Fig. 7
From: A tensor-based bi-random walks model for protein function prediction
- ROC curves of seven methods using leave-one-out cross validation. The figure denotes the ROC (receiver-operating) curves of RWRT and other six competing methods (Zhang, DCS, DSCP, PON and GrAPFI) based on the average prediction performance over all testing proteins. The vertical and horizontal coordination of the ROC curves are the values of true positive rate and false positive rate, respectively. a ROC curves of seven methods on the BioGRID dataset. b ROC curves of various methods on the DIP dataset