Skip to main content

Table 2 The performance of different machine learning methods using 3-fold cross-validation

From: Prediction of protein solvent accessibility using PSO-SVR with multiple sequence-derived features and weighted sliding window scheme

Method

PSAP2312

 

MAE (%)

PCC

wKNN1

14.9

0.63

GBR2

15.1

0.64

SVR

14.8

0.67

  1. 1weighted K-Nearest Neighbor, kernel = triangular, k = 19; 2Generalized Boosting Regression, distribution = Gaussian, n.trees = 1000, shrinkage = 0.05, interaction.depth = 3; best results are shown in bold.
Back to article page

BioData Mining

ISSN: 1756-0381