Happy to share CellAnnotator, a lightweight Python package to query OpenAI models for initial cell type annotations: github.com/quadbio/cell...

Inspired by ideas in www.nature.com/articles/s41... and github.com/VPetukhov/GP..., implemented as an scVerse ecosystem package with docs and tutorials.

From cell lines to full embryos, drug treatments to genetic perturbations, neuron engineering to virtual organoid screens — odds are there’s something in it for you!

Built on flow matching, CellFlow can help guide your next phenotypic screen: biorxiv.org/content/10.1101/2025.04.11.648220v1

Our paper benchmarking feature selection for scRNA-seq integration and reference usage is out now www.nature.com/articles/s41...!

Keep reading for more about how we did the study and what we found out 🧵 👇

1/16

⚡️Our findings have implications for understanding how prenatal stressors can shape brain function and contribute to mental health disorders later in life. A critical step toward bridging the gap between genetics and environment in brain health.

Check out the press release ⬇️

🧵6/6

⚠️ Why it matters: We show how environmental factors, like GC exposure, can converge to affect brain development through common molecular mechanisms as genetic risk factors: priming of the inhibitory neuron lineage.

🧵5/6

We identified PBX3 as an example of a TF that is closely linked to the inhibitory neuron lineage priming. In silico perturbation experiments of multimodal GRNs suggest PBX3 as a potential mediator of the effect. 🧬🔑


🧵4/6

Our findings show that chronic GC exposure alters lineage specification, with a selective priming of the inhibitory neuron lineage. 🧠


🧵3/6

In our study, we looked at how chronic GC exposure affects neural differentiation and lineage specification in human neural organoids, using single-cell techniques to map the molecular changes in detail. 🔬🧬

🧵2/6

🚨🧠 New paper alert: Stress alters neuronal balance in the developing brain 🧠🚨

Our latest study in @science.orgAdvances explores how glucocorticoid exposure—a key environmental risk factor—shapes early human brain development using #organoids.
@mpi-psychiatry.bsky.social @drcricru.bsky.social

🧵👇

Insightful study by L. Dony @anthikrontira.bsky.social @drcricru.bsky.social @binderlabmpip.bsky.social @silvianeuro.bsky.social @fabiantheis.bsky.social on the effects of chronic exposure to glucocorticoids for neurodevelopment. Organoid model reveals amplification of inhibitory neuron cell fate 🧪

When applying machine learning to human health data, it is not enough to just improve a metric by another percent. We have to go deeper. In our perspective in Nature Cell Biology, we discuss caveats and biases of human single-cell data analysis: nature.com/articles/s41...
🧵 1/10

Good to see moscot-tools.org published in @nature.com ! We made existing Optimal Transport (OT) applications in single-cell genomics scalable and multimodal, added a novel spatiotemporal trajectory inference method and found exciting new biology in the pancreas! tinyurl.com/33zuwsep

If diving into scientific papers isn’t on your pre-Christmas to-do list, @spiegel.de has you covered! 📰 They featured our Neural Organoid Atlas in a piece on the Human Cell Atlas and related advancements in machine learning. 🤖🧬 It’s a great overview of this exciting field and the work behind it.

And of course to our amazing PIs @graycamplab.bsky.social, @fabiantheis.bsky.social, and Barbara Treutlein for all their guidance and support! 🚀

This work is part of the Human Cell Atlas effort to map all human cells. Explore more @natureportfolio.bsky.social: www.nature.com/immersive/d4...

🧵8/8

A huge thank you to all collaborators: @chatgtp.bsky.social , @katelynxli.bsky.social, Irena Slišković, Hsiu-Chuan Lin, Malgorzata Santel, Alexander Atamian, @giorgiaquadrato.bsky.social, Jieran Sun, @sergiuppasca.bsky.social & the Human Cell Atlas Organoid Biological Network. 🙏
🧵7/8

Contextualising New Data 🗺: The atlas serves as a powerful tool for annotating cell types, comparing protocols, and contextualising your new neural organoid scRNA-seq dataset. We provide a Python package (github.com/devsystemsla...) and interactive web interface (through www.archmap.bio#/).

🧵6/8

Disease Modeling 😷 : Our atlas can be leveraged as a diverse control cohort to contextualise organoid models of disease, helping identify underlying genes and pathways. We found that comprehensive control data is vital for disentangling disease from regional effects.

🧵5/8

Quantifying Organoid Fidelity 📊: By estimating the transcriptomic similarity between primary and organoid brain counterparts, we provide a robust framework for assessing protocol variation and fidelity across labs and methods. Cell stress seems to be quite dependent on protocol.

🧵4/8

Identifying Missing Cell States 🔍: We map neural organoid cell types and states to a developing human brain reference, highlighting gaps in the diversity of brain regions present in current in vitro models. ⚠️While the telencephalon seems well-captured, this is not true for all brain regions.

🧵3/8

Introducing the Human Neural Organoid Cell Atlas 🗺️: We’ve integrated 36 neural organoid datasets across 26 protocols. This produced a comprehensive, integrated reference atlas, including a hierarchical cell-type annotation, partially derived by mapping to primary human 🧠.


🧵2/8

Super excited to share our Human Neural Organoid Atlas, now out in Nature! Led by @zhisonghe.bsky.social @josch1.bsky.social, and myself, this resource was created from 36 scRNA-seq datasets—totalling over 1.7 million cells! 🔬✨
 www.nature.com/articles/s41...


Find out how it can serve you ⏬

🧵1/8