Table 4.

Prediction of variability in the CD4-binding site of Env using KBC and other algorithms

Clade	Methods	Balanced Accuracy a,b	Accuracy	Precision	Recall	F1 Score
Clade C	KBC	0.71 (± 0.01)	0.85 (± 0.01)	0.81 (± 0.07)	0.45 (± 0.03)	0.58 (± 0.02)
	DT	0.61 (± 0.13)	0.76 (± 0.03)	0.32 (± 0.23)	0.34 (± 0.42)	0.25 (± 0.25)
	RF	0.56 (± 0.04)	0.76 (± 0.03)	0.49 (± 0.08)	0.19 (± 0.18)	0.22 (± 0.14)
	QDA	0.59 (± 0.07)	0.75 (± 0.04)	0.50 (± 0.08)	0.29 (± 0.28)	0.28 (± 0.15)
	LDA	0.69 (± 0.11)	0.79 (± 0.03)	0.59 (± 0.09)	0.50 (± 0.31)	0.46 (± 0.19)
	NB	0.67 (± 0.09)	0.73 (± 0.09)	0.45 (± 0.11)	0.58 (± 0.31)	0.45 (± 0.16)
	ADA	0.46 (± 0.18)	0.62 (± 0.24)	0.44 (± 0.29)	0.15 (± 0.10)	0.20 (± 0.14)
	LogReg	0.65 (± 0.12)	0.79 (± 0.01)	0.56 (± 0.04)	0.39 (± 0.33)	0.38 (± 0.21)
	SVM	0.64 (± 0.11)	0.76 (± 0.03)	0.50 (± 0.06)	0.43 (± 0.35)	0.37 (± 0.16)
Clade B	KBC	0.69 (± 0.02)	0.89 (± 0.01)	0.78 (± 0.02)	0.40 (± 0.04)	0.53 (± 0.04)
	DT	0.54 (± 0.02)	0.82 (± 0.02)	0.33 (± 0.02)	0.13 (± 0.08)	0.17 (± 0.10)
	RF	0.53 (± 0.02)	0.82 (± 0.03)	0.35 (± 0.18)	0.11 (± 0.05)	0.15 (± 0.06)
	QDA	0.56 (± 0.03)	0.82 (± 0.04)	0.42 (± 0.16)	0.17 (± 0.11)	0.21 (± 0.09)
	LDA	0.58 (± 0.05)	0.82 (± 0.01)	0.38 (± 0.05)	0.24 (± 0.13)	0.28 (± 0.10)
	NB	0.64 (± 0.08)	0.75 (± 0.10)	0.34 (± 0.14)	0.47 (± 0.21)	0.37 (± 0.13)
	ADA	0.48 (± 0.03)	0.17 (± 0.02)	0.15 (± 0.01)	0.93 (± 0.10)	0.26 (± 0.02)
	LogReg	0.56 (± 0.04)	0.84 (± 0.00)	0.42 (± 0.05)	0.17 (± 0.10)	0.23 (± 0.11)
	SVM	0.55 (± 0.04)	0.82 (± 0.03)	0.35 (± 0.15)	0.17 (± 0.11)	0.21 (± 0.10)

^aStandard deviation values are indicated in parentheses

^bValues in bold font indicate the highest point estimation value for each metric