{
  "abstract": "Introduction: Spatial multi‐omics technologies jointly profile multiple molecular layers in situ, enabling integrated characterization of tissue organization and cellular states. However, many graph-based approaches remain computationally demanding because they rely on repeated message passing over global graphs, whereas naive local sampling may disrupt cell-level correspondence when multimodal features and graph topologies are not induced synchronously. Moreover, simple concatenation or fixed-weight fusion does not explicitly account for unequal uncertainty between expression‐derived and spatial evidence, making the learned representations sensitive to feature corruption, technical noise and modality inconsistency.\n\nMethods: We present SubPoE, a subgraph-induced Product-of-Experts framework for spatial multi‐omics integration. SubPoE synchronously induces aligned local subgraphs from modality‐specific molecular similarity graphs and a shared spatial graph, preserving molecular‐similarity topology correspondence while reducing per‐iteration graph complexity. Dual‐topology variational graph encoders model expression-derived structure and spatial context as probabilistic experts, which are adaptively fused according to their uncertainty through a Product‐of‐Experts formulation. A composite self-supervised objective further improves robustness and cross‐modal alignment.\n\nResults: Across eight public paired spatial multi‐omics datasets, SubPoE achieves competitive and comparatively stable performance against existing methods. Ablation, sensitivity, robustness and efficiency experiments further support the contributions of synchronous subgraph induction and uncertainty‐aware fusion.\n\nDiscussion: These results establish SubPoE as an effective approach for learning topology‐preserving, uncertainty-aware representations of heterogeneous spatial multi‐omics data.",
  "abstract_shown": true,
  "affiliations": [
    "School of Medicine and Health, Harbin Institute of Technology, Harbin, China",
    "Zhengzhou Advanced Research Institute of Harbin Institute of Technology, Zhengzhou, China",
    "School of Computer Science and Technology, Zhoukou Normal University, Zhoukou, China",
    "School of Artificial Intelligence, Henan University, Zhengzhou, China",
    "College of Animal Science and Technology, Henan University of Animal Husbandry and Economy, Zhengzhou, China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Yuanfang Li"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Wentao Gao"
    },
    {
      "affs": [
        3
      ],
      "name": "Junhao Ren"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Qianran Wei"
    },
    {
      "affs": [
        4
      ],
      "name": "Xinlei Wang"
    },
    {
      "affs": [
        4
      ],
      "name": "Liheng Zhang"
    },
    {
      "affs": [
        4
      ],
      "name": "Ruiting Li"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Yadong Wang"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Xiao Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2msejc7y33jyf.bib",
  "cited_by": 0,
  "doi": "10.3389/fgene.2026.1977260",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13734670/",
  "id": "2msejc7y33jyf",
  "issns": [
    "1664-8021"
  ],
  "landing_url": "https://doi.org/10.3389/fgene.2026.1977260",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7223096096",
  "pdf_url": "https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2026.1977260/pdf",
  "pmcid": "PMC13734670",
  "pmid": "42985653",
  "published": "2026-10-22",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/2msejc7y33jyf.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T12:24:06Z",
      "native_id": "PMC13734670",
      "source": "pmc",
      "url": "https://doi.org/10.3389/fgene.2026.1977260"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Single-cell and spatial transcriptomics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "SubPoE: a subgraph-induced Product-of-Experts framework for spatial multi-omics integration",
  "title_text": "SubPoE: a subgraph-induced Product-of-Experts framework for spatial multi-omics integration",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:24:06Z",
  "url": "https://research.draconitic.com/paper/2msejc7y33jyf",
  "venue": "Frontiers in Genetics",
  "versions": []
}