Subcellular location prediction of proteins using support vector machines with alignment of block sequences utilizing amino acid composition

Table 5 Comparison of predictive accuracy for plant proteins in the TargetP data set with three types of feature vectors

Predictor	Location	Sensitivity	Specificity	MCC	Average MCC	Overall Accuracy
20 feature vectors (amino acid composition)	cTP	0.8440	0.9015	0.8507	0.8655	0.9096
	mTP	0.9348	0.9125	0.8735
	SP	0.9665	0.9319	0.9282
	other	0.8148	0.8684	0.8095
400 feature vectors (all adjacent amino acid composition)	cTP	0.8227	0.4128	0.4806	0.6126	0.7372
	mTP	0.8342	0.8797	0.7686
	SP	0.8253	0.8880	0.8015
	other	0.2963	0.8000	0.4339
40 feature vectors	cTP	0.8014	0.9040	0.8270	0.8594	0.9064
	mTP	0.9402	0.9081	0.8739
	SP	0.9628	0.9317	0.9255
	other	0.8272	0.8590	0.8110

ISSN: 1471-2105