In 2020, an artificial intelligence lab called DeepMind unveiled technology that can predict the shape of proteins—the microscopic mechanisms that drive the behavior of the human body and all other living things.
A year later, the lab shared with scientists a tool called AlphaFold, and it generated predicted forms of more than 350,000 proteins, including all proteins expressed by the human genome. He immediately changed the course of biological research. If scientists can recognize the shapes of proteins, they can accelerate their ability to understand diseases, develop new medicines, and otherwise explore the mysteries of life on Earth.
Now DeepMind has published predictions for almost every protein known to science. On Thursday, the London-based lab, which is owned by the same parent company as Google, said it had added more than 200 million predictions to an online database that was freely available to scientists around the world.
With this new release, the scientists behind DeepMind hope to accelerate research into more obscure organisms and usher in a new field called metaproteomics.
“Scientists can now sift through this entire database and look for patterns — correlations between species and evolutionary patterns that might not have been apparent before,” said Demis Hassabis, DeepMind’s CEO, in a phone interview.
Proteins begin as strings of chemical compounds, then twist and fold into three-dimensional shapes that determine how those molecules bond with others. If scientists can determine the shape of a particular protein, they can figure out how it works.
This knowledge is often a vital part of fighting illness and disease. For example, bacteria resist antibiotics by expressing certain proteins. If scientists can understand how these proteins work, they can begin to fight antibiotic resistance.
Previously, determining the shape of a protein required extensive experiments using X-rays, microscopes, and other tools on the lab bench. Now, given the chemical compounds that make up a protein, AlphaFold can predict its shape.
Technology is not perfect. But it can predict a protein’s shape with an accuracy that rivals physical experiments about 63 percent of the time, according to independent benchmark tests. With a forecast, a scientist can verify its accuracy relatively quickly.
Clement Verba, a researcher at the University of California, San Francisco who uses the technology to understand the coronavirus and prepare for similar pandemics, said the technology has “supercharged” that work, often saving months of experimentation. Others have used this tool to fight gastroenteritis, malaria, and Parkinson’s disease.
Technology has also accelerated research beyond the human body, including efforts to improve the health of honey. DeepMind’s expanded database could help an even larger community of scientists reap similar benefits.
Like Dr. Hassabis, Dr. Verba believes the database will provide new ways to understand how proteins behave across species. He also sees it as a way to nurture a new generation of scientists. Not all researchers are well versed in this kind of structural biology; All known protein databases lower the entry bar. “It can bring structural biology to the masses,” said Dr. Verba.