iiinova — where your digital self keeps evolving

If you think this seems cool and useful, checkout our updated preprint and GitHub: www.biorxiv.org/content/10.6... github.com/jproney/Prot...

biorxiv.org

040

Additionally, we conducted an initial study on protein folding pathways! We ran direct Langevin simulations on Protein G, NuG2, and Protein L. We found that Protein G folds through the C terminus while NuG2 and Protein L are shifted toward the N terminus, which is consistent with experiment!

1112

This difference is especially pronounced for proteins with few homologues, such as de novo proteins.

150

ProteinEBM-x gives a huge boost in performance, both in ranking and stability prediction. In particular, ProteinEBM-x achieves state-of-the-art results at zero-shot stability ranking in ProteinGym, outperforming PLMs with over 15x the parameters.

140

Diffusion models actually learn a series of time-indexed energy landscapes, which are corrupted with different amounts of noise. The ranking ability of ProteinEBM peaked slightly above t=0. Inspired by this finding we trained an "expert" model only on low time levels, which we call ProteinEBM-x.

151

To recap our original method, we used denoising score matching to train an energy-based model that approximates the free energies of protein conformations. We found that this worked well for ranking protein structures and predicting the effects of mutations on stability.

150

Brooke Fitzwater, PhD (she/her) 🐟🪱🏳️‍🌈♾️ @oceanfilly.bsky.social · 25/01/2026

I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou @sokrypton.org!

14111

Reposted by jproney

They are kidnapping young children and murdering citizens in the street in broad daylight and lying to us when we can see what they are doing. This will be in textbooks and generations from now will ask us what we stood for. 🖕🧊

0398

jproney @jproney.bsky.social · 23/12/2025

But for the CA representation used by our EBM, it seems like the entropy due to local backbone and side chain fluctuations might be much more tractable?

100

jproney @jproney.bsky.social · 23/12/2025

I might be wrong, but it seems like the difficulty of learning chain entropy would be very related to the level of coarse graining. If you’re looking at a reaction coordinate like fraction of native contacts, each macrostate contains a massive number of chain confrontations

100

jproney @jproney.bsky.social · 23/12/2025

Thanks for the insight! I’ll definitely keep this is mind for future analyses. For what it’s worth i might caution against interpreting the decoy ranking plot as a “folding landscape,” since all those decoys are basically folded, just in wrong conformations.

200

jproney @jproney.bsky.social · 17/12/2025

Also let me know if any of that sounds wrong! Feedback from someone with your level of MD/StatMech knowledge is very much appreciated 🙂

100

jproney @jproney.bsky.social · 17/12/2025

Good question! Ideally it should be a free energy because it learns the PMF over coarse-grained states (at the temperature of the MD data), integrating out fine-grained DOFs. To test if this is true in practice maybe we could examine systems where entropy over the fine DOFs plays a big role?

jproney @jproney.bsky.social · 12/12/2025

As a bonus, here's a video of ProteinEBM folding up the fast-folder NTL9, rendered in stunning 2D by py2Dmol from @sokrypton.org! We hope models like ProteinEBM can serve as a step toward solving the "real" protein folding problem.

1365

GitHub - jproney/ProteinEBM

If this sounds interesting to you, check out the preprint on bioRxiv: www.biorxiv.org/content/10.6.... All of our code and model weights are available at github.com/jproney/Prot.... Thanks for listening!

github.com

Contribute to jproney/ProteinEBM development by creating an account on GitHub.

030

This research builds on my undergraduate work using AlphaFold2 for structure scoring. Compared to AF2Rank, ProteinEBM is more efficient and versatile, and has a firmer theoretical foundation. We see ProteinEBM as an important step toward developing physically-grounded ML models for protein science.

And finally, we combined large-scale ProteinEBM sampling with AF2Rank to create an ab initio structure prediction protocol that beats massive sampling from both AlphaFold2 and AlphaFold3 in the MSA-free regime.

140

When used for sampling fast-folding proteins, ProteinEBM produces energy funnels with minima very close to the native structures

ProteinEBM can also rank the effects of mutations on stability, with accuracy comparable to sequence-supervised models like ProteinMPNN, despite not being trained to predict sequences.

ProteinEBM performs very well at ranking the correctness of candidate protein structures, and compares favorably to Rosetta in terms of ranking correlations.

110

Introducing ProteinEBM: a fast, transferable Energy-Based Model for protein conformations. ProteinEBM is trained using energy-based score matching. After training on sequence-structure pairs and MD data, the model energy should match the log data density (i.e., the free energy landscape)!

110

A very general approach to protein modeling is the development of energy functions that describe protein conformational landscapes. With a good enough energy, you can use optimization to predict structures, simulate dynamics, estimate conformational preferences, predict stabilities, and more.

110