Fig. 4 | Scientific Reports

Fig. 4

From: Identification of palmitoylated biomarkers in non-alcoholic fatty liver disease via integrated bioinformatics analysis and machine learning

Fig. 4

Construction and evaluation of seven machine models. (A) The reverse cumulative distribution of residuals for seven machine learning models (NNET, RF, KNN, GLM, DT, SVM, LASSO). (B) The boxplot of residuals. The boxplot illustrates the distribution of residuals for the seven machine learning models (NNET, RF, KNN, GLM, DT, SVM, LASSO). Red dots represent the root mean square error (RMSE) of the residuals. (C) The ROC curves and corresponding AUC values for seven machine learning models (RF, SVM, GLM, KNN, NNET, LASSO, DT). (D) The top 10 significant feature variables in seven machine learning models (DT, GLM, KNN, LASSO, NNET, RF, SVM), ranked according to root mean square error (RMSE). (E) The intersection of the top 10 predicted genes in NNET and DT models. (F) The ROC curves and corresponding AUC values for TYMS, WNT5A, and ZFP36.

Back to article page