OntoCodex: a multi-agent biomedical ontology enrichment framework
Ontology enrichment is a critical but labor-intensive step in semantic knowledge representation. To address this challenge, we propose OntoCodex, a multi-agent framework that integrates large language models (LLMs), ontologies, curated knowledge sources, and standard vocabularies to support semi-automated ontology enrichment with formal OWL-based integration and a feedback loop. OntoCodex consists of five coordinated agents for ontology parsing, task decision-making, knowledge retrieval, terminology normalization, and automated script generation. We evaluated OntoCodex using a ChatGPT-4o–powered implementation to enrich concepts across five chronic diseases, including stroke, chronic obstructive pulmonary disease, atrial fibrillation, osteoporosis, and Parkinson’s disease. Compared with baseline ChatGPT-4o, OntoCodex improved concept extraction across most domains, achieving higher precision, recall, and F1 scores, including perfect performance in laboratory test extraction, and demonstrated greater accuracy in standardized terminology mapping, particularly for medications, while showing lower performance in laboratory test mapping. Automatically generated Python scripts successfully enriched the MCC-CDO with new concepts and annotations without errors. These results demonstrate that OntoCodex substantially improves ontology enrichment and has strong potential to accelerate clinical and translational research.