Table 2.

Comparison of precision, recall and computational complexity of the models.

Sr. No.	Method	Precision (%)	Recall (%)	Computational Complexity	References
1.	DAP	85.5	83.57	H	[1]
2.	GA SIWR	91.2	89.14	M	[2]
3.	FP Tree	88.35	86.36	M
4.	FP SVM	85.5	83.57	H
5.	i6m	86.36	84.41	H	[5]
6.	EdeepVPP	94.24	92.11	VH	[55]
7.	Vira Miner	87.69	85.71	H	-
8.	Vira Seeker	87.21	85.24	H
9.	Deep Vira Finder	88.35	86.36	H
10.	RF	92.15	90.07	H	[15]
11.	GBM	91.2	89.14	VH
12.	PLS	90.25	88.21	H
13.	VFM	92.15	90.07	H	[56]
14.	BMTME	85.5	83.57	H	[57]
15.	MTR	86.45	84.5	H
16.	AKOM	86.64	84.69	H	[59]
17.	CMSPAM	85.03	83.11	H
18.	Spectrometry	89.3	87.29	H	[60]
19.	Random Selection	84.55	82.64	M
20.	MLP	86.45	84.5	H	[23]
21.	DNN	92.15	90.07	VH	[31]
22.	RF	87.02	85.06	H	[33]
23.	GCA & SCA	86.55	84.59	H	[26]
24.	GeneXNet	93.96	91.84	VH	[38]
25.	ResNet	91.68	89.61	VH
26.	DenseNet	90.54	88.49	VH
27.	RPLS	84.06	84.5	H	[39]
28.	RF-SVM	82.71	83.15	H
29.	IP	83.7	84.14	H	[41]
30.	GA ICA	81.27	81.7	H	[43]
31.	AUFL DT	82.89	83.33	H	[45]
32.	AUFL kNN	82.98	83.42	H
33.	CNV Bayesian	89.34	89.82	VH	[46]
34.	PSODT	87.21	87.67	H	[47]
35.	SVM	88.61	89.07	H	[48]
36.	DAE	88.73	89.2	VH
37.	RF	82.85	83.29	H
39.	BiLSTM CNN	89.96	90.43	VH	[63]
40.	PLS TTZ	83.39	83.83	H	[51]
41.	RIPPER SVM	89.73	90.2	VH	[54]