# AlphaFold
> **Machine-Evolution Nexus:** [[articles/Digital Darwinism and the Invisible World of Machine Evolution|Digital Darwinism and the Invisible World of Machine Evolution]] places this node within the history and governance of substrate-independent evolution.
**Domain:** AI for Science / Structural Biology
**Doc Type:** Canonical Wiki Node
**Maturity:** Developed
## Definition
AlphaFold is a family of machine-learning systems for predicting biomolecular structure, best known for high-accuracy protein structure prediction.
## Nexus Context
Its models use sequence, structural and evolutionary information; multiple-sequence relationships expose conservation and covariation created by descent. Machine intelligence thus reads an archive evolution produced.
## Evidence Boundary
A prediction includes uncertainty and is not a complete account of dynamics, cellular function or experimental truth. AlphaFold’s architecture and inputs have changed across versions.
## Relationships
[[wiki/Protein Structure Prediction|Protein Structure Prediction]], [[wiki/Multiple Sequence Alignment|Multiple Sequence Alignment]], [[wiki/Evolutionary Covariation|Evolutionary Covariation]], [[wiki/AI for Science|AI for Science]]
## Sources / Provenance
- Jumper et al., _Nature_ 596 (2021); AlphaFold documentation.