`atomworks.ml` on the other hand offers advanced dataset featurization and sampling for deep learning workflows, all operating on the canonical AtomArray object from @biotite_python so that all transforms are traceable and generalizable between models. 4/6

AtomWorks has two main components: atomworks.io takes a file (cif, sdf, ...) and does parsing, cleaning and more. You can also look at your structures in a notebook or via PyMol thanks to pymol-remote, so you can directly inspect if your code does what you want! 3/6

(7/7)
We also want to give a shout-out to [Biotite](www.biotite-python.org/latest/), which is the bedrock of our approach. Biotite has made our framework vastly more performant and flexible. We're excited for what's next!

(6/7)
Frank DiMaio both directed and carried the team - he deserves the most recognition

(5/7)
It's been the pleasure my life to work alongside @simonmathis.bsky.social, @rkrishna3.bsky.social, @kinasekid.bsky.social , and so many other unbelievably talented individuals on this project. And extra credit to @kdidi.bsky.social for jumping into the frenzy to bring this work across the line

(4/7)
There's no reason every researcher in the BioML space re-invents the wheel ever time they train a structure-based model. The complexity of loading and annotating biomolecular data for machine learning applications should be done once, and done right — that was our goal with AtomWorks

(3/7)
We're also thrilled to release AtomWorks, which we used as the foundation for not only RF3, but also RF2AA, LigandMPNN, ProteinMPNN, and a design model — all by just swapping out a handful of modular components we call Transforms (just like Torchdata, for those familiar)

(2/7)
We're thrilled to share RF3 fully open-source with the community — it handles chirality better than any other model, it supports arbitrary atomic templating (which we included at train-time), and it narrows the open-source gap to AF3