Deepstacked-AVPs: predicting antiviral peptides using tri-segment evolutionary profile and word embedding based multi-perspective features with deep stacking model

Table 1 Hyper parameters of classifiers learning model

Methods	Parameter	Optimal value
DNN	Activation function	ReLu, sigmoid
	Learning rate	0.01
	Number of hidden layer Neurons	64,32,16
	Optimizer	Adam
	Regularization L1	0.001
	Dense layers	3
	Dropout	0.25,0.5
RF	n_estimators	200
	Random_state	42
	Max features	Auto
	Max_depth	32
	Bootstrap	TRUE
	min_samples_leaf	4
	min_samples_split	10
XGB	n_estimators	200
	LEARNING rate	0.001
	Max depth	15
	reg_lambda	2
	Objective function	Binary-logistic
	Gamma	1
	Booster	Gbtree
	reg_alpha	1
ETC	Random_state	42
	n_estimators	150
	Criterion	Entropy
	Max_features	Sqrt

ISSN: 1471-2105