AlphaFold 2 solves protein structure prediction at CASP14

DeepMind's AlphaFold 2 predicts protein structures with accuracy competitive with experiment, addressing a 50-year-old grand challenge.

What happened and why it matters

At the CASP14 assessment AlphaFold 2 achieved a median GDT score of ~92 across targets, a level organisers judged comparable to experimental methods. Protein folding had been an open problem since the 1970s; this was the first time an AI system effectively closed a recognised scientific grand challenge.

Sources

• AlphaFold: a solution to a 50-year-old grand challenge in biology ↗ Google DeepMind · 30 Nov 2020