Julia Zeitlinger

Want to interpret DNA sequence-to-function models to understand the underlying molecular mechanisms? Then this is a must read!

The abstract submission deadline is March 6.

AlphaGenome is out in @nature.com today along with model weights! 🧬

📄 Paper: www.nature.com/articles/s41...

💻 Weights: github.com/google-deepm...

Getting here wasn’t a straight path. We discussed the story behind the model, paper & API in the following roundtable: youtu.be/V8lhUqKqzUc

Ziga, congrats again to you and your team!

Today @nature.com, it's #AlphaGenome, to decipher and determine functionality of the regulatory (very challenging) variants in our genome.
Another big step of AI for advancing life science
nature.com/articles/s41...

Sonic hedgehog is not a limb morphogen but acts as a trigger to specify all digits in mice Limb patterning by Sonic hedgehog (Shh), via either graded spatial or temporal signal integration, is a paradigm for “morphogen” function, yet how Shh…

Finally had a chance to read this beautiful paper from Susan Mackem's lab. It's interesting that even well-established paradigms, like Sonic Hedgehog's role as a traditional morphogen in limb development, can be proven wrong over time.
www.sciencedirect.com/science/arti...

Thanks to
@ferhatay.bsky.social
and Aly Khan, we’re excited to announce a new chapter for RECOMB-RSG 2026. After years with ISCB/DREAM, we are transitioning to an official RECOMB satellite meeting (May 25 in Thessaloniki). recomb-rsg.github.io

Our work on TFIID is finally out as preprint!

Don't miss Bing Ren (@columbiauniversity.bsky.social) as the keynote speaker for #SRCKC26! Ren's work in #epigenomics and gene regulation continues to transform our understanding of #genome function. Organized by: @saukaspengler.bsky.social, @juliazeitlinger.bsky.social, Neşet Özel

🔗 bit.ly/4rMvVoI

Interested in spending the summer doing #science? Don't miss your chance to apply for the #StowersGrad Summer Scholars program! Applications close 1/16. ⬇️

A SWI/SNF-specific Ig-like domain, SWIFT, is a transcription factor binding platform Mammalian SWI/SNF chromatin remodeling complexes modulate DNA accessibility and gene expression; however, their genomic targeting mechanisms remain incompletely understood. Here, we identify SWIFT (SW...

🧬 @science.org A SWI/SNF-specific Ig-like domain, SWIFT, is a transcription factor binding platform | Science www.science.org/doi/10.1126/... @ckadoch.bsky.social @danafarber.bsky.social @harvardmed.bsky.social @broadinstitute.org @hhmi-science.bsky.social 🔬 #chromatin #transcription #cancer 🧫

Stowers Research Conferences: Development, Regulatory Genomics & AI Organized by Julia Zeitlinger, Ph.D., Neşet Özel, Ph.D., and Tatjana Sauka-Spengler, Ph.D.

“Development, regulatory genomics & AI on April 22-24 www.stowers.org/events/stowe...

Please consider attending and RT. Great lineup of speakers!

Allele Frequencies at Recessive Disease Genes are Mainly Determined by Pleiotropic Effects in Heterozygotes The classic theory of mutation-selection balance predicts the equilibrium frequency of genetic variation under negative selection. The model predicts a simple relationship between the total frequency ...

Our latest preprint revisits the classic model of mutation-selection balance.

Do human recessive genes fit Haldane's 100-year old model?

This work is by the wonderful @jonj-udd.bsky.social, and co-mentored by @jeffspence.github.io

www.biorxiv.org/content/10.6...

Very proud of our new paper! Great job @mweilert.bsky.social, our experimentalists and modeling collaborator Rosa Martinez-Corral. It was fun to see the story grow and get feedback from various experts. Thank you all!

It's always special when you find your own paper in the table of contents of the journal 😍

"The cis-regulatory logic integrating spatial and temporal patterning in the vertebrate neural tube" -> Now out in its final form

www.cell.com/developmenta...

Nice to see this out. This was a completely new research direction for me 7 years ago. I am so grateful for all the people who made this possible!

Promoter-proximal gatekeepers restrict pleiotropic enhancer inputs to achieve tissue specificity Developmental enhancers are central regulatory elements that can activate multiple genes, yet how they selectively regulate one gene over its neighbours remains unclear. Using the Drosophila twist E3 ...

Ever wondered what drives enhancer-promoter specificity? Why would an enhancer activate one gene rather than another neighboring one?

Check our latest preprint, led by @mmasoura.bsky.social, to find out!
www.biorxiv.org/content/10.1...

Emergence of activation or repression in transcriptional control under a fixed molecular context | PNAS Transcription factors (TFs) can be both activators and repressors of gene transcription. This can manifest as “duality,” where the transcriptional ...

Emergence of activation or repression in transcriptional control under a fixed molecular context www.pnas.org/doi/10.1073/...

Excited to share another new preprint from our lab in which we developed a cluster-based phasing strategy using long read nano-NOMe-seq data to link distinct CTCF binding states—captured at the single molecule level—to the transcriptional status of genes: biorxiv.org/content/10.1...

bioRxiv - An unbiased survey of distal element-gene regulatory interactions with direct-capture targeted Perturb-seq

New preprint from our lab!

What can we learn about the properties of gene regulatory elements by CRISPR’ing a random set of accessible sites in human cells?

Find out here: www.biorxiv.org/content/10.1...

👇

1/

It is my pleasure to share with you the latest from @jsvejstrup.bsky.social lab, where we look at how the reduction of RNAPII levels has a severe, yet organized transcriptional response in the cell.

Very nice talk on this at CSH Mechanisms of Eukaryotic Transcription. Elegant approach!

Happy to see my lab here, too! Please follow if you are passionate about regulatory genomics and deep learning.

Abstract deadline for CSH Asia meeting on Systems Biology of Gene Regulation and Genome Editing is extended to September 5th.

🍷 + 🧬 = a perfect Friday night. Investigator @juliazeitlinger.bsky.social joined the "Science Over Spirits" series at Baldwin City Distillery to share "How to use Al to read the language of DNA".

Only ~2% of our DNA codes for proteins. What about the rest?

#AI tools are helping scientists, including Investigator @juliazeitlinger.bsky.social , decipher how non-coding #DNA shapes health and disease. 🧬

📖 Read more @nature.com: go.nature.com/4mLGGEl

Looking forward to my first talk in a distillery!

Registration & abstract submission now open for #SRCKC25 AI-Driven Approaches to Emergent Protein Behaviors Oct. 22–24. Join a community of researchers exploring how artificial intelligence is advancing our understanding of complex protein behaviors. #ResearchSky

Register: bit.ly/3GgsQtC

*Easter egg alert* NOT in the published paper. We also benchmarked Evo 2 and while it did better than other gLMs (consistent that scale can improve gLMs), it still falls short of a basic CNN trained using one-hot sequences and far short of supervised SOTA