Boltz v0.4.0 is here! Today, we’re releasing our full data processing pipeline, making it easier than ever to build on top of Boltz. This release also includes our evaluation code and new results. Oh, and also pocket conditioning :)
Comments
Log in with your Bluesky account to leave a comment
The full data processing pipeline and associated documentation can be found here: https://github.com/jwohlwend/boltz/blob/main/docs/training.md. We’re grateful to AWS Open Data for generously hosting the data. We’re excited to see the many ways that the community will build on top of Boltz!
You can now also add prior knowledge to the predictions via pocket conditioning. Simply indicate a binder chain (small molecule, protein, …) and one or more residues it binds to on other chains! Full documentation for predictions at: https://github.com/jwohlwend/boltz/blob/main/docs/prediction.md
Finally, to encourage transparent benchmarking in the community, we released a full set of evaluations on PDB test set and CASP15 for Boltz-1, Chai-1 and AlphaFold3! All the instructions at https://github.com/jwohlwend/boltz/blob/main/docs/evaluation.md
Comments
our updated manuscript: https://gcorso.github.io/assets/boltz1.pdf
and join the Boltz Slack community: https://join.slack.com/t/boltz-community/shared_invite/zt-2w0bw6dtt-kZU4png9HUgprx9NK2xXZw
Merry Shipmas from the Boltz team with @jeremywohlwend.bsky.social and Saro! 🤗🎄🎅