DeepMind reveals structure of 200 million proteins in a scientific breakthrough | Contemplation

Artificial intelligence has deciphered the structure of almost every protein known to science, paving the way for the development of new drugs or technologies to tackle global challenges like famine or pollution.

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

AI group in November 2020 Contemplation He announced that he had developed a program called AlphaFold and was able to quickly predict this information using an algorithm. Since then, he’s been breaking down the genetic codes of every organism whose genome has been sequenced, and predicting the structures of the hundreds of millions of proteins they collectively contain.

Last year, DeepMind published the protein structures of 20 species. Nearly all of the 20,000 human-expressed proteins – in the open database. Now he’s done and published the predicted structures for more than 200 million proteins.

“In fact, you can think of it as encompassing the entire protein universe. Demis Hassabis, founder of DeepMind, said: “It includes predictive structures for plants, bacteria, animals, and many other organisms, and AlphaFold’s impact on important issues like sustainability, food insecurity and neglected diseases. It opens up great new opportunities for the company,” said the chief executive.

Scientists are already using some of their earlier predictions to help develop new drugs. In May, researchers led by Prof Matthew Higgins at the University of Oxford announced They used AlphaFold’s models to help determine the structure of an important malaria parasite protein and explored where antibodies could bind that could prevent transmission of the parasite.

“Previously, we were using a technique called protein crystallography to find out what this molecule looked like, but we couldn’t deal with it because it’s pretty dynamic and moving,” Higgins said. “When we took the AlphaFold models and combined them with this experimental evidence, everything suddenly made sense. This understanding will now be used to design advanced vaccines that induce the most potent transmission-blocking antibodies.”

Sign up for our free daily newsletter First Edition – every weekday at 7:00 am

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 can be modified to digest and recycle plastics. “It took us quite some time to go through this huge database of structures, but it opened up this new array of three-dimensional shapes we’ve never seen before that can actually break down plastics,” said Professor John McGeehan. work. “There’s a complete paradigm shift. Wherever we go from here, we can really accelerate, and that helps us channel these valuable resources into what matters.”

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

About the author


Leave a Comment