Metraipolis › archive › dc_16dedee2ab0a
Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models — arXiv:2609.28386
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28386
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:30:09.321Z
- SHA-256 of the archived text
90537e8edf88326e9a533a9c973fcaa70e7dcc558e5ef6791d1999f860971d77- Stable URL of this page
https://metraipolis.com/documento/dc_16dedee2ab0a
How to cite
Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models — arXiv:2609.28386 — arXiv (en), https://arxiv.org/abs/2609.28386 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16dedee2ab0a (Metraipolis archive dc_16dedee2ab0a, sha256 90537e8edf88326e9a533a9c973fcaa70e7dcc558e5ef6791d1999f860971d77)
BibTeX
@misc{dc16dedee2ab0a,
title = {Motif-Vocab: StatisticallyCalibrated Transcription-Factor-Identity Tokenization forGenomic Language Models — arXiv:2609.28386},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28386},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16dedee2ab0a; sha256 90537e8edf88326e9a533a9c973fcaa70e7dcc558e5ef6791d1999f860971d77},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28386. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-09-24 in q-bio.GN). Categorie arXiv: Genomics (q-bio.GN). Pagina del lavoro: https://arxiv.org/abs/2609.28386 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:13:01.690Z dalla pagina https://arxiv.org/catchup/q-bio.GN/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).