Episode 13 Tortured Protein Department Podcast: Long Live with @fraserlab.com! Catch my big news with the @diffuseproject.bsky.social, psycho travel stories, April Fools pranks, and AI grad students. podcasts.apple.com/us/podcast/l...

The DiffUSE Project Unlocking Protein Dynamics

I'm ecstatic to share that I'm joining the @diffuseproject.bsky.social (diffuse.science) full-time as Scientific Program Director at @asterainstitute.bsky.social .

🙏 author email notifications. This will lead us back to posting directly on site! we had stopped using disqus in favor of @prereview.bsky.social

I almost guessed it based on the two arms with what I presume are unusual detectors - should have been more bold!!!

ESS!!! Basically part of the larger maxiv ecosystem.

Oak ridge?

💎

Max iv?

Code?

Excited to share Sampleworks led by @karsonchrispens.bsky.social with @diffuseproject.bsky.social. It's a modular framework connecting structure predictors to experimental data and guidance methods. Swap predictors or guidance methods. All open and made to be built upon. t.co/fvNHH3gfVu

great preprint Alex!!!

I agree - we have been trying to assess how different models do in a challenging DMS test case (+/- different inhibitors - pmc.ncbi.nlm.nih.gov/articles/PMC...) - we use a very stringent test set that held out positions and residues, finding that most models do not perform well...

New nonprofit launches with at least $500 million to modernize scientific process for AI era A new nonprofit called Radial is launching with at least $500 million to modernize the scientific process for the AI era.

Radial is live! A new organization at @asterainstitute.bsky.social bringing together structural biologists, engineers, and ML scientists to redesign how we do science. @statnews.com has the story: www.statnews.com/2026/03/11/r...

Congrats!!!

Great read, one small correction - pretty sure it's Dan's wife Marian who was nicknamed "Bunny" not Dan Koshland...

Science-ing Through the Lightning Strikes Podcast Episode · The Tortured Proteins Department · February 22 · 1h 5m

12th episode (full year!) of the Tortured Protein Department Podcast with@fraserlab.com!

podcasts.apple.com/us/podcast/s...

Do we need a go-fund-me for a Claude Code Max subscription for @jeremymberg.bsky.social to unlock even more valuable reports?

GitHub - GrotjahnLab/surface_morphometrics: Morphometrics for Membrane Surfaces Segmented from Cryo-ET or other volumetric imaging. Morphometrics for Membrane Surfaces Segmented from Cryo-ET or other volumetric imaging. - GrotjahnLab/surface_morphometrics

I've been working on Surface Morphometrics for a new version (coming soon), and made some significant (AI-assisted) performance improvements, especially in pycurv (20-50x!). If you've had technical issues or just felt like it was too slow, give it another try! #teamtomo github.com/GrotjahnLab/...

AI is not a peer, so it can’t do peer review If we still believe that science is a vocation grounded in argument, curiosity and care, we can’t delegate judgement to machines, says Akhil Bhardwaj

'to treat peer review as a throughput problem is to misunderstand what is at stake. Review is not simply a production stage in the research pipeline; it is one of the few remaining spaces where the scientific community talks to itself.' 1/3

On the plus side - hallucination is dramatically lower now than a year ago. In the downside- peer review should be fun an a mental exercise (two things you should never outsource to AI)

Post your reviews! And only review preprints - helps with this: fraserlab.com/reviews/

Back to December Podcast Episode · The Tortured Proteins Department · 01/27/2026 · 52m

New TTPD with @fraserlab.com! We chat about travels, new preprints, and vibe coding.

podcasts.apple.com/us/podcast/b...

open.spotify.com/episode/6QCR...

🤯

New Preprint!! We show that binding entropy can be quantitatively predicted from crystallographic ensemble models, accounting for both protein conformational entropy and solvent entropy! www.biorxiv.org/content/10.6...

A recent podcast by Stephanie Wankowicz and James @fraserlab.com picked up our work (with Alex Bronstein & coworkers) on Guiding AlphaFold3 with experimental data (cryoEM, X-ray, NMR) to generate protein ensembles. (Thanks for the kind words 🙂)
👉 creators.spotify.com/pod/profile/... (from 35:50)

As soon as NIH decided that preprints were A-OK we started preprinting everything.

The biggest negative is that now once we've preprinted I lose interest in the actual peer-reviewed article. Which for me isn't a big deal (I'm tenured) but my folk aren't. So I need to force myself to keep up on it

fraserlab - Overview fraserlab has 2 repositories available. Follow their code on GitHub.

Do you have a repo I can look at invite github.com/fraserlab if private if you are comfortable?

Benchmate.ai

This is cool - is it: app.benchmate.ai/pricing or something you are writing?

Happy new year #teamtomo! We've resumed our OHSU tomo journal club, and this year I am going to be sharing it on bluesky. This week we did a roundtable, where attendees each brought a paper and did a 3-5 minute discussion of what they thought was cool about it. Here are the papers they discussed!

Me too. Just trying to brainstorm ideas that might incentivize more retirement without a forcing function of a hard cutoff