🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to share the paper: Huntington's disease is a DNA process for almost all of a cell's life. Inherited HD alleles are innocuous, just unstable – CAG repeats slowy expand throughout life. We call it a "ticking DNA clock". cell.com/cell/fulltext/…

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

The progress in AI is down to three basic resources; (1) people (experts), (2) data, and (3) infrastructure. Arguably, at this point the US is only ahead in (3). Also, at this point the Chinese open source models are ahead. Not only DeepSeek but also Qwen. This is a fact.

Interested in GxE interaction #gwas? Now, you can identify and filter them on our website! Check the great review made by Genevieve Wojcik, PhD MHS et al. at @JohnsHopkinsEPIThey. They also analysed the data we hosted and showed a lack of #SumStats available. tinyurl.com/bdfmsmtd

Can DNA sequence models predict mutations affecting human traits? We introduce TraitGym, a curated benchmark of causal regulatory variants for 113 Mendelian & 83 complex traits, and evaluate functional genomics and DNA language models. Joint work w/ gokcen and Yun S. Song 🧵👇

I and my colleague, Sahar Gelfman, at RGC had the privilege to write a News and Views article for @nature about a recent work on Huntington's disease by Steve McCarroll and team. In this incredible work, through an innovative single cell RNA sequencing methodology, Handsaker et

I wrote about how population stratification in genetic analyses led to a decade of false findings and almost certainly continues to bias emerging results. But we are starting to have statistical tools to sniff it out. A 🧵:

14% of 55-69 men with polygenic risk scores (PRS) in the top 10% had prostate cancer classified as intermediate or higher risk, a higher percentage than would have been identified using PSA or MRI screening. This seems like a strong argument for integrating polygenic risk scores

Story by Alvin Powell on Sonia Vallabh and Eric Minikel’s very personal mission with our lab and others to develop a gene editing treatment for prion disease: news.harvard.edu/gazette/story/…. The research paper in Nature Medicine can be found below. prionalliance

In the future soon, we will be able to communicate with many intelligent animal species - can't wait to better understand what my dog🐶is saying! Congrats to the DolphinGemma team building on our Gemma models - the most powerful single GPU/TPU open source models out there!

Sequence diversity lost in early pregnancy | Nature @nature congrats to all collaborators on this landmark paper nature.com/articles/s4158…

In this Article, the authors introduce PIGEON, a statistical framework for estimating gene-environment interactions for complex traits. Jiacheng Miao Qiongshi Lu nature.com/articles/s4156…

Jiacheng Miao's PIGEON paper on GxE methodology is now published Nature Human Behaviour with a new title. In our view, this paper can reshape the study design for future complex trait GxE work. Paper📰doi.org/10.1038/s41562… Software🧑‍💻github.com/qlu-lab/GSUB

Excited to share our latest preprint on the impact of background selection on complex trait evolution. It’s amazing to finally see one of the major projects from my PhD journey come to life. Huge thanks to Jeremy J. Berg and John Novembre for their guidance and support.

I’m very excited to be joining MIT Biological Engineering MIT Dept of BE as an Assistant Professor and the Ragon Institute Ragon Institute as a member in January 2026! I will be recruiting students and postdocs (see more info below).

Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6

We ran a randomized controlled trial to see how much AI coding tools speed up experienced open-source developers. The results surprised us: Developers thought they were 20% faster with AI tools, but they were actually 19% slower when they had access to AI than when they didn't.

📢New conference where AI is the primary author and reviewer! agents4science.stanford.edu Current venues don't allow AI-written papers, so it's hard to assess the +/- of such works🤔 #Agents4Science solicits papers where AI is the main author w/ human advisors. 💡Initial reviews by

Can an AI model predict perfectly and still have a terrible world model? What would that even mean? Our new ICML paper formalizes these questions One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵

Excellent example of the core issue I was trying to get at wrt "virtual cells" - optimizing a prediction objective will not necessarily provide an accurate representation of physical or biological phenomena. It's extremely important to be very clear about this. 1/