Cox-Sage: enhancing Cox proportional hazards model with interpretable graph neural networks for cancer prognosis
Briefings in Bioinformatics · 04.03.2025 · 26 (2)
DOI: 10.1093/bib/bbaf108 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 11.03.2025. Verfasst von Ruijun Mao und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Taiyuan University of Technology, 79 Yingze West Avenue, Wanbailin District, Taiyuan, Shanxi Province 030024, Chi…. Hauptthemen laut MEDLINE: Neoplasms, Biomarkers, Tumor, Neural Networks, Computer. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Basic Research Programs of Shanxi Province.
Abstract (Originalsprache)
High-throughput sequencing technologies have facilitated a deeper exploration of prognostic biomarkers. While many deep learning (DL) methods primarily focus on feature extraction or employ simplistic fully connected layers within prognostic modules, the interpretability of DL-extracted features can be challenging. To address these challenges, we propose an interpretable cancer prognosis model called Cox-Sage. Specifically, we first propose an algorithm to construct a patient similarity graph from heterogeneous clinical data, and then extract protein-coding genes from the patient’s gene expression data to embed them as features into the graph nodes. We utilize multilayer graph convolution to model proportional hazards pattern and introduce a mathematical method to clearly explain the meaning of our model’s parameters. Based on this approach, we propose two metrics for measuring gene importance from different perspectives: mean hazard ratio and reciprocal of the mean hazard ratio. These metrics can be used to discover two types of important genes: genes whose low expression levels are associated with high cancer prognosis risk, and genes whose high expression levels are associated with high cancer prognosis risk. We conducted experiments on seven datasets from TCGA, and our model achieved superior prognostic performance compared with some state-of-the-art methods. As a primary research, we performed prognostic biomarker discovery on the LIHC (Liver Hepatocellular Carcinoma) dataset. Our code and dataset can be found at https://github.com/beeeginner/Cox-sage.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Artificial Intelligence, Taiyuan University of Technology, 79 Yingze West Avenue, Wanbailin District, Taiyuan, Shanxi Province 030024, China.
- College of Computer Science and Technology, 79 Yingze West Avenue, Wanbailin District, Taiyuan University of Technology, Taiyuan, Shanxi Province 030024, China.
ORCID-Profile: Dongxi Li
Förderung
- Basic Research Programs of Shanxi Province
Zitieren
APA
Mao, R., Wan, L., Zhou, M., & Li, D. (2025). Cox-Sage: enhancing Cox proportional hazards model with interpretable graph neural networks for cancer prognosis. Briefings in Bioinformatics, 26(2). https://doi.org/10.1093/bib/bbaf108
Vancouver
Mao R, Wan L, Zhou M, Li D. Cox-Sage: enhancing Cox proportional hazards model with interpretable graph neural networks for cancer prognosis. Briefings in Bioinformatics. 2025;26(2). doi:10.1093/bib/bbaf108
BibTeX
@article{Mao2025,
author = {Mao, Ruijun and Wan, Li and Zhou, Minghao and Li, Dongxi},
title = {Cox-Sage: enhancing Cox proportional hazards model with interpretable graph neural networks for cancer prognosis},
journal = {Briefings in Bioinformatics},
year = {2025},
volume = {26},
number = {2},
doi = {10.1093/bib/bbaf108}
}
EUVIMED