{
  "abstract": "Predicting molecular receptor status, including estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2), directly from routine hematoxylin and eosin (H&E)-stained whole-slide images (WSIs) could reduce reliance on costly immunohistochemistry, but image-only models have no access to the transcriptomic programs that define these subtypes. Here we show that coupling a whole-slide vision transformer (GigaPath) with bulk RNA-sequencing profiles through a training-time-only contrastive objective improves receptor-status classification from WSIs alone, without requiring any RNA-seq data at inference. Rather than training a dedicated bulk-transcriptomics encoder, we purpose the gene-sentence encoding and pretrained text encoder from BioBERT1 and apply them to bulk RNA-seq profiles from The Cancer Genome Atlas breast cancer cohort (TCGA-BRCA). Under five-fold cross-validation, this RNA-guided pre-training consistently improved AUROC for ER, PR, and HER2 relative to a contrastive-pre-training-free baseline and reproducibly introduced receptor-relevant structure into the learned slide representation. However, evaluation on independent external cohorts revealed a striking, receptor-dependent divergence: gains for ER and PR, both governed by broad, multi-gene luminal transcriptional programs, generalized robustly, whereas the apparent AUROC improvement for HER2, driven by focal ERBB2 amplification rather than a coordinated transcriptional signature, masked a severe loss of classification sensitivity at the operating threshold. These findings establish training-time transcriptomic supervision as a practical route to enhancing histology-only molecular subtyping, while showing that gene-selection strategy, and not model architecture alone, determines which molecular alterations such supervision can teach a vision model to recognize.",
  "abstract_shown": true,
  "affiliations": [
    "Boston University Chobanian & Avedisian School of Medicine"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "A. Zou"
    },
    {
      "name": "E. Huang"
    },
    {
      "name": "Q. Wu"
    },
    {
      "name": "M. E. Barnard"
    },
    {
      "affs": [
        0
      ],
      "name": "C. Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ekh1z1mpwv579.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.24.754149",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754149v1.full",
  "id": "ekh1z1mpwv579",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754149v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "pathology"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7214910731",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754149v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ekh1z1mpwv579.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:29Z",
      "native_id": "10.64898/2026.09.24.754149",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.24.754149v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "biorxiv:pathology",
      "subfield": "general"
    }
  ],
  "title": "RNA-guided contrastive learning enhances patient-level prediction from histology",
  "title_text": "RNA-guided contrastive learning enhances patient-level prediction from histology",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:29Z",
  "url": "https://research.draconitic.com/paper/ekh1z1mpwv579",
  "venue": "bioRxiv",
  "versions": []
}