---

ABSTRACT

GS consists of genotyping (markers) and phenotyping individuals in the reference (training) population and, with the help of statistical machine learning models, predicting the phenotypes or breeding values of the candidates for selection in the testing (evaluation) population that were only genotyped. Then, with the output of the trained model, predictions are performed for new candidate individuals not included in the training data set, but only if genotypic information is available for those candidate individuals. Selection of training and testing population is most critical step in genomic prediction, which in turn decides the accuracy of genomic selection. Most popularly used genomic selection models includes; stepwise regression, ridge regression, BLUP, RRBLUP, Bayes A, Bayes B, Bayes C, LASSO, RKHS, ANN, SVR, Random Forest tools etc. It is advised that one can choose the suitable statistical models based on the nature of the data.

Keywords: Genomic Selection, GEBV’s, BLUP, Training Population, Testing Population.

---

Genomic Selection in Plant Breeding.pdf