🔥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 work with co-first author Mo Ameen. Gene regulation is a delicate balance b/w cis-regulatory sequence & TF conc, but these components are often studied in isolation. Reprogramming is a fantastic system to study their interplay 1/16 biorxiv.org/content/10.110…

Excited to share our latest work on bioRxiv! biorxiv.org/content/10.110… A highly collaborative effort with Kristy S. Mualim Alireza Karbalayghareh, maya sheth, Kushal K Dey, Evelyn Jagoda, PhD👩🏻‍🔬,Wang Xi, Lars Steinmetz, Anshul Kundaje (anshulkundaje@bluesky), Jesse Engreitz and many others from ENCODE Project! Thread👇

I'm on the faculty market! My goal is to build language systems that we understand deeply through discovery and by design, so we can precisely control them and treat their failures. Let's tackle this grand challenge of science and engineering together. nlp.stanford.edu/~johnhew/

Sequence-based ML methods (Enformer, ChromBPNet...) are invaluable in genomics but the ecosystem for their *use* after training is less developed. Introducing, `tangermeme`: a PyTorch library for genomics discovery for everything-other-than-the-model. github.com/jmschrei/tange… 1.

Attributions are invaluable in genomics for identifying the drivers of model predictions, but it's easy to make a mistake WITHOUT REALIZING. Here is a short vignette describing the challenges you might encounter and how tangermeme makes it easier for you. github.com/jmschrei/tange…

Check out ProCapNet by Kelly Cochran, a robust, local sequence context deep learning model of base-resolution transcription initiation profiles (PRO-cap) that provides deep insights into the cis-regulatory code of initiation & more ... biorxiv.org/content/10.110… 1/

Thrilled to share the bulk of my PhD work, now up on bioRxiv! This project brings together aspects of network theory, systems biology, and single cell genomics, towards understanding properties of gene regulatory networks (GRNs). Read on for more —> (1/) doi.org/10.1101/2024.0…

Excited to present “scooby”, which models multi-omic profiles (scRNA-seq coverage & scATAC-seq insertions) directly from 500 kb DNA sequence at single-cell resolution. This was a fantastic collaboration co-led with Johannes Hingerl. biorxiv.org/content/10.110…

🧵 Thrilled to share our latest in nature! We’ve mapped fetal blood development in Down syndrome (DS) using single-cell multi-omics, studying why children with DS face a 150-fold higher leukemia risk and blood abnormalities at birth. nature.com/articles/s4158…

A great collaboration with the ML team here at Genentech. Happy to see this pre-print out: biorxiv.org/content/10.110… (@lal_avantika gokcen Surag Nair and many others)

Just landed in Denver and I’m excited for #ASHG24! I’ll be giving a talk on Friday at 1:30 based on my postdoc work at Stanford - we’re studying rare non-coding variants with deep learning in collab w/ Soumya Kundu Anshul Kundaje (anshulkundaje@bluesky) @sbmontgom . Hope to see you there!

Excited to share our latest preprint, as part of ENCODE4, on a consensus variant-to-function (cV2F) score for functionally prioritizing variants for complex disease - led by Tabassum Fabiha and co-mentored with Alkes Price. biorxiv.org/content/10.110…

We use Multiome and HiC to build a comprehensive single cell variant to enhancer to gene map for coronary artery disease. Join effort with Paul Chungroh Lee and IttaiEres in Nate Stitziel Lab and in collaboration with Amgen 🧪🔬🧬 Test Account medrxiv.org/content/10.110…

New preprint w/ Soumya Kundu, Anshul Kundaje (anshulkundaje@bluesky), & Stephen Montgomery! Using deep learning & scATAC-seq, we studied context-specific variants in disease & evolution, and introduce FLARE for de novo mutations—with application to autism-affected families. doi.org/10.1101/2025.0…

Now online! CXCL12 drives natural variation in coronary artery anatomy across diverse populations dlvr.it/TJLtv6

Today was a big day for the lab. We had two back to back thesis defenses and the defenders defended with great science and character. Congrats to DR. Kelly Cochran & DR. Soumya Kundu on this momentous achievement. Brilliant scientists with brilliant futures ahead. 🎉🎉🎉

Enhancers, how do they work (in vivo)? To find out, we mutagenized 7 human enhancers comprehensively in 12bp blocks and scored for activity in developing mouse embryos. rdcu.be/erD22 nature #mutagenesis #noncoding #enhancers

Sara Mostafavi (Genentech ) & I (Stanford University) r excited to announce co-advised postdoc positions for candidates with deep expertise in ML for bio (especially sequence to function models, causal perturbational models & single cell models). See details below. Pls RT 1/

Happy to introduce AlphaGenome, Google DeepMind's new AI model for genomics. AlphaGenome offers a comprehensive view of the human non-coding genome by predicting the impact of DNA variations. It will deepen our understanding of disease biology and open new avenues of research.

Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by Amber Tang with help from Nirali Somia & Steven Yu is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10.11…