{
  "abstract": "Identifying cell types from single-cell RNA sequencing (scRNA-seq) data typically requires several separate and often uninterpretable steps: dimensionality reduction, batch-correction, clustering, marker-gene identification and the discovery of finer-grained structure. Here we introduce scFLAME (single-cell Factor Latent Analysis with Mixture Embeddings), a probabilistic generative model that unifies these tasks: a negative binomial factor analysis of the raw counts - which can be adjusted for batch - is coupled to a Gaussian mixture prior over the latent space, learning the embedding and clustering jointly, while a shared linear decoder provides cluster-specific marker genes directly from the fitted model, and a merging procedure recovers a probabilistic hierarchy of finer-grained partitions. On simulated and real data, scFLAME matches or exceeds state-of-the-art clustering accuracy, is robust across sequencing platforms, and scales near-linearly to hundreds of thousands of cells. scFLAME thus replaces a chain of separate tools with a single, interpretable model for single-cell analysis.",
  "abstract_shown": true,
  "affiliations": [
    "MRC Biostatistics Unit"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "J. Rao"
    },
    {
      "name": "M. Jihad"
    },
    {
      "name": "G. Biffi"
    },
    {
      "name": "P. D. Kirk"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dtmbzv9habtn8.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.04.749363",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1.full",
  "id": "dtmbzv9habtn8",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1",
  "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": "W7212005253",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dtmbzv9habtn8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:19Z",
      "native_id": "10.64898/2026.09.04.749363",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.04.749363v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "scFLAME: a unified generative model for interpretable clustering, hierarchical structure discovery and marker-gene identification in single-cell RNA-seq data",
  "title_text": "scFLAME: a unified generative model for interpretable clustering, hierarchical structure discovery and marker-gene identification in single-cell RNA-seq data",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:19Z",
  "url": "https://research.draconitic.com/paper/dtmbzv9habtn8",
  "venue": "bioRxiv",
  "versions": []
}