A herculean effort by many, but esp. the first three authors: Ujjwal Rathore, Eli Dugan, and Hunter Thornton working in the Krogan and Marson labs, with a veritable army of collaborators from HARC (harc.ucsf.edu) and beyond.

Press release: gladstone.org/news/scienti... (inc. paper link)

Don't be shy to take on a little two-week side project. These five months will be the most precious three years of your academic journey.

Check out how we exploit observations of homology from evolution to design enhancers, even when we don't have prior knowledge or ability to specify function!

1/
🧬 Happy to share our new preprint on modeling cis-regulatory variation in human brain enhancers across a large Parkinson’s disease cohort: www.biorxiv.org/content/10.6...
Details in the thread below:

Very proud of this and so cool that enhancer-level models can predict the effect of genetic variation. There is so much personal variation in terms of gene regulation in the human brain, it is fantastic to uncover this thanks to technology (whole-genome sequencing and single-cell multiomics) and AI

Run an MD simulation of any protein in the AlphaFold Protein Structure Database using AF-CALVADOS

Thanks to @sobuelow.bsky.social AF-CALVADOS is now on Colab

colab.research.google.com/github/KULL-...

Agents for comp bio are advancing rapidly, but evals are lagging. Current benchmarks can be overly prescriptive. Full analysis vignettes are hard to verify. We introduce CompBioBench: 100 diverse, challenging, verifiable tasks. We benchmark Codex and Claude Code.

biorxiv.org/content/10.6...

1/9

New preprint @cxqiu.bsky.social @jshendure.bsky.social ! Can we learn regulatory grammars of human cell types — by training on mouse development and transferring across 241 mammalian genomes? Introducing STEAM & a whole-organism scATAC-seq atlas from E10 to birth.
www.biorxiv.org/content/10.6...

Phase separation across membranes and condensates in cell organization and function Nature Reviews Molecular Cell Biology, Published online: 09 April 2026; doi:10.1038/s41580-026-00961-5Phase separation — the demixing of cellular components into distinct phases — shapes membrane domains and forms biomolecular condensates. This Review examines how condensates and membranes influence each other and highlights their combined importance for cellular organization and function.

New Online! Phase separation across membranes and condensates in cell organization and function

"Light Fossils" dinosaur light painting by artist Darren Pearson, known as Darius Twin, using a unique photography technique.

The artwork is created using long-exposure photography, where the camera shutter remains open while the artist moves handheld lights to "draw" the figures in real-time.

Genetic background shapes AI-predicted variant effects

Figure 1

Figure 2

Figure 3

Genetic background shapes AI-predicted variant effects [new]
...uncovering heterogeneous predictions where variants shift between pathogenic and benign outcomes across diverse genomic contexts, crucial for interpretation.

Stoked to announce that I’m starting a lab as an Assistant Professor in the School of Biomedical Engineering and Centre for Brain Health at UBC!

mcdiarmid-lab.sbme.ubc.ca

Recruiting at all levels - please share the word!

Cheers and happy long weekend all!

Why do schizophrenia GWAS signals look so flat across the genome?

In our recent preprint, we explored why psychiatric disorders — and, more broadly, brain-related traits involving the central nervous system — appear to have unusual genetic architectures.

🧵1/n

Join us for a postdoc in AI in human genetics at @embl.org in close collaboration with Adrian Cortes (GSK) and @brianfclarke.bsky.social - exploring the effects of rare variants using population-scale cohorts and single-cell readouts.

🔗 Apply now: embl.wd103.myworkdayjobs.com/en-US/EMBL/d...

Preprint servers are more complex than people think. arXIv chief Ramin Zabih shows their workflow at the Newton Institute. 1/n

What does it take to learn the rules of RNA base pairing? A lot less than you may think - Communications Biology Deep-learning models typically require large parameter spaces and extensive training data. Here the authors demonstrate that learning the fundamental biological rules of RNA base pairing can be achiev...

www.nature.com/articles/s42...

