Skip to main content

Table 11 Mean and standard deviation of the Pearson correlation for the SVR models constructed from subsets of SNPs selected by raw p-values of the real database with QC.

From: SNPs selection using support vector regression and genetic algorithms in GWAS

Group

SNP selection with raw p-values*

# SNPs

Linear**

RBF**

PUK**

1

< 10-9

12

0.67(0.10)

0.67(0.10)

0.67(0.10)

2

< 10-8

17

0.64(0.10)

0.67(0.10)

0.67(0.10)

3

< 10-7

43

0.59(0.12)

0.68(0.09)

0.70(0.08)

4

< 10-6

105

0.31(0.18)

0.72(0.07)

0.71(0.07)

5

< 10-5

242

0.67(0.09)

0.77(0.08)

0.78(0.07)

6

< 10-4

595

0.77(0.08)

0.69(0.09)

0.79(0.07)

7

< 10-3

1,397

0.78(0.08)

0.79(0.09)

0.79(0.08)

8

< 10 -2

3,357

0.80(0.08)

0.75(0.08)

0.80(0.08)

  1. *Raw p-values of the Spearman correlation (without Bonferroni correction).
  2. ** Mean and standard deviation of the Pearson correlation in 10-fold cross validation.
  3. The bold line indicates the best model from the first selection for PUK.