Figure 5From: Mapping the stabilome: a novel computational method for classifying metabolic protein stabilityComparison of protein stability prediction models trained on a trimmed data set. The performance of the BN, SVM and BN+SVM model on a trimmed data set with secreted and transmembrane proteins removed. Due to the set containing a smaller number of samples (300 stable proteins and 227 unstable proteins), 25-fold cross validation was used to calculate the ROC curves.Back to article page