Multi-Omics clustering by integrating clinical features from large language model
Methods · 2025-07 · 239 · 64-71
DOI: 10.1016/j.ymeth.2025.03.017 ↗Kurz gefasst
Fachartikel in der Zeitschrift Methods, 2025-07. Verfasst von Xiucai Ye und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan. Electronic address: yexiucai@cs.tsukuba.ac.jp. Hauptthemen laut MEDLINE: Neoplasms, Genomics, Computational Biology. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: Japan Science and Technology Agency, Japan Society for the Promotion of Science London, Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Multi-omics clustering has emerged as a powerful approach for understanding complex biological systems and enabling cancer subtyping by integrating diverse omics data. Existing methods primarily focus on the integration of different types of omics data, often overlooking the value of clinical context. In this study, we propose a novel framework that incorporates clinical features extracted from large language model (LLM) to enhance multi-omics clustering. Leveraging clinical data extracted from pathology reports using a BERT-based model, our framework converts unstructured medical text into structured clinical features. These features are integrated with omics data through an autoencoder, enriching the information content of each omics layer to improve feature extraction. The extracted features are then projected into a latent subspace using singular value decomposition (SVD), followed by spectral clustering to obtain the final clustering result. We evaluate the proposed framework on six cancer datasets on three omics levels, comparing it with several state-of-the-art methods. The experimental results demonstrate that the proposed framework outperforms existing methods in multi-omics clustering for cancer subtyping. Moreover, the results highlight the efficacy of integrating clinical features derived from LLM, significantly enhancing clustering performance. This work underscores the importance of clinical context in multi-omics analysis and showcases the transformative potential of LLM in advancing precision medicine.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan. Electronic address: yexiucai@cs.tsukuba.ac.jp.
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan.
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan. Electronic address: huangdong@fafu.edu.cn.
Förderung
- Japan Science and Technology Agency
- Japan Society for the Promotion of Science London
- Japan Society for the Promotion of Science
Zitieren
APA
Ye, X., Shi, T., Huang, D., & Sakurai, T. (2025). Multi-Omics clustering by integrating clinical features from large language model. Methods, 239, 64-71. https://doi.org/10.1016/j.ymeth.2025.03.017
Vancouver
Ye X, Shi T, Huang D, Sakurai T. Multi-Omics clustering by integrating clinical features from large language model. Methods. 2025;239:64-71. doi:10.1016/j.ymeth.2025.03.017
BibTeX
@article{Ye2025,
author = {Ye, Xiucai and Shi, Tianyi and Huang, Dong and Sakurai, Tetsuya},
title = {Multi-Omics clustering by integrating clinical features from large language model},
journal = {Methods},
year = {2025},
volume = {239},
pages = {64--71},
doi = {10.1016/j.ymeth.2025.03.017}
}
EUVIMED