arXiv cs.AI· Yifan Chang, Yunze Li, Feifei Jiang, Juntao Wu, Xin Chen, Han Hu, Yucheng Wu, Wei Tang, Mingqian Ma, Wanli Ouyang, Kaipeng Zhang, Lei Bai, Hongting Tang, Feiran Li, Yuchen Ren·· 4 小时前AI 评分34
RIVER：证据引导的多智能体检索框架用于酶-反应双向发现
RIVER: Evidence-guided multi-agent retrieval for enzyme--reaction discovery
AI 导读
研究团队发布 RIVER（Reaction–enzyme Inference via Evidence-guided Retrieval），一个用于酶-反应双向检索的多智能体框架，可为给定酶识别可能催化的反应，并为给定反应排序候选酶。
正文 · 原文
Authors:Yifan Chang, Yunze Li, Feifei Jiang, Juntao Wu, Xin Chen, Han Hu, Yucheng Wu, Wei Tang, Mingqian Ma, Wanli Ouyang, Kaipeng Zhang, Lei Bai, Hongting Tang, Feiran Li, Yuchen Ren
Abstract:Enzyme function annotation and the identification of candidate enzymes for a given reaction are essential steps in connecting genomic information to biochemical reaction networks. However, existing methods rely on sequence or structural similarity or on training with known enzyme--reaction pairs, making it difficult to integrate biochemical evidence across large candidate spaces; they also struggle with retrieval tasks involving enzyme families whose members are highly similar. Here, we introduce RIVER (Reaction--enzyme Inference via Evidence-guided Retrieval), a multi-agent framework for bidirectional enzyme--reaction retrieval that identifies potentially catalyzed reactions for a given enzyme and ranks candidate enzymes for a given reaction. RIVER coordinates large language models, specialized biochemical computational tools, and external knowledge resources to assemble evidence at multiple levels, including reaction chemistry, protein sequences and domains, catalytic mechanisms, and database annotations. Dedicated validation modules further examine evidence gaps and potential conflicts and rerank candidates using traceable evidence records. On public benchmarks, RIVER achieves the highest success rates in both enzyme retrieval and enzyme annotation. In family-specific enzyme retrieval, RIVER outperforms the evaluated baselines on the selected datasets and metrics. In Escherichia coli enzyme retrieval tasks constructed from recent literature, RIVER achieves the best retrieval results with closed-source and open-source model configurations, substantially outperforming closed-source general-purpose and biology-specialized multi-agent systems, including Claude Code, Codex, and Phylo Max. These results suggest that evidence-guided multi-agent retrieval can prioritize biochemically supported enzyme--reaction relationships, providing a basis for subsequent experimental validation.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07757 [cs.AI] |
| (or arXiv:2611.07757v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07757 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yifan Chang [view email]
[v1]
Thu, 5 Nov 2026 10:01:08 UTC (2,325 KB)
来源：arXiv cs.AI · arxiv.org