Skip to main content

Table 2 Parameter search details used for the construction of nine ML-based classifiers

From: TIPred: a novel stacked ensemble approach for the accelerated discovery of tyrosinase inhibitory peptides

Methoda

Parameters

Range of parameters

ADA

n_estimators

[20, 50, 100, 200, 500]

ET

n_estimators

[20, 50, 100, 200, 500]

LGBM

n_estimators

[20, 50, 100, 200, 500]

LR

Cost

[0.001, 0.01, 0.1, 1, 10, 100]

MLP

hidden_layer_sizes

[20, 50, 100, 200, 500]

RF

n_estimators

[20, 50, 100, 200, 500]

SVMLN

Cost

[20 to 25] in log2 steps

SVMRBF

Cost

[2−4 to 24] in log2 steps

XGB

n_estimators

[20, 50, 100, 200, 500]

  1. aADA: AdaBoost, DT: decision tree, ET: extremely randomized trees, KNN: k-nearest neighbor, LGBM: light gradient boosting machine, LR: logistic regression, MLP: multilayer perceptron, NB: naive Bayes, PLS: partial least squares, RF: random forest, SVMRBF: support vector machine with radial basis function, SVMLN: support vector machine with linear kernels, XGB: extreme gradient boosting
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us