Prediction of Hanwoo Cattle Phenotypes from Genotypes Using Machine Learning Methods

Simple Summary Machine learning has been extensively used in analyzing big data and in conditions where the number of parameters is much bigger than the number of observations. Recently, there have been an increasing number of successful applications of machine learning in genomic prediction as this method makes weaker assumptions, is capable of dealing with the dimensionality problem, and can be more flexible for describing complex relationships. In this study, we evaluated the predictive ability of three machine learning methods, namely, random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM), when predicting the carcass traits of Hanwoo cattle. These machine learning algorithms were compared with the standard linear method (GBLUP). Our results revealed that XGB method had the best predictive correlation for carcass weight and marbling score. Meanwhile, the best predictive correlation for backfat thickness and eye muscle area was delivered by GBLUP. Moreover, in terms of mean squared error (MSE) of prediction, GBLUP delivered the lowest MSE value for all traits. Hanwoo was originally raised for draft purposes, but the increase in local demand for red meat turned that purpose into full-scale meat-type cattle rearing; it is now considered one of the most economically important species and a vital food source for Koreans. The application of genomic selection in Hanwoo breeding programs in recent years was expected to lead to higher genetic progress. However, better statistical methods that can improve the genomic prediction accuracy are required. Hence, this study aimed to compare the predictive performance of three machine learning methods, namely, random forest (RF), extreme gradient boosting method (XGB), and support vector machine (SVM), when predicting the carcass weight (CWT), marbling score (MS), backfat thickness (BFT) and eye muscle area (EMA). Phenotypic and genotypic data (53,866 SNPs) from 7324 commercial Hanwoo cattle that were slaughtered at the age of around 30 months were used. The results showed that the boosting method XGB showed the highest predictive correlation for CWT and MS, followed by GBLUP, SVM, and RF. Meanwhile, the best predictive correlation for BFT and EMA was delivered by GBLUP, followed by SVM, RF, and XGB. Although XGB presented the highest predictive correlations for some traits, we did not find an advantage of XGB or any machine learning methods over GBLUP according to the mean squared error of prediction. Thus, we still recommend the use of GBLUP in the prediction of genomic breeding values for carcass traits in Hanwoo cattle.

Automated summary

This study evaluated the predictive performance of three machine learning methods in predicting carcass traits of Hanwoo cattle. The results showed that XGB and GBLUP had the best predictive correlations for different traits, suggesting that GBLUP is still recommended for predicting genomic breeding values in Hanwoo cattle.