1/ New preprint! with @solersanchisx.bsky.social @cwjpugh.bsky.social @federicobilleci.bsky.social @jonnyfrazer.bsky.social and Mafalda Dias, we introduce a scalable framework to improve stability prediction and separate folding from functional constraints. www.biorxiv.org/content/10.6...

Blending physics-based and inverse folding models to disentangle variant effects on stability and function

Protein sequences are constrained not only by the need to fold into stable structures, but also by specific functional requirements imposed by natural selection. Yet predictions of how amino-acid chan...

biorxiv.org

Applications are open for the @crg_eu PhD Programme! 20 fully funded positions — including one in our group through the Evolutionary Medical Genomics ITN. Join us to develop deep generative models of cross-species data to tackle open questions in disease genetics. www.crg.eu/en/content/t...

Centre de Regulació Genòmica (CRG)@crg.eu · 10mo ago

Are you looking for a PhD? Join us in Barcelona! You'll dive into a community of >100 PhD students from 30 countries exploring the frontiers of biology. You can also join an online workshop on 6 November (15:00 CET) to learn how to find the right lab for you. More info: www.crg.eu/en/content/t...

Check out our new preprint! How can we get more out of existing protein/genome language models without retraining them?

Charlie Pugh@cwjpugh.bsky.social · last yr.

New preprint in collaboration with @paulinanunezv.bsky.social supervised by @jonnyfrazer.bsky.social and Mafalda Dias – we propose a simple approach to improving zero-shot variant effect prediction in pre-existing protein and genome language models: 🧶 1/n www.biorxiv.org/content/10.1...

Awesome paper. Simple post-hoc trick (averaging over homologs) with elegant evolution theory dramatically improves zero shot coding variant effect prediction in pLMs & actually delivers better results from the larger models (inverting the trend with raw likelihoods). 1/

bioRxivpreprint@biorxivpreprint.bsky.social · last yr.

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models https://www.biorxiv.org/content/10.1101/2025.05.20.655154v1

@cwjpugh.bsky.social at #VariantEffect25

Proud supervisor moment! Next up at #VariantEffect25: Charles Pugh @cwjpugh.bsky.social, PhD student in Mafalda’s and my group, presents: From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models #AI #ProteinML

A lovely summary of what we have learnt about scaling from ProteinGym -- Have we reached a performance plateau? More on this later in the week from @cwjpugh.bsky.social