{
  "abstract": "Single-cell foundation models (scFMs) increasingly rely on large-scale transcriptomic pretraining, yet expanding pretraining data can yield diminishing gains while substantially increasing computational cost. Our data scaling analyses showed that incorporating biological knowledge, including cell-level text annotation and gene-level regulatory information, provided additional scaling dimension than simply increasing data size. Motivated by this observation, we present scKITE, a simple yet effective scFM that integrates cell-annotation and gene-regulatory supervision into a shared transcriptomic Transformer encoder through lightweight auxiliary decoders. These decoders are used only during pretraining and subsequently discarded, yielding a general-purpose encoder enriched with biological knowledge for downstream applications. With only 179,067 pretraining samples, i.e., less than 0.5\\% of those used by previous strong scFMs, scKITE outperformed these models across diverse downstream tasks, highlighting knowledge-enhanced pretraining as a promising paradigm for biologically grounded scFMs.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.14970",
  "author_total": 10,
  "authors": [
    {
      "name": "Hanqing Zhang"
    },
    {
      "name": "Jie Bao"
    },
    {
      "name": "Mei Ma"
    },
    {
      "name": "Shuai Liu"
    },
    {
      "name": "Jiaying Ma"
    },
    {
      "name": "Jiaguan Liu"
    },
    {
      "name": "Jiaxiao Li"
    },
    {
      "name": "Zhenbo Li"
    },
    {
      "name": "Wenwen Gong"
    },
    {
      "name": "Zhijun Ca"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0e4b0h2btpk1z.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.14970",
  "fulltext_url": null,
  "id": "0e4b0h2btpk1z",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.14970",
  "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.AI"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7213251894",
  "pdf_url": "https://arxiv.org/pdf/2609.14970",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0e4b0h2btpk1z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:30Z",
      "native_id": "2609.14970",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.14970"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Towards a knowledge-enhanced single-cell foundation model",
  "title_text": "Towards a knowledge-enhanced single-cell foundation model",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:30Z",
  "url": "https://research.draconitic.com/paper/0e4b0h2btpk1z",
  "venue": "arXiv",
  "versions": []
}