Agentic AI integrated with scientific knowledge: laboratory validation in systems biology
Journal article, 2026
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.
laboratory automation
systems biology
automation of science
inductive logic programming
machine learning
large language models
Author
Daniel Brunnsåker
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
University of Gothenburg
Alexander Gower
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
University of Gothenburg
Prajakta Naval
Chalmers, Life Sciences, Infrastructures
Erik Bjurström
Chalmers, Life Sciences, Infrastructures
Filip Kronström
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
University of Gothenburg
Ievgeniia Tiukova
Royal Institute of Technology (KTH)
Chalmers, Life Sciences, Infrastructures
Ross King
University of Cambridge
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
University of Gothenburg
Journal of the Royal Society Interface
1742-5689 (ISSN) 1742-5662 (eISSN)
Vol. 23 240 20260043Subject Categories (SSIF 2025)
Computer Sciences
DOI
10.1098/rsif.2026.0043
PubMed
42413936