Seeing molecules together.
AlphaFold 3 expanded structural prediction to complexes of proteins and other biomolecules.
Original sources ↓ · Revision history ↓
Demonstrated · source published 2024-05-08
The human problem
Biology depends on interacting molecules, not isolated proteins.
The prior constraint
Different types of molecular complexes often required different modeling tools.
AI’s actual role
A diffusion-based model predicted joint molecular structures.
The documented result
The work improved performance across several interaction benchmarks.
Why it may matter
Researchers gained hypotheses about molecular partnerships.
Limitations
Structural predictions are not proof of binding, biological function, or clinical efficacy.
Unresolved questions
Validate predictions experimentally.
Source history & evidence assessment
- Maturity
- Demonstrated
- Claim confidence
- unassessed
- Event date
- Not recorded
- Source published
- 2024-05-08
- Captured
- Not recorded
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- London, United Kingdom · institution-location
Legacy source check; no named human reviewer is recorded in this projection.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Original sources
Accurate structure prediction of biomolecular interactions with AlphaFold 3 ↗ · paper
Institutions: Google DeepMind & Isomorphic Labs
Explore the underlying question
Related developments
Editorial connections between distinct settings and results; these links do not imply replication.
Revision & correction history
No corrections recorded.