Seeing molecules together.
AlphaFold 3 expanded structural prediction to complexes of proteins and other biomolecules.
- Maturity
- Demonstrated, stage 3 of 4
- Support
- 1 source · paper
- Evidence detail
- How we know ↓
Biology depends on interacting molecules, not isolated proteins.
Different types of molecular complexes often required different modeling tools.
A diffusion-based model predicted joint molecular structures.
What was shown, and what wasn’t
Shown
The work improved performance across several interaction benchmarks.
Not shown · limits
- Structural predictions are not proof of binding, biological function, or clinical efficacy.
Bright editorial interpretation
Researchers gained hypotheses about molecular partnerships.
Still open
Validate predictions experimentally.
How we know1 source · checked 2026-09-05 · no corrections
Original sources
Institutions: Google DeepMind & Isomorphic Labs
- Maturity
- Demonstrated
- Source published
- 2024-05-08
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- London, United Kingdom · institution-location
Bright compared this account with the linked original and supporting sources and kept reported, budgeted, projected, and observed claims distinct. Bright did not independently audit the underlying records.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Revision & correction history
No corrections recorded.
Keep exploring
Explore the shared question in another setting. These connections do not imply replication.