A deep learning-based multiscale integration of spatial omics with tumor morphology

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 of cancer patients. Here, we present a deep learning-based approach for multiscale integration of spTx with tumor morphology (MISO). We train MISO to predict spTx from H&E and validate it on a dataset of 72 10X Genomics Visium samples. We further validate our approach on 348 samples from five indications from the MOSAIC consortium and show that MISO significantly outperforms competing methods in extensive benchmarks. We demonstrate that MISO enables near single-cell-resolution, spatially-resolved gene expression prediction.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-11-27
DOI
https://doi.org/10.1038/s41467-025-66691-y
Primary Topic
Single-cell and spatial transcriptomics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A deep learning-based multiscale integration of spatial omics with tumor morphology

Benoît Schmauch, Julien Taı̈eb, Elodie Pronier, Eric Y. Durand et al.
Nature Communications
Single-cell and spatial transcriptomics
article

A deep learning-based multiscale integration of spatial omics with tumor morphology

Benoît Schmauch, Julien Taı̈eb, Elodie Pronier, Eric Y. Durand, Valentina Di Proietto, Thomas Duboudin, Jean-Baptiste Schiratti, Loïc Herpin, Delphine Le Corre, Jean‐François Emile, Rémy Dubois, Antoine Olivier, Wolf H. Fridman, Alexandre Filiot, Pierre Laurent‐Puig, Lucie Gillet, A Bourgoin
article en

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 of cancer patients. Here, we present a deep learning-based approach for multiscale integration of spTx with tumor morphology (MISO). We train MISO to predict spTx from H&E and validate it on a dataset of 72 10X Genomics Visium samples. We further validate our approach on 348 samples from five indications from the MOSAIC consortium and show that MISO significantly outperforms competing methods in extensive benchmarks. We demonstrate that MISO enables near single-cell-resolution, spatially-resolved gene expression prediction.

Nature CommunicationsVol. 16(1)
Inserm (FR), Université de Versailles Saint-Quentin-en-Yvelines (FR), Université Paris Cité (FR), Université Paris-Saclay (FR), Sorbonne Université (FR), Université Sorbonne Paris Nord (FR), Centre de Recherche des Cordeliers (FR), Assistance Publique – Hôpitaux de Paris (FR), Hôpital Ambroise-Paré (FR), Owl Research Institute (US)
University of Pittsburgh, Centre Hospitalier Universitaire Vaudois, Institut Gustave-Roussy, Universitätsklinikum Erlangen
Openalex Percentile: Top 66%
Single-cell and spatial transcriptomics
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.