However, for many proteins, “we are interested in understanding how their structure is altered by mutations and natural allele variation, and that will not be addressed by this database, ‘ said AlQuraishi. “But of course the field is evolving rapidly, and so I expect the tools to accurately model protein variants will start to emerge soon,” he added.
Peng said the quality of AlphaFold’s predictions may also be inaccurate for rarer proteins with less evolutionary information.
The move is the latest development in DeepMind’s effort into “digital biology,” where “AI and computational methods can help understand and model important biological processes,” Hassabis said. speak. Hassabis also leads a new venture, also owned by Alphabet, called Isomorphic Labs, which is developing AI for drug discovery.
Pushmeet Kohli, head of science AI at DeepMind, says the company has a lot of life science challenges it still wants to solve, such as how proteins work and interact with other proteins.
Hassabis says his dream is for AI to not only help figure out the structure of proteins, but to become “an important part of the discovery process of new drugs and cures.”
