{
  "abstract": "Tokenization is a central design choice in genomic language models, yet most deoxyribonucleic acid (DNA) tokenizers use characters, fixed-length k-mers, or frequency-derived subwords without explicitly using prior information about the specificity of DNA-binding regulatory factors. We introduce Motif-Vocab, a biologically informed tokenizer that scans both DNA strands for statistically calibrated motif matches, emits transcription-factor (TF) identity tokens, and applies nucleotide, $k$-mer, or byte-pair encoding (BPE) to unmatched sequence. Motif-specific null distributions put position-weight matrices (PWMs) of different lengths and degeneracy on a common significance scale; deterministic overlap rules make the representation reproducible. In controlled Bidirectional Encoder Representations from Transformers (BERT) pretraining on two billion base pairs, real motif libraries outperform randomized-motif controls on 54 of 55 in-scope downstream tasks. On a motif-disjoint recognition task derived from DART-Eval Task 2, TF-specific tokens improve macro-F1 by 0.040 over a position-matched generic motif token and by 0.033 over a matched no-motif tokenizer (95\\% bootstrap confidence interval: 0.027--0.038). Motif tokens also receive stronger attribution and produce larger occlusion effects than shuffled controls. Dense no-motif tokenizers remain strong general-purpose baselines, including a near-tie on the five-task BERT-base panel. Thus, Motif-Vocab is not a universal accuracy replacement; it is a targeted, interpretable inductive bias for motif-sensitive genomic modeling.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.28386",
  "author_total": 2,
  "authors": [
    {
      "name": "Liangyu Li"
    },
    {
      "name": "Michael White"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cnm10tsbrmc9t.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.28386",
  "fulltext_url": null,
  "id": "cnm10tsbrmc9t",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.28386",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "q-bio.GN"
    ],
    [
      "openalex",
      "1312|Machine Learning in Bioinformatics"
    ]
  ],
  "openalex": "W7214165820",
  "pdf_url": "https://arxiv.org/pdf/2609.28386",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cnm10tsbrmc9t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:01Z",
      "native_id": "2609.28386",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.28386"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.GN",
      "subfield": "genetics-genomics"
    }
  ],
  "title": "Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models",
  "title_text": "Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:01Z",
  "url": "https://research.draconitic.com/paper/cnm10tsbrmc9t",
  "venue": "arXiv",
  "versions": []
}