Figure 6 | Scientific Reports

Figure 6

From: Identification of Hedyotis diffusa Willd-specific mRNA–miRNA–lncRNA network in rheumatoid arthritis based on network pharmacology, bioinformatics analysis, and experimental verification

Figure 6

MMP9 was identified as the core gene of RA through three computational learning algorithms. (A) Penalized parameter adjustment by LASSO logistic regression algorithm with tenfold cross-validation was used to select 6 RA-related features. (B) SVM-RFE algorithm to filter 16 key genes to determine the best combination of key genes. Finally, 1 gene (maximum precision = 0.833, minimum RMSE = 0.167) was identified as the best key gene. (C) Key gene screening was performed by random forest algorithm, and 3 genes were identified as key genes based on gene importance greater than 1.0. (D) Key gene MMP9 obtained from LASSO, SVM-RFE and RF models.

Back to article page