Identification of combinatorial host-specific signatures with a potential to affect host adaptation in influenza A H1N1 and H3N2 subtypes

Table 9 Performance of the H1N1 models on H3N2 data and vice versa

	Protein	Sensitivity	Specificity	MCC
H3N2 data - H1N1 models	HA	1	0	na
	M1	1	0.895	0.941
	M2	1	0.73	0.84
	NA	1	0	na
	NP	1	0.882	0.932
	NS1	1	0.747	0.85
	NEP	1	0.648	0.78
	PA-X	0	1	na
	PA	0.021	0.93	−0.11
	PB1-F2	0.023	1	0.056
	PB1	0.563	0.909	0.302
	PB2	0.979	0.949	0.873
H1N1 data - H3N2 models	HA	0	na	na
	M1	0.957	0.975	0.885
	M2	0.987	0.766	0.804
	NA	1	0	−0.004
	NP	0.364	0.984	0.251
	NS1	0.365	0.993	0.237
	NEP	0.027	1	0.061
	PA-X	0.201	0.982	0.223
	PA	0.247	0.995	0.177
	PB1-F2	0.991	0.804	0.832
	PB1	0.992	0.877	0.888
	PB2	0.956	0.951	0.786

Sensitivity is the ability to correctly predict human sequences and specificity is the ability to correctly predict avian sequences where 1 means perfect prediction and 0 means no correct prediction. Matthews correlation coefficient (MCC) value is a measure of how well the model performs overall where 1 means a perfect classification, 0 is for a prediction no better than random and −1 indicates a total disagreement between predictions and observations. “na” means the measure could not be calculated for the given model

ISSN: 1471-2164