CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs
Journal of the American Medical Informatics Association · 2024
DOI: 10.1093/jamia/ocae115 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2024. Verfasst von Huaiyuan Ying und 4 weiteren Autor:innen. Beteiligte Einrichtung: Center for Statistical Science, Department of Industrial Engineering, Tsinghua University, Beijing, 100084, China. Hauptthemen laut MEDLINE: Unified Medical Language System, Algorithms, Natural Language Processing, Machine Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Foundation of Beijing Municipality, Natural Science Foundation of China.
Abstract (Originalsprache)
Objectives
Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from large language models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. Materials and Methods The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology.
Results
We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35 580 932 terms from the Biomedical Informatics Ontology System (BIOS) into 22 104 559 clusters with O(N) queries to ChatGPT. Case studies highlight the model’s efficacy in handling challenging samples, aided by information from explanations.
Conclusion
By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Statistical Science, Department of Industrial Engineering, Tsinghua University, Beijing, 100084, China.
- Weiyang College, Tsinghua University, Beijing, 100084, China.
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA 98195, United States.
ORCID-Profile: Huaiyuan Ying, Zhengyun Zhao, Sihang Zeng
Förderung
- Natural Science Foundation of Beijing Municipality
- Natural Science Foundation of China
Zitieren
APA
Ying, H., Zhao, Z., Zhao, Y., Zeng, S., & Yu, S. (2024). CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocae115
Vancouver
Ying H, Zhao Z, Zhao Y, Zeng S, Yu S. CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs. Journal of the American Medical Informatics Association. 2024. doi:10.1093/jamia/ocae115
BibTeX
@article{Ying2024,
author = {Ying, Huaiyuan and Zhao, Zhengyun and Zhao, Yang and Zeng, Sihang and Yu, Sheng},
title = {CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs},
journal = {Journal of the American Medical Informatics Association},
year = {2024},
doi = {10.1093/jamia/ocae115}
}
EUVIMED