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

BMC Bioinformatics

Table 1 Performance metrics of seven machine learning models for prediction of IL-13 inducing peptides on the top 95 features via mRMR (iIL13Pred) and its comparison with the state of the art (IL13Pred)

Classifier	Dataset	Sensitivity		Specificity		Accuracy		AUCROC		MCC
Classifier	Dataset	Proposed study	Jain et al. [19]	Proposed study	Jain et al. [19]	Proposed study	Jain et al. [19]	Proposed study	Jain et al. [19]	Proposed study	Jain et al. [19]
DT	Training	70.80	65.96	76.09	66.38	75.57	66.34	0.76	0.70	0.31	0.19
	Validation	63.49	51.28	74.40	66.31	73.33	64.50	0.71	0.60	0.25	0.12
GNB	Training	67.12	63.83	80.13	79.58	78.88	78.14	0.81	0.78	0.33	0.29
	Validation	50.79	38.46	78.69	77.43	75.97	72.71	0.71	0.61	0.20	0.12
KNN	Training	66.00	57.02	69.91	65.61	69.53	64.83	0.73	0.64	0.23	0.14
	Validation	61.90	50.00	81.79	69.31	79.84	66.98	0.74	0.62	0.31	0.13
LR	Training	70.00	73.62	70.00	73.99	70.00	73.95	0.77	0.83	0.25	0.30
	Validation	61.90	58.97	73.37	68.25	72.25	67.13	0.71	0.68	0.23	0.19
SVC	Training	74.00	72.34	72.14	71.25	72.32	71.35	0.82	0.79	0.29	0.27
	Validation	68.25	51.28	71.31	68.08	71.00	66.05	0.80	0.62	0.25	0.13
RF	Training	77.60	82.13	76.78	79.88	76.86	80.09	0.85	0.88	0.36	0.41
	Validation	74.60	70.51	79.21	77.07	78.76	76.28	0.84	0.83	0.36	0.34
XGB	Training	77.27	73.62	72.27	76.59	72.76	76.32	0.83	0.84	0.31	0.32
	Validation	73.02	69.23	79.73	73.19	79.07	72.71	0.81	0.80	0.36	0.30

ISSN: 1471-2105