AlphaFold 2 solves protein structure prediction at CASP14
AlphaFold 2 achieved a median GDT score of 92.4 at CASP14, accuracy competitive with experimental methods, widely seen as solving the 50-year-old protein folding problem for single chains.
Key facts
- CASP14 results announced 30 November 2020
- Median GDT of 92.4 across all targets
- Nature paper and open-source code published July 2021
- AlphaFold Protein Structure Database (with EMBL-EBI) launched July 2021; expanded to 200M+ structures in 2022
- Led to the 2024 Nobel Prize in Chemistry for Hassabis and Jumper
Science result
- Field
- biology / structural biology
- Problem
- Protein folding / structure prediction problem (open since 1972)
- Result
- Median GDT_TS of 92.4 across CASP14 targets — accuracy comparable to experimental structures for most single-chain proteins; later used to predict 200M+ structures.
- AI system
- AlphaFold 2
- Human role
- Human-designed system; predictions autonomous in blind assessment
- Verification
- Blind community assessment (CASP14); peer-reviewed in Nature (2021); widely experimentally corroborated
- Status
- confirmed
- Why surprising
- CASP co-founder John Moult said the 50-year-old problem had been 'in a sense solved' — years or decades earlier than most structural biologists expected.
What happened
Using an attention-based architecture (Evoformer) trained on known structures, AlphaFold 2 predicted 3D protein structures from amino-acid sequence with near-experimental accuracy.
Why it matters
The clearest case of AI producing a major scientific breakthrough; used by millions of researchers and recognized with a Nobel Prize.
Changelog
- 2026-09-29: created
- 2026-09-29: added science block (science & math tab)
Related events
- AlphaFold (v1) tops the CASP13 protein-structure prediction assessment ★★★★
- AlphaFold 3 predicts structures and interactions of all life's molecules ★★★★
- Nobel Prize in Chemistry for protein design and AlphaFold ★★★★★
- FT: Google DeepMind has broken up its Nobel-winning AlphaFold team; Jumper, Adler and Pritzel now at Anthropic ★★★
Sources (3)
- officialAlphaFold: a solution to a 50-year-old grand challenge in biology (DeepMind)
- paperHighly accurate protein structure prediction with AlphaFold (Nature, DOI)
- officialAlphaFold Protein Structure Database
id: 2020-11-30-alphafold-2 · updated 2026-09-29 · open in the interactive timeline