Google’s DeepMind AI cracks 3D structure of nearly all proteins known to science in major breakthrough

Sign up to our free weekly IndyTech newsletter delivered straight to your inbox Sign up to our free IndyTech newsletter Sign up to our free IndyTech newsletter SIGN UP I would like to be emailed about offers, events and updates from The Independent. Read our privacy policy Google’s DeepMind AI has predicted the 3D structure of nearly all proteins known to science, an advance that can lead to a better understanding of rare genetic diseases, and also help develop new vaccines and drugs. DeepMind announced on Thursday that its AlphaFold AI has cracked the structure of over 200 million proteins – the entire “universe of proteins” known to scientists. With the release of AlphaFold in 2020, over half a million researchers across the world have used the AI application to crack the structure of “nearly all catalogued proteins known to science.” AlphaFold was exposed to about 100,000 known protein folding structures – already cracked by scientists – from which the AI has learned to decode the rest, the company says. The latest advance, according to DeepMind, will expand the AlphaFold Protein Structure Database from nearly 1 million structures to over 200 million structures, with the potential to accelerate progress on important real-world problems “ranging from plastic pollution to antibiotic resistance.” In the new update, DeepMind has added the predicted structures for proteins found in plants, bacteria, animals, and other organisms, which may help solve important global issues, “including sustainability, food insecurity, and neglected diseases,” the company noted in a statement.