arXiv cs.AI· Joel Shor, Subhashini Venugopalan·· 3 天前AI 评分32
AutoNovo：智能体程序搜索发现可迁移的核酸设计算法
AutoNovo: Agentic Program Search Discovers Transferable Nucleic Acid Design Algorithms
AI 导读
AutoNovo 用智能体程序搜索迭代地提出、执行、评估和修改核酸设计器代码，其设计器在 3/3 个 DNA 设计任务的 in-silico 性能上取得所评估方法中的最佳均值，并在 6/6 个独立模型迁移任务上表现最佳。这些设计器来自一个被发现的设计器家族，而非单一通用最优设计器，团队计划发布这些设计器。
正文 · 原文
Abstract:In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit model-specific artifacts and fail to generalize to independent models. Recent studies have shown that not all designers generalize equally well to independent models. In this work, we use agentic program search to iteratively propose, execute, evaluate, and revise code for nucleic-acid designers. We describe the successful strategies used to prompt the search. AutoNovo designers achieved the best observed mean among the evaluated methods on 3/3 DNA-design tasks in terms of in-silico performance, and 6/6 transfer tasks in terms of independent models. The designers come from a family of discovered nucleic acid designers rather than a single universal best designer. We plan to release the resulting designers. These results are the first steps in creating nucleic acid designers that maximize cross-model generalization, and thus improving the odds that in-silico designed sequences reflect real biology.
| Comments: | 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: Agentic AI for Biological Discovery |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2610.16232 [cs.LG] |
| (or arXiv:2610.16232v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16232 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joel Shor [view email]
[v1]
Mon, 12 Oct 2026 06:08:54 UTC (131 KB)
来源：arXiv cs.AI · arxiv.org