“New Era in Digital Biology”: AI Reveals Structures of Almost All Known Proteins | Science

What a difference a year makes. Twelve months ago, artificial intelligence (AI) company DeepMind stunned many scientists with the release of expected structures for around 350,000 proteins, part of the work recognized as ScienceThe turning point of the year 2021. Yesterday, DeepMind and its partners went far, far beyond. The company has unveiled the likely structures of nearly every known protein – more than 200 million from bacteria to humans – a surprising achievement for AI and a potential treasure trove for drug development and evolutionary studies.

“We are now releasing the structures for the entire protein universe,” said Demis Hassabis, founder and CEO of DeepMind, at a press conference in London.

The structural reward comes from AlphaFold, one of the new artificial intelligence programs that solved the problem of protein folding, the long-standing challenge of accurately deriving the 3D shapes of proteins from their amino acid sequences. AlphaFold’s newly planned facilities were released yesterday into an existing database through a partnership with the European Molecular Biology Laboratory’s European Institute of Bioinformatics (EMBL-EBI). The database “has provided structural biologists with this powerful new tool where they can search for the 3D structure of a protein almost as easily as a keyword search on Google can be done,” said Hassabis.

Eric Topol, director of the Scripps Research Translational Institute, echoed the amazement of many outside scientists. “AlphaFold is the singular and momentous advance in life sciences that demonstrates the power of AI,” he tweeted. “With this new addition of structures that illuminate nearly the entire protein universe, we can expect more biological mysteries to be solved every day.”

The release of the DeepMind facility is “remarkable,” said Ewan Birney, Deputy CEO of EMBL, at the press conference. “It will get many researchers around the world to think about what experiments they can do now.”

The proteins resolved by AlphaFold come from organisms ranging from bacteria to plants to vertebrates, including mice, zebrafish and humans. Kathryn Tunyasuvunakool, a DeepMind researcher, said that AlphaFold took about 10-20 seconds to make each protein prediction. The company had to work closely with EMBL-EBI, she noted, to figure out how to present the immense number of structures in the database.

DeepMind says more than 500,000 researchers have already used the database since its launch last year. Hassabis predicted a “new era in digital biology” where drug developers could move from AI-predicted protein structures important for any medical condition to using AI to design small molecules that influence those proteins. and thus they cure a disease.

Others are using the facility’s predictions to develop candidate vaccines, probe basic biology questions such as how the so-called nuclear pore complex keeps which molecules enter a cell’s nucleus, or examine the evolution of proteins as life has evolved. for the first time.

Hassabis, however, warned that the release of the facilities is only a starting point. “Obviously there is still a lot of biology and a lot of chemistry, which needs to be done.”

Leave a Comment

Your email address will not be published.