Metraipolis › archive › dc_b72c33f04ebe
Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design — arXiv:2610.41736
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41736
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:52:25.228Z
- SHA-256 of the archived text
5e5adeef002851ba14dd43d51ec6b2ac23c81ea78105c1de07743364fad45ebb- Stable URL of this page
https://metraipolis.com/documento/dc_b72c33f04ebe
How to cite
Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design — arXiv:2610.41736 — arXiv (en), https://arxiv.org/abs/2610.41736 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b72c33f04ebe (Metraipolis archive dc_b72c33f04ebe, sha256 5e5adeef002851ba14dd43d51ec6b2ac23c81ea78105c1de07743364fad45ebb)
BibTeX
@misc{dcb72c33f04ebe,
title = {Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design — arXiv:2610.41736},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41736},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b72c33f04ebe; sha256 5e5adeef002851ba14dd43d51ec6b2ac23c81ea78105c1de07743364fad45ebb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41736. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Designing regulatory DNA sequences for targeted gene-expression control is an important challenge. Recent approaches frame this task as property-conditioned generation, where diffusion models trained on natural sequences are guided toward high predicted activity through reward-based fine-tuning or sampling-time guidance. We show that single-reward evaluation can obscure reward-hacking behavior. By decomposing evaluation into property, novelty, and plausibility, we identify an empirically underexplored region of the evaluation space in which all three objectives are satisfied, but no existing baseline succeeds. We postulate that this gap arises because prior methods treat guidance primarily as a matter of magnitude. In regulatory DNA, however, sequence grammar is spatially nonuniform: motif positions are sensitive to perturbation, while background regions allow more exploration. We therefore propose LOCOGEN by reformulating guidance as a problem of locality. LOCOGEN learns an invariant motif mask through sequence-level invariance learning to protect motif positions, while applying OOD damping only to background positions. It operates at sampling time on a frozen diffusion backbone, without retraining the backbone. Across HepG2, K562, and SK-N-SH, LOCOGEN reaches this previously underexplored region of the property-novelty-plausibility space. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Genomics (q-bio.GN). Pagina del lavoro: https://arxiv.org/abs/2610.41736 — 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 2026-11-02T04:45:12.906Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).