Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle
Abstract 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) an...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-57234-4 |
| _version_ | 1827316100222681088 |
|---|---|
| author | Lucio F. M. Mota Leonardo M. Arikawa Samuel W. B. Santos Gerardo A. Fernandes Júnior Anderson A. C. Alves Guilherme J. M. Rosa Maria E. Z. Mercadante Joslaine N. S. G. Cyrillo Roberto Carvalheiro Lucia G. Albuquerque |
| author_facet | Lucio F. M. Mota Leonardo M. Arikawa Samuel W. B. Santos Gerardo A. Fernandes Júnior Anderson A. C. Alves Guilherme J. M. Rosa Maria E. Z. Mercadante Joslaine N. S. G. Cyrillo Roberto Carvalheiro Lucia G. Albuquerque |
| author_sort | Lucio F. M. Mota |
| collection | DOAJ |
| description | Abstract 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 ~ 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. |
| first_indexed | 2024-04-24T23:07:47Z |
| format | Article |
| id | doaj.art-255f0e2883864d93bf7da31b71847a9a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T23:07:47Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-255f0e2883864d93bf7da31b71847a9a2024-03-17T12:20:48ZengNature PortfolioScientific Reports2045-23222024-03-0114111410.1038/s41598-024-57234-4Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattleLucio F. M. Mota0Leonardo M. Arikawa1Samuel W. B. Santos2Gerardo A. Fernandes Júnior3Anderson A. C. Alves4Guilherme J. M. Rosa5Maria E. Z. Mercadante6Joslaine N. S. G. Cyrillo7Roberto Carvalheiro8Lucia G. Albuquerque9School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)Department of Animal and Dairy Sciences, University of WisconsinInstitute of Animal Science, Beef Cattle Research CenterInstitute of Animal Science, Beef Cattle Research CenterSchool of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)School of Agricultural and Veterinarian Sciences, São Paulo State University (UNESP)Abstract 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 ~ 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.https://doi.org/10.1038/s41598-024-57234-4 |
| spellingShingle | Lucio F. M. Mota Leonardo M. Arikawa Samuel W. B. Santos Gerardo A. Fernandes Júnior Anderson A. C. Alves Guilherme J. M. Rosa Maria E. Z. Mercadante Joslaine N. S. G. Cyrillo Roberto Carvalheiro Lucia G. Albuquerque Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle Scientific Reports |
| title | Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle |
| title_full | Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle |
| title_fullStr | Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle |
| title_full_unstemmed | Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle |
| title_short | Benchmarking machine learning and parametric methods for genomic prediction of feed efficiency-related traits in Nellore cattle |
| title_sort | benchmarking machine learning and parametric methods for genomic prediction of feed efficiency related traits in nellore cattle |
| url | https://doi.org/10.1038/s41598-024-57234-4 |
| work_keys_str_mv | AT luciofmmota benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT leonardomarikawa benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT samuelwbsantos benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT gerardoafernandesjunior benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT andersonacalves benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT guilhermejmrosa benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT mariaezmercadante benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT joslainensgcyrillo benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT robertocarvalheiro benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle AT luciagalbuquerque benchmarkingmachinelearningandparametricmethodsforgenomicpredictionoffeedefficiencyrelatedtraitsinnellorecattle |