DeepMind uncovers structure of 200m proteins in scientific leap forward

Artificial intelligence has been able to decipher the structure of almost every molecule of science, paving the way for the development of new medicines or technologies to tackle global challenges.

Life is made up of the building blocks of the human body. Their 3D structure is what determines their function. You can understand how aProtein folds up once you know how it works. Until recently, scientists had only deciphered a fraction of the 200m or so proteins known to science.

The artificial intelligence group DeepMind announced in November of 2020 that it had developed a program called AlphaFold that could quickly predict this information. Since then, it has been crunching through the genetic codes of all the organisms that have had their genomes mapped.

A year ago, DeepMind published the structures for 20 species, including nearly all 20,000 humans, on an open database. Predicted structures for over 200m are now available.

You can think of it as covering the whole of theProtein universe. It opens up huge new opportunities for AlphaFold to have an impact on important issues, such as food security, and neglected diseases.

Some of its earlier predictions are being used by scientists. In May, researchers led by Prof Matthew Higgins at the University of Oxford announced they had used AlphaFold's models to help determine the structure of a key malaria parasite protein.

Due to the molecule being dynamic and moving around, we just couldn't get to grips with it. It all made sense when we combined the AlphaFold models with the experimental evidence. Improved vaccines which induce the most potent transmission- blocking antibodies will be designed using this insight.

Scientists at the University of Portsmouth's Centre for Enzyme Innovation are using AlphaFold's models to identify enzymes from the natural world that can be modified to digest and recycle plastic. It took us quite a long time to go through this massive database of structures, but we were able to open this whole array of new three-dimensional shapes we hadn't seen before. A paradigm shift is happening. We can really speed up where we go from here.

Prof Dame Janet Thornton said that AlphaFold predictions are being used in a lot of ways. Thanks to the fact that the data are open for all to use, I expect that this latest update will cause an explosion of new discoveries in the months and years to come.