Age-stratified analysis of therapeutic, immune, and glycosylation gene expression in colorectal cancer using machine learning

Basit Öğe Kaydı
dc.contributor.authorCelik, Hakan
dc.contributor.authorBansal, Benu
dc.contributor.authorGill, Jappreet Singh
dc.contributor.authorCorrea, Jacqueline Kim
dc.contributor.authorHerman, Kristian
dc.contributor.authorGoyal, Reet
dc.contributor.authorMathur, Ramkumar
dc.date.accessioned2026-03-14T11:48:51Z
dc.date.available2026-03-14T11:48:51Z
dc.date.issued2025
dc.departmentSiirt Üniversitesi
dc.description.abstractColorectal 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. This knowledge gap limits the development and clinical deployment of age-tailored interventions. In this study, we applied an age-aware machine learning framework to uncover gene signatures stratified by age using the GSE44076 microarray dataset. We analyzed three CRC-relevant gene categories (Therapeutic, Immune, and Glycosylation) across three data versions: Original, WithAge (age as a feature), and Age Regressed (residual expression). Patient samples were stratified into younger (< 70 years) and older (>= 70 years) cohorts to identify age-influenced molecular shifts. Random Forest (RF)-based feature selection yielded compact gene signatures that discriminated against tumor, normal, and mucosa. Under 5 x 10 nested cross-validation, Top-10 gene models achieved Balanced Accuracy approximate to 0.94-0.99 and macro-averaged OvR AUC approximate to 0.96-0.99, while Top-3 sets retained strong performance (Balanced Accuracy approximate to 0.87-0.95). We benchmarked RF against Gradient Boosting Machine (GBM), Support Vector Machine (SVM), and k-Top Scoring Pairs (KTSP) classifiers. RF provided the best overall multivariate metrics under shallow-tree constraints (depth 1-2; min leaf 1-2), KTSP models consistently captured age-dependent gene ranking shifts with enhanced sensitivity, especially in external validation. KTSP's robustness in identifying directional age effects was most evident in the Glycosylation category, where glycan-processing genes showed pronounced age-stratified performance. Permutation tests that replicated the full nested pipeline (N = 100) yielded p approximate to 0.01, confirming that results are unlikely under the null. To uncover deeper regulatory mechanisms, we modeled gene-age interactions, revealing additional biomarkers. External validation using the GSE106582 cohort further supported our findings, although batch harmonization constrained gene coverage by removing platform-unique probes, highlighting a key limitation for microarray-based biomarker translation. Nonetheless, core signatures retained their predictive power, confirming generalizability. Altogether, our results establish age as a critical biological variable influencing CRC gene expression and classifier performance. This study provides a rigorous framework for integrating machine learning, statistical interaction modeling, and biological annotation to guide age-stratified biomarker discovery. Our findings support the development of precision oncology tools tailored to the distinct molecular landscapes of young-onset and late-onset CRC.
dc.description.sponsorshipNational Institute of General Medical Sciences of the National Institutes of Health [P20GM155890]
dc.description.sponsorshipResearch reported in this publication was supported by the National Institute of General Medical Sciences of the National Institutes of Health under Award Number P20GM155890 to RM.
dc.identifier.doi10.1038/s41598-025-31499-9
dc.identifier.issn2045-2322
dc.identifier.issue1
dc.identifier.pmid41390349
dc.identifier.scopus2-s2.0-105027577204
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1038/s41598-025-31499-9
dc.identifier.urihttps://hdl.handle.net/20.500.12604/8990
dc.identifier.volume16
dc.identifier.wosWOS:001663118700003
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherNature Portfolio
dc.relation.ispartofScientific Reports
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WoS_20260310
dc.subjectColorectal Cancer
dc.subjectAge-Stratified Analysis
dc.subjectMachine Learning
dc.subjectTherapeutic Genes
dc.subjectImmune Genes
dc.subjectGlycosylation
dc.titleAge-stratified analysis of therapeutic, immune, and glycosylation gene expression in colorectal cancer using machine learning
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu