A meta-learning approach for B-cell conformational epitope prediction

BMC Bioinformatics

Table 13 Ablation analysis of influence of linear base learners on cascade meta classifiers

Classifier^*	TPR	FPR	Precision	Accuracy	F-score	MCC	AUC
Conformational cascade	0.154	0.010	0.397	0.954	0.222	0.228	0.743
+BCPREDS	0.204	0.007	0.577	0.960	0.301	0.327	0.745
+ABCpred	0.184	0.005	0.617	0.960	0.284	0.323	0.760
+AAP	0.189	0.006	0.603	0.960	0.288	0.323	0.765
+ BepiPred	0.199	0.008	0.519	0.958	0.288	0.304	0.789

^*Classifiers tested in the ablation analysis. The first classifier in the first row is the cascade meta classifier that only employs the 4 conformational base learners. The remaining classifiers are listed in the order in which they were selected to be added iteratively to the cascade meta classifier for the ablation study. `+’ indicates “added”. For example, the second classifier is the cascade meta classifier after BCPREDS was added, and the third classifier is the cascade meta classifier after BCPREDS and ABCpred were added to the meta model. The meta classifier in the final row applied all the base learners after the final prediction tool BepiPred was added.

ISSN: 1471-2105