So excited our single-cell transcriptomic survey of the adult human brain is on bioRxiv! Sten Linnarsson Alejandro Mossi Kawai Ernest Arenas A really fun collaboration with Rebecca Hodge, Trygve Bakken, Ed Lein and others at the Allen Institute doi.org/10.1101/2022.1…

Excited to present our new preprint! We sequenced 2.4 million marmoset brain cell nuclei across major neocortical and subcortical structures. Here’s what we learned. biorxiv.org/content/10.110…

Excited to share the single-cell adult #macaque brain atlas—our contribution to a big week of #brainatlas preprints! W/ Xingfan Fanny Huang, Michael Platt, Jay Shendure, & Noah Snyder-Mackler—we profiled 4.2M nuclei across 30 regions from females+males. Here’s what we found bit.ly/3CL0zpQ

Census: accurate, automated, deep, fast, and hierarchical scRNA-seq cell-type annotation biorxiv.org/content/10.110…

2/n Here, we propose NCEM (nature.com/articles/s4158…) and leverage spatial proximity of cells in tissues as a prior for statistical dependency. We use graph neural networks to capture this dependency and relate this statistical phenomenon to cell communication and tissue niches.

I’m thrilled to be at the #SACNAS conference this year in Puerto Rico. If you are here stop by the CZI booth 1115 to learn more about our science team. I’m happy to share about our work in #singlecell and #cellxgene.

Amazing week for #DeepLearning in #spatial #singlecell biology, with 2🔥new Graph Neural Networks methods! 1.STELLAR🇺🇸 Jure Leskovec: a cell type annotation & discovery atlas-type framework 2.NCEM🇪🇺 Fabian Theis: an approach to infer cellular communication patterns Deep dive below🧵

We had seen embryonic expression of transposable elements as means of protecting the genome of plants before. Amazing to see a similar process in humans!!

Happy to share our latest work (w/ Natasa Tagasovska, Stephen Ra, Kyunghyun Cho, Jonathan Pritchard and Aviv Regev) about learning causal representations of single-cell perturbation data sets arxiv.org/pdf/2211.03553….

“Where’s my gene?” A tweetorial 🧵on how to use #CZCellxGene to answer this question using data from multiple datasets

We are excited to release Seurat v5- with new methods for multimodal, spatially resolved, and massively scalable single-cell analysis. satijalab.org/seurat

Excited for the new opportunities that the #CZCellxGene Census opens up to the Single-Cell community. Made from community-contributed data, e.g. Human Cell Atlas, the Census expedites single-cell data access! I am so proud of the Census team at CZI to get this out in the open.

I am beyond excited to share that SIMBA, a versatile single-cell graph embedding method, has been published Nature Methods nature.com/articles/s4159… (1/6)

We are excited to share Geneformer, our foundation model pretrained on 30 million single cell transcriptomes to enable predictions in network biology. Manuscript: rdcu.be/ddrx0 Model: huggingface.co/ctheodoris/Gen… Pretraining corpus: huggingface.co/datasets/ctheo…

🚨New #CZCellxGene Census Python package alert: Now you can calculate average & variance gene expression and find highly variable genes across 33M+ cells with just a standard laptop 💻! Get started streaming large scale #SingleCell analyses: bit.ly/44TwX5L

New to CZ #CELLxGENE Census: A normalized expression layer & gene and cell stats for all 33M cells! In Python and R you can work with #SingleCell CPM values and quickly filter genes and cells, for example get all cells with more than 100 expressed genes. bit.ly/normalized_lay…

1/6 The CZI Science team’s preprint on how CZ #CellxGene Discover serves as a centralized hub for standardized, interoperable and openly available #SingleCell matrices is out! Really proud of what we’re building to address the community’s needs bit.ly/40kFX2W 🧵

I'm honored to have worked with an amazing team at CZI Science and comp bios to deliver the first marketplace of models and embeddings along one of the largest aggregations of standardized #singlecell data from #CELLxGENE Census. Explore the models! bit.ly/census_models

I'm excited to announce that starting this week CELLxGENE Census supports categorical variables for cell metadata of the now 59M cells . Fetching data will now utilize less memory!! However in some cases the change may break existing code. Details here: chanzuckerberg.github.io/cellxgene-cens…

Proud to be part of an amazing group of engineers, scientists, and program officers contributing to developing CELLxGENE to further cell bio research. Now with gene expression for >85M cells, our free and open-source tools enable cell biologists to advance their research.