AlphaMissense classifies 89% of all 71 million possible human missense mutations
AlphaMissense (Science, Sept 2023) scored all ~71 million possible single amino-acid substitutions in 19,233 human proteins and classified 89%: 57% likely benign and 32% likely pathogenic. Human experts had classified only 0.1%.
Key facts
- 71M variants scored; 89% classified (57% likely benign, 32% likely pathogenic)
- Human experts had confidently classified only ~0.1% of missense variants
- Predictions released freely; model weights restricted
Science result
- Field
- medicine / human genetics
- Problem
- Interpreting 'variants of uncertain significance' in rare-disease diagnosis
- Result
- Proteome-wide pathogenicity predictions for every possible missense variant.
- AI system
- AlphaMissense
- Human role
- Human-designed; predictions automated
- Verification
- Peer-reviewed in Science; benchmarked against clinical databases
- Status
- confirmed
What happened
Built on AlphaFold-style protein modelling, AlphaMissense predicted which mutations likely disrupt protein function.
Why it matters
It gives clinicians a first-pass interpretation for millions of variants they otherwise could not assess.
Changelog
- 2026-09-29: created
Related events
- AlphaGenome predicts how DNA variants affect thousands of gene-regulation signals from 1 Mb of sequence ★★★
- AlphaGenome Atlas predicts the effect of all ~9 billion possible single-letter human DNA variants ★★★
Sources (2)
- paperAccurate proteome-wide missense variant effect prediction with AlphaMissense (Science)
- officialDeepMind: A catalogue of genetic mutations to help pinpoint the cause of diseases
id: 2023-09-19-alphamissense · updated 2026-09-29 · open in the interactive timeline