Faculty, Staff and Student Publications
Multi Agent Large Language Models for Biomedical Hypothesis Generation in Drug Combination Discovery
Language
English
Publication Date
12-19-2025
Journal
iScience
DOI
10.1016/j.isci.2025.113984
PMID
41362614
PMCID
PMC12682125
PubMedCentral® Posted Date
11-10-2025
PubMedCentral® Full Text Version
Post-print
Abstract
Recent advancements in large language models (LLMs) have demonstrated their potential in scientific reasoning, but their ability to open-ended hypotheses in data-scarce domains remains underexplored. Here, we introduce Combinatorial Alzheimer’s Disease Therapeutic Efficacy Decision (Coated-LLM), an AI-driven framework that is inspired by scientific collaboration to predict efficacious combinatorial therapy when data-driven prediction is infeasible. Coated-LLM employs multiple specialized LLM agents—Researcher, Reviewers, and Moderator—to systematically generate and evaluate hypotheses through several in-context learning techniques. Using Alzheimer’s disease (AD) as a test case, Coated-LLM outperformed traditional knowledge-based methods (accuracy: 0.74 vs. 0.52), with external validation achieving an accuracy of 0.82. In addition, a drug combination predicted from Coated-LLM was experimentally validated to significantly reduce amyloid aggregation in vitro. These findings highlight the potential of our framework to augment human reasoning in complex scientific reasoning tasks, offering a scalable approach for hypothesis generation in biomedical research.
Keywords
Health sciences, Medicine, Drugs, Artificial intelligence
Published Open-Access
yes
Recommended Citation
Xu, Qidi; Soto, Claudio; Shahnawaz, Mohammad; et al., "Multi Agent Large Language Models for Biomedical Hypothesis Generation in Drug Combination Discovery" (2025). Faculty, Staff and Student Publications. 3811.
https://digitalcommons.library.tmc.edu/uthmed_docs/3811