{
  "abstract": "Nanopore sequencing reads nucleic acids as changes in ionic current that carry information beyond the base sequence. Self-supervised pretrained models have advanced genomic sequence modeling and single-cell analysis, but remain underexplored for raw nanopore signals, which are continuous and lack a native token vocabulary. Here we present Brieno, an approach combining reconstruction-based tokenization through residual vector quantization with a Transformer for contextual representation learning. We pretrain the Transformer using masked-token prediction on raw nanopore signals from 118 million reads. With frozen or fine-tuned features, the model identifies species without requiring reference genomes. It complements Dorado by accurately classifying reads left unclassified in native-barcode demultiplexing, approaches Dorado's basecalling performance across six genomes, and exceeds Dorado's specialized 5-methylcytosine model as well as a dedicated 6-methyladenine caller. Brieno also supports accurate CpG methylation detection with limited labeled data. Across tasks, pretrained contextual representations improve downstream performance over non-pretrained baselines and generalize across sequencing runs. Together, these findings support self-supervised pretraining as a basis for transferable representations of raw nanopore signals.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "G. Cheng"
    },
    {
      "name": "E. Pitkänen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0rkzb35vpkrnx.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.05.764536",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764536v1.full",
  "id": "0rkzb35vpkrnx",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764536v1",
  "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": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764536v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0rkzb35vpkrnx.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T00:21:14Z",
      "native_id": "10.64898/2026.11.05.764536",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.05.764536v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Towards a foundation model for raw nanopore signal through discrete tokenization",
  "title_text": "Towards a foundation model for raw nanopore signal through discrete tokenization",
  "type": "preprint",
  "updated_at": "2026-11-08T00:21:05Z",
  "url": "https://research.draconitic.com/paper/0rkzb35vpkrnx",
  "venue": "bioRxiv",
  "versions": []
}