Agentic AI integrated with scientific knowledge: laboratory validation in systems biology
Journal of the Royal Society Interface · 08.07.2026 · 23 (240)
DOI: 10.1098/rsif.2026.0043 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Royal Society Interface, online erschienen am 08.07.2026. Verfasst von Daniel Brunnsåker und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Chalmers University of Technology , Gothenburg, Sweden. Hauptthemen laut MEDLINE: Systems Biology, Saccharomyces cerevisiae, Models, Biological. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Autonomous Systems and Software Program (WASP), Knut and Alice Wallenberg Foundation, UK Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
Automation is transforming scientific discovery by enabling systematic exploration of complex hypotheses. Large language models (LLMs) perform well across diverse tasks and promise to accelerate research, but often struggle with logical structures. Here, we present a framework for biological discovery integrating LLM-based agents with laboratory automation, guided by logical scaffolds incorporating symbolic relational learning, structured vocabularies and experimental constraints. This integration improves coherence and reliability in automated workflows. We couple this AI-driven approach to automated cell-culture and metabolomics platforms, enabling integrated hypothesis validation and refinement, yielding a flexible discovery system. The system identified novel interactions in Saccharomyces cerevisiae, including glutamate-induced growth inhibition in spermine-treated cells and aminoadipate’s partial rescue of formic-acid stress. All hypotheses, experiments and data are captured in a graph database employing controlled vocabularies. Existing ontologies are extended, and a novel representation of scientific hypotheses is presented using description logics. This work demonstrates the potential for a reliable machine-driven discovery process in systems biology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, Chalmers University of Technology , Gothenburg, Sweden.
- Department of Life Sciences, Chalmers University of Technology , Gothenburg, Sweden.
- Division of Industrial Biotechnology, KTH Royal Institute of Technology , Stockholm, Sweden.
- Department of Chemical Engineering and Biotechnology, University of Cambridge , Cambridge, UK.
ORCID-Profile: Daniel Brunnsåker, Erik Yuusuke Bjurström, Ross King
Förderung
- Autonomous Systems and Software Program (WASP)
- Knut and Alice Wallenberg Foundation
- UK Engineering and Physical Sciences Research Council
- Chalmers AI Research Centre (CHAIR)
- Swedish Research Council Formas
Zitieren
APA
Brunnsåker, D., Gower, A. H., Naval, P., Bjurström, E. Y., Kronström, F., Tiukova, I., & King, R. (2026). Agentic AI integrated with scientific knowledge: laboratory validation in systems biology. Journal of the Royal Society Interface, 23(240). https://doi.org/10.1098/rsif.2026.0043
Vancouver
Brunnsåker D, Gower AH, Naval P, Bjurström EY, Kronström F, Tiukova I, et al. Agentic AI integrated with scientific knowledge: laboratory validation in systems biology. Journal of the Royal Society Interface. 2026;23(240). doi:10.1098/rsif.2026.0043
BibTeX
@article{Brunnsker2026,
author = {Brunnsåker, Daniel and Gower, Alexander Howard and Naval, Prajakta and Bjurström, Erik Yuusuke and Kronström, Filip and Tiukova, Ievgeniia and King, Ross},
title = {Agentic AI integrated with scientific knowledge: laboratory validation in systems biology},
journal = {Journal of the Royal Society Interface},
year = {2026},
volume = {23},
number = {240},
doi = {10.1098/rsif.2026.0043}
}
EUVIMED