{
  "abstract": "Single-cell RNA sequencing measures cellular states at high resolution, but sparse high-dimensional count data remain difficult to model interpretably. We introduce the Single-Cell Euclidean Network Embedding (SCENE), a probabilistic latent-distance model that jointly embeds cells and genes from Unique Molecular Identifier (UMI) counts. SCENE treats the count matrix as a weighted bipartite cell-gene graph, where Euclidean distances represent transcriptional affinity, and combines this geometry with a zero-inflated count likelihood that separates gene detection from expression magnitude. Across real and simulated scRNA-seq datasets, SCENE recovers biologically structured cell and gene embeddings with state-of-the-art performance. Surprisingly, major biological structure is preserved in native two- and three-dimensional latent spaces, enabling directly interpretable visualization. Perturbation analyses show that SCENE organizes glucocorticoid-response genes and T-cell receptor regulatory programs coherently in gene space, capturing biology beyond cell-type separation. SCENE provides a transparent representation learning framework in which low-dimensional Euclidean geometry supports accurate modeling and biological interpretation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "O. L. Moberg"
    },
    {
      "name": "M. B. Petersen"
    },
    {
      "name": "T. Herlau"
    },
    {
      "name": "L. E. Kristensen"
    },
    {
      "name": "L. E. Jessen"
    },
    {
      "name": "M. Morup"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9jn59xdmvybqn.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.12.750699",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.12.750699v1.full",
  "id": "9jn59xdmvybqn",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.12.750699v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7213592021",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.12.750699v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9jn59xdmvybqn.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:09Z",
      "native_id": "10.64898/2026.09.12.750699",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.12.750699v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Setting the SCENE for Interpretable Cell-Gene Embeddings in Single-Cell RNA-seq",
  "title_text": "Setting the SCENE for Interpretable Cell-Gene Embeddings in Single-Cell RNA-seq",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:09Z",
  "url": "https://research.draconitic.com/paper/9jn59xdmvybqn",
  "venue": "bioRxiv",
  "versions": []
}