arXiv cs.AI· Qiming Guo, Malaka Sudhakara Bava Sukruth Reddy, Honggang Zhao, Ye Wang, Chen Pan, Wenlu Wang·· 14 小时前AI 评分26
RADAgent：用私有开源 LLM 自动化 RADseq 流程
RADAgent: Automating RADseq Pipelines with Private Open-Source LLMs
AI 导读
RADAgent 用开放权重 LLM 将 RADseq 分析流程拆成 16 个可独立执行与验证的智能体模块，并配合模型无关运行时完成受限工具调用、磁盘验证与故障恢复。在包含 19 个种群、476 个样本的真实群体基因组数据集上，RADAgent 可靠地自动化了完整 RADseq 流程，且基因组数据与模型推理均保留在本地计算环境。代码已公开，论文被 IEEE BIBM 2026 接收。
正文 · 原文
Abstract:Restriction site-associated DNA sequencing (RADseq) is a family of reduced-representation sequencing methods. It uses restriction enzymes to sample subsets of the genome, therefore allowing multiple individuals to be sequenced and genotyped together at low cost. RADseq is widely used for population genomics, evolutionary biology, marker discovery, and the development of SNP panels, but complete analysis still requires expert coordination across multiple tools and processing stages. Traditional RADseq analysis requires expert coordination of heterogeneous bioinformatics tools, intermediate artifacts, quality-control checks, and parameter-dependent decisions across multiple stages. Although individual steps can be scripted, executing the complete workflow still requires human oversight for state tracking, result validation, and failure handling. To automate this expert-driven coordination, we present RADAgent, which introduces a modular agentic method for reliable RADseq workflow execution with an open-weight LLM. RADAgent maps the natural boundaries of the RADseq workflow into 16 independently executable and verifiable agent modules and uses a model-independent runtime for bounded tool execution, on-disk verification, and failure recovery. We evaluate RADAgent on a real population-genomics dataset containing 476 samples from 19 populations. The results demonstrate that RADAgent reliably automates the complete RADseq workflow with an open-weight LLM while keeping genomic data and model execution within the local computing environment. The code is publicly available at this https URL.
| Comments: | Accepted at IEEE BIBM 2026. Code: this https URL |
| Subjects: | Genomics (q-bio.GN); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.33009 [q-bio.GN] |
| (or arXiv:2610.33009v1 [q-bio.GN] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33009 arXiv-issued DOI via DataCite |
Submission history
From: Qiming Guo [view email]
[v1]
Wed, 7 Oct 2026 21:11:48 UTC (220 KB)
来源：arXiv cs.AI · arxiv.org