Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)

• Published in: Journal of biomedical semantics Vol. 15; no. 1; pp. 19 - 16
• Main Authors: Toro, Sabrina, Anagnostopoulos, Anna V., Bello, Susan M., Blumberg, Kai, Cameron, Rhiannon, Carmody, Leigh, Diehl, Alexander D., Dooley, Damion M., Duncan, William D., Fey, Petra, Gaudet, Pascale, Harris, Nomi L., Joachimiak, Marcin P., Kiani, Leila, Lubiana, Tiago, Munoz-Torres, Monica C., O‘Neil, Shawn, Osumi-Sutherland, David, Puig-Barbe, Aleix, Reese, Justin T., Reiser, Leonore, Robb, Sofia MC, Ruemping, Troy, Seager, James, Sid, Eric, Stefancsik, Ray, Weber, Magalie, Wood, Valerie, Haendel, Melissa A., Mungall, Christopher J.
• Format: Journal Article
• Language: English
• Published: London BioMed Central 17.10.2024; BioMed Central Ltd; BMC
• Subjects: Algorithms; Analysis; Artificial Intelligence; Automation; Biocuration; Bioinformatics; Biological Ontologies; Combinatorial Libraries; Computational Biology/Bioinformatics; Computational linguistics; Computer Appl. in Life Sciences; Computer Science; Data Mining and Knowledge Discovery; Health aspects; Humanities and Social Sciences; Informatics; Information Storage and Retrieval - methods; Knowledge; Knowledge graphs; Knowledge management; KNOWLEDGE MANAGEMENT AND PRESERVATION; Knowledge representation; Language processing; Large language models; Library and information sciences; Life Sciences; Mathematics; Mathematics and Statistics; Methods; Natural language interfaces; Natural Language Processing; Ontologies; Ontology; Ontology engineering; Reasoning; Retrieval; Semantics; Software engineering; Unstructured data; United States; Ontologies; Biocuration; Large language models; Artificial intelligence; Knowledge graphs; Ontology engineering
• ISSN: 2041-1480; 2041-1480
• DOI: 10.1186/s13326-024-00320-3

Background Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts, curators, and ontology experts. We present Dynamic Retrieval Augmented Generation of Ontologies using AI (DRAGON-AI), an ontology generation method employing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). DRAGON-AI can generate textual and logical ontology components, drawing from existing knowledge in multiple ontologies and unstructured text sources. Results We assessed performance of DRAGON-AI on de novo term construction across ten diverse ontologies, making use of extensive manual evaluation of results. Our method has high precision for relationship generation, but has slightly lower precision than from logic-based reasoning. Our method is also able to generate definitions deemed acceptable by expert evaluators, but these scored worse than human-authored definitions. Notably, evaluators with the highest level of confidence in a domain were better able to discern flaws in AI-generated definitions. We also demonstrated the ability of DRAGON-AI to incorporate natural language instructions in the form of GitHub issues. Conclusions These findings suggest DRAGON-AI's potential to substantially aid the manual ontology construction process. However, our results also underscore the importance of having expert curators and ontology editors drive the ontology generation process.