Use of supervised machine learning for prediction of genetic values based on two generations of ancestors
DOI:
https://doi.org/10.33448/rsd-v12i6.41904Keywords:
Artificial intelligence; Machine learning; Linear regression.Abstract
Efficient use of tools aimed at accelerating genetic improvement such as targeted mating requires genetic value information from both breeders and mothers, however, low accuracy or lack thereof can compromise genetic improvement programs, thus estimating genetic values of females is challenging. Methodologies that use only information from male ancestors to calculate genetic values of females have already been proposed, however, the emergence of supervised machine learning technologies have made relevant contributions to genetic improvement. Therefore, this study aims to evaluate a methodology based on a supervised linear regression algorithm in function of the consolidated method in literature, which can be employed in genetic improvement programs. The results of Pearson's correlation analysis were all significant (p<0.0001) between predicted values from both models and actual values, showing that both models can be used to estimate genetic values. However, by using the model based on machine learning it was possible to observe errors with smaller standard deviations for the characteristics of milk, fat, protein and productive life, and equal for the other characteristics analyzed, indicating that models using technologies derived from machine learning have promising applications in genetic improvement.
References
Bourdon, R. (2014). Understanding Animal Breeding. (2a ed.), Pearson. p. 560.
Faceli, K., Lorena, A. C., Gama, J. & Carvalho, A. C. P. L. F. (2011). Artificial intelligence: a machine learning approach. Ed. LTC.
Forabosco, F., Jakobsen, J., & Fikse, W. (2009). International genetic evaluation for direct longevity in dairy bulls. Journal of Dairy Science, 92(5), 2338–2347. https://doi.org/10.3168/jds.2008-1214.
Ghotbaldini, H., Mohammadabadi, M., Nezamabadi-pour, H., Babenko, O. I., Bushtruk, M. V., & Tkachenko, S. V. (2019). Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed. Acta Scientiarum. Animal Sciences, 41(1), 45282. https://doi.org/10.4025/actascianimsci.v41i1.45282.
Groen, A. F., & der Waaij, L. V. (1999). Some basics about mating schemes | Interbull Bulletin. https://journal.interbull.org/index.php/ib/article/view/562.
Hedrick, P. W. (1987). Gametic Disequilibrium Measures: Proceed With Caution. Genetics, 117(2), 331–341. https://doi.org/10.1093/genetics/117.2.331.
Jenko, J., Gorjanc, G., Kovač, M., & Ducrocq, V. (2013). Comparison between sire-maternal grandsire and animal models for genetic evaluation of longevity in a dairy cattle population with small herds. Journal of Dairy Science, 96(12), 8002–8013. https://doi.org/10.3168/jds.2013-6830.
Lewontin, R. C. (1988). On measures of gametic disequilibrium. Genetics, 120(3), 849–852. https://doi.org/10.1093/genetics/120.3.849.
Ma, L., Sonstegard, T. S., Cole, J. B., VanTassell, C. P., Wiggans, G. R., Crooker, B. A., Tan, C., Prakapenka, D., Liu, G., Da, Y. (2019). Genome changes due to artificial selection in U.S. Holstein cattle. BMC Genomics, 20(1). https://doi.org/10.1186/s12864-019-5459-x.
Molas, A. (2022). Why do we minimize the mean squared error? Acesso em dez 2022. Towards Data Science. https://towardsdatascience.com/why-do-we-minimize-the-mean-squared-error-3b97391f54c.
Monard, & Baranauskas. (2003). Conceitos sobre aprendizado de máquina. Sistemas Inteligentes Fundamentos e Aplicações. Manole Ltda.
Mrode. (2005). Linear models for the prediction of animal breeding values (3rd ed.). CABU.
Nayeri, S., Sargolzaei, M., & Tulpan, D. (2019). A review of traditional and machine learning methods applied to animal breeding. Animal Health Research Reviews, 20(1), 31–46. https://doi.org/10.1017/s1466252319000148.
Neves, H. H., Carvalheiro, R., Cardoso, V., Fries, L. A., & de Queiroz, S. A. (2009). Acasalamento dirigido para aumentar a produção de animais geneticamente superiores e reduzir a variabilidade da progênie em bovinos. Revista Brasileira de zootecnia, 38(7). https://doi.org/10.1590/S1516-35982009000700006.
Pour Hamidi, S., Mohammadabadi, M. R., Asadi Foozi, M., & Nezamabadi-pour, H. (2017). Prediction of breeding values for the milk production trait in Iranian Holstein cows applying artificial neural networks. Journal of Livestock Science and Technologies, 5(2), 53-61. 10.22103/jlst.2017.10043.1188.
Schenkel, F., & Schaeffer, L. (2008). Effects of nonrandom parental selection on estimation of variance components. Journal of Animal Breeding and Genetics, 117(4), 225–239. https://doi.org/10.1111/j.1439-0388.2000.00262.x
Silva, G. N., Tomaz, R. S., Sant’Anna, I. D. C., Nascimento, M., Bhering, L. L., & Cruz, C. D. (2014). Neural networks for predicting breeding values and genetic gains. Scientia Agricola, 71(6), 494–498. https://doi.org/10.1590/0103-9016-2014-0057.
sklearn.linear_model.LinearRegression. (2022). Acesso em dez 2022. https://scikit-learn/stable/modules/generated/sklearn.linear_model.LinearRegression.html.
Wellmann, R. (2019). Optimum contribution selection for animal breeding and conservation: the R package optiSel. BMC Bioinformatics, 20(1). https://doi.org/10.1186/s12859-018-2450-5.
White, D. J., Wolff, J. N., Pierson, M., & Gemmel, N. J. (2008). Revealing the hidden complexities of mtDNA inheritance. Molecular Ecology, 17(23), 4925–4942. https://doi.org/10.1111/j.1365-294x.2008.03982.x.
Wright, S. (1922). Coefficients of Inbreeding and Relationship. The American Naturalist, 56(645), 330–338. https://doi.org/10.1086/279872.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Fernando Jean Dijkinga
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
