DeepMind and EMBL Unveil Open Database of All Human Protein Structures
DeepMind and EMBL partner to release the most complete database of predicted 3D human protein structures. This open resource more than doubles the known high-accuracy protein structures available to scientists.
DeepMind and the European Molecular Biology Laboratory (EMBL) partner to make the most complete and accurate database of predicted human protein structures freely available to the scientific community. The AlphaFold Protein Structure Database covers all approximately 20,000 proteins expressed by the human genome. This massive release dramatically expands the accumulated knowledge of protein structures and more than doubles the number of high-accuracy human protein structures accessible to researchers.
This breakthrough builds on AlphaFold's 2020 success in solving the 50-year-old grand challenge of protein structure prediction. The artificial intelligence system provides structural biologists with powerful new tools for examining the three-dimensional shape of these fundamental building blocks of life. Because proteins underpin every biological process in every living thing, understanding their exact structures is crucial for scientific discovery.
The real-world impact of this open database is already visible among early partners in the scientific community. Researchers utilize these predicted structures to study neglected diseases, investigate antibiotic resistance, and explore methods for recycling single-use plastics. By offering this treasure trove of data openly, AlphaFold heralds a new era for AI-enabled biology and accelerates research across a huge variety of scientific fields.