Conformational B-Cell Epitopes Prediction from Sequences Using Cost-Sensitive Ensemble Classifiers and Spatial Clustering

Table 1

Detailed compositions of the bound, unbound and independent datasets.

Dataset	No. of Sequences	(numP, numN)*
Bound structure	83	(1076, 16744)
Unbound structure	48	(898, 8759)
Independent	19	(440, 4944)

∗(numP, numN) represent the numbers of positive (antigenic determinant residues) and negative (non-antigenic determinant residues) samples, respectively.