Figure 2From: Identification of yeast cell cycle regulated genes based on genomic featuresPerformance of prediction methods. (A) ROC curves for TF binding, motif, and TF + Motif combined models using penalized logistic regression with 10-fold cross validations. (B) AUC comparisons of four different machine learning methods, penalized logistic regression (PLR), random forest (RF), support vector machine (SVM) and ordinary logistic regression (LR). (C) Significant genomics features discriminating cell cycle regulated genes from non-cell cycle regulated ones (p-value < 0.01).Back to article page