Science

DeepMind reveals the structure of 200 million proteins in a scientific leap forward | deep mind

Artificial intelligence has deciphered the structure of virtually every protein known to science, paving the way for the development of new medicines or technologies to tackle global challenges such as hunger or pollution.

Proteins are the building blocks of life. Made up of chains of amino acids folded into complex shapes, their 3D structure largely determines their function. Once you know how a protein folds, you can begin to understand how it works and how you can change its behavior. Although DNA provides the instructions for making the chain of amino acids, it has been more difficult to predict how they will interact to form a 3D shape, and until recently scientists only had a fraction of the approximately 200 million proteins known to science , decrypted.

In November 2020, the KI group deep mind announced that it has developed a program called AlphaFold that can quickly predict this information using an algorithm. Since then, it has scoured the genetic codes of every organism whose genome has been sequenced, predicting the structures of the hundreds of millions of proteins that together make them up.

Last year, DeepMind published the protein structures for 20 species – including almost all 20,000 proteins expressed by humans – it is open Database. Now it has finished the work and published predicted structures for more than 200 million proteins.

“Essentially, you can imagine that it covers the entire protein universe. It includes predictive structures for plants, bacteria, animals and many other organisms and opens up tremendous new possibilities for AlphaFold to impact important issues such as sustainability, food insecurity and neglected diseases,” said Demis Hassabis, Founder and Founder of DeepMind.

Scientists are already using some of his earlier predictions to help develop new drugs. In May, researchers led by Prof Matthew Higgins at the University of Oxford announced They had used AlphaFold’s models to determine the structure of a key protein in the malaria parasite and to find out where antibodies that could block transmission of the parasite are likely to bind.

“Previously, we had used a technique called protein crystallography to figure out what this molecule looks like, but because it’s quite dynamic and moving, we just couldn’t get a handle on it,” Higgins said. “When we took the AlphaFold models and combined them with this experimental evidence, everything suddenly made sense. This finding is now being used to develop improved vaccines that induce the strongest transmission-blocking antibodies.”

Sign up for First Edition, our free daily newsletter – every weekday morning at 7am BST

AlphaFold’s models are also being used by scientists at the University of Portsmouth’s Center for Enzyme Innovation to identify enzymes from the natural world that could be optimized for the digestion and recycling of plastics. “It took us quite a long time to search through this huge database of structures, but we opened up this whole array of new three-dimensional shapes that we’ve never seen before that can actually decompose plastics,” said Prof. John McGeehan, who lead the study is the work. “There is a complete paradigm shift. From here we can really accelerate where we’re going – and that helps us direct those valuable resources to the things that matter.”

Prof. Dame Janet Thornton, group leader and senior scientist at the European Molecular biology The lab’s European Bioinformatics Institute said: “AlphaFold protein structure predictions are already used in myriad ways. I expect this latest update will unleash an avalanche of new and exciting discoveries in the months and years to come, all thanks to the fact that the data is open to all.”

About the author

admin

Leave a Comment