Table 8. Performance comparison of different methods on Z277 dataset.

Method	Prediction accuracy (%)
	All-α	All-β	α/β	α+β	Overall
Rough sets by Cao et al.(2006) [20]	77.1	77.0	93.8	66.2	79.4
Information-theoretical approach by Zheng et al. (2010) [22]	87.1	80.3	93.8	67.7	83.0
LogitBoost by Feng et al. (2005) [21]	81.4	88.5	92.6	72.3	84.1
VPMCD by Raghuraj and Lakshminarayanan(2008) [38]	85.7	85.0	92.9	84.4	84.2
IGA-SVM by Li et al. (2008) [24]	84.3	88.5	92.6	70.7	84.5
CWT-PCA-SVM by Li et al. (2009) [25]	85.7	90.2	87.7	80.1	85.9
Markov-SVM by Qin et al. (2012) [27]	90.0	85.2	86.4	81.5	85.9
AAC-PSSM-AC by Liu et al. (2012) [23]	88.6	95.1	97.5	81.5	91.0
Our method	100.00	98.31	100.00	100.00	99.64