We are excited to share GPN-Star, a cost-effective, biologically grounded genomic language modeling framework that achieves state-of-the-art performance across a wide range of variant effect prediction tasks relevant to human genetics. www.biorxiv.org/content/10.1... (1/n)

Staff scientist position (computational): I am looking for a computational scientist to join my genomics lab at Stanford. They should have an outstanding skillset in ML/statistical methods for genomic applications, postdoc experience and a strong publication record. #sciencejobs

What a joy to work on exciting science AND do it with a great friend like @itskatelawrence.bsky.social! Check out her 🧵 on our recent preprint with @sbmontgom.bsky.social:

Modern GWAS can identify 1000s of significant hits but it can be hard to turn this into biological insight. What key cellular functions link genetic variation to disease? I'm very excited to present our new work combining associations and Perturb-seq to build interpretable causal graphs! A 🧵

Thrilled to share the first paper of my PhD! It was so much fun working on this collaborative project from day one as a rotation student! Huge thanks @khoulahan.bsky.social, @lisemangiante.bsky.social, @crissotomayor.bsky.social, @cncurtis.bsky.social, Jennifer Caswell-Jin & the Curtis lab!

What do GWAS and rare variant burden tests discover, and why? Do these studies find the most IMPORTANT genes? If not, how DO they rank genes? Here we present a surprising result: these studies actually test for SPECIFICITY! A 🧵on what this means... (🧪🧬) www.biorxiv.org/content/10.1...

In a new preprint led by @TheNikhilMilind, we explored a fascinating paradox: For many traits the number of duplications or loss-of-function (LoF) mutations is correlated with phenotype. Curiously, for most traits, the AVERAGE direction of LoFs and Dups is the SAME. Why?

Just posting this to #popgen Here's a link to my notes on population & quantitative genetics: github.com/cooplab/popg... Hoping to extend it more after the winter holidays, as I'm just finishing up teaching the undergrad version of class.

🧬 What are protein language models (PLMs) actually learning about biology? Our paper introduces InterPLM - a framework that reveals interpretable features in PLMs using sparse autoencoders, giving us a window into how these models represent protein structure and function. 🧵(1/8)

I’ve decided to leave Scientific American after an exciting 4.5 years as editor in chief. I’m going to take some time to think about what comes next (and go birdwatching), but for now I’d like to share a very small sample of the work I’ve been so proud to support (thread)