Pep-3D-Search: a method for B-cell epitope prediction based on mimotope analysis

BMC Bioinformatics

Table 2 Evaluation and comparison of the performances of Pep-3D-Search.

PDB ID	1jrh	1bj1	1g9m	1e6j	1n8z	1iqd	1yy9	2adf	1avz	1hx1	Average
CED ID	CE0179	CE0175	CE0058	CE0170	CE0096	CE0176	CE0199	CE0154	--	--
Epitope size	21	19	15	11	20	16	15	15	16	24
Antigen size	94	93	304	209	580	155	612	188	102	111
Pep-3D-Search
TP/PE	19/40	7/13*	10/39	11/36	20/35*	6/47	10/25	12/36	10/39	13/39
MCC	0.3902	0.1442	0.1394	0.2285	0.1856	0.0356	0.1030	0.2153	0.1643	0.152	0.1758
Sensitivity	0.475	0.5833	0.2564	0.3056	0.5714	0.1277	0.4	0.3333	0.2564	0.3333	0.3642
Precision	0.9048	0.3684	0.6667	1.0	1.0	0.375	0.6667	0.8	0.625	0.5417	0.6948
PepSurf
TP/PE	19/28	2/17	9/31	10/30	6/11	8/31	1/8*	10/18	14/25	12/25
MCC	0.4134	-0.0537	0.1257	0.2056	0.0596	0.1272	0.0067	0.1832	0.3348	0.1863	0.1589
Sensitivity	0.6786	0.1176	0.2903	0.3333	0.5455	0.2581	0.125	0.5556	0.56	0.48	0.3944
Precision	0.9048	0.1053	0.6	0.9091	0.3	0.5	0.0476	0.6667	0.875	0.5	0.5409
Mapitope
TP/PE	19/22	2/18	13/33	1/6	9/13	15/106	3/23*	0/10	6/9*	5/21
MCC	0.4224	-0.062	0.1899	0.0154	0.0909	0.2401	0.0209	-0.0173	0.1387	0.0135	0.1053
Sensitivity	0.8636	0.1111	0.3939	0.1667	0.6923	0.1415	0.1304	0.0	0.6667	0.2381	0.3404
Precision	0.9048	0.1053	0.8667	0.0909	0.45	0.9375	0.1429	0.0	0.375	0.2083	0.4081

TP: number of true positives; PE: number of residues in the predicted epitope; TN: number of true negatives; FP: number of false positives; FN: number of false negatives; Matthews correlation coefficient $(MCC) = \frac{(T P \cdot T N) - (F P \cdot F N)}{\sqrt{(T P + F P) (T P + T N) (T N + F P) (T N + F N)}}$ ; $Sensitivity (Se) = \frac{T P}{T P + F N}$ ; $Precision (Pr) = \frac{T P}{T P + F P}$ .
*For the cases, the best prediction was found in the second-ranked candidate.

ISSN: 1471-2105