iIL13Pred: improved prediction of IL-13 inducing peptides using popular machine learning classifiers

BMC Bioinformatics

Table 6 Comparison of the proposed model on the baseline dataset and the enhanced dataset on the basis of performance metrics

Classifier	Number of features selected	Sensitivity		Specificity		Accuracy		AUCROC		MCC
Classifier	Number of features selected	iIL13 Pred	iIL13Pred with enhanced positive dataset	iIL13 Pred	iIL13Pred with enhanced positive dataset	iIL13 Pred	iIL13Pred with enhanced positive dataset	iIL13 Pred	iIL13Pred with enhanced positive dataset	iIL13 Pred	iIL13Pred with enhanced positive dataset
RF	95	74.6	76.19	79.21	79.89	78.76	79.53	0.84	0.86	0.36	0.38
XGB	10	74.6	76.19	75.77	77.66	75.66	77.51	0.83	0.82	0.33	0.35

Random forest used 95 features and eXtreme gradient boosting used 10 features selected using mRMR. The higher values are highlighted in bold

ISSN: 1471-2105