Machine learning-driven SLC prognostic signature for glioma: predicting survival and immunotherapy response

Gliomas are the most common and aggressive primary brain tumors, characterized by significant heterogeneity and poor prognosis. Despite advancements in treatment, therapeutic resistance and tumor recurrence remain major challenges. Identifying novel molecular biomarkers is essential for improving prognosis and developing more effective therapies.

In this study, we developed a solute carrier family prognostic signature (SLCFPS) for gliomas using univariate Cox regression and machine learning algorithms across five independent glioma cohorts. Prognostic performance was evaluated through Kaplan-Meier survival analysis, concordance index (C-index), and receiver operating characteristic (ROC) curve analysis. The immune landscape, immunotherapy response, and drug sensitivity were further analyzed using bioinformatics tools such as ESTIMATE, xCell, TIDE, and drug response correlation analysis.

SLCFPS effectively stratified glioma patients into high- and low-risk groups, with higher scores associated with poorer survival outcomes. The model demonstrated superior predictive performance compared to existing glioma prognostic models. Additionally, SLCFPS was linked to an immunosuppressive tumor microenvironment and upregulated immune checkpoints, indicating potential implications for immunotherapy response. Furthermore, SLCFPS correlated with drug sensitivity, suggesting potential therapeutic options for glioma treatment.

Our findings highlight SLCFPS as a robust biomarker for glioma prognosis and treatment response. By providing insights into tumor immunity, this model may aid in the development of personalized therapeutic strategies. Further validation in clinical settings is necessary to explore its full potential in guiding glioma management.