Accurate structure prediction of biomolecular interactions with AlphaFold 3

ABSTRACT

The interactions of proteins with other molecules, such as DNA, RNA, ligands and ions, are fundamental to biological function. Here we describe AlphaFold 3, a model that can predict the joint three-dimensional structure of a complex containing almost any combination of these molecules. We introduce a new generative diffusion-based architecture that replaces the previous structure module, predicting raw atom coordinates directly rather than predicting inter-atomic distances. AlphaFold 3 demonstrates substantially higher accuracy than specialized tools for protein-ligand, protein-nucleic acid and antibody-antigen prediction, enabling structure-based drug design across a vastly expanded biomolecular space.