{
  "abstract": "The rapid expansion of single-cell RNA sequencing (scRNA-seq) has made accurate cell type annotation a critical bottleneck for biological discovery. Existing computational methods are often limited by reference data dependency, while emerging single Large Language Model (LLM) approaches are susceptible to model-specific biases and provide insufficient uncertainty quantification. To address these limitations, we introduce mLLMCelltype, a framework that harnesses collective intelligence-the emergent problem-solving capacity arising when multiple independent agents interact through structured deliberation to produce solutions exceeding individual capabilities-of multiple LLMs through an iterative deliberation process. Across 49 diverse datasets, our framework achieves a mean accuracy of 77.2%, a 15.7-percentage-point improvement over the best-performing single-LLM baseline (61.5%). The consensus mechanism demonstrates high robustness to noisy input and generalizes to datasets released after the LLMs' training. By providing transparent reasoning chains and robust consensus-based confidence metrics, mLLMCelltype minimizes manual annotation effort and enables reliable interpretation of complex cellular landscapes. The framework is available as an open-source package and an accessible web server.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Statistics, Texas A&M University, College Station, TX, USA",
    "Department of Statistics, Texas A&M University, College Station, TX, USA. zhangxiany@stat.tamu.edu",
    "Division of Computational Biology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN, USA. Chen.Jun2@mayo.edu"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yang Chen",
      "orcid": "0009-0009-9151-2901"
    },
    {
      "affs": [
        1
      ],
      "name": "Xianyang Zhang",
      "orcid": "0000-0002-2512-1816"
    },
    {
      "affs": [
        2
      ],
      "name": "Jun Chen",
      "orcid": "0000-0003-0563-542X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7kas40a4yn9jc.bib",
  "cited_by": 16,
  "doi": "10.1038/s42003-026-10420-8",
  "fulltext_url": null,
  "id": "7kas40a4yn9jc",
  "issns": [
    "2399-3642"
  ],
  "landing_url": "https://doi.org/10.1038/s42003-026-10420-8",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W4409727640",
  "pdf_url": "https://www.nature.com/articles/s42003-026-10420-8_reference.pdf",
  "pmcid": null,
  "pmid": "42260142",
  "published": "2026-06-08",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/7kas40a4yn9jc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:26:46Z",
      "native_id": "W4409727640",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s42003-026-10420-8"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "openalex:1312|Single-cell and spatial transcriptomics",
      "subfield": "molecular-biology"
    }
  ],
  "title": "Large language model consensus substantially improves the cell type annotation accuracy for scRNA-seq data",
  "title_text": "Large language model consensus substantially improves the cell type annotation accuracy for scRNA-seq data",
  "type": "peer-reviewed",
  "updated_at": "2026-11-05T13:20:46Z",
  "url": "https://research.draconitic.com/paper/7kas40a4yn9jc",
  "venue": "Communications Biology",
  "versions": []
}