Skip to main content

Table 3 Linear regression analysis using different combinations of predictors

From: SeqRate: sequence-based protein folding type classification and rates prediction

 

estCN

estLRO

estLRO+estCN

α + β Contents

All Predictors

Cor2Rate

0.64

0.66

0.69

0.67

0.72

RMSE

1.3

1.14

1.12

1.27

1.16

F-value

21.27

37.03

38.69

34.66

35.52

P-value

6.9e-05

1.1e-06

8.7e-07

6.5e-05

7.3e-06

  1. Results of linear regression analysis using R package [35] with different combinations of predictors, such as etsCN (estimated Contact number), estLRO (estimated Long range order), estLRO+estCN (using combination of predictors estCN and estLRO), α + β Contents (using combination of predictors α-helix content and β -sheet Content) and All Predictors (using all 4 predictors). Results can be shown as Cor2Rate (correlation between estimated rates and real rates using selected predictors), RMSE (Root mean square error for the regression), F-value and P-value.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us