{
  "abstract": "Multiple instance learning (MIL) is the dominant framework for whole-slide image analysis in computational pathology, typically combining a frozen patch encoder, a projection layer, and a slide-level aggregator. While encoders and aggregators have been extensively studied, the projection layer remains a largely morphology-only bottleneck. This limits endpoints such as biomarker status and survival, which are governed by a molecular state that is not fully captured by H&E morphology. We introduce Molecularly Informed Staining Transform (MIST), a plug-in replacement for the MIL projection layer that uses paired spatial transcriptomics only during training to construct virtual molecular stains. MIST clusters gene expression profiles into cross-modal prototypes, anchors them in the frozen foundation model feature space, and uses them to reorganize H&E patch features along molecularly guided axes. It requires no transcriptomics at inference and can be inserted before standard MIL aggregators. We evaluate MIST across 23 downstream tasks and 8 MIL aggregators. MIST improves 240 of 256 configurations over the standard projection layer, with an average gain of +3.5%, observed consistently across endpoint types: +5.2% on survival prediction, +3.3% on tissue subtyping, and +2.6% on biomarker prediction. Ablations confirm that gene-derived prototypes are the primary source of the gains, while spatial, biological, and pathological analyses show that cross-modal prototype affinities capture spatially coherent molecular programs from H&E alone.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.16392",
  "author_total": 9,
  "authors": [
    {
      "name": "Yucheng Xing"
    },
    {
      "name": "Pei Liu"
    },
    {
      "name": "Jingying Ma"
    },
    {
      "name": "Ruping Hong"
    },
    {
      "name": "Jiangdong Qiu"
    },
    {
      "name": "Tianyu Liu"
    },
    {
      "name": "Kai He"
    },
    {
      "name": "Ling Huang"
    },
    {
      "name": "Mengling Feng"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7qp5q5dbfbaqe.bib",
  "cited_by": 1,
  "doi": "10.48550/arxiv.2605.16392",
  "fulltext_url": null,
  "id": "7qp5q5dbfbaqe",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.16392",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1702|AI in cancer detection"
    ]
  ],
  "openalex": "W7161749420",
  "pdf_url": "https://arxiv.org/pdf/2605.16392",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7qp5q5dbfbaqe.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T15:21:01Z",
      "native_id": "2605.16392",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.16392"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Bridging the Modality Bottleneck in Pathology MIL through Molecularly Guided Feature Adaptation",
  "title_text": "Bridging the Modality Bottleneck in Pathology MIL through Molecularly Guided Feature Adaptation",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:31Z",
  "url": "https://research.draconitic.com/paper/7qp5q5dbfbaqe",
  "venue": "arXiv",
  "versions": []
}