Boltz-1 is a great tools from MIT, but, as said the creators of tool: "often failed to fully respect physical laws. This led to issues like distorted internal geometries, wrong chirality, steric clashes, and even overlapping chains".
So, now, they create Boltz-1X that solves these problems and have a lot of new features (like Cuda kernels or prediction of cyclic peptides)

---

Some weeks after Boltz 1-X, they released Boltz 2 (under fully-MIT permissive license with the community)

Binding affinity prediction for protein-small molecules, closing the gap with free energy perturbation methods at 1000x speedup!
More user control via structural templates (including mutlimeric), contact and method conditioning.
Improved performance on antibodies and other modalities
Improved modeling of ensembles when using MD conditioning

---

From admins:

With Boltz team we are pushing to release to the public repo all the additional features introduced in the paper like contact and pocket conditioning, screening automation, evals scripts and the training code&data. Expect several updates coming in the the next few days!

---

don't write here for nothing. So called admins don't read these messages. you should start your own project where you can use new cool features. Right?

Does this project even use CPU instruction set extensions like AVX? There was a discussion about them on Ralph@home once, but that project is dead.

don't write here for nothing. So called admins don't read these messages. you should start your own project where you can use new cool features. Right?

If you're speaking to me, i'm NOT writing scientific news for Admins. They are "on the field", so they know the advancement of bio-computational research.
I'm writing for volunteers who, maybe, are interested in these things.

---