Fig. 5 | Scientific Reports

Fig. 5

From: Machine learning analysis of gene expression profiles of pyroptosis-related differentially expressed genes in ischemic stroke revealed potential targets for drug repurposing

Fig. 5

Construction of a PRDEGs-based model for IS vs Control. (A) Number of genes with the lowest error rate obtained by the SVM modeling. (B) Number of genes with the highest accuracy rate obtained by the SVM modeling. (C) Plot of model training error for the random forest algorithm. (D) Random forest model showing top 30 PRDEGs (in descending order of IncNodePurity). (E) Forest plot of the logistic (logistic) regression model. (F) Diagnostic plot for the LASSO regression model. (G) Variable trajectory plot for the LASSO regression model. (H) Column line plot (Nomogram) of the 12-PRDEGs in the diagnostic model. (I,J) Calibration curve plot (I), DCA plot (J) for the PRDEGs-based model. SVM support vector machine, PRDEGs pyroptosis-related differentially expressed genes, LASSO least absolute shrinkage and selection operator, DCA decision curve analysis.

Back to article page