Comparative analysis and prediction of nucleosome positioning using integrative feature representation and machine learning algorithms

Table 10 Comparison of our predictors with other models via 10-fold cross-validation for C. elegans

Method	Feature	ACC	Sn	Sp	MCC	AUC
DLNN-5 [24]		0.8962	0.9304	0.8634	~	~
ZCMM [23]		0.8534	0.7880	0.8410	0.6200	0.9120
SVM	FCGR	0.8603	0.8948	0.8263	0.7229	0.9295
	FCGR + DAC	0.8574	0.8863	0.8290	0.7164	0.9283
	FCGR + TAC	0.8561	0.8824	0.8302	0.7137	0.9272
	FCGR + DACC	0.8471	0.8777	0.8171	0.6961	0.9122
	FCGR + TACC	0.8470	0.8641	0.8301	0.6949	0.9179
	FCGR + PCPseDNC	0.8576	0.8921	0.8236	0.7176	0.9275
	FCGRPCPseTNC	0.8539	0.8839	0.8244	0.7096	0.9275
	All features	0.8431	0.8461	0.8401	0.6867	0.9139
ELM	FCGR	0.8754	0.8944	0.8566	0.7515	0.9421
	FCGR + DAC	0.8707	0.8863	0.8555	0.7421	0.9355
	FCGR + TAC	0.8696	0.8890	0.8505	0.7400	0.9359
	FCGR + DACC	0.8684	0.8831	0.8539	0.7376	0.9358
	FCGR + TACC	0.8680	0.8917	0.8447	0.7371	0.9329
	FCGR + PCPseDNC	0.8624	0.8847	0.8405	0.7258	0.9318
	FCGR + PCPseTNC	0.8557	0.8847	0.8271	0.7132	0.9262
	All features	0.8597	0.8863	0.8336	0.7210	0.9271
XGBoost	FCGR	0.8487	0.8797	0.8182	0.6995	0.9202
	FCGR + DAC	0.8526	0.8831	0.8225	0.7068	0.9234
	FCGR + TAC	0.8508	0.8738	0.8282	0.7028	0.9195
	FCGR + DACC	0.8462	0.8703	0.8225	0.6938	0.917
	FCGR + TACC	0.8417	0.8676	0.8163	0.6848	0.9162
	FCGR + PCPseDNC	0.8456	0.8808	0.811	0.6934	0.92
	FCGR + PCPseTNC	0.8493	0.8789	0.8202	0.7004	0.9178
	All features	0.8481	0.8695	0.8271	0.6973	0.9195
MLP	FCGR	0.8537	0.8613	0.8462	0.7092	0.9225
CNN	FCGR	0.8495	0.8839	0.8156	0.702	0.9181

The table shows the optimal results of each classifier, and the specific parameters are shown in the previous tables
Best values are in bold

ISSN: 1471-2105