OntologyAligner：面向生物医学本体标准化的本体对齐检索与层级引导的大语言模型重排序

中文摘要 AI 辅助

生物医学本体标准化将自由文本表达映射到结构化概念，从而实现生物医学数据的一致整合与分析。由于词汇变异以及层级相关概念之间的细微差异可能模糊概念边界，该任务仍具挑战性。我们提出OntologyAligner，一个三阶段框架，结合了本体对齐检索、大语言模型候选重排序和选择性层级引导精炼。我们还构建了PhenoNormBench，一个统一基准，包含来自七个人类表型本体数据集的13,390个样本。OntologyAligner在HPO标准化上取得了最先进的性能，Macro Top-1准确率为88.78%，Micro Top-1准确率为86.75%，分别超过最强基线4.85和5.07个百分点。消融分析显示三个阶段均有互补贡献，敏感性分析证明其在候选集大小和模型骨干方面具有稳定性。应用于MONDO、MEDIC和NCBITaxon进一步确立了其向其他本体的可移植性。OntologyAligner为生物医学文本到结构化本体概念的准确映射提供了一个通用框架。PhenoNormBench和代码在此https URL公开可用。

英文摘要

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.

发表机构

• West China Hospital, Sichuan University（四川大学华西医院）
• Chengdu Medical College（成都医学院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

4 figures