Skip to main content

Table 12 Mean and standard deviation of the correlation coefficient of Pearson in 10-folds with 10 repetitions in the best subset found by GA with the same parameters used for the group 8 of the Table 11

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

Real Database

# SNPs

Kernel

  

Linear

RBF

PUK

Database without QC before GA

6,512

0.81 (0.08)

0.81(0.08)

0.81 (0.08)

Database without QC after GA

3,073

0.84(0.07)

0.67(0.14)

0.84(0.07)

Database with QC before GA

3,357

0.80(0.08)

0.75(0.08)

0.80(0.08)

Database with QC after GA

1,073

0.82(0.08)

0.44(0.25)

0.81(0.08)

  1. ** Mean and standard deviation of the Pearson correlation in 10-fold cross validation.
  2. The bold lines indicate the best model from the second selection for PUK.
  3. The parameters used by the GA were: population size = 20, number of generations = 20, crossover probability = 0.60, mutation probability = 0.033, seed = 1.