A deep learning-based multiscale integration of spatial omics with tumor morphology.
Benoît Schmauch, Loïc Herpin, Antoine Olivier, Thomas Duboudin, Rémy Dubois, Lucie Gillet, Alexandre Filiot, Jean-Baptiste Schiratti, Valentina Di Proietto, Delphine Le Corre, Alexandre Bourgoin, Julien Taı̈eb, Jean‐François Emile, Wolf H. Fridman, Elodie Pronier, , Eric Y. Durand
This paper introduces MISO, a deep learning method that predicts spatial transcriptomics data from H&E slides, enabling spatially resolved gene expression and patient representation for downstream tasks.
Nature Communications · Nov 27, 2025Peer-reviewedBioinformatics