Stress can cause eczema to flare up – now we know why Scientists have identified the neurons that worsen the condition during stress.

Stress can cause eczema to flare up – now we know why www.nature.com/articles/d41...

Protein language models are bad at mutational effect prediction Biology is hard. Yes, even for AI.

Protein language models are bad at mutational effect prediction
blog.genesmindsmachines.com/p/protein-la...

Unstructured transcription factor interactions enable emergent specificity How intrinsically disordered regions (IDRs) influence chromatin binding and nuclear organization of transcription factors (TFs) remains unclear. We employed proximity-assisted photoactivation (PAPA), ...

Unstructured transcription factor interactions enable emergent specificity | @science.org www.science.org/doi/10.1126/...

Excited to share new preprint with NVIDIA on GPU-accelerated single-cell analysis 🚀

rapids-singlecell brings native GPU support to scverse/AnnData: hours → seconds (1M cells: ~52m → ~25s), scaling to 100M cells. Huge thanks to Severin Dicks 🙌

📄 arxiv.org/abs/2603.02402

Congratulations @heatherkarner.bsky.social and @tabeamittmann.bsky.social for getting this awesome project across the finish line!

AF2BIND: predicting small-molecule binding sites using the pair representation of AlphaFold2 Nature Methods - AF2BIND is a logistic regression model trained on AlphaFold2 pair features to predict small-molecule binding-site residues in proteins, without multiple sequence alignments,...

Our paper with @sokrypton.org using AlphaFold2 to predict small-molecule binding sites in proteins is now out in Nature Methods! 🧵
rdcu.be/e7SnX
www.nature.com/articles/s41...

🚀 New in Communications Biology:
Generative models of cell dynamics - from Neural ODEs to Flow Matching
www.nature.com/articles/s42...

We discuss modeling single-cell dynamics beyond snapshots: from cont-time Neural ODEs to simulation-free flow matching for scalable pop modeling.

Review from Fia B. Larsen in @rhp-lab.bsky.social with everything you always wanted to know about proteasomal control of transcription factors (but were afraid to ask about)

Proteasomal control of transcription factors: mechanisms, regulation and dysregulation.
doi.org/10.1007/s000...

Excited to share this preprint that describes my latest work on using GPUs to accelerate processing of RNA-seq data.

The title says it all: "RNA-seq analysis in seconds using GPUs" now on biorxiv www.biorxiv.org/content/10.6... and github github.com/pachterlab/k...

Figure 1 shows they key result

Massively parallel reporter assay for mapping gene-specific regulatory regions at single-nucleotide resolution Integrated locus-specific and mutational MPRAs reveal regulatory modules and nucleotide determinants governing cell type-specific gene expression, providing a scalable framework for mapping cis-regulatory...

Massively parallel reporter assay for mapping gene-specific regulatory regions at single-nucleotide resolution

Join us for our next Kipoi Seminar with Sam Boshar, Instadeep
@instadeep.bsky.social

👉 A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction

🗓️ Wed Mar 4, 5:30pm CET
🧬 kipoi.org/seminar
🦋 @kipoizoo.bsky.social

White House stalls release of approved US science budgets The US Congress rejected sweeping cuts to science agencies. But the NIH, the NSF and NASA have had their spending slowed.

Congress rejected massive cuts to US science budgets for 2026, but much of the money still isn’t flowing to researchers.

The culprit? The White House Office of Management and Budget (OMB) is quietly slow-walking the release of funds. 🧵👇

Congress has appropriated the funds to NSF but OMB is delaying the release. When funds are released, NSF, which has lost almost 1/5 of its staff, will struggle to evaluate proposals. Since they have to award the funds, big projects with established PIs will benefit. This is how US science dies.

New paper alert 🚀 Our organism-wide single-cell ATAC-seq atlas of mammalian aging is now out in @science.org, led by our fantastic graduate student Ziyu Lu from @rockefeller.edu!
www.science.org/doi/10.1126/...