MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bekbergenova, Madina, Pradi, Lucas, Navet, Benjamin, Tysinger, Emma, Michel, Franck, Feraud, Matthieu, Taghzouti, Yousouf, Chen, Yan Zhou, Kirchhoffer, Olivier, Mehl, Florence, Legrand, Martin, Jiang, Tao, Pagni, Marco, Hassoun, Soha, Wolfender, Jean-Luc, Bittremieux, Wout, Gandon, Fabien, Nothias, Louis-Félix
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910262068510720
author Bekbergenova, Madina
Pradi, Lucas
Navet, Benjamin
Tysinger, Emma
Michel, Franck
Feraud, Matthieu
Taghzouti, Yousouf
Chen, Yan Zhou
Kirchhoffer, Olivier
Mehl, Florence
Legrand, Martin
Jiang, Tao
Pagni, Marco
Hassoun, Soha
Wolfender, Jean-Luc
Bittremieux, Wout
Gandon, Fabien
Nothias, Louis-Félix
author_facet Bekbergenova, Madina
Pradi, Lucas
Navet, Benjamin
Tysinger, Emma
Michel, Franck
Feraud, Matthieu
Taghzouti, Yousouf
Chen, Yan Zhou
Kirchhoffer, Olivier
Mehl, Florence
Legrand, Martin
Jiang, Tao
Pagni, Marco
Hassoun, Soha
Wolfender, Jean-Luc
Bittremieux, Wout
Gandon, Fabien
Nothias, Louis-Félix
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs
Bekbergenova, Madina
Pradi, Lucas
Navet, Benjamin
Tysinger, Emma
Michel, Franck
Feraud, Matthieu
Taghzouti, Yousouf
Chen, Yan Zhou
Kirchhoffer, Olivier
Mehl, Florence
Legrand, Martin
Jiang, Tao
Pagni, Marco
Hassoun, Soha
Wolfender, Jean-Luc
Bittremieux, Wout
Gandon, Fabien
Nothias, Louis-Félix
Artificial Intelligence
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.
title MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs
topic Artificial Intelligence
url https://arxiv.org/abs/2510.01724