Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Comprehensive ensemble in QSAR prediction for drug discovery

Fig. 3

Learning procedure of the proposed comprehensive ensemble. The individual i-th learning algorithm \(\mathcal {L}_{i}\) outputs its prediction probability Pi for the training dataset through 5-fold cross-validation. The n diverse learning algorithms produce n prediction probabilities (P1,P2,⋯,Pn). The probabilities are concatenated and then used as input to the second-level learning algorithm \(\boldsymbol {\mathcal {L}}\), which makes a final decision \(\hat {y}\). a First-level learning. b Second-level learning

Back to article page