view article

Figure 7
Classifier validation plots comparing an all-features classifier against classifiers trained on single features. (a) Confusion matrix for the entire data set (4438 rows of input features). (b) Classifier validation metrics for each classifier trained on single metrics against the classifier trained on all metrics comparing overall ROC AUC, F1 score, recall, precision and accuracy. (c) Receiver operating characteristic (ROC) curve for each classifier. ROC AUC, receiver operating characteristic area under the curve.

Journal logoSTRUCTURAL
BIOLOGY
ISSN: 2059-7983
Follow Acta Cryst. D
Sign up for e-alerts
Follow Acta Cryst. on Twitter
Follow us on facebook
Sign up for RSS feeds