A large language model framework for literature-based disease–gene association prediction
Briefings in Bioinformatics · 22.11.2024 · 26 (1)
DOI: 10.1093/bib/bbaf070 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 25.02.2025. Verfasst von Peng-Hsuan Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Taiwan AI Labs, 6F., No. 70, Sec. 1, Chengde Road, Datong Dist., Taipei 10355, Taiwan. Hauptthemen laut MEDLINE: Computational Biology, Genetic Association Studies, Genetic Predisposition to Disease. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Advanced Computing and Imaging in Biomedicine, Ministry of Education in Taiwan.
Abstract (Originalsprache)
With the exponential growth of biomedical literature, leveraging Large Language Models (LLMs) for automated medical knowledge understanding has become increasingly critical for advancing precision medicine. However, current approaches face significant challenges in reliability, verifiability, and scalability when extracting complex biological relationships from scientific literature using LLMs. To overcome the obstacles of LLM development in biomedical literature understating, we propose LORE, a novel unsupervised two-stage reading methodology with LLM that models literature as a knowledge graph of verifiable factual statements and, in turn, as semantic embeddings in Euclidean space. LORE captured essential gene pathogenicity information when applied to PubMed abstracts for large-scale understanding of disease–gene relationships. We demonstrated that modeling a latent pathogenic flow in the semantic embedding with supervision from the ClinVar database led to a 90% mean average precision in identifying relevant genes across 2097 diseases. This work provides a scalable and reproducible approach for leveraging LLMs in biomedical literature analysis, offering new opportunities for researchers to identify therapeutic targets efficiently.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Taiwan AI Labs, 6F., No. 70, Sec. 1, Chengde Road, Datong Dist., Taipei 10355, Taiwan.
- Department of Life Science, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei 10617, Taiwan.
- Center for Computational and Systems Biology, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan.
- Center for Advanced Computing and Imaging in Biomedicine, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan.
- Department of Biomechatronics Engineering, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617, Taiwan.
- Institute of Information Science, Academia Sinica, No. 128, Academia Road, Section 2, Nankang, Taipei 11529, Taiwan.
ORCID-Profile: Hsueh-Fen Juan, Chien-Yu Chen, Huai-Kuang Tsai, Jia-Hsin Huang
Förderung
- Advanced Computing and Imaging in Biomedicine
- Ministry of Education in Taiwan
Zitieren
APA
Li, P. H., Sun, Y. Y., Juan, H. F., Chen, C. Y., Tsai, H. K., & Huang, J. H. (2024). A large language model framework for literature-based disease–gene association prediction. Briefings in Bioinformatics, 26(1). https://doi.org/10.1093/bib/bbaf070
Vancouver
Li PH, Sun YY, Juan HF, Chen CY, Tsai HK, Huang JH. A large language model framework for literature-based disease–gene association prediction. Briefings in Bioinformatics. 2024;26(1). doi:10.1093/bib/bbaf070
BibTeX
@article{Li2024,
author = {Li, Peng-Hsuan and Sun, Yih-Yun and Juan, Hsueh-Fen and Chen, Chien-Yu and Tsai, Huai-Kuang and Huang, Jia-Hsin},
title = {A large language model framework for literature-based disease–gene association prediction},
journal = {Briefings in Bioinformatics},
year = {2024},
volume = {26},
number = {1},
doi = {10.1093/bib/bbaf070}
}
EUVIMED