Using amino acid features to identify the pathogenicity of influenza B virus

Table 4 Performance of the optimal class features

Feature	ACC	SE	SP	MCC	TP	TN	FP	FN
Optimal class features	94.2	95.0	93.4	88.4	822	802	57	43
OLP (k = 28)	91.1	86.6	95.7	82.6	749	822	37	116
PC-PseAAC (λ = 5)	94.0	94.0	94.1	88.1	813	808	51	52
GGAP (g = 5)	93.6	92.7	94.4	87.1	802	811	48	63
BIT20 (k = 12)	91.0	86.2	95.7	82.3	746	822	37	119

SE sensitivity, SP specificity, ACC accuracy, MCC Matthew’s correlation coefficient, TP true positive, TN true negative, FP false positive, FN false negative, PC-PseAAC parallel correlation-based pseudo-amino-acid composition, GGAP the G-gap dipeptide composition, BIT20 twenty-bit feature, OLP overlapping property feature

ISSN: 2049-9957