The third episode of The Tortured Proteins Department is out now! We chatted about grant cancellations, exciting regional meetings and reunions, two fun new preprints, community norms around code release, and the importance of giving kudos. @fraserlab.com

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/...

While this paper looks interesting, let me just say (again) that (essentially all) NMR ensembles in the PDB are NOT thermodynamic ensembles or meant to represent these. They are "uncertainty ensembles" and using them to benchmark machine learning (or other) models of dynamics is not a good idea.

Do you wish working with T-cell receptor structures was easier? Us too! STCRpy, our software suite for T cell receptor structure parsing, interaction profiling and machine learning dataset preparation is now available! Github: github.com/npqst/stcrpy/ Pre-print: www.biorxiv.org/content/10.1... 1/3

3-year postdoc opportunity as part of the Novo Nordisk - Oxford Fellowship programme! Develop machine learning approaches for drug discovery with me, Charlotte Deane (Oxford), and Christos Nicolaou (Novo Nordisk). 1 week left to apply! Details in next post

Backbone predictions are great - but what about side chains? Me and @emilthomasen.bsky.social are happy to present AF2χ, a tool for predicting side-chain heterogeneity in protein structures!. If you want to read more about it, check out our preprint and localColabFold implementation!

AlphaFold is amazing but gives you static structures 🧊 In a fantastic teamwork, @mcagiada.bsky.social and @emilthomasen.bsky.social developed AF2χ to generate conformational ensembles representing side-chain dynamics using AF2 💃 Code: github.com/KULL-Centre/... Colab: github.com/matteo-cagia...

Mark your calendars now. The next variant effects seminar is Monday, 1 April, 9 am (Pacific), featuring Joyce Kang @harvard.edu @broadinstitute.org & Yiyun Rao @pennstateuniv.bsky.social. @varianteffect.bsky.social Learn more: www.varianteffect.org/seminar-series

Delighted to announce that our paper "Predicting absolute protein folding stability using generative models"(lnkd.in/dZJMiY4r) has been awarded the Protein Science BEST PAPER 2024 by @proteinsociety.bsky.social.

I am happy to share our latest review, which discusses the challenges of predicting unbound antibody structures using deep learning. Special thanks to Alexander Greenshields-Watson for leading and coordinating this work! 🧬💻 doi.org/10.1016/j.sb... #AntibodyEngineering #DeepLearning

OPIG is now on Bluesky! Follow us for updates about the group's latest work, web app updates, and more. opig.stats.ox.ac.uk

Predicting absolute protein folding stability using generative models @mcagiada.bsky.social @sokrypton.org & I used ESM-IF to predict ∆G for folding & conformational change Paper, code and colab 📜 dx.doi.org/10.1002/pro.... 💾 github.com/KULL-Centre/... 👩‍💻 colab.research.google.com/github/KULL-...

New preprint with @mcagiada.bsky.social & @sokrypton.org in which we present a benchmark and predictions of absolute protein stability (ΔG not ΔΔG) using using likelihoods from a generative model, and also benchmark it for conformational free energies against NMR 🧬 🧶 doi.org/10.1101/2024...

I'm excited to present Francesco Pesce's work on developing, applying & experimental testing of a method to design intrinsically disordered proteins. Our algorithm combines MC sampling in sequence space with an efficient CG simulation model and alchemical free-energy calculations. 🍝 🧶🧬