Identification and characterization of plastid-type proteins from sequence-attributed features using machine learning

Table 9 Overall performance of various feature classifiers on an 'independent test' dataset for the classification of diverse plastid-types^* (phase-I I)

Feature type	Sensitivity (%)	Specificity (%)	Accuracy (%)	MCC	Precision (%)	ER (%)
AAC	57.26	63.89	72.54	0.30	62.45	27.47
PseAA	57.26	63.88	72.48	0.31	65.25	27.52
Dipep	61.29	65.96	74.97	0.40	73.97	25.03
NCC	61.29	75.82	77.15	0.40	60.42	22.85
Physico-Chem	45.97	65.30	66.63	0.14	47.03	33.37

*classification of 4 plastid types: chloroplast, chromoplast, etioplast, amyloplast; individual performance of these classifiers on each class can be seen in supplementary material; AAC = amino acid composition, PseAA = Pseudo amino acid composition, Dipep = Dipeptide composition, NCC = N_terminal-Center-C_terminal composition (sequence divided into 3 parts), Physico-Chem = Protein physicochemical properties, MCC = Matthews Correlation Coefficient, ER = Error Rate.

ISSN: 1471-2105