David Baker’s lab shows generative AI can design antibodies. But are they good enough to become drugs?

The promise of us­ing ar­ti­fi­cial in­tel­li­gence to de­sign bi­o­log­ic drugs from scratch is start­ing to look a lot less ab­stract.

This week, sci­en­tists led by David Bak­er at the Uni­ver­si­ty of Wash­ing­ton re­vealed work show­ing that they have cre­at­ed ther­a­peu­ti­cal­ly ac­tive pro­teins from scratch. Us­ing the lab’s gen­er­a­tive AI mod­el they cre­at­ed an an­ti­body that neu­tral­izes a bac­te­r­i­al tox­in and three that tar­get the virus­es re­spon­si­ble for Covid-19, RSV and the flu.

Unlock this article instantly by becoming a free subscriber.

You’ll get access to free articles each month, plus you can customize what newsletters get delivered to your inbox each week, including breaking news.