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

Table 6 Performance of the SFS strategy

Learning strategies	ACC	SE	SP	MCC	TP	TN	FP	FN
Optimal class features	94.2	95.0	93.4	88.4	822	802	57	43
Optimal probabilistic features	94.1	94.9	93.3	88.2	820	802	58	44
Major voting	93.5	92.0	95.0	87.1	796	816	43	69
Probability averaging	93.0	90.9	95.2	86.2	786	818	41	79

SFS sequential forward search, SE sensitivity, SP specificity, ACC accuracy, MCC Matthew’s correlation coefficient, TP true positive, TN true negative, FP false positive, FN false negative

ISSN: 2049-9957