Artificial intelligence has understood the structure of every protein known to science, paving the way for the development of new drugs or technologies to tackle global challenges such as famine 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 to change its behavior. Although DNA provides the instructions for building a chain of amino acids, predicting how they interact to form a 3D pattern is tricky, and until recently, scientists understood only a fraction of the 200m or so proteins known to science.
In November 2020, the AI team deep mind announced that it has developed a program called AlphaFold that can quickly predict this information using an algorithm. Since then, its genome has been crunched through the genetic codes of each organism sequenced, predicting the structures of the hundreds of millions of proteins they collectively contain.
Last year, DeepMind published protein structures for 20 species — including Nearly 20,000 proteins are expressed by humans – In the open position database. Now it has completed the work and published the predicted structures for more than 200m proteins.
“Essentially, you can think of it as covering the entire protein universe. It includes predictive structures for plants, bacteria, animals and many other species, opening up huge new opportunities for Alphafold on critical issues like sustainability, food insecurity and neglected diseases,” said Demis Hassabis, Chief Executive.
Scientists are already using some of its earlier predictions to develop new drugs. In May, researchers led by Professor Matthew Higgins at the University of Oxford declared They used alphafoldin models to determine the structure of a key malaria parasite protein, and to identify where antibodies that could block the spread of the parasite might bind.
“Previously, we used a technique called protein crystallography to figure out what this molecule looks like, but because it’s so dynamic and moving, we couldn’t capture it,” Higgins said. “When we took the alphafold models and combined them with this experimental evidence, it suddenly made sense. This insight can now be used to design improved vaccines that induce more potent transfer-blocking antibodies.
Sign up for the first edition of our free daily newsletter – every week at 7am BST
Alphafold’s samples are being used by scientists at the University of Portsmouth’s Center for Enzyme Discovery to identify enzymes from the natural world that could be adapted to digest and recycle plastic. “It took us a long time to wade through this huge structural database, but we opened up a whole series of new three-dimensional shapes that can break down plastic,” said lead author Professor John McKeehan. Work. “There’s been a complete paradigm shift. We can really accelerate where we go from here — and it helps direct these precious resources to things that matter.
Professor Dame Janet Thornton, Group Leader and European Molecular Senior Scientist Biology The lab’s European Bioinformatics Institute said: “Alphafold protein structure predictions are already used in countless ways. I expect this latest update to trigger an avalanche of new and exciting discoveries in the coming months and years, thanks to the data being openly available for everyone to use.”

“Lifelong social media lover. Falls down a lot. Creator. Devoted food aficionado. Explorer. Typical troublemaker.”