AlphaFold predicts nearly all known proteins

The AlphaFold algorithm from DeepMind has predicted the structures of more than 200 million proteins. This accounts for nearly all protein molecules known to science, found in plants, bacteria, and animals.

According to the developers, thanks to AlphaFold’s open-source code, scientists around the world can use it in their research. In July 2021 the algorithm decoded 350,000 3D structures. Since then thousands of scientists have used the system, according to DeepMind.

More than 500,000 researchers and biologists have used the database to view more than 2 million structures. And these predictive structures have helped scientists make new brilliant discoveries,

said DeepMind founder and CEO Demis Hassabis.

For example, in April 2022, Yale University scientists used the AlphaFold database to develop a new highly effective malaria vaccine. In July 2021, researchers at the University of Portsmouth turned to the system to design enzymes that will tackle environmental pollution from single-use plastics.

This has moved us forward by a year, if not two,

said John McGihan, director of the Portsmouth Center for Enzyme Innovation.

DeepMind also said that over the past year scientists published more than 1,000 papers using AlphaFold. In the future, researchers plan to deploy the algorithm to create drugs against less-studied but widespread tropical diseases such as лейшманиоза.

In July 2021, DeepMind introduced AlphaFold, which had modeled 20,000 human protein structures. The developers opened access to the program to researchers around the world.

In November, Alphabet founded Isomorphic Laboratories, which uses AI to search for new kinds of medicines.

In July 2022, MIT developed the deep learning model EquiBind, which binds molecules to proteins 1,200 times faster than alternatives in drug design.

Subscribe to ForkLog in Telegram: ForkLog AI — all the news from the world of AI!