Without Code for DeepMind’s Protein AI, One Lab Wrote Its Own

The Google subsidiary solved a fundamental problem in biology but didn’t promptly share its solution. So a University of Washington team tried to recreate it.

For biologists who study the structure of proteins, the recent history of their field is divided into two epochs: before CASP14, the 14th biennial round of the Critical Assessment of Protein Structure conference, and after. In the decades before, scientists had spent years slowly chipping away at the problem of how to predict the structure of a protein from the sequence of amino acids that it comprises. After CASP14, which took place in December 2020, the problem had effectively been solved, by researchers at the

→ Continue reading at Wired - Science

More from author

Related posts


Latest posts

How Activia went from stodgy digestive aid to trendy wellness brand

Danone launched Activia, the probiotic yogurt that claims to support gut health, in the United States in 2006. Curtis became the brand's spokesperson the...

Police Investigate 2 Shootings in Oakland

Oakland Police are investigating shootings that occurred on Friday, one of which resulted in a homicide. The first shooting occurred at approximately 10:09 p.m....

Tesla posts rare drop in sales in second quarter

The electric automaker reported that completed sales dropped nearly 18%, to about 255,000 vehicles in the second quarter compared to the first three months...