Genomic selection(GS) as a promising molecular breeding strategy has been widely implemented and evaluated for plant breeding, because it has remarkable superiority in enhancing genetic gain, reducing breeding time an...Genomic selection(GS) as a promising molecular breeding strategy has been widely implemented and evaluated for plant breeding, because it has remarkable superiority in enhancing genetic gain, reducing breeding time and expenditure, and accelerating the breeding process. In this study the factors affecting prediction accuracy(rMG) in GS were evaluated systematically, using six agronomic traits(plant height, ear height, ear length, ear diameter,grain yield per plant and hundred-kernel weight) evaluated in one natural and two biparental populations. The factors examined included marker density, population size, heritability,statistical model, population relationships and the ratio of population size between the training and testing sets, the last being revealed by resampling individuals in different proportions from a population. Prediction accuracy continuously increased as marker density and population size increased and was positively correlated with heritability; rMGshowed a slight gain when the training set increased to three times as large as the testing set. Low predictive performance between unrelated populations could be attributed to different allele frequencies, and predictive ability and prediction accuracy could be improved by including more related lines in the training population. Among the seven statistical models examined, including ridge regression best linear unbiased prediction(RR-BLUP), genomic BLUP(GBLUP), Bayes A, Bayes B, Bayes C, Bayesian least absolute shrinkage and selection operator(Bayesian LASSO), and reproducing kernel Hilbert space(RKHS), the RKHS and additive-dominance model(Add + Dom model) showed credible ability for capturing non-additive effects, particularly for complex traits with low heritability. Empirical evidence generated in this study for GS-relevant factors will help plant breeders to develop GS-assisted breeding strategies for more efficient development of varieties.展开更多
基金supported by the National Basic Research Program of China(2014 CB138206)National Key Research and Development Program of China(2016YFD0101803)+3 种基金the National Natural Science Foundation of China-CGIAR International Collaborative Program(31361140364)the Agricultural Science and Technology Innovation Program(ASTIP)of CAASFundamental Research Funds for Central Non-Profit of Institute of Crop Sciences,CAAS(1610092016124)supported by the Bill and Melinda Gates Foundation and the CGIAR Research Program MAIZE
文摘Genomic selection(GS) as a promising molecular breeding strategy has been widely implemented and evaluated for plant breeding, because it has remarkable superiority in enhancing genetic gain, reducing breeding time and expenditure, and accelerating the breeding process. In this study the factors affecting prediction accuracy(rMG) in GS were evaluated systematically, using six agronomic traits(plant height, ear height, ear length, ear diameter,grain yield per plant and hundred-kernel weight) evaluated in one natural and two biparental populations. The factors examined included marker density, population size, heritability,statistical model, population relationships and the ratio of population size between the training and testing sets, the last being revealed by resampling individuals in different proportions from a population. Prediction accuracy continuously increased as marker density and population size increased and was positively correlated with heritability; rMGshowed a slight gain when the training set increased to three times as large as the testing set. Low predictive performance between unrelated populations could be attributed to different allele frequencies, and predictive ability and prediction accuracy could be improved by including more related lines in the training population. Among the seven statistical models examined, including ridge regression best linear unbiased prediction(RR-BLUP), genomic BLUP(GBLUP), Bayes A, Bayes B, Bayes C, Bayesian least absolute shrinkage and selection operator(Bayesian LASSO), and reproducing kernel Hilbert space(RKHS), the RKHS and additive-dominance model(Add + Dom model) showed credible ability for capturing non-additive effects, particularly for complex traits with low heritability. Empirical evidence generated in this study for GS-relevant factors will help plant breeders to develop GS-assisted breeding strategies for more efficient development of varieties.
