OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization

2026-09-09

AI Summary

本文提出OntologyAligner框架，通过结合本体对齐检索、大型语言模型重排序及层次指导的精炼方法，有效解决了生物医学本体规范化问题。

Abstract

Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical variation and subtle distinctions among hierarchically related concepts can obscure concept boundaries. We present OntologyAligner, a three-stage framework that combines ontology-aligned retrieval, large language model candidate reranking, and selective hierarchy-guided refinement. We also construct PhenoNormBench, a unified benchmark comprising 13,390 samples from seven Human Phenotype Ontology datasets. OntologyAligner achieved state-of-the-art performance on HPO normalization, with 88.78% Macro Top-1 Accuracy and 86.75% Micro Top-1 Accuracy, exceeding the strongest baseline by 4.85 and 5.07 percentage points, respectively. Ablation analyses showed complementary contributions from all three stages, and sensitivity analyses demonstrated stability across candidate-set sizes and model backbones. Applications to MONDO, MEDIC, and NCBITaxon further established portability to other ontologies. OntologyAligner offers a generalizable framework for accurate mapping of biomedical text to structured ontology concepts. PhenoNormBench and the code are publicly available at https://github.com/zhelishisongjie/OntologyAligner.

Problem

• Ontology Normalization
• Lexical Variation
• Hierarchical Concepts
• Biomedical Data

Innovation

• Ontology-Aligned Retrieval
• Large Language Model Reranking
• Hierarchy-Guided Refinement
• PhenoNormBench