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 complex and 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 novel deep learning-based approach for multiscale integration of spTx with tumor morphology (MISO). We trained MISO to predict spTx from H&E on a new unpublished dataset of 72 10X Genomics Visium samples, and derived a novel estimate of the upper bound on the achievable performance. We demonstrate that MISO enables near single-cell-resolution, spatially-resolved gene expression prediction from H&E. In addition, MISO provides an effective patient representation framework that enables downstream predictive tasks such as molecular phenotyping or MSI prediction.
Competing Interest Statement
Persons affiliated with Owkin own stocks in the company (BS, LH, AO, TD, RD, LG, JBS, VDP, EP, ED). JT has received honoraria as a speaker or in an advisory role from Sanofi, Roche, Merck Serono, Amgen, Servier, Pierre Fabre, Lilly, AstraZeneca, and MSD. WHF is a consultant for Novartis, Adaptimmune, Anaveon, Catalym, OSE Immunotherapeutic, Oxford Biotherapeutics, Genenta and Parthenon. PLP has received honoraria as a speaker or in an advisory role from ESMO, Amgen, Servier, Pierre Fabre, Biocartis, and stocks from Methys DX.
