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

Table 5 Performance of the optimal probabilistic features

Feature	ACC	SE	SP	MCC	TP	TN	FP	FN
Optimal probabilistic features	94.1	94.9	93.3	88.2	820	802	58	44
BIT21 (k = 32)	91.8	88.3	95.3	83.9	764	819	40	101
BIT20 (k = 4)	91.0	86.2	95.7	82.3	746	822	37	119
AAC	93.8	93.5	94.1	87.6	809	808	51	56
BIT21 (k = 4)	91.0	86.2	95.8	82.4	746	823	36	119

SE sensitivity, SP specificity, ACC accuracy, MCC Matthew’s correlation coefficient, TP true positive, TN true negative, FP false positive, FN false negative, AAC amino acid composition, BIT20 twenty-bit feature, BIT21 twenty-one-bit feature

ISSN: 2049-9957