Skip to main content

Table 2 Results of k-NN, SVM, and PLS modelling using subsets of full kinase-inhibitor dataset

From: Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniques

Data analysis method:

k-NN

SVM

PLS

Size of the dataset:

P 2

P 2 kin

P 2

P 2 kin

P 2

P 2 kin

80%

0.65

0.64

0.73

0.70

0.67

0.65

60%

0.60

0.59

0.70

0.67

0.64

0.62

40%

0.52

0.51

0.65

0.62

0.58

0.56

20%

0.44

0.43

0. 56

0.53

0.49

0.47

10%

0.32

0.30

0.47

0.42

0.41

0.37

  1. For explanation of abbreviations see legend to Table 1.