AlphaFold 3

Predicts the structure of proteins and their complexes with ligands and nucleic acids

Field
Biology & genomics
Method
Deep learning
Data it takes
sequence
License
CC-BY-NC-SA-4.0 — restricted use

AlphaFold 3 predicts three-dimensional structures for proteins and for complexes: protein with ligand, protein with nucleic acid, protein with protein. Complex prediction is the capability that distinguishes it from AlphaFold 2.

Boltz-2 and Chai-1 predict the same class of structures. Running more than one on a target shows how far a prediction depends on the method rather than the input.

The model parameters are available for non-commercial use. Commercial applications require separate arrangement with the upstream provider.

Upstream project →

Catalog entry last checked 2026-08-17. All models →

Run AlphaFold 3 on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab