Researchers have managed, using artificial intelligence, to solve a 50-year-long scientific challenge about the structure of proteins that could revolutionize medical research.
Within each cell, thousands of different proteins make up the machinery that keeps all living things alive and wellfrom humans and plants to microscopic bacteria. Almost all diseases, including cancer, dementia, and even infectious diseases like COVID-19, They are related to the way these proteins work.
Because the function of each protein is directly related to its three-dimensional shape, scientists around the world have struggled for half a century to find a fast and accurate method that allows them to discover the shape of any protein.
This Monday the researchers of the 14th Community Experiment for Critical Evaluation of Protein Structure Prediction Techniques (CASP14) announced that a solution to the challenge has been found using artificial intelligence.
Building on the work of hundreds of researchers around the world, an artificial intelligence program called ‘AlphaFold’, created by the London-based DeepMind artificial intelligence laboratory, has been shown to be capable of determining the shape of many proteins. Has done it with a level of precision comparable to that achieved with costly and time-consuming laboratory experiments.
CASP14 is organized by its president, Dr. John Moult, from the University of Maryland, in the United States; Krzysztof Fidelis and Andriy Kryshtafovych, from the University of California Davis; Dr. Torsten Schwede, from the University of Basel and the Swiss Institute of Bioinformatics SIB, in Switzerland, and Dr. Maya Topf, University of London, in the United Kingdom, and from the Center for Structural Systems Biology in Hamburg, Germany.
Dr Moult explains that “proteins are extremely complicated molecules, and their precise three-dimensional structure is key to the many functions they perform, for example, insulin that regulates sugar levels in our blood and antibodies that help us fight infection“.
“Even small rearrangements of these vital molecules can have catastrophic effects on our health,” he adds, “so one of the most efficient ways to understand disease and find new treatments is to study the proteins involved.”
The doctor adds that “there are tens of thousands of human proteins and many billions in other species, including bacteria and viruses, but working the form of just one requires expensive equipment and can take years. Almost 50 years ago,” he recalls. , Christian Anfinsen received a Nobel Prize for demonstrating that it should be possible to determine the shape of proteins based on their amino acid sequence, the individual building blocks that make up proteins. That is why our community of scientists has been working on the biennial CASP challenge “.
Teams participating in the CASP challenge receive the amino acid sequences of a pool of around 100 proteins. As scientists study proteins in the laboratory to determine their shape experimentally, about 100 participating CASP teams from more than 20 countries will try to do the same using computers. The results are evaluated by independent scientists.
Dr. Fidelis explains that “the CASP approach has created an intense collaboration between researchers working in this field of science and we have seen how it has accelerated scientific advances. Since we made the challenge for the first time in 1994 she continues, “ we have seen a succession of discoveries, each of which solved one aspect of this problemSo computer models of protein structures have become progressively more useful in medical research. “
During the latest round of the challenge, DeepMind’s ‘AlphaFold’ program has determined the shape of around two-thirds of the proteins with precision comparable to that of laboratory experiments. The accuracy of ‘AlphaFold’ with most of the other proteins was also high, although not quite at that level.
CASP organizers say this success builds on achievements made in previous CASP rounds, both by the DeepMind team and other participants, and that other teams participating in CASP14 have also produced some high-precision structures during this round.
Dr. Kryshtafovych emphasizes that “What ‘AlphaFold’ has accomplished is truly remarkable and today’s announcement is a victory for DeepMind, but it is also a triumph for team science. The unique and intense way we collaborate with researchers around the world through CASP, and the contributions of many teams of scientists over the years, have led to this breakthrough. “
And he adds: “Being able to investigate the shape of proteins quickly and accurately has the potential to revolutionize the life sciences. Now that the problem has been largely solved for individual proteins, the way is open for developing new methods to determine the shape of protein complexes – collections of proteins that work together to form much of the machinery of life, and for other applications. “
Professor Dame Janet Thornton, director emerita of EMBL’s European Bioinformatics Institute (EMBL-EBI), which is not affiliated with CASP or DeepMind, recalls that “one of the biggest mysteries in biology is how proteins fold to create structures exquisitely unique three-dimensional. The thing, from the smallest bacteria to plants, animals and humans, it is defined and fueled by the proteins that help it function at the molecular level. “
“Until now, this mystery remained unsolved, and determining the structure of a single protein often required years of experimental effort,” he continues. “It is tremendous to see the triumph of human curiosity, effort and intelligence to solve it. This problem. A better understanding of protein structures and the ability to predict them using a computer means a better understanding of life, evolution and, of course, human health and disease. “