NN-align. An artificial neural network-based alignment algorithm for MHC class II peptide binding prediction

Table 4 Predictive performance in terms of the AUC on the Wang benchmark data set.

Allele	*ARB*	*MHC2Pred*	*MHCpred*	*Propred*	*Rankpep*	*SMM-align*	*SVRMHC*	*SYF*	*Cons*	*NN-W-P1*	*NN-W*
DRB1*0101	0.76	0.67	0.62	0.74	0.70	0.77	0.69	0.71	0.79	0.88	0.87
DRB1*0301	0.66	0.53		0.65	0.67	0.69		0.50	0.72	0.82	0.82
DRB1*0401	0.67	0.52	0.60	0.69	0.63	0.68	0.66	0.65	0.69	0.73	0.72
DRB1*0404	0.72	0.64		0.79	0.66	0.75			0.80	0.83	0.83
DRB1*0405	0.67	0.51		0.75	0.62	0.69	0.62		0.72	0.81	0.80
DRB1*0701	0.69		0.63	0.78	0.58	0.78		0.68	0.83	0.86	0.87
DRB1*0802	0.74	0.70		0.77		0.75			0.82	0.79	0.81
DRB1*0901	0.62	0.48			0.61	0.66		0.73	0.68	0.68	0.69
DRB1*1101	0.73	0.60		0.80	0.70	0.81			0.80	0.89	0.89
DRB1*1302	0.79	0.54		0.58	0.52	0.69			0.73	0.78	0.78
DRB1*1501	0.70	0.63		0.72	0.62	0.74	0.64	0.67	0.72	0.77	0.76
DRB3*0101	0.59					0.68				0.85	0.86
DRB4*0101	0.74	0.61			0.65	0.71			0.74	0.86	0.86
DRB5*0101	0.70	0.59		0.79	0.73	0.75	0.63		0.79	0.87	0.87
Ave	0.70	0.59	0.62	0.73	0.64	0.73	0.65	0.66	0.76	0.82	0.82

NN-W-P1 is the NN-based method including data redundancy step-size rescaling and P1-PSSM encoding and NN-W is the NN-based method including data redundancy step-size rescaling. Both methods were evaluated using 10-fold cross-validation. The performance values for the 9 other methods were taken from Wang et al. [18]. For each allele, the best performing NN method is highlighted in bold and the best performing of all methods is underlined.