Boltz-2

Predicts structures of molecular complexes and estimates binding affinity.

Field
Biology & genomics
Method
Deep learning
Data it takes
sequence
License
MIT

Boltz-2 predicts structures for molecular complexes and estimates binding affinity. Multiple sequence alignments are supplied as input.

AlphaFold 3 and Chai-1 cover the same class of structures. Comparing predictions across them separates results that hold regardless of method from those that do not.

Both the code and the weights are MIT licensed, the most permissive terms of the three.

Upstream project →

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

Run Boltz-2 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