Using a GNN trained on transcript neighborhood graphs, pyTrance computes embeddings that encode spatial RNA localization. RNAs with similar embeddings are likely to co-localize.
And in addition to the postdoc position (1 week left to apply!), just opened a PhD position in AI and RNA biology 🤩
I'm very excited to announce that my PhD work is out on biorxiv!
pyTrance is a computational method to predict and quantify subcellular RNA co-localization from spatial transcriptomics data.
www.biorxiv.org/content/10.6...
Going one step further, we performed RNA-protein co-staining for Gad1, which showed a strong signal overlap, suggesting it is translated locally.
PhD position in my lab in #AI #RNA, in co-supervision with superstar @florianjug.bsky.social
www.polimi.it/dottorato/fu...
We validated and benchmarked pyTrance on simulated data, where it reliably clustered RNAs by their simulated subcellular localization patterns and identified further subclusters with different localization strength.
Check out the python package and documentation:
github.com/rajewsky-lab...
rajewsky-lab.github.io/pytrance/
Whats most exciting: In a Xenium mouse brain dataset we predicted four GABAergic markers (Gad1, Gad2, Hapln1, Kcnmb2) to co-localize in neuronal projections. Experimental validation confirmed our predictions.
(Col19a1 is used as negative control bellow)
1/6 We are hiring!!! 🐣🐣🐣
Fully funded postdoc position in my group!
humantechnopole.it/en/research-...
Big thanks to @cledicj.bsky.social , @nukappa.bsky.social , Nikolaus Rajewsky and the whole Rajewsky lab for the support throughout the project!
www.biorxiv.org
Contribute to rajewsky-lab/pytrance development by creating an account on GitHub.
