A Deep Representation Learning Method for Quantitative Immune Defense Function Evaluation and Its Clinical Applications
Advanced Science · 2026
DOI: 10.1002/advs.202515929 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2026. Verfasst von Zhen-Lin Tan und 7 weiteren Autor:innen. Beteiligte Einrichtung: Hubei Key Laboratory of Bioinformatics and Molecular-imaging, College of Life Science and Technology, Huazhong University of Science and Technology, …. Hauptthemen laut MEDLINE: Deep Learning, Sepsis, Acquired Immunodeficiency Syndrome. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, 1.3.5 project for disciplines of excellence from West China Hospital of Sichuan University, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
The immune defense function protecting the body from invasive pathogens is a key indicator of an individual's health and lacks of methods for quantitative evaluation. This study introduces ImmuDef, a novel algorithm for precisely and quantitatively assessing anti‐infection immune defense function based on RNA‐seq data. ImmuDef selects immune signatures through comparisons of acquired immunodeficiency syndrome (AIDS) or severe sepsis vs. healthy controls (HC) and reduces dimension to construct a latent space via a variational autoencoder (VAE) model (QImmuDef‐VAE), a representation deep learning model. Based on this model, a defense immune score (DImmuScore) was calculated by measuring the distance between a patient and HC within latent space. We validated ImmuDef on 3202 samples across four immune states: immunodeficiency, immunocompromised, immunocompetent, and immunoactive. As a result, DImmuScore achieves high classification accuracy (mean accuracy: 71.75%–76.25%) among samples with various immune states and infections. Furthermore, DImmuScore can serve as a metric for infectious disease severity, where its gradient directly quantifies disease severity. As an application, DImmuScore can be a strong prognostic indicator, effectively stratifying mortality/survival in both sepsis and COVID‐19 patients with no symptomatic difference. This framework was validated across five infectious diseases, establishing the first quantitative standard for cross‐disease immune defense assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Hubei Key Laboratory of Bioinformatics and Molecular-imaging, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, China.
- Department of Laboratory Medicine, West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China.
ORCID-Profile: Zhen-Lin Tan, An-Yuan Guo
Förderung
- National Natural Science Foundation of China
- 1.3.5 project for disciplines of excellence from West China Hospital of Sichuan University
- Fundamental Research Funds for the Central Universities
- National Outstanding Youth Foundation of China
Zitieren
APA
Tan, Z. L., Luo, T., Lin, Y., Wu, X. J., Shen, W. K., Chen, J., Lei, Q., & Guo, A. Y. (2026). A Deep Representation Learning Method for Quantitative Immune Defense Function Evaluation and Its Clinical Applications. Advanced Science. https://doi.org/10.1002/advs.202515929
Vancouver
Tan ZL, Luo T, Lin Y, Wu XJ, Shen WK, Chen J, et al. A Deep Representation Learning Method for Quantitative Immune Defense Function Evaluation and Its Clinical Applications. Advanced Science. 2026. doi:10.1002/advs.202515929
BibTeX
@article{Tan2026,
author = {Tan, Zhen-Lin and Luo, Tao and Lin, Yu and Wu, Xiao-Jun and Shen, Wen-Kang and Chen, Jie and Lei, Qian and Guo, An-Yuan},
title = {A Deep Representation Learning Method for Quantitative Immune Defense Function Evaluation and Its Clinical Applications},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.202515929}
}
EUVIMED