Skip to main content

Advertisement

Table 4 Virtual Screening results for Thrombin at five different applicability levels

From: Estimation of the applicability domain of kernel-based machine learning models for virtual screening

Kernel ADE   Threshold AUROC BEDROC (α) Ligands Decoys
      100.00 53.6 32.2 20.0   
OAK KDE 50% 0.64 0.88 0.61 0.60 0.60 0.61 11 575
   33% 0.66 0.87 0.66 0.63 0.63 0.64 10 380
   200 0.68 0.97 0.78 0.72 0.73 0.73 8 192
   100 0.69 0.97 0.90 0.81 0.81 0.78 8 92
  wKDE 50% 0.64 0.88 0.61 0.60 0.60 0.61 11 575
   33% 0.66 0.87 0.66 0.63 0.63 0.64 10 380
   200 0.68 0.97 0.78 0.73 0.73 0.74 8 192
   100 0.69 0.97 0.90 0.81 0.81 0.78 8 92
  ONE 50% -9.61 0.88 0.62 0.60 0.60 0.60 11 478
   33% -9.11 0.87 0.66 0.63 0.63 0.64 10 380
   200 -8.06 0.94 0.77 0.69 0.68 0.68 9 191
   100 -7.08 0.97 0.90 0.81 0.81 0.78 8 92
FlexOAK KDE 50% 0.64 0.85 0.43 0.47 0.48 0.52 11 575
   33% 0.65 0.91 0.49 0.53 0.53 0.59 9 381
   200 0.67 0.91 0.59 0.58 0.58 0.63 8 192
   100 0.68 0.91 0.74 0.67 0.67 0.69 8 92
  wKDE 50% 0.64 0.78 0.41 0.45 0.46 0.49 12 574
   33% 0.65 0.91 0.49 0.53 0.53 0.59 9 381
   200 0.67 0.91 0.59 0.58 0.58 0.63 8 192
   100 0.68 0.91 0.74 0.67 0.67 0.69 8 92
  ONE 50% -9.80 0.91 0.49 0.54 0.54 0.59 10 576
   33% -9.07 0.91 0.55 0.59 0.60 0.64 9 381
   200 -8.10 0.92 0.62 0.63 0.64 0.68 8 192
   100 -7.32 0.98 0.74 0.68 0.68 0.71 7 93
MARG KDE 50% 0.876 0.81 0.45 0.43 0.43 0.45 12 574
   33% 0.885 0.96 0.56 0.58 0.58 0.62 8 382
   200 0.893 0.94 0.62 0.58 0.58 0.59 8 192
   100 0.899 0.93 0.90 0.80 0.79 0.74 8 92
  wKDE 50% 0.882 0.81 0.46 0.44 0.44 0.47 12 574
   33% 0.891 0.96 0.56 0.58 0.58 0.62 8 382
   200 0.899 0.95 0.77 0.69 0.69 0.68 8 192
   100 0.905 0.93 0.90 0.80 0.79 0.74 8 92
  ONE 50% -2.631 0.80 0.42 0.42 0.43 0.46 11 531
   33% -2.334 0.88 0.52 0.50 0.50 0.52 9 381
   200 -1.932 0.93 0.61 0.54 0.54 0.54 8 192
   100 -1.607 0.92 0.73 0.64 0.63 0.61 7 93
  1. The threshold is adjusted such that either a certain fraction (50%, 33%) of the compounds or that exactly n compounds (n = 200, 100) remain in the domain. Results, which differ significantly from random rankings (p-Value < 0.01) are shown in bold.