DeepMind has discovered the structure of almost every protein known to science

DeepMind publishes a free extensive database with its predictions of the structure of nearly every protein known to science, the company, a subsidiary of Google parent Alphabet, announced today.

DeepMind transformed science in 2020 with its AlphaFold AI software, which produces highly accurate predictions of protein structures — information that can help scientists understand how they work, which can help treat diseases and develop drugs. It began publicly publishing AlphaFold predictions last summer via a database built in collaboration with the European Molecular Biology Laboratory (EMBL). This initial set comprised 98% of all human proteins.

Today, the database extends to more than 200 million structures, “covering nearly every organism on Earth whose genome has been sequenced,” DeepMind said in a statement.

“You can think of it as spanning the whole protein universe,” Demis Hassabis, CEO of DeepMind, said in a press briefing. “We are at the beginning of a new era now in digital biology.”

The database is growing to include over 200 million proteins.
Image: DeepMind

AlphaFold’s protein structures are already widely used by research teams around the world. They are cited in research on things like a malaria vaccine candidate and honey bee health. “We believe AlphaFold is the most significant contribution AI has made to the advancement of scientific knowledge to date,” Pushmeet Kohli, AI lead for science at DeepMind, said in a statement.

Alphabet continues to build on the success of AlphaFold. Alphabet has launched a company called Isomorphic Labs that will direct AI tools towards drug discovery, and while separate from DeepMind, the two companies will collaborate. DeepMind has also set up a lab at the Francis Crick Institute, where researchers can conduct experiments testing information from the AI ​​system.

Having easy access to predicted protein structures gives scientists a boost in research efforts across the scientific landscape – such as those trying to understand how complex processes work in the body or which molecules can be used to target things. like pollution. “With this new addition of structures illuminating nearly the entire protein universe, we can expect more biological mysteries to be solved every day,” said Eric Topol, founder and director of the Scripps Research Translational Institute, in a statement. .

Leave a Comment