Peer-Reviewed Publication
Nat Commun2025;16(1):11674.November 27, 2025Journal Article
A deep learning-based multiscale integration of spatial omics with tumor morphology.
Benoît Schmauch1, Loïc Herpin2, Antoine Olivier2, Thomas Duboudin2, Rémy Dubois2, Lucie Gillet2, Alexandre Filiot2, Jean-Baptiste Schiratti2, Valentina Di Proietto2, Delphine Le Corre3, Alexandre Bourgoin4, Julien Taïeb3,5, Jean-François Emile6,7, Wolf H Fridman3, Elodie Pronier2, Pierre Laurent-Puig3,8, Eric Y Durand2
1Owkin, Paris, France. benoit.schmauch@owkin.com.
2Owkin, Paris, France.
3Centre de Recherche des Cordeliers, INSERM, Sorbonne Université, Université de Paris, F-75006, Paris, France.
4Direction de la Recherche Clinique, de l'Innovation, des Relations avec les universités et les organismes de recherche (DRCI), Assistance Publique-Hôpitaux de Paris (APHP), Paris, France.
5Institut du cancer Paris Carpem, APHP, department of Garoenterology & Digestive Oncology, APHP.Centre-Université Paris Cité, Paris, France.
6Paris-Saclay University, Versailles SQY University (UVSQ), EA4340-BECCOH, Boulogne, France.
7Assistance Publique-Hôpitaux de Paris (APHP), Ambroise Paré Hospital, Smart Imaging, Service de Pathologie, Boulogne, France.
8Institut du Cancer Paris CARPEM, APHP, Department of Biology, APHP.Centre-Université Paris Cité, Paris, France.
Abstract
Spatial Transcriptomics (spTx) offers unprecedented insights into the spatial arrangement of the tumor microenvironment, tumor initiation/progression and identification of new therapeutic target candidates. However, spTx remains unlikely to be routinely used in the near future. Hematoxylin and eosin (H&E) stained histological slides, on the other hand, are routinely generated for a large fraction…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans