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.

---

Boltz 2.2 released

Fixes for contact and pocket conditioning which was not fully functional for Boltz2
New potentials
Kernels are now optional to avoid installation issues on non-linux platforms
New security features for use of the MSA server (thanks @papagala!)

---

Boltz + Vina = Boltzina!!

---

Boltz-ABFE

A groundbreaking study introduces Boltz-ABFE, a novel pipeline that combines Boltz-2 structure prediction models with absolute free energy perturbation (ABFE) protocols to estimate small molecule binding affinity without relying on experimental crystal structures. This innovation significantly expands the applicability of FEP in early-stage drug discovery, where suitable crystal structures are often unavailable. The researchers emphasize the importance of careful sequence and biological assembly tailoring when generating co-folded structures for MD simulations. They demonstrate that truncating low-confidence regions and including binding partners can significantly improve model confidence scores and structural validity, leading to more accurate ABFE predictions.

---