Prediction of S-Nitrosylation Modification Sites Based on Kernel Sparse Representation Classification and mRMR Algorithm

Table 2

Performances of six algorithms on the training set with the respective optimal features using 10-fold cross validation.

	SN	SP	ACC	MCC
KSRC	0.4048	0.7543	0.6393	0.1634
SRC	0.3489	0.7876	0.6433	0.1467
KNN	0.3852	0.7469	0.6279	0.1358
RF	0.3399	0.7957	0.6458	0.1473
SMO	0.2840	0.8705	0.6776	0.1887
Dagging	0.3610	0.8320	0.6771	0.2150

KSRC: kernel sparse representation classification; SRC: sparse representation classification; KNN: -nearest neighbor algorithm; RF: random forest method; SMO: sequential minimal optimization; Dagging refers to the use of majority vote to combine multiple models derived from a single learning algorithm using disjoint samples.