MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs
On the map: LLM agents and tool use → Medical and scientific domain agents
Abstract (arXiv)
Mass spectrometry-based metabolomics generates complex, high-dimensional data that holds vast potential for biological discovery but remains difficult to integrate and interpret. Knowledge graphs (KGs) unify this heterogeneous information by representing spectra, annotations, taxa, chemical classes, and biological activities as a single interoperable network; however, their practical use is limited by the steep learning curve of corresponding specialized representation and query languages. Here we introduce MetaboT, an open-source multi-agent Large Language Model (LLM) framework that translates natural-language questions into executable SPARQL queries over metabolomics knowledge graphs. MetaboT mitigates the hallucination and schema-compliance limitations of single-model approaches through a modular architecture in which specialised agents handle scope validation, entity resolution against authoritative resources, schema-aware query generation, iterative refinement, and result interpretation. We validated MetaboT on the Experimental Natural Products Knowledge Graph (ENPKG), using an expert-authored benchmark of natural-language questions paired with reference SPARQL queries, and demonstrate its ability to answer complex questions about plant--metabolite relationships and biological activities. MetaboT lowers the technical barrier for metabolomics researchers and enables semantic data mining without specialised programming expertise.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 12 of its 57 references that are in the map. First posted on arXiv 2 Oct 2025.
Builds on
12 of 57 references.
References · 12
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2017Billion-scale similarity search with GPUscited by 2,477
- 2024A Survey on LLM-as-a-Judgecited by 1,384
- 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
- 2020Knowledge Graphscited by 619
- 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
- 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 54
- 2024LLM-based SPARQL Query Generation from Natural Language over Federated Knowledge Graphscited by 22
- 2024Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answeringcited by 18
- 2024Assessing SPARQL capabilities of Large Language Modelscited by 14
- 2023On the Potential of Artificial Intelligence Chatbots for Data Exploration of Federated Bioinformatics Knowledge Graphscited by 9
- 2021A Framework for Federated SPARQL Query Processing over Heterogeneous Linked Data Fragmentscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training
- 2026AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs
- 2025RAG-Enhanced Collaborative LLM Agents for Drug Discovery
- 2025Large Language Model Agent for Modular Task Execution in Drug Discovery
- 2026MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models
- 2025LLM Agent Swarm for Hypothesis-Driven Drug Discovery
- 2025DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
- 2026From Single to Multi-Agent Reasoning: Advancing GeneGPT for Genomics QA