In July 2022, we released AlphaFold protein structure predictions for nearly all cataloged proteins known to science. Read the latest blog here.
Today, I am very proud and excited to announce that DeepMind is making a significant contribution to humanity’s understanding of biology.
When we announced AlphaFold 2 last December, it was hailed as a solution to a 50-year-old problem of protein folding. Last week, we published the science paper and source code explaining how we built this highly innovative system, and today we’re sharing high-quality predictions for the shape of every protein in the human body, as well as for the proteins of 20 additional organisms that scientists rely on for their research.
As researchers search for cures for disease and seek solutions to other big problems facing humanity — including antibiotic resistance, microplastic pollution, and climate change — they will benefit from new insights into the structure of proteins. Proteins are like tiny, tiny biological machines. In the same way that the structure of a machine tells you what to do, so the structure of a protein helps us understand its function. Today, we share a collection of information that amplifies humanity’s understanding of human proteins, revealing the protein structures found in 20 other organisms, from Escherichia coli to yeast, and from fruit fly to mouse.
This will be one of the most important datasets since the mapping of the human genome.
Ewan Birney, Deputy General Manager of EMBL and Director of EMBL-EBI
As a powerful tool that supports the efforts of researchers, we believe that this is the most important contribution that artificial intelligence has made to the development of scientific knowledge to date, and is a great example of the benefits that artificial intelligence can bring to humanity. These insights will support many exciting future developments in our understanding of biology and medicine. Thanks to five years of hard work and a lot of ingenuity from the AlphaFold team, and working closely over the past few months with our partners at EMBL’s European Bioinformatics Institute (EMBL-EBI), we are able to share this huge and valuable resource with the world.
This latest work builds on announcements we made last December, at the CASP14 conference, when DeepMind unveiled a radical new version of our AlphaFold system, which rating regulators recognized as a solution to a 50-year-old great challenge to understand. The three-dimensional structure of proteins. Determining protein structures experimentally is a time-consuming and painstaking process, but AlphaFold has demonstrated that AI can accurately predict the shape of a protein, on scales and in minutes, down to atomic precision. At CASP, we have pledged to share our methods and provide broad access to this body of knowledge.
This month we have completed an enormous amount of hard work to meet this commitment. We have published two peer-reviewed papers in nature (1,2) and the open source AlphaFold code. Today, in partnership with EMBL-EBI, we are extremely proud to launch the AlphaFold protein structure database, which presents the most complete and accurate picture of human proteins to date, more than doubling humanity’s accumulated knowledge of high-resolution human protein structures.
In addition to human proteins (about 20,000 proteins expressed in the human genome), we provide open access to the proteins of 20 other biologically important organisms, totaling more than 350,000 protein structures. Research into these organisms has been the subject of countless research papers and several major breakthroughs, and has resulted in a deeper understanding of life itself. In the coming months we plan to expand coverage significantly Almost every sequence protein known to science – Over 100 million structures covering most of the UniProt reference database. It’s a true protein calendar for the world. The system and database will be updated periodically as we continue to invest in future improvements to AlphaFold.
Most excitingly, in the hands of scientists around the world, this new protein calendar will enable and accelerate research that will advance our understanding of these building blocks of life. Already, through our early collaborations, we’ve seen promising signals from researchers using AlphaFold in their work. For example, the Drugs for Neglected Diseases Initiative (DNDi) has advanced its research into life-saving treatments for diseases that disproportionately affect poorer parts of the world, and the University of Portsmouth’s Center for Enzyme Innovation (CEI) is using AlphaFold to help engineer faster enzymes to recycle some plastics. Most polluting single use. For those scientists relying on experimental protein structure determination, AlphaFold’s predictions have helped accelerate their research. As another example, a team at the University of Colorado Boulder found promise in using AlphaFold’s predictions to study antibiotic resistance, while a group at the University of California San Francisco used it to increase their understanding of the biology of SARS-CoV-2. And this is just the beginning of what we hope will be a revolution in structural bioinformatics. With AlphaFold in the world, there is a treasure trove of data now waiting to be funneled into future developments.
AlphaFold opens up new research frontiers, and it is inspiring to see a powerful, cutting-edge AI that enables work on diseases that are concentrated almost exclusively in poor populations.
Ben Berry, Open Innovation Leader in Drug Discovery for Neglected Diseases (DNDi)
For the AlphaFold team at DeepMind, this work represents the culmination of five years of tremendous effort, including having to creatively overcome several difficult setbacks, resulting in a host of complex new algorithmic innovations that were all required to finally solve the problem. It builds on the discoveries of generations of scientists, from the early pioneers of protein imaging and crystallography, to the thousands of prognosticators and structural biologists who have spent years experimenting with proteins since then. Our dream is that AlphaFold, by providing this fundamental understanding, will assist countless scientists in their work and open up entirely new avenues of scientific discovery.
What took us months and years to do, AlphaFold was able to do in a weekend.
– Professor John McGeehan, Professor of Structural Biology and Center Director, Center for Enzyme Innovation (CEI) at the University of Portsmouth
At DeepMind, our thesis has always been that AI can greatly accelerate breakthroughs in many areas of science, and thus the progress of humanity. We have created AlphaFold and the AlphaFold Protein Structure Database to support and advance the efforts of scientists around the world in the important work that they do. We believe that artificial intelligence has the potential to revolutionize how science works in the 21st century, and we eagerly await discoveries that may help the scientific community unlock the future.
To learn more, head to Nature to read our peer-reviewed papers describing our complete method and the human proteome. You can read more about it in our tech blog. If you’d like to explore our system, here’s the open source code for AlphaFold and Colab’s notebook to run single sequences. To explore our structures, EMBL-EBI, the world leader in biological data, hosts them in a searchable, open database free for all.
We’d love to hear your feedback and understand how AlphaFold has been helpful in your search. Share your stories at alphafold@deepmind.com.