Construction of a Wilms tumor risk model based on machine learning and identification of cuproptosis-related clusters

Jingru Huang ¹, Yong Li ¹, Xiaotan Pan ¹

⁰Department of Pediatric Surgery, The First Affiliated Hospital of Guangxi Medical University, Guangxi Zhuang Autonomous Region, No. 6, Shuangyong Road, Nanning, 530022, China.

Bmc Medical Informatics and Decision Making +

|

November 4, 2024

View abstract on PubMed

Summary

This study links Wilms tumor (WT) to cuproptosis-related genes (CRGs), developing a predictive model for WT risk. Five key genes were identified, offering new insights into WT mechanisms and potential therapeutic targets.

Area Of Science

Oncology
Cell Biology
Genetics

Background

Cuproptosis, a copper-induced programmed cell death, has poorly understood mechanisms in Wilms tumor (WT).
This research investigates the association between WT and cuproptosis-related genes (CRGs).

Purpose Of The Study

To explore the link between WT and CRGs.
To develop a predictive model for WT risk assessment.

Main Methods

Analysis of four WT gene expression datasets from the GEO database.
Differential expression analysis, immune infiltration studies, and weighted gene co-expression network analysis of CRGs.
Construction and validation of a WT risk prediction model using machine learning (SVM) and a nomogram.

Main Results

Identification of 13 differentially expressed CRGs.
Distinct immune cell infiltration patterns in WT, including lower CD8+ T cells and higher M0 macrophages and T follicular helper cells.
A support vector machine (SVM) model using 5 key genes demonstrated satisfactory predictive performance on validation datasets.

Conclusions

Established a significant link between WT and cuproptosis.
Developed a novel predictive model for WT risk.
Identified five critical genes associated with WT, potentially serving as biomarkers or therapeutic targets.

Keywords:

Cuproptosis Immune infiltration Machine learning Molecular clusters Wilms tumor