AlphaFold (v1) tops the CASP13 protein-structure prediction assessment
DeepMind's first AlphaFold ranked first in the CASP13 blind assessment of protein structure prediction, an early sign that deep learning could crack the protein folding problem.
Key facts
- CASP13 results announced December 2018
- Predicted inter-residue distances with a deep network, then optimized structures
- Nature paper published January 2020
- Precursor to AlphaFold 2, which essentially solved single-chain structure prediction at CASP14 (2020)
Science result
- Field
- biology / structural biology
- Problem
- Protein structure prediction from amino-acid sequence (CASP13 free-modelling targets) (open since 1972)
- Result
- Ranked first of ~100 groups at CASP13 by predicting inter-residue distance distributions with a deep network and folding by gradient descent on the resulting potential.
- AI system
- AlphaFold 1
- Human role
- Human-designed system; predictions made autonomously in a blind assessment
- Verification
- Blind community assessment (CASP13); peer-reviewed in Nature (2020)
- Status
- confirmed
- Why surprising
- A newcomer with no structural-biology track record beat long-established academic groups by a clear margin.
What happened
AlphaFold placed first overall among ~100 groups in the free-modeling category of CASP13.
Why it matters
Marked AI's entry into a grand challenge of biology and set up the 2020 AlphaFold 2 breakthrough.
Changelog
- 2026-09-29: created
- 2026-09-29: added science block (science & math tab)
Related events
Sources (2)
- paperImproved protein structure prediction using potentials from deep learning (Nature, DOI)
- discussionWikipedia: AlphaFold
id: 2018-12-02-alphafold-1-casp13 · updated 2026-09-29 · open in the interactive timeline