AI group says it has solved one of biology’s ‘grand challenges’

An artificial intelligence group says its program has successfully predicted the structure of nearly every protein known to science – effectively solving one of biology’s ‘grand challenges’ and paving the way for new discoveries and technologies in fields as diverse as medicine, food security and climate science.

DeepMind, an artificial intelligence company owned by Google’s parent company Alphabet, announced on Thursday that its AlphaFold program has expanded its open an online database to include over 200 million protein structures.

The vast catalog now encompasses “the entire protein universe,” Demis Hassabis, CEO of DeepMind, told a press conference – from the sequenced genomes of nearly every organism on the planet.

Proteins are long, complex chains of amino acids that are the building blocks of life. Scientists have long sought to unravel how these strings are elegantly twisted and bent into 3D shapes, because understanding their structure can yield valuable insights into their function. Knowing the specific shape of a protein and how its different molecules interact can, for example, help researchers narrow down potential targets for medical treatments.

AlphaFold prediction for the structure of the F20H23.2 protein.
AlphaFold prediction for the structure of the F20H23.2 protein.DeepMind

AlphaFold’s enhanced database includes protein structures for plants, bacteria, animals and other organisms, according to DeepMind.

These updates provide “new opportunities for researchers to use AlphaFold to advance their work on important issues, including sustainability, food insecurity, and neglected diseases.” Hassabis wrote in a blog post released Thursday on the milestone.

“By demonstrating that AI could accurately predict the shape of a protein down to atomic precision, at scale and in minutes, AlphaFold not only provided a solution to a 50-year grand challenge, it also became the first major point of proof of our founding thesis. : that artificial intelligence can dramatically accelerate scientific discovery and, in turn, advance humanity,” he wrote.

AlphaFold was introduced in 2020, and last year DeepMind wowed the scientific community by unveiling a catalog of structures that included virtually every protein in the human body. the said AlphaFold Protein Structure Databasebuilt in collaboration with the European Molecular Biology Laboratory, included hundreds of thousands of newly predicted protein structures.

The wealth of information is already being used by researchers around the world to study topics ranging from antibiotic resistance to plastic pollution, according to Hassabis.

Researchers at the University of Portsmouth in the UK, for example, announced in July 2021 that they were using the database to help design enzymes for recycling certain types of single-use plastics.

“AlphaFold provides us with an exciting new library of models to design faster, more stable and cheaper enzymes for plastic recycling,” said John McGeehan, director of the Center for Enzyme Innovation at the University of Portsmouth, said in a statement at the time.

Hassabis said DeepMind is working to further expand its database, with a particular focus on applications related to drug development, basic biology research, climate science, quantum chemistry and fusion.

“AlphaFold is a glimpse into the future,” he wrote, “and what might be possible with computational and AI methods applied to biology.”

Leave a Comment