Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)
2024
Toro, Sabrina | Anagnostopoulos, Anna | Bello, Susan | Blumberg, Kai | Cameron, Rhiannon | Carmody, Leigh | Diehl, Alexander | Dooley, Damion | Duncan, William | Fey, Petra | Gaudet, Pascale | Harris, Nomi | Joachimiak, Marcin | Kiani, Leila | Lubiana, Tiago | Munoz-Torres, Monica | Osumi-Sutherland, David | Puig-Barbe, Aleix | Reese, Justin | Reiser, Leonore | Robb, Sofia Mc. | Ruemping, Troy | Seager, James | Sid, Eric | Stefancsik, Ray | Weber, Magalie | Wood, Valerie | Haendel, Melissa | Mungall, Christopher | University of North Carolina [Chapel Hill] (UNC) ; University of North Carolina System (UNC) | The Jackson Laboratory [Bar Harbor] (JAX) | University of Arizona | Simon Fraser University = Université Simon Fraser (SFU.ca) | University at Buffalo [SUNY] (SUNY Buffalo) ; State University of New York (SUNY) | Roswell Park Comprehensive Cancer Center | Northwestern University [Evanston] | Swiss Institute of Bioinformatics [Genève] (SIB) | Lawrence Berkeley National Laboratory [Berkeley] (LBNL) | Universidade de São Paulo = University of São Paulo (USP) | Sanger Institute ; Welcome Trust | European Bioinformatics Institute [Hinxton] (EMBL-EBI) ; EMBL Heidelberg | Phoenix Bioinformatics [Newark, CA, USA] | Stowers Institute for Medical Research | International Center for Food Ontology Operability Data & Semantics (IC-FOODS) | Rothamsted Research ; Biotechnology and Biological Sciences Research Council (BBSRC) | National Center for Advancing Translational Sciences (NCATS) ; National Institutes of Health [Bethesda, MD, USA] (NIH) | Unité de recherche sur les Biopolymères, Interactions Assemblages (BIA) ; Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE) | University of Cambridge [UK] (CAM) | United States Department of Health & Human Services National Institutes of Health (NIH) - USA ; NIH National Human Genome Research Institute (NHGRI): HG010860, HG012212, HG010859 ; United States Department of Health & Human Services : National Institutes of Health (NIH) - USA : R24 OD011883 ; United States Department of Energy (DOE) : DE-AC0205CH11231 ; National Science Foundation (NSF) : OAC-2112606 ; Wellcome Trust : 218236/Z/19/Z; Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) : 19/26284-1. Bosch Research.
International audience
Afficher plus [+] Moins [-]anglais. 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.
Afficher plus [+] Moins [-]Informations bibliographiques
Cette notice bibliographique a été fournie par Institut national de la recherche agronomique
Découvrez la collection de ce fournisseur de données dans AGRIS