Identification and prediction of molecular subtypes of atherosclerosis based on m6A immune cell infiltration

Abstract

Background: Atherosclerosis is a complex disease with multiple molecular subtypes that are not yet fully understood. Recent studies have suggested that N6-methyladenosine (m6A) alterations may play a role in the pathogenesis of atherosclerosis. However, the relationship between m6A regulators and atherosclerosis remains unclear.

Methods: In this study, we analyzed the expression levels of 25 m6A regulators in a cohort of atherosclerosis (AS) and non-AS patients using the R "limma" package. We also used machine learning models, including random forest (RF), support vector machine (SVM), generalized linear model (GLM), and extreme gradient boosting (XGB), to predict the molecular subtypes of atherosclerosis based on m6A immune cell infiltration.

Results: We found that METTL3, YTHDF2, IGFBP1, and IGF2BP1 were overexpressed in AS patients compared to non-AS patients, while the other significant m6A regulators showed no significant difference. Our machine learning models achieved high accuracy in predicting the molecular subtypes of atherosclerosis based on m6A immune cell infiltration.

Conclusion: Our study suggests that m6A alterations may play a role in the pathogenesis of atherosclerosis, and that machine learning models can be used to predict molecular subtypes of atherosclerosis based on m6A immune cell infiltration. These findings may have important implications for the detection and management of atherosclerosis.

Keywords: Atherosclerosis(AS); Machine learning; m6A methylation.