{
  "abstract": "Cell-type deconvolution, the task of estimating the proportions of constituent cell types in a heterogeneous biological sample, is a core problem in computational biology. Methods that rely on epigenetic marks such as DNA methylation typically operate on aggregated methylation estimates, discarding the pattern-level information carried by individual DNA reads. Existing read-level approaches that exploit this information are scarce, and all remain restricted to few-class settings; scaling them further is an open problem because, at scale, non-discriminative reads dominate and hard labels conflict with the many-to-many mapping between methylation patterns and cell types, preventing classifier convergence. To overcome this, we propose data-driven soft labels that estimate the conditional cell-type distribution for each read, and integrate this scheme into $Syto$, a new modular framework for read-level classification-based deconvolution. On a whole-body atlas of 39 human cell types, $Syto$ reduces MSE by 3.7$\\times$ over the best examined baseline, with gains transferring to an out-of-distribution dataset spanning 16 tissues. $Syto$ lays the foundation for modeling increasingly large cell-type panels, with improved applications in biology and healthcare. The proposed soft-labeling scheme is further translatable to any setting with a many-to-many signal-to-label mapping.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.04987",
  "author_total": 3,
  "authors": [
    {
      "name": "Dmytro Rizdvanetskyi"
    },
    {
      "name": "Nathan Roos"
    },
    {
      "name": "Pavlo Lutsik"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e1nz8nyfa0vnt.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.04987",
  "fulltext_url": null,
  "id": "e1nz8nyfa0vnt",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.04987",
  "language": null,
  "licence": "CC-BY-SA-4.0",
  "licence_label": "CC BY-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1312|Single-cell and spatial transcriptomics"
    ]
  ],
  "openalex": "W7167577387",
  "pdf_url": "https://arxiv.org/pdf/2607.04987",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-20",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/e1nz8nyfa0vnt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:08Z",
      "native_id": "2607.04987",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.04987"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    },
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution",
  "title_text": "Data-Driven Soft Labeling Scales DNA Read Classification to Whole-Body Cell-Type Deconvolution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:08Z",
  "url": "https://research.draconitic.com/paper/e1nz8nyfa0vnt",
  "venue": "arXiv",
  "versions": []
}