Figure 7 .
ROC curves of eight training datasets with different sizes based on 5-fold cross validation tests on ATP168. 1:1, 1:2, …, and 1:8 mean that the sizes of negative training subsets are 1 ~ 8 times respectively the sizes of corresponding positive datasets.
Zhang et al. BMC Bioinformatics 2012 13:118 doi:10.1186/1471-2105-13-118