AlphaFold 3
paperCredibility Rating
Gold standard. Rigorous peer review, high editorial standards, and strong institutional reputation.
Rating inherited from publication venue: Nature
AlphaFold 3 is a significant advancement in protein structure prediction using diffusion-based architecture for complex biomolecular interactions, relevant to AI safety as a major capability development in AI-driven biological research with potential dual-use implications.
Paper Details
Metadata
Summary
AlphaFold 3 introduces a substantially updated diffusion-based architecture capable of predicting the joint structure of complex biomolecular interactions including proteins, nucleic acids, small molecules, ions, and modified residues within a single unified framework. The model demonstrates significantly improved accuracy compared to specialized tools across multiple domains: superior performance for protein-ligand interactions versus state-of-the-art docking tools, higher accuracy for protein-nucleic acid interactions compared to nucleic-acid-specific predictors, and substantially better antibody-antigen prediction accuracy than AlphaFold-Multimer v.2.3. This work demonstrates that high-accuracy modeling across diverse biomolecular space is achievable through a single deep-learning framework rather than requiring separate specialized tools.
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| Scientific Research Capabilities | Capability | 68.0 |
Cached Content Preview
Accurate structure prediction of biomolecular interactions with AlphaFold 3 | Nature
Skip to main content
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Advertisement
Accurate structure prediction of biomolecular interactions with AlphaFold 3
Download PDF
Download PDF
Subjects
Drug discovery
Machine learning
Protein structure predictions
Structural biology
An Addendum to this article was published on 27 November 2024
Abstract
The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design 2 , 3 , 4 , 5 , 6 . Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3 7 , 8 . Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.
Similar content being viewed by others
Benchmarking all-atom biomolecular structure prediction with FoldBench
Article
Open access
04 December 2025
Highly accurate protein structure prediction with Alpha
... (truncated, 86 KB total)880baf1e28dfad5e | Stable ID: sid_xpTv93KF8H