{
  "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 We trained MISO to predict spTx from H&E on a new unpublished dataset of 72 10X Genomics Visium samples, and derived a novel estimate of the upper bound on the achievable performance.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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 17,
  "authors": [
    {
      "name": "Benoît Schmauch"
    },
    {
      "name": "Loïc Herpin"
    },
    {
      "name": "Antoine Olivier"
    },
    {
      "name": "Thomas Duboudin"
    },
    {
      "name": "Rémy Dubois"
    },
    {
      "name": "Lucie Gillet"
    },
    {
      "name": "Alexandre Filiot"
    },
    {
      "name": "Jean-Baptiste Schiratti"
    },
    {
      "name": "Valentina Di Proietto"
    },
    {
      "name": "Delphine Le Corre"
    },
    {
      "name": "Alexandre Bourgoin"
    },
    {
      "name": "Julien Taïeb"
    },
    {
      "name": "Jean-François Emile"
    },
    {
      "name": "Wolf H. Fridman"
    },
    {
      "name": "Elodie Pronier"
    },
    {
      "name": "Pierre Laurent-Puig"
    },
    {
      "name": "Eric Y. Durand"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6t62ngpebd8g2.bib",
  "cited_by": 26,
  "doi": "10.1038/s41467-025-66691-y",
  "fulltext_url": null,
  "id": "6t62ngpebd8g2",
  "issns": [
    "2041-1723",
    "2041-1723"
  ],
  "landing_url": "https://hal.science/hal-05851873v1",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.sdv"
    ],
    [
      "hal",
      "1.sdv.bbm"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W4416772233",
  "pdf_url": "https://www.nature.com/articles/s41467-025-66691-y_reference.pdf",
  "pmcid": null,
  "pmid": "41310346",
  "published": "2026-11-04",
  "publisher": "Nature Publishing Group",
  "ris": "https://research.draconitic.com/paper/6t62ngpebd8g2.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:13Z",
      "native_id": "hal-05851873",
      "source": "hal",
      "url": "https://hal.science/hal-05851873v1"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Single-cell and spatial transcriptomics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "A deep learning-based multiscale integration of spatial omics with tumor morphology",
  "title_text": "A deep learning-based multiscale integration of spatial omics with tumor morphology",
  "type": "peer-reviewed",
  "updated_at": "2026-11-06T12:20:44Z",
  "url": "https://research.draconitic.com/paper/6t62ngpebd8g2",
  "venue": "Nature Communications",
  "versions": []
}