Skip to main content

Table 4 Prospective Performance Comparison

From: Industry-scale application and evaluation of deep learning for drug target prediction

 Null Hyp.: DNN AUC < row AUC
 Wilcoxon testSign test
AlgorithmAstraZenecaJanssenAstraZenecaJanssen
XGB7.17e−152.62e−151.27e−146.84e−14
MF4.01e−093.23e−112.98e−083.04e−11
  1. p-values of comparing the respective algorithm prospective ROC-AUC evaluation performance in the table row with that of DNNs using two different statistical tests