Mathematical modeling for genomic selection in Serbian dairy cattle

This manuscript has come as a result of an efficient breeding program in Serbian cattle populations for some economically important traits. Genomic selection the last two decades been main challenge animal programs and genetics. Many SNP markers are used statistical analysis predicting accuracy values young animals without their performance. The new tendency allows genetic progress with reducing cost. In this study, 92 Holstein cows from various regions Serbia were analyzed based on molecular markers. Within investigation, empirical model was developed prediction Yield Traits Fertility variables, according to Key traits data dairy cattle. gave reasonable fit successfully predicted (such Fat Protein Percent, Cheese Merit, Fluid Cow Livability) variables Sire Calving Ease, Heifer Conception Rate, Daughter Stillbirth, Gestation Length). A total build variables. artificial neural network model, Broyden- Fletcher-Goldfarb-Shanno iterative algorithm, showed good capabilities (the r2 during training cycle before mentioned output range between 0.444 0.989).