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 2510.16082q-bio.QMcs.AIcs.LG
收藏

BIOGEN:基于证据的多智能体推理框架用于抗菌药物耐药性中的转录组解释

BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance

College of Engineering and Computer Science, University of Central Florida(中佛罗里达大学工程与计算机科学学院)

Elias Hossain, Mehrdad Shoeibi, Ivan Garibay, Niloofar Yousefi

AI总结:

BIOGEN通过结合生物信息检索、结构化推理和多批评验证,生成可追溯的转录组模块解释,其在抗菌药物耐药性研究中表现出强生物学基础和零幻觉率。

摘要:

解读RNA测序(RNA-seq)中的基因簇仍具挑战性,特别是在抗菌药物耐药性研究中,机制洞察对假设生成至关重要。现有通路富集方法可总结共表达模块,但通常提供有限的簇特异性解释和弱的文献支持连接。我们提出了BIOGEN,一种基于证据的多智能体框架,用于事后解释RNA-seq转录模块。BIOGEN结合生物信息检索、结构化推理和多批评验证,以生成具有明确证据和置信度标签的簇级解释。在主要的沙门氏菌数据集上,BIOGEN实现了强生物学基础,包括BERTScore 0.689,语义对齐得分0.715,KEGG功能相似性0.342,以及与LLM-only基线相比幻觉率0.000。在四个额外的细菌RNA-seq数据集中,BIOGEN在相同固定流程下也保持零幻觉。与代表性的开源代理AI基线相比,BIOGEN是唯一一个在所有五个数据集中保持零幻觉的框架。这些发现表明,检索本身不足以获得可靠的生物学解释,证据导向的协调对于透明且可追溯的转录组推理至关重要。

英文摘要:

Interpreting gene clusters from RNA sequencing (RNA-seq) remains challenging, especially in antimicrobial resistance studies where mechanistic insight is important for hypothesis generation. Existing pathway enrichment methods can summarize co-expressed modules, but they often provide limited cluster-specific explanations and weak connections to supporting literature. We present BIOGEN, an evidence-grounded multi-agent framework for post hoc interpretation of RNA-seq transcriptional modules. BIOGEN combines biomedical retrieval, structured reasoning, and multi-critic verification to generate traceable cluster-level explanations with explicit evidence and confidence labels. On a primary Salmonella enterica dataset, BIOGEN achieved strong biological grounding, including BERTScore 0.689, Semantic Alignment Score 0.715, KEGG Functional Similarity 0.342, and a hallucination rate of 0.000, compared with 0.100 for an LLM-only baseline. Across four additional bacterial RNA-seq datasets, BIOGEN also maintained zero hallucination under the same fixed pipeline. In comparisons with representative open-source agentic AI baselines, BIOGEN was the only framework that consistently preserved zero hallucination across all five datasets. These findings suggest that retrieval alone is not enough for reliable biological interpretation, and that evidence-grounded orchestration is important for transparent and source-traceable transcriptomic reasoning.

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。

↑