Last year, the artificial intelligence group DeepMind solved a mystery that has puzzled scientists for decades: uncovering the structure of proteins, the building blocks of life. Now, having accumulated a database of almost all human protein structures, the company makes the resource available online free of charge for researchers to use.
The key to understanding our basic biological machinery is its architecture. The chains of amino acids that make up proteins twist and twist to create the most confusing three-dimensional shapes. It is this elaborate form that explains the function of proteins; from enzymes that are crucial for metabolism to antibodies that fight infectious attacks.
Despite years of burdensome and expensive laboratory work that began in the 1950s, scientists have only decoded the structure of a fraction of human proteins. DeepMind’s artificial intelligence program AlphaFold has predicted the structure of almost all of the 20,000 proteins expressed by humans. In an independent benchmark test that compared predictions to known structures, the system was able to predict the shape of a protein to a good standard 95% of the time.
DeepMind, which has partnered with the European Bioinformatics Institute (EMBL-EBI) of the European Molecular Biology Laboratory, hopes the database will help researchers analyze how life works at the atomic scale by unpacking the apparatus that powers some diseases, advance the field of personalized medicine, create more nutritious crops, and develop “green enzymes” that can break down plastic.
Collaboration in recent months with scientists working on a variety of projects, from diseases that disproportionately affect the poorest parts of the world to studying antibiotic resistance or the biology of the virus that causes Covid, has already started.
“The applications are actually limited only by our imagination, but at a more fundamental level, the AlphaFold database will increase our understanding of how proteins work and their role in fundamental life processes,” said Professor Edith Heard, CEO. of the EMBL.
“This understanding means that we can be better equipped to unravel the molecular mechanisms of life and accelerate our quests to protect and treat human health, as well as the health of our planet, and making this tool open access will accelerate the power of research, discovery and innovation for scientists around the world. “
AlphaFold’s ability to predict protein structure with breakneck precision was unveiled at last year’s biennial “protein Olympics.” Participants were given the amino acid sequences of approximately 100 proteins and challenged to solve them. AlphaFold not only outshined the performance of other software, it achieved precision analogous to laborious laboratory methods.
“I almost fell out of my chair with excitement and amazement that this age-old problem of how proteins fold has been solved,” said Professor Ewan Birney, director of EMBL-EBI, after the results were first presented. time in November.
“This dataset is more like the human genome … and it is this dataset where we start some new bits of science that we couldn’t do beforehand. I am very excited to start walking down that path. “
George is Digismak’s reported cum editor with 13 years of experience in Journalism