Extended Data Fig. 5: Comparison of different statistical models for predicting enhancers and promoters using six features.
From: Supervised enhancer prediction with epigenetic pattern recognition and targeted validation
The performance of the different statistical models to integrate the information from six epigenetic features for promoter and enhancer prediction is shown. a) The numbers within the parentheses refer to the AUROC and AUPR for predicting the promoters with histone peaks while the numbers outside the parentheses refer to the AUROC and AUPR for predicting enhancers. The promoters and enhancers from multiple STARR-seq experiments with different core promoters are merged in this analysis. b) The individual ROC and PR curves for each statistical model is shown. The contribution of the matched filter score for each epigenetic feature to the different integrated models for promoter prediction (c) and enhancer prediction (d) are shown. The mean value is displayed in the bar plot while the error bars show the standard deviation of feature weights measured by ten-fold cross validation.
