Chapter 2 of branched RNA: chemically modified branched cap for multi-capped mRNA and capped circular RNA (QRNA)--the cellular translation machinery is surprisingly tolerant of unnatural structures! Beyond enhanced performance, the mechanism is intriguing: rdcu.be/dUQKX

Chromatin interactions profiles are useful, but how can we deconvolute cell-type info from the complex tissues? 🎯 Led by Lei Chang , we just released Droplet Hi-C: a faster, cheaper, and high-throughput single-cell Hi-C method using microfluidics: nature.com/articles/s4158…

Recent advances in #AI and #DataScience affect the landscape of medicine and biomedical research. Join experts to learn about the challenges and opportunities of this #HealthTech. REGISTER BY 10/22: niddk.nih.gov/news/meetings-… #NIDDK #HealthTech #DigitalHealth

Out in Nature Communications ! ChromaFold predicts 3D contact maps using single-cell ATAC-seq alone. nature.com/articles/s4146…

🚀 [CFP] Join Us at AAAI 2025 for the Second AI4Research Workshop! 🧪 Dive into the breakthroughs in AI-assisted research lifecycle. 🗓️Submission Deadline: Nov 24 AAAI #callforpapers #aaai2025 #ai4research Submit your work now! twtr.to/_sqcK

Stanford Graph Learning Workshop! 🚀 live stream starting at 9 AM PT, join us to dive into groundbreaking advances in Machine Learning & AI for relational domains, foundation models, and agents! Live stream: youtube.com/live/gnTqU30rw… Program: snap.stanford.edu/graphlearning-… Q&A:

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 often think of an "equilibrium" as something standing still, like a scale in perfect balance. But many equilibria are dynamic, like a flowing river which is never changing—yet never standing still. These dynamic equilibria are nicely described by so-called "detailed balance"

Great paper from my colleague Chongyuan Luo combining single cell HiC and single cell methylation data to reveal an unexpected amount of methylation and chromatin conformation remodelling during human perinatal development nature.com/articles/s4158…

"Sure, i'll be happy to go over your draft"

Heterogeneous enhancer states orchestrate β cell responses to metabolic stress | Nature Communications nature.com/articles/s4146…

What gets erased when you integrate single cell data, and can you recover it? Finally, we know what happens and how to recover the lost signals. So excited to share CellANOVA, published online today in NBT! go.nature.com/4hZnzW5

scE2G: Mapping enhancer-gene regulatory interactions from single-cell data biorxiv.org/content/10.110…

Predicting gene expression from histone marks using chromatin deep learning models depends on histone mark function, regulatory distance and cellular states academic.oup.com/nar/advance-ar…

5/ In my experience, most of the time, you don’t need deep learning. Often, simple methods like linear regression or random forests work well — especially for moderate-sized datasets. Deep learning excels in image analysis & protein structure prediction.

Super excited to share our new study from the Jason Buenrostro Lab in nature! We developed a computational method for tracking transcription factor and nucleosome binding using single-cell ATAC-seq and deep learning. Paper: nature.com/articles/s4158…

Our spatial multi-omics technology that co-profiles five modalities is now published in Nature Methods Nature Methods! Huge thanks to Marek Bartosovic, Mingyao Li, and my amazing team, including postdoc Pengfei_Guo and PhD student Liran Mao! nature.com/articles/s4159…

Attending a conference without presenting

Meeting the person you suspect is reviewer #2 in a conference

Interested in single cell genomics but need help getting started? Check out the full agenda for our Single Cell Genomics Day on Friday 4/25. All talks will be live-streamed (no registration required) at satijalab.org/scgd25