Table 3.
Performance comparison of deepGBLUP with the other genomic prediction methods on the Korean native cattle dataset across different traits and marker densities
| Density | Method | CWT | BF | EMA | MS |
|---|---|---|---|---|---|
| 50K | GBLUP | 0.729 ± 0.015 | 0.647 ± 0.009 | 0.726 ± 0.017 | 0.670 ± 0.014 |
| DGBLUP | 0.731 ± 0.016 | 0.639 ± 0.01 | 0.729 ± 0.017 | 0.668 ± 0.013 | |
| EGBLUP | 0.724 ± 0.016 | 0.641 ± 0.01 | 0.721 ± 0.019 | 0.664 ± 0.014 | |
| BayesA | 0.730 ± 0.015 | 0.658 ± 0.009 | 0.720 ± 0.016 | 0.667 ± 0.014 | |
| BayesB | 0.746 ± 0.015 | 0.667 ± 0.009 | 0.723 ± 0.019 | 0.670 ± 0.013 | |
| BayesC | 0.737 ± 0.015 | 0.662 ± 0.01 | 0.726 ± 0.018 | 0.668 ± 0.014 | |
| deepGBLUP | 0.752 ± 0.016 | 0.673 ± 0.009 | 0.746 ± 0.017 | 0.672 ± 0.012 | |
| 10K | GBLUP | 0.676 ± 0.015 | 0.577 ± 0.008 | 0.678 ± 0.018 | 0.613 ± 0.011 |
| DGBLUP | 0.675 ± 0.015 | 0.571 ± 0.009 | 0.678 ± 0.018 | 0.607 ± 0.01 | |
| EGBLUP | 0.684 ± 0.016 | 0.585 ± 0.009 | 0.684 ± 0.019 | 0.619 ± 0.012 | |
| BayesA | 0.700 ± 0.015 | 0.59 ± 0.008 | 0.682 ± 0.019 | 0.620 ± 0.011 | |
| BayesB | 0.695 ± 0.015 | 0.585 ± 0.007 | 0.675 ± 0.018 | 0.612 ± 0.012 | |
| BayesC | 0.689 ± 0.016 | 0.589 ± 0.008 | 0.681 ± 0.018 | 0.616 ± 0.012 | |
| deepGBLUP | 0.713 ± 0.017 | 0.612 ± 0.008 | 0.705 ± 0.018 | 0.626 ± 0.012 | |
| 5K | GBLUP | 0.638 ± 0.015 | 0.543 ± 0.01 | 0.631 ± 0.019 | 0.548 ± 0.011 |
| DGBLUP | 0.632 ± 0.016 | 0.533 ± 0.011 | 0.633 ± 0.019 | 0.544 ± 0.011 | |
| EGBLUP | 0.653 ± 0.016 | 0.556 ± 0.011 | 0.646 ± 0.02 | 0.564 ± 0.012 | |
| BayesA | 0.668 ± 0.016 | 0.557 ± 0.009 | 0.650 ± 0.019 | 0.568 ± 0.013 | |
| BayesB | 0.658 ± 0.016 | 0.543 ± 0.008 | 0.643 ± 0.018 | 0.562 ± 0.013 | |
| BayesC | 0.655 ± 0.017 | 0.555 ± 0.008 | 0.647 ± 0.019 | 0.567 ± 0.013 | |
| deepGBLUP | 0.681 ± 0.016 | 0.58 ± 0.01 | 0.672 ± 0.019 | 0.582 ± 0.011 | |
| 1K | GBLUP | 0.535 ± 0.017 | 0.429 ± 0.014 | 0.537 ± 0.021 | 0.424 ± 0.013 |
| DGBLUP | 0.519 ± 0.015 | 0.401 ± 0.012 | 0.529 ± 0.023 | 0.405 ± 0.014 | |
| EGBLUP | 0.552 ± 0.017 | 0.444 ± 0.014 | 0.555 ± 0.022 | 0.443 ± 0.014 | |
| BayesA | 0.568 ± 0.016 | 0.442 ± 0.014 | 0.557 ± 0.022 | 0.443 ± 0.014 | |
| BayesB | 0.564 ± 0.016 | 0.437 ± 0.012 | 0.556 ± 0.021 | 0.441 ± 0.013 | |
| BayesC | 0.551 ± 0.017 | 0.440 ± 0.013 | 0.552 ± 0.021 | 0.441 ± 0.014 | |
| deepGBLUP | 0.581 ± 0.016 | 0.467 ± 0.014 | 0.584 ± 0.022 | 0.466 ± 0.013 |
Each value in the cells are means and standard errors of the predictive abilities for 10-fold tests. We highlight the best results in italic