Many thanks to our collaborators Egle-Helene Ervin and @bb-lab.bsky.social, to @asarigun.bsky.social and @denizgermen.bsky.social for their work and to @juliosaezrod.bsky.social and @tanevski.bsky.social for their support and guidance.

Beyond prediction, SpaCEy identifies compact and interpretable spatial patterns associated with outcomes such as survival and disease progression, with strong results across lung and breast cancer spatial proteomics datasets.

🎉 Happy to share our new work SpaCEy, now available🧬
SpaCEy is an explainable method for learning clinically relevant spatial tissue organization directly from spatial omics data—without predefined cell types or regions.
📄 Paper: www.biorxiv.org/content/10.6...
💻 Code repo: github.com/saezlab/SpaCEy

Over the past 3 years, we led a fantastic @wellcomeleap.bsky.social collaboration w. @oliverstegle.bsky.social, Behjati, Mall, Mair, @jamesbriscoe.bsky.social & @juliosaezrod.bsky.social labs. We created a massive multiomic atlas & new comp models to discover human GB biology www.gbmspace.org

🧠 Excited to share my main PhD project! We mapped the regulatory rules governing Glioblastoma plasticity using single-cell multi-omics and deep learning. This work is part of a two-paper series with @bayraktarlab.bsky.social @oliverstegle.bsky.social and @moritzmall.bsky.social, Preprint at end🧵👇