Martin Coulter
LONDON (Reuters) – Google (NASDAQ:) Deepmind has unveiled the third major version of its AlphaFold artificial intelligence model, designed to help scientists develop drugs and fight disease more effectively.
The company made significant progress in molecular biology in 2020, using AI to successfully predict the behavior of microscopic proteins.
Using the latest version of AlphaFold, researchers from DeepMind and its subsidiary Isomorphic Labs, led by co-founder Demis Hassabis, have mapped the behavior of all molecules of life, including human DNA.
The interactions of proteins—from enzymes critical to human metabolism to antibodies that fight infectious diseases—with other molecules are key to drug discovery and development.
DeepMind said the findings, published in the research journal Nature on Wednesday, will reduce the time and money needed to develop potentially life-changing treatments.
“With these new capabilities, we can design a molecule that will bind to a specific site on a protein, and we can predict how strongly it will bind,” Hassabis said at a press briefing Tuesday.
“This is a critical step if you want to develop drugs and compounds that will help diseases.”
The company also announced the release of the “AlphaFold Server,” a free online tool that scientists can use to test their hypotheses before conducting real-world tests.
Since 2021, AlphaFold’s predictions have been freely available to non-profit researchers as part of a database of more than 200 million protein structures, and have been cited thousands of times in other papers.
remove advertising
.
DeepMind said the new server requires less computational expertise, allowing researchers to run tests with just a few clicks of a button.
John Jumper, a senior scientist at DeepMind, said: “It will be very important how much the AlphaFold server makes it easier for biologists—biologists, not computer scientists—to test larger, more complex cases.”
Dr Nicole Wheeler, a microbiology expert at the University of Birmingham, said AlphaFold 3 could significantly speed up the drug development process as “the physical production and testing of biological samples is currently a big bottleneck in biotechnology.”