Last year, the artificial intelligence group DeepMind unraveled a mystery that has baffled scientists for decades: exposing the structure of proteins, the building blocks of life. Now after amassing a database ofalmost all human protein structures, the company makes the resource online free for researchers.
The key to understanding our basic biological machinery is its architecture. The chains of amino acids that make up proteins twist and turn to create the most confusing 3D shapes. It is this elaborate form that explains the function of proteins; from enzymes essential for bolism to antibodies that fight infectious attacks.
Despite years From the expensive and expensive lab work that began in the 1950s, scientists have only decoded the structure of a fraction of human proteins. DeepMind's AI program AlphaFold predicted the structure of almost all of the 20,000 proteins expressed by humans . In an independent benchmark test that compared the predictions to known structures, the system was able to predict the shape of a protein to a good level 95% of the time.
DeepMind, which has partnered with the European Institute of Bioinformatics at the European Laboratory for Molecular Biology (EMBL-EBI), hopes the database will help researchers analyze how life works at home. 'atomic scale by unboxing the device that causes certain diseases, to advance personalized medicine, create more nutritious cultures, and develop "green enzymes" that can break down plastic.
Collaboration in recent months with scientists working on a range of projects - from the diseases that disproportionately affect the poorest regions of the world to the study of antibiotic resistance or the biology of the virus that causes Covid - alreadystarted.
"Applications are actually limited only by our imagination - but on 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, Executive Director of EMBL.
" This understanding means that we can be better equipped to unravel the molecular mechanisms of life and accelerate our efforts to protect and treat human health, as well as the health of our planet, and making this open access tool will accelerate the power of research, discovery and of innovation for scientists around the world. "
The ability of AlphaFold to predict protein structure with precision vertigineuse was unveiled at the “protein olympics” biennial last year. Participants were given the amino acid sequences of around 100 proteins and were challenged to determine them. AlphaFold not only eclipsed the performance of other computer programs, but also achieved precision analogous to that of labor-intensive laboratory methods.
"I have almost fell out of my chair out of sheer excitement and amazement that this long-standing problem with how proteins fold up, ”said Professor Ewan Birney, Director of EMBL-EBI, after the results were first presented in November .
"This dataset is kind of like the target human genome … and it 's this dataset where we start new science that we were notnot able to do before. I am very excited to start walking this road. "