Fig. 5
From: A tensor-based bi-random walks model for protein function prediction
- The average FPR of seven methods according to different functional size of target proteins. The figure depicts the average false positive rate of our method and other competing methods fluctuate under different functional size of target proteins. Here functional size means the number of GO terms in each target protein. Size ranges from 1 to 14, except for 13. a Predicting results of seven methods on the BioGRID dataset. b Predicting results of seven methods on the DIP dataset