Fig. 5
From: Exploration of biomarkers for systemic lupus erythematosus by machine-learning analysis
Three machine learning algorithms were applied to further explore the optimal key genes. A The LASSO algorithm determined the candidate optimal feature genes and the optimal lambda. Each coefficient curve in the left picture represents a single gene. The dashed vertical lines in the right picture represent the partial likelihood deviance. B The SVM-RFE algorithm was performed to further candidate optimal feature genes with the highest accuracy and lowest error obtained in the curves. C Top 10 key genes with importance > 2 were identified in the Random Forest algorithm. D Random forest for the relationships between the number of trees and error rate. E Venn diagram displayed the five optimal key genes overlapped by LASSO, Random Forest, and SVM-REF algorithms