Check out our pre-print, where we train a protein and small molecule force field from scratch with a graph neural network. We show comparable performance to existing, manually-tuned force fields on a range of tasks including binding free energy prediction. (1/4) arxiv.org/abs/2603.16770

New paper from former PhD student @tkschulze.bsky.social on supervised learning of protein variant effects across large-scale mutagenesis datasets MAVE/DMS experiments provide large amounts of data for benchmarking variant effect predictors, but may be difficult to use in supervised learning. 1/5

We (@sobuelow.bsky.social & @kejohansson.bsky.social) tested AF-CALVADOS using the recently described PeptoneBench SAXS benchmark that contains SAXS data for >400 proteins with different amounts of order and disorder. The results look pretty good 😇 so we are sharing here while updating the preprint📝

🎙️ Next up Dec 2 in VESS! Thea Schulze (Lindorff-Larsen Lab): Predicting mutated protein abundance @tkschulze.bsky.social Taylor Mighell (Lehner Lab): Massive mutagenesis to understand GPCRs @taylor-mighell.bsky.social 🔗 More info at varianteffect.org/seminar-series @varianteffect.bsky.social

We (@sobuelow.bsky.social) developed AF-CALVADOS to integrate AlphaFold and CALVADOS to simulate flexible multidomain proteins at scale See preprint for: — Ensembles of >12000 full-length human proteins — Analysis of IDRs in >1500 TFs 📜 doi.org/10.1101/2025... 💾 github.com/KULL-Centre/...

Arriën & Giulio's paper on A coarse-grained model for disordered proteins under crowded conditions (that is the CALVADOS PEG model) is now published in final form: dx.doi.org/10.1002/pro.... @asrauh.bsky.social @giuliotesei.bsky.social

Led by @vvouts.bsky.social in @rhp-lab.bsky.social, we measured the degron potency of >200,000 30-residue tiles from >5,000 cytosolic human proteins and trained an ML model for degrons 📜 www.biorxiv.org/content/10.1... 🖥️ github.com/KULL-Centre/...

Happy to share a walkthrough of the applications of our package for simulations using CALVADOS! Big thanks to @sobuelow.bsky.social, @lindorfflarsen.bsky.social, and the whole team for making this possible. Thrilled to mark this as my first last-author paper!

Do you like CALVADOS but are not quite sure how to make it? We’ve got your back! @sobuelow.bsky.social & @giuliotesei.bsky.social—together with the rest of the team—describe our software for simulations using the CALVADOS models incl. recipes for several applications. 1/5 doi.org/10.48550/arX...

Supervised training using data generated by multiplexed assays of variant effects is potentially very powerful, but is made difficult by assay- and protein-specific effects Here @tkschulze.bsky.social devised a strategy to take this into account while training models www.biorxiv.org/content/10.1...

New preprint w @tkschulze.bsky.social who analysed cellular abundance (VAMP-seq) data for ~32,000 variants of six proteins 🧪 We find that much of the variation can be explained and predicted by a burial-dependent substitution matrix Lots more goodies in the paper doi.org/10.1101/2024...

Big congratulations to PhD student Thea K Schulze from our PRISM centre on being awarded the elite research travel grant by the Minister for Higher Education and Science, Christina Egelund, to support a stay at Berkeley to study protein variant effects www1.bio.ku.dk/nyheder/2024...