Promoters and enhancers can be distinguished from one another based on DNA sequence properties alone. (A) ROC curve and (B) PR curve evaluating SVM classifiers trained to distinguish FANTOM promoters from enhancers using patterns of short DNA sequences (6-mers) as features. Plots show the mean, maximum, and minimum curves obtained from classifiers, trained and evaluated on nine unique subsets of 3000 promoters and 3000 enhancers from the full data sets. AUC, area under the curve; PR, precision recall; ROC, receiver operator characteristic; SVM, support vector machine.