Fig. 3 | Scientific Reports

Fig. 3

From: Identification of marker genes associated with oxidative stress in hypertrophic cardiomyopathy using bioinformatics analysis and experimental validation

Fig. 3

7 OS-DEGs were identified as potential diagnostic genes for HCM. (A and B) By LASSO logistic regression algorithm, with penalty parameter tuning conducted by 10-fold cross-validation, was used to select 14 HCM-related features. (C and D) SVM-RFE algorithm to filter the 14 OS-DEGs to identify the optimal combination of feature genes. Finally, 7 genes (maximal accuracy = 0.985, minimal RMSE = 0.0146) were identified as the optimal feature genes. (E) The marker genes obtained from the LASSO and SVM-RFE models. F: ROC curves for the 7 marker genes.

Back to article page