5 September 2026

DeepMind's AlphaFold predicted protein structures with experimental accuracy

• AlphaFold, an AI system from DeepMind (Google's AI research lab), learned to predict how proteins fold into their three-dimensional shapes.
• Proteins can theoretically form 10 to the 300th power different shapes, making prediction extremely difficult before this system existed.
• AlphaFold's predictions matched the accuracy of laboratory experiments, which traditionally required months of work to determine protein structures.

How it was covered

MindstreamAdam Biddlecombe

DeepMind's AlphaFold AI system achieved a major breakthrough in 2020 by accurately predicting protein structures despite proteins having 10^300 possible theoretical shapes, matching the accuracy of experimental methods.