Investigation and identification of protein carbonylation sites based on position-specific amino acid composition and physicochemical features

Table 1 Data statistics of positive and negative sequences (with window size 21) in training and testing datasets

Dataset	Residues	Number of proteins	Number of positive sequences	Number of negative sequences
Training dataset	K	155	206	1166
	R	90	101	504
	T	81	96	488
	P	77	94	412
Independent testing dataset	K	67	78	301
	R	65	67	276
	T	50	53	124
	P	71	82	304

ISSN: 1471-2105