The DiffUSE Project

Open data. Public logbooks. No waiting for publications. The DiffUSE Project is redesigning the structural biology pipeline from sample prep to modeling, all in the open. Meet DiffUSE: youtu.be/_DILlMou1GM?si…

Unlocking protein dynamics requires infrastructure we all can access. ICYMI: all of our software packages live on GitHub, updated in the open: github.com/diff-use

Open science is useful science. One effort we are developing are logbooks where we share research as it happens: what works, what doesn't, what we've learned. This effort is led by DiffUSE Scientist Steve Meisburger (@meisborg). See the latest: diffuse.science/logbook/beamti…

What's happening in protein dynamics research right now? Jaime & Stephanie break down NIH policy changes, preprints & the conformational ensembles conference. New episode up: diffuse.science/posts/TTPD-15/ #StructuralBiology

In a test case, swapping Phenix's flat bulk-solvent mask for an MD-derived map lowered cross-validated R-free from 0.147 to 0.109 in one 0.96 Å. Code here: github.com/jmholton/pheni…

Bulk solvent fills ~half a protein crystal. Modeling this is required for a good fit to experimental data. How best to model this remains an open question. New from diffUSE: a Phenix patch to supply your own solvent map (MD, 3D-RISM, EDEN, neural nets). thestacks.org/publications/m…

Our most recent blog: diffuse.science/post/science-i… #SciComm #OpenScience

We share science at The DiffUSE Project in a few ways: blogs for motivation and intuition, scholarly outputs for methods, data, and code with a citable DOI. All open and shared rapidly for the best science. Our latest pub: doi.org/10.82153/jkxj-…

To realize AI for science, we have to change how we feed the machine. sampleworks, the first publication from @radialscience‘s @diffuseproject is a step: an open, modular platform for building and benchmarking structure predictors against experimental data 👇

We tested how well current models recover alternative conformations from the PDB. Success varied widely across proteins, a sign that models rely on memorization rather than true generalization, pointing to new training paradigms for structure-ensemble prediction.

(2 / 3) sampleworks was built openly and is made to be easily built upon for many different methods development approaches. github.com/diff-use/sampl…

(1 / 3) First scholarly publication from The DiffUSE Project. sampleworks: an open, modular platform for generating and evaluating biomolecular conformational ensembles from structure predictors guided by experimental data. doi.org/10.82153/jkxj-…

Want to shape the future of structural biology? We are seeking a Project Manager to help lead the DiffUSE Project, guiding ML researchers, computational scientists, national labs, and university partners. Apply: buff.ly/gZlj9AP #StructuralBiology #MachineLearning #Hiring

The DiffUSE Project wants examples where structural heterogeneity matters but cannot be encoded in PDBx/mmCIF. X-ray, cryo-EM, time-resolved, multi-map, or fragment screening data welcome. Submit yours: diffuse.science/submit/

Simulations can be valuable but there is a huge need for scalable experiments that probe protein dynamics- of course we're expanding our work here and there's also great work from others @HWaymentSteele @ginaelnesr @BasileWicky @diffUSEproject

ICYMI: The latest Tortured Proteins Department episode. @stephanie_mul and @fraser_lab on: NIH strategic plan comments (due 5/26), AI lab guidelines, two new cryo-EM preprints, training scientists for what's next diffuse.science/posts/TTPD-14/

Love all the AI-native initiatives for research sharing I’m starting to see pop up across the ecosystem. If you’re building in this space, I’d love to hear from you as there may be some synergies or opportunities across our open science efforts at @AsteraInstitute

This tube is a library of bacteria with every single-base-pair genome mutation, all DNA-barcoded.🧪Growth + barcode sequencing = data on millions of mutations. 📄 Report: biorxiv.org/content/10.648… Retweet if you want more data, and read on if you want to use the library! 🧵

🎉🎉🎉

Hosted in partnership with the DiffUSE Project! 🎉👇

We are SO lucky to have @stephanie_mul joining Radial to lead @diffUSEproject 🙌🏼