Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle

Autor(es)

Mota, Lucio F. M. ; Arikawa, Leonardo M. ; Santos, Samuel W. B. ; Fernandes, Gerardo A. ; Alves, Anderson A. C. ; Rosa, Guilherme J. M. ; Mercadante, Maria E. Z. ; Cyrillo, Joslaine N. S. G. ; Carvalheiro, Roberto ; Albuquerque, Lucia G.

• Tipo de documento: Artigo Científico
• Fonte: SCIENTIFIC REPORTS; v. 14, n. 1, p. 14-pg., 2024-03-17.

Resumo

Genomic selection (GS) offers a promising opportunity for selecting more efficient animals to use consumed energy for maintenance and growth functions, impacting profitability and environmental sustainability. Here, we compared the prediction accuracy of multi-layer neural network (MLNN) and support vector regression (SVR) against single-trait (STGBLUP), multi-trait genomic best linear unbiased prediction (MTGBLUP), and Bayesian regression (BayesA, BayesB, BayesC, BRR, and BLasso) for feed efficiency (FE) traits. FE-related traits were measured in 1156 Nellore cattle from an experimental breeding program genotyped for similar to 300 K markers after quality control. Prediction accuracy (Acc) was evaluated using a forward validation splitting the dataset based on birth year, considering the phenotypes adjusted for the fixed effects and covariates as pseudo-phenotypes. The MLNN and SVR approaches were trained by randomly splitting the training population into fivefold to select the best hyperparameters. The results show that the machine learning methods (MLNN and SVR) and MTGBLUP outperformed STGBLUP and the Bayesian regression approaches, increasing the Acc by approximately 8.9%, 14.6%, and 13.7% using MLNN, SVR, and MTGBLUP, respectively. Acc for SVR and MTGBLUP were slightly different, ranging from 0.62 to 0.69 and 0.62 to 0.68, respectively, with empirically unbiased for both models (0.97 and 1.09). Our results indicated that SVR and MTGBLUBP approaches were more accurate in predicting FE-related traits than Bayesian regression and STGBLUP and seemed competitive for GS of complex phenotypes with various degrees of inheritance. (AU)

• Processo FAPESP: 09/16118-5 - Ferramentas genômicas no melhoramento genético de características de importância econômica direta em bovinos da raça Nelore
• Beneficiário: Lucia Galvão de Albuquerque
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/10630-2 - Aspectos genéticos da qualidade, eficiência e sustentabilidade da produção de carne em animais da raça Nelore
• Beneficiário: Lucia Galvão de Albuquerque
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 18/20026-8 - EMU concedido no processo 2017/10630-2: servidor
• Beneficiário: Lucia Galvão de Albuquerque
• Modalidade de apoio: Auxílio à Pesquisa - Programa Equipamentos Multiusuários
• Processo FAPESP: 16/24228-9 - Estudo de associação genômica ampla para características de eficiência alimentar em programas de melhoramento de bovinos da raça Nelore
• Beneficiário: Samuel Wallace Boer dos Santos
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 17/13411-0 - Avaliação dos benefícios em combinar duas populações Nelore para a seleção genômica
• Beneficiário: Samuel Wallace Boer dos Santos
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Mestrado