Skip to main content
. 2021 May 18;22(6):bbab146. doi: 10.1093/bib/bbab146

Figure 5 .


Figure 5

Performance comparison of the proposed nhKcr, the state-of-the-art predictor Deep-Kcr and the DirectInput-CNN. (A) ROC curves. Colored lines represent the different predictors. Diagonal gray dashed lines represent the performance of a random classifier. Legend box contains the AUC for each predictor. (B) pair-wise performance comparison between three methods in terms of P-value.