AI Helps Solve a Biology Problem (Much!) Sooner Than Anybody Thought

How do proteins achieve their 3D structure? That’s a head-scratcher scientists have spent fifty years trying to solve. Now, an artificial intelligence (AI) engine has found the solution to this protein-folding problem – decades earlier than expected!

“We have been stuck on this one problem – how do proteins fold up – for nearly 50 years,” says John Moult from the University of Maryland, co-founder of the experiment called Critical Assessment of protein Structure Prediction (CASP). “To see [UK-based AI company] DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts wondering if we’d ever get there, is a very special moment.”

Researchers thought it would take longer than the age of the Universe to sample all possible protein configurations, but the CASP experiment has beaten all odds by being able to predict the structure of proteins with the highest level of accuracy. Now that the biology community knows how proteins fold up, it can better develop drugs and fight diseases. “It has occurred decades before many people in the field would have predicted,” says structural biologist Venki Ramakrishnan, president of the Royal Society.