Back to timeline

AlphaFold 2

DeepMind's AlphaFold 2 solves the protein structure prediction problem at CASP14, achieving accuracy comparable to experimental methods.

Research

What Happened

At the CASP14 (Critical Assessment of protein Structure Prediction) competition in November 2020, DeepMind's AlphaFold 2 achieved a median GDT score of 92.4 out of 100 — a level of accuracy comparable to experimental methods like X-ray crystallography. This effectively solved the protein structure prediction problem, a grand challenge in biology that had remained unsolved for 50 years.

Why It Matters

Protein structure prediction was considered one of the most important open problems in biology. Understanding how proteins fold determines their function, which is fundamental to drug discovery, disease understanding, and biotechnology. AlphaFold 2's breakthrough:

Technical Details