Yufeng Shen

this is a thing that I didn't know I needed 🤩

Our work of protein language models trained on biophysical dynamics was just published in @pnas.org. URL: doi.org/10.1073/pnas...

📢 Our Dept. of Systems Biology at Columbia University has an open tenure-track Assistant Professor position in the broad area of quantitative biology. Come join our awesome department in NYC! Please circulate.
apply.interfolio.com/177622
Suggested deadline: 12/15/2025.
@columbiasysbio.bsky.social

OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇

Congrats!!

congratulations!!

Congratulations!!

Molecular dynamics simulations of intrinsically disordered protein regions enable biophysical interpretation of variant effect predictors Predictive models for missense variant pathogenicity offer little functional interpretation for intrinsically disordered regions, since they rely on conservation and coevolution across homologous sequ...

How can we better understand pathogenic variants in intrinsically disordered regions (IDRs)? How do models such as AlphaMissense and ESM1b predict pathogenicity, when these regions typically exhibit lower genomic conservation than ordered regions? Read more:
doi.org/10.1101/2025...

Why do large protein language models like ESM2-15B underperform compared to medium-sized ones like ESM2-650M in predicting mutation effects? 🤔

We dive into this issue in our new preprint—bringing insights into model scaling on mutation effect prediction. 🧬📉

We have updated our protein lanuage model trained on structure dynamics. Our new models show significant better zero-shot performance on mutation effects of designed and viral proteins compared to ESM2. check the new preprint here: www.biorxiv.org/content/10.1...

Congratulations!!

Why do association studies prioritize trait-specific variants???

A quick thread about the importance of thinking about all traits at once 👇 1/6 (🧪🧬)

Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science.

www.biorxiv.org/content/10.1...

Most of the talks from our Oct meeting are now online, with a few more to come: www.precisionmedicine.columbia.edu/videos

Right. With zeros, the point estimate of effect size is just too far off. Maybe you can use pseudo count to stabilize it, although how to do pseudo count depends on assumptions about priors

Small sample size is a problem, but my hunch is normal approximation would underestimate the tail on the right side of the distribution, therefore stderr based meta analysis would deflate type I

congratulations!!

The final program for the conference is now up: events.columbia.edu/cal/event/ev...

Open rank faculty search in the Program for Mathematical Genomics at Columbia University:

www.nature.com/naturecareer...

I highly recommend it as a generic method. In our analysis, it has the most consistent score scale across genes, even for genes under-represented in ClinVar or with somewhat weak MSA. A few other methods, like REVEL, gMVP (from us), and EVE, are better for certain genes but less inconsistent.

I'm delighted to release the first half of my new textbook in human genetics:
web.stanford.edu/group/pritch...

"An Owner's Guide to the Human Genome: an introduction to human population genetics, variation and disease"

2nd Bluesky post … faculty search! Genomics and Comp Bio dept @ UMass Chan Med School academicjobsonline.org/ajo/jobs/25641 pop genomics, imaging, stat. genetics, machine learning aka cool science w big data.

Collab & supportive environment where you can innovate & make discoveries. Join us!