Genetics Selection Evolution

Table 7 Performance comparison of deepGBLUP with the other genomic prediction methods on the simulated data across different heritabilities and multiple QTL effects

From: deepGBLUP: joint deep learning networks and GBLUP framework for accurate genomic prediction of complex traits in Korean native cattle

Heritability	Method	QTL effect
Heritability	Method	a + d	a + e	d + e	a + d + e
0.5	GBLUP	0.628 ± 0.009	0.614 ± 0.007	0.610 ± 0.007	0.610 ± 0.008
	DGBLUP	0.622 ± 0.009	0.609 ± 0.007	0.606 ± 0.007	0.606 ± 0.008
	EGBLUP	0.626 ± 0.01	0.612 ± 0.008	0.609 ± 0.007	0.610 ± 0.009
	BayesA	0.622 ± 0.01	0.608 ± 0.008	0.604 ± 0.007	0.606 ± 0.009
	BayesB	0.622 ± 0.009	0.607 ± 0.008	0.601 ± 0.006	0.603 ± 0.008
	BayesC	0.627 ± 0.009	0.608 ± 0.007	0.606 ± 0.007	0.607 ± 0.008
	deepGBLUP	0.636 ± 0.009	0.623 ± 0.006	0.618 ± 0.006	0.620 ± 0.007
0.3	GBLUP	0.579 ± 0.025	0.572 ± 0.026	0.557 ± 0.026	0.565 ± 0.025
	DGBLUP	0.578 ± 0.026	0.573 ± 0.027	0.559 ± 0.026	0.566 ± 0.025
	EGBLUP	0.579 ± 0.026	0.571 ± 0.026	0.558 ± 0.026	0.565 ± 0.025
	BayesA	0.563 ± 0.025	0.552 ± 0.027	0.542 ± 0.025	0.549 ± 0.024
	BayesB	0.574 ± 0.026	0.563 ± 0.026	0.553 ± 0.027	0.559 ± 0.025
	BayesC	0.574 ± 0.026	0.570 ± 0.027	0.553 ± 0.026	0.562 ± 0.025
	deepGBLUP	0.601 ± 0.026	0.593 ± 0.026	0.583 ± 0.026	0.585 ± 0.025
0.1	GBLUP	0.453 ± 0.024	0.441 ± 0.027	0.427 ± 0.022	0.438 ± 0.023
	DGBLUP	0.450 ± 0.024	0.438 ± 0.027	0.425 ± 0.022	0.435 ± 0.023
	EGBLUP	0.459 ± 0.024	0.446 ± 0.026	0.435 ± 0.022	0.444 ± 0.022
	BayesA	0.408 ± 0.028	0.390 ± 0.03	0.377 ± 0.028	0.399 ± 0.027
	BayesB	0.436 ± 0.024	0.435 ± 0.028	0.417 ± 0.023	0.433 ± 0.021
	BayesC	0.446 ± 0.026	0.439 ± 0.03	0.421 ± 0.025	0.431 ± 0.023
	deepGBLUP	0.528 ± 0.018	0.524 ± 0.026	0.513 ± 0.017	0.507 ± 0.018

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

Back to article page

ISSN: 1297-9686

Contact us

Submission enquiries: gse@inrae.fr
General enquiries: info@biomedcentral.com