Skip to main content
. 2022 Oct 4;13:986995. doi: 10.3389/fgene.2022.986995

FIGURE 3.

FIGURE 3

Identification of m6A Regulator as biomarkers of hypertrophic cardiomyopathy. (A) Selection of significant m6A regulators by support vector machine recursive feature elimination (SVM-RFE) model. (B) Selection of significant m6A regulators by random forest (RF) model. (C) Venn diagram of five overlapped candidate genes shared by the SVM-RFE and RF algorithms. (D,E) Least absolute shrinkage and selection operator (LASSO) coefficient profiles of hub genes and cross-validation of the model. (F) receiver operating curves (ROC) of LASSO model in GSE36961. (G,H) ROC assessment and difference analysis (Wilcox rank sum test) of the candidate biomarkers using GSE36961. (I) Validation of the diagnostic value of candidate biomarkers using GSE130036. (J) The expressions of candidate diagnostic biomarkers in the GSE130036 dataset (Wilcox rank sum test). *p < 0.05, **p < 0.01, ***p < 0.001.