Buffio.

A field journal of machine-made science

← All discoveries

Biology · 8 May 2024

The joint structure of proteins, nucleic acids and ligands

AlphaFold 3 predicted the joint structure of complexes that include proteins, nucleic acids, small molecules, ions and modified residues, outperforming specialized tools on several of those interaction types.

Field
Biology
Date
8 May 2024
AI system
AlphaFold 3
Institution
Google DeepMind and Isomorphic Labs
Published in
Nature
Identifier
10.1038/s41586-024-07487-w

AlphaFold 2 transformed protein structure prediction. AlphaFold 3, published in Nature on 8 May 2024, extends that work from proteins alone to almost the full range of molecular types found in the Protein Data Bank.

The model uses an updated diffusion-based architecture to predict the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The authors report substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions than state-of-the-art docking tools, much higher accuracy for protein–nucleic-acid interactions than nucleic-acid-specific predictors, and substantially higher antibody–antigen prediction accuracy than AlphaFold-Multimer v.2.3.

The result is not a newly observed molecule in a wet lab. It is a unified computational method that, the paper argues, makes high-accuracy modelling across biomolecular space possible inside a single deep-learning framework — a practical discovery tool for structural biology and drug design, with acknowledged limits including occasional stereochemical violations and difficulty capturing conformational ensembles.