Skip to main content

Table 3 Comparison of prediction performance for DITL-KRR approach with Mapped Prediction (MP) and Direct Prediction (DP) approaches for 4 common drugs

From: Application of transfer learning for cancer drug sensitivity prediction

Drug Number of features Pearson Correlation NRMSE
   MP DP DITL-KRR MP DP DITL-KRR
17-AAG 47 0.6319 0.4749 -0.2885 0.1942 0.2167 0.4056
AZD6244 49 0.4407 0.4016 -0.1468 0.1554 0.1570 0.2042
Nilotinib 35 0.9338 0.4674 -0.1701 0.1003 0.1257 0.1410
Nutlin-3 48 0.5921 0.5207 -0.1500 0.1881 0.1903 0.2697
  1. Here, intersection of top 50 genes is taken as the feature set. Bold values indicate the best performance