Age-Stratified Analysis of Therapeutic, Immune, and Glycosylation Gene Expression in Colorectal Cancer Using Machine Learning

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Colorectal cancer (CRC) is a major global health issue, yet current treatment strategies rarely consider patient age differences, leading to variable therapeutic efficacy and clinical outcomes. Although numerous biomarkers for CRC have been identified, their age-specific expression profiles and biological implications remain poorly understood, limiting the potential for age-tailored interventions. This study aimed to address this gap by identifying age-stratified gene expression patterns using Random Forest–based feature selection on the GSE44076 microarray dataset. We analyzed gene expression profiles from younger (<65 years) and older (≥65 years) CRC patient cohorts, focusing on three functional gene categories relevant to CRC biology (Therapeutic, Immune, and Glycosylation). Using Random Forest-based classification and feature selection, we identified minimal yet highly predictive gene signatures within each functional category. The performance of these signatures was rigorously evaluated via cross-validation and permutation testing, demonstrating robust predictive accuracy. Full models utilizing the top 10 genes from each category achieved exceptionally high cross-validation accuracy ranging from 97.2% to 98.6%. Even minimal models restricted to the top three predictive genes retained substantial classification power (85.2%–100%). Comparative analysis with Gradient Boosting Machines (GBM) and Support Vector Machines (SVM) classifiers affirmed the superiority and interpretability of Random Forest in discerning biologically meaningful gene interactions. Volcano plot analyses reinforced the significance of individual gene expression differences across age groups but highlighted Random Forest's unique ability to identify complex multi-gene interactions, particularly within the Therapeutic and Glycosylation gene categories. Glycosylation genes showed pronounced age-dependent expression changes, suggesting a role for glycosylation modifications in CRC pathogenesis and therapeutic responsiveness. Our study validates the hypothesis that carefully selected minimal gene sets can reliably differentiate CRC tissue types across age groups, uncovering age-related biological alterations with potential diagnostic and therapeutic implications. These findings underscore the critical need for further validation in independent patient cohorts and detailed functional studies to translate these age-specific biomarkers into clinical practice, enhancing personalized treatment strategies for colorectal cancer patients.

Article activity feed