Stack-VTP: prediction of vesicle transport proteins based on stacked ensemble classifier and evolutionary information

Table 4 Performance of different meta-classifiers on the training set with 10-fold cross-validation

	ACC (%)	SN	SP	MCC	Time	ACC_Std	SN_std	SP_Std	MCC_Std	AUC_Std
GBM	72.92	0.734	0.726	0.459	382.590	0.014	0.026	0.023	0.027	0.018
RF	71.82	0.716	0.722	0.437	277.694	0.016	0.025	0.026	0.032	0.018
SVM	73.66	0.796	0.679	0.478	287.667	0.015	0.041	0.036	0.033	0.019
ERT	72.10	0.715	0.729	0.443	365.482	0.015	0.026	0.017	0.030	0.017
NB	74.50	0.754	0.737	0.490	365.941	0.016	0.020	0.024	0.033	0.015
AdaBoost	74.27	0.754	0.732	0.485	366.721	0.017	0.027	0.018	0.035	0.014
DT	64.75	0.651	0.645	0.295	364.414	0.020	0.031	0.030	0.039	0.020
LR	74.90	0.760	0.738	0.498	351.539	0.018	0.023	0.020	0.035	0.015
XGB	72.01	0.726	0.716	0.441	367.720	0.017	0.019	0.029	0.035	0.018

\({}^{\textrm{ACC}\_\textrm{Std,SN}\_\textrm{std,SP}\_\textrm{Std,MCC}\_\textrm{Std,AUC}\_\textrm{Std}}\) these are the standard deviations of ACC, SN, SP, MCC and AUC when each classifier performs ten-fold cross validation on the training set

ISSN: 1471-2105