AlphaFold 2 solves protein structure prediction at CASP14
Result confirmed
Importance: historic (5 of 5)The takeaway
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.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- Historic (5 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
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
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.
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 3 primary
Primary
- AlphaFold: a solution to a 50-year-old grand challenge in biology (DeepMind)deepmind.google, official
- Highly accurate protein structure prediction with AlphaFold (Nature, DOI)doi.org, paper
- AlphaFold Protein Structure Databasealphafold.ebi.ac.uk, official
Changes
- Added science block (science & math tab)
- Filed