Mal-Prec: computational prediction of protein Malonylation sites via machine learning based feature integration

BMC Genomics

Table 4 Comparison of state-of-the-art approaches in terms of Acc and AUC in different organisms

Approach	Feature	Species	Acc (%)	AUC (%)
mRMR+SVM [9]	K-gram+AAindex	N/A	N/A	79.35
IG + SVM [10]	AAC + BINA (sequence-based)	E. coli	72.30	75.50
	EBGW (physicochemical)	Mouse	74.65	82.70
	KNN + PSSM (evolutionary)	Homo sapiens	73.72	87.10
IG + SVM [11]	PKsaap+AAindex+DC	Mouse	N/A	73.90
IG + SVM [11]	PKsaap+AAindex+DC	Homo sapiens	N/A	74.30
LSTM+RF [12]	EAAC+word embedding	Mouse	88.00	82.40
LSTM+RF [12]	EAAC+word embedding	Homo sapiens	88.00	82.40
SVM [13]	Binary+PSSM+AAindex+Structured (ASA + SS + HSE + IDR)	Mouse	N/A	76.00
Proposed method	AAindex+One-hot+CKSAAP	Homo sapiens	90.65	90.91

ISSN: 1471-2164