Machine learning-driven prediction model for cuproptosis-related genes in spinal cord injury - construction and experimental validation

Aug 5, 2026

Upload by Riley

Machine learning is used to connect spinal cord injury (SCI) with cuproptosis by constructing predictive models based on gene-expression signatures. Differential expression and correlations of 13 cuproptosis-related genes distinguish SCI from non-SCI samples, while ssGSEA supports assessment of immune infiltration. Unsupervised clustering and WGCNA identify key modules and pathway enrichment. RF, LASSO, and SVM select candidate genes, validated by a nomogram and confirmed in an SCI rat model with behavioral, histologic, ultrastructural, and qRT-PCR evidence.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Methods

Gene expression and cuproptosis-related gene analysis

Clustering, WGCNA, and enrichment

Machine learning model construction and validation

Animal experiments

Results

Discussion

TYPE Original Research PUBLISHED 23 April 2025 DOI 10.3389/fneur.2025.1525416 OPEN ACCESS EDITED BY Wencai Liu, Shanghai Jiao Tong University, China REVIEWED BY Dunpeng Cai, University of Missouri, United States Zhuce Shao, Third Hospital of Shanxi Medical University, China Junqiao Lv, Shanxi Medical University, China Xinli Hu, Capital Medical University, China *CORRESPONDENCE Yu Zhou [zyhenry123@163.com](zyhenry123@163.com)[ ](zyhenry123@163.com)Xiaohong Mu [muxiaohong2006@126.com](muxiaohong2006@126.com) †These authors have contributed equally to this work and share first authorship ‡These authors have contributed equally to this work RECEIVED 28 November 2024 ACCEPTED 21 March 2025 PUBLISHED 23 April 2025 CITATION Zhou Y, Li X, Wang Z, Ng L, He R, Liu C, Liu G, Fan X, Mu X and Zhou Y (2025) Machine learning-driven prediction model for cuproptosis-related genes in spinal cord injury: construction and experimental validation. Front. Neurol. 16:1525416 . doi: 10.3389/fneur.2025.1525416 COPYRIGHT © 2025 Zhou, Li, Wang, Ng, He, Liu, Liu, Fan, Mu and Zhou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning-driven prediction model for cuproptosis-related genes in spinal cord injury: construction and experimental validation Yimin Zhou1†, Xin Li2†, Zixiu Wang3†, Liqi Ng4, Rong He5, Chaozong Liu4, Gang Liu1, Xiao Fan6, Xiaohong Mu1*‡ andYu Zhou2,7*‡ 1 Department of Orthopedics, Dongzhimen Hospital of Beijing University of Chinese Medicine, Beijing, China, 2 Postdoctoral Research Workstation, Orthopedic Hospital, Chonqqing University of Chinese Medicine, Chongqing, China, 3College of Pharmacy, Gannan Medical University, Ganzhou, China, 4 Institute of Orthopaedics and Musculoskeletal Science, University College London, Royal National Orthopaedic Hospital, London, United Kingdom, 5College of Integrated Chinese and Western Medicine, Changchun University of Chinese Medicine, Changchun, China, 6 Department of Orthopedics, Qingdao Municipal Hospital, Qingdao, Shandong, China, 7 Department of Orthopedics, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China Introduction: Spinal cord injury (SCI) severely affects the central nervous system. Copper homeostasis is closely related to mitochondrial regulation, and cuproptosis is a novel form of cell death associated with mitochondrial metabolism. This study aimed to explore the relationship between SCI and cuproptosis and construct prediction models. Methods: Gene expression data of SCI patient samples from the GSE151371 dataset were analyzed. The differential expression and correlation of 13 cuproptosis-related genes (CRGs) between SCI and non-SCI samples were identified, and the ssGSEA algorithm was used for immunological infiltration analysis. Unsupervised clustering was performed based on differentially expressed CRGs, followed by weighted gene co-expression network analysis (WGCNA) and enrichment analysis. Three machine learning models (RF, LASSO, and SVM) were constructed to screen candidate genes, and a Nomogram model was used for verification. Animal experiments were carried out on an SCI rat model, including behavioral scoring, histological staining, electron microscopic observation, and qRT-PCR. Results: Seven CRGs showed differential expression between SCI and non-SCI samples, and there were significant differences in immune cell infiltration levels. Unsupervised clustering divided 38 SCI samples into two clusters (Cluster C1 and Cluster C2) . WGCNA identified key modules related

FAQs

What clinical or biological problem does the study address?

The study addresses how spinal cord injury is linked to cuproptosis and how predictive models can be built from cuproptosis-related gene signatures.

Which key computational steps are used to construct the prediction models?

It analyzes differential expression and gene correlations, uses ssGSEA for immune infiltration, applies unsupervised clustering, then runs WGCNA and enrichment. RF, LASSO, and SVM screen candidate genes and a nomogram model verifies them.

What candidate genes and performance were reported?

Four candidate genes are identified: SLC31A1, DBT, DLST, and LIAS. SLC31A1 shows the best performance with AUC=0.958.

Aug 5, 2026

Upload by Riley