Skip to main content

Table 14 AUPR, AUC, and CI for different kernels under CVT setting

From: Drug-target interactions prediction using marginalized denoising model on heterogeneous networks

Kernel Method AUPR AUC CI CI_PCC
2D Kronecker_rls 0.5010 0.8912 0.8037
DTIP_MDHN 0.7919 0.9701 0.7875 0.8293
3D Kronecker_rls 0.5494 0.9045 0.8192
DTIP_MDHN 0.7903 0.9708 0.7854 0.8344
ECFP4 Kronecker_rls 0.6024 0.9201 0.8408
DTIP_MDHN 0.7942 0.9700 0.8313 0.8354
  1. The best results in each column are in bold. CI_PCC is the values of CI calculated by DTIP_MDHN with PCC kernel