arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.41736cs.LGq-bio.GN
收藏

用于鲁棒调控DNA序列设计的局部性控制分布外引导

Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design

Wellcome Sanger Institute(惠康桑格研究所)

Dabin Jeong, Marwane Bourdim, Mo Lotfollahi

AI总结:

针对调控DNA序列设计中现有方法的奖励黑客问题,提出LOCOGEN模型,通过局部性控制引导实现属性、新颖性与合理性的平衡,在三种细胞系上取得良好效果。

摘要:

设计用于靶向基因表达控制的调控DNA序列是一项重要挑战。近期方法将该任务视为属性条件生成,其中基于天然序列训练的扩散模型通过基于奖励的微调或采样时引导,被导向高预测活性。我们发现单一奖励评估可能掩盖奖励黑客行为。通过将评估分解为属性、新颖性和合理性,我们确定了评估空间中一个经验上未充分探索的区域,该区域满足所有三个目标,但现有基准均未成功。我们假设这一差距的产生是因为先前方法主要将引导视为幅度问题。然而在调控DNA中,序列语法在空间上是非均匀的:基序位置对扰动敏感,而背景区域允许更多探索。因此,我们提出LOCOGEN,将引导重新表述为局部性问题。LOCOGEN通过序列级不变性学习学习不变基序掩码以保护基序位置,同时仅对背景位置应用分布外(OOD)阻尼。它在采样时运行于冻结的扩散骨干上,无需重新训练骨干。在HepG2、K562和SK-N-SH细胞系中,LOCOGEN达到了属性-新颖性-合理性空间中这一先前未充分探索的区域。代码可在this https URL获取。

英文摘要:

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 https://github.com/Lotfollahi-lab/LocoGen.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