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
Over the past few years, deep-learning-based methods have revolutionized the field of protein structure prediction. Tools like AlphaFold can now reliably model the structure of a protein based solely on its amino acid sequence, even when few homologous sequences and structures are available. These advances promise to transform our understanding of individual proteins’ biological functions, with implications for drug discovery, de novo protein design, and protein-protein interaction research.
This Collection will feature Articles applying this exciting new technology in these and other areas.