Skip to main content

Table 1 Comparison of prediction performances between conventional single-step (SS-GBLUP) and single-step NNMM (SS-NN-GBLUP)

From: Interpreting single-step genomic evaluation as a neural network of three layers: pedigree, genotypes, and phenotypes

Method

% non-genotyped individuals

30%

50%

70%

90%

SS-GBLUP

0.808 (0.005)

0.757 (0.007)

0.694 (0.013)

0.558 (0.015)

SS-NN-GBLUP

0.810 (0.006)

0.754 (0.007)

0.691 (0.013)

0.559 (0.014)

  1. The average prediction accuracies from 10 replications with the standard deviation in brackets
Back to article page

Genetics Selection Evolution

ISSN: 1297-9686