predicts protein 3D structures, it typically produces only a single dominant conformation and cannot account for structural variations that occur under different experimental conditions. The new approach addresses this limitation by guiding the AI tool with experimental information to capture structural heterogeneity.
Why it matters
This advancement could significantly improve protein structure prediction accuracy for proteins that adopt multiple conformations or change shape under different conditions. Better modeling of protein structural diversity is crucial for drug discovery and understanding biological processes where proteins must shift between different shapes to function.
Understand the Science
The AI-based program AlphaFold predicts a protein’s 3D structure with remarkable accuracy. However, it tends to reduce heterogeneous structures to a single dominant conformation, or shape, and overlooks experimental conditions that can alter local structure. Researchers at the Institute of Science and Technology Austria (ISTA) and international collaborators have now developed a way to guide AlphaFold with experimental data. Their approach, published in Nature Biotechnology, paves the way for improved future predictive models.
Source: Toward experiment-guided AlphaFold: Researchers overcome AI tool's single-conformation limitation