7/ This project has been possible because of all the awesome people involved! Especially @javdh.bsky.social, Tony Kuo, Aviv Regev, & Hector Corrada Bravo

GitHub - Genentech/scimilarity: A unifying representation of single cell expression profiles that quantifies similarity between expression states and generalizes to represent new studies without addit... A unifying representation of single cell expression profiles that quantifies similarity between expression states and generalizes to represent new studies without additional training. - Genentech/s...

6/ SCimilarity is open-source and available as a Python API, enabling easy querying, embedding, annotating, and analyzing single-cell data. Check it out for your own research today! 💻 github.com/Genentech/sc...

5/ There were also similar cells found growing in a new 3D culture system.🤔 A new cell model?💡It activated many marker genes! We would’ve never considered this model because it was designed to expand HSCs from PBMCs, completely unrelated to ILD macrophages! 🙌

4/ We used SCimilarity to search for macrophage profiles from interstitial lung disease and found similar profiles in other fibrotic diseases and tissues. 🔍

3/ You can use SCimilarity to represent single-cell profiles without retraining, quantify cell similarity of millions of cells, or quickly annotate cell types✨

2/ With SCimilarity, perform searches across a reference database of 23.4M cells from 412 diverse studies in under a second! 🔍🧬⚡

1/ Introducing SCimilarity, a new foundation model to explore single-cell RNA-seq data across tissues and diseases! It learns a common measure of cell similarity by training a deep metric learning model on millions of cells from various human tissues and conditions. www.nature.com/articles/s41...