{
  "abstract": "To our knowledge, scRM is the first single-cell foundation model trained on sequencing reads, demonstrating that raw data pretraining is not only feasible but competitive at a fraction of the computational cost. We anticipate that scaling this framework and exploring alternative architectures will unlock biological information inaccessible to count models and extend the dataset-specific pretraining it already makes possible. The source code is available at https://github.com/altos-labs/scRM.",
  "abstract_shown": true,
  "affiliations": [
    "Altos Labs"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "D. He"
    },
    {
      "name": "R. Patro"
    },
    {
      "name": "M. Nassar"
    },
    {
      "name": "H. Wu"
    },
    {
      "name": "Q. Yan"
    },
    {
      "name": "G. Xu"
    },
    {
      "name": "K. Torkenczy"
    },
    {
      "name": "J. Liu"
    },
    {
      "name": "S. Tyanova"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7ezag25t1ayyh.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.24.761590",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.24.761590v1.full",
  "id": "7ezag25t1ayyh",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.24.761590v1",
  "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": "W7225118949",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.24.761590v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7ezag25t1ayyh.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T12:20:51Z",
      "native_id": "10.64898/2026.10.24.761590",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.24.761590v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "scRM: A single-cell foundation model trained on scRNA-seq reads",
  "title_text": "scRM: A single-cell foundation model trained on scRNA-seq reads",
  "type": "preprint",
  "updated_at": "2026-11-05T00:21:17Z",
  "url": "https://research.draconitic.com/paper/7ezag25t1ayyh",
  "venue": "bioRxiv",
  "versions": []
}