Skip to main content

Table 4 Comparison with other prediction models on test set 1 when the cutoff is 50%

From: HobPre: accurate prediction of human oral bioavailability for small molecules

Model Data set size Method ACC (test) AUC (test) Cut-off value
Current study 1588 RF 0.793 0.830 F = 50%
Falcón-Cano et al. [8] 1448 CART, MLP, NB, GBT, SVM 0.783a 0.800a F = 50%
admetSAR [9] 995 RF 0.697a 0.752a logK(%F)b = 0
(F = 50%)
Kim et al. [10] 995 RF, SVM-consensus CTG 0.76a NA F = 50%
  1. CART classification and regression trees; MLP multilayer perceptron; NB naive Bayes; GBT gradient boosted trees; SVM support vector machines
  2. aTaken from respective references
  3. b\(\mathrm{log}K\left(\mathrm{\%}F\right)=\mathrm{log}\left(\frac{\mathrm{\%}F}{100-\mathrm{\%}F}\right)\)