DeepMind AI predicts the structure of nearly every known protein

28 Jul 2022

Image: © Christoph Burgstedt/Stock.adobe.com

The expanded protein database could help scientists solve ‘biological mysteries’ and tackle issues from plastic pollution to antibiotic resistance.

Google-owned DeepMind says its AlphaFold AI has made a massive scientific breakthrough by predicting the structure of more than 200m proteins.

The company first shared details of AlphaFold at the end of 2020, when it claimed the AI system had solved the problem of ‘protein folding’.

One year ago, AlphaFold was released as an open-source project and the company created the AlphaFold Protein Structure Database.

DeepMind said its AI system has been accessed by more than 500,000 researchers since then and used to accelerate progress on important problems ranging from plastic pollution to antibiotic resistance.

Now, the database has been expanded to cover nearly every protein known to science. The company said these structures are available for bulk download, to make AlphaFold “even more accessible to scientists around the world”.

Scripps Research Translational Institute founder Eric Topol said AlphaFold is the “singular and momentous advance in life science that demonstrates the power of AI”. He added that the AI system has enabled “massive discoveries”, such as cracking the structure of the nuclear pore complex.

“Determining the 3D structure of a protein used to take many months or years, it now takes seconds,” Topol said. “With this new addition of structures illuminating nearly the entire protein universe, we can expect more biological mysteries to be solved each day.”

DeepMind CEO and founder Demis Hassabis said it has been “inspiring” to see the various ways researchers have used AlphaFold.

He noted that AlphaFold has already been used in projects to understand diseases, protect honey bees, decipher biological puzzles and look “deeper into the origins of life itself”.

“As pioneers in the emerging field of ‘digital biology’, we’re excited to see the huge potential of AI starting to be realised as one of humanity’s most useful tools for advancing scientific discovery and understanding the fundamental mechanisms of life,” Hassabis wrote in a blogpost.

He added that the expanded database will aid countless more scientists in their work and open up completely new avenues of scientific exploration, such as metaproteomics.

10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.

Leigh Mc Gowran is a journalist with Silicon Republic

editorial@siliconrepublic.com