Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs
Abstract Background Recently, machine learning (ML) has become attractive in genomic prediction, but its superiority in genomic prediction over conventional (ss) GBLUP methods and the choice of optimal ML methods need to be investigated. Results In this study, 2566 Chinese Yorkshire pigs with reprod...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-05-01
|
Series: | Journal of Animal Science and Biotechnology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40104-022-00708-0 |
_version_ | 1811341224287666176 |
---|---|
author | Xue Wang Shaolei Shi Guijiang Wang Wenxue Luo Xia Wei Ao Qiu Fei Luo Xiangdong Ding |
author_facet | Xue Wang Shaolei Shi Guijiang Wang Wenxue Luo Xia Wei Ao Qiu Fei Luo Xiangdong Ding |
author_sort | Xue Wang |
collection | DOAJ |
description | Abstract Background Recently, machine learning (ML) has become attractive in genomic prediction, but its superiority in genomic prediction over conventional (ss) GBLUP methods and the choice of optimal ML methods need to be investigated. Results In this study, 2566 Chinese Yorkshire pigs with reproduction trait records were genotyped with the GenoBaits Porcine SNP 50 K and PorcineSNP50 panels. Four ML methods, including support vector regression (SVR), kernel ridge regression (KRR), random forest (RF) and Adaboost.R2 were implemented. Through 20 replicates of fivefold cross-validation (CV) and one prediction for younger individuals, the utility of ML methods in genomic prediction was explored. In CV, compared with genomic BLUP (GBLUP), single-step GBLUP (ssGBLUP) and the Bayesian method BayesHE, ML methods significantly outperformed these conventional methods. ML methods improved the genomic prediction accuracy of GBLUP, ssGBLUP, and BayesHE by 19.3%, 15.0% and 20.8%, respectively. In addition, ML methods yielded smaller mean squared error (MSE) and mean absolute error (MAE) in all scenarios. ssGBLUP yielded an improvement of 3.8% on average in accuracy compared to that of GBLUP, and the accuracy of BayesHE was close to that of GBLUP. In genomic prediction of younger individuals, RF and Adaboost.R2_KRR performed better than GBLUP and BayesHE, while ssGBLUP performed comparably with RF, and ssGBLUP yielded slightly higher accuracy and lower MSE than Adaboost.R2_KRR in the prediction of total number of piglets born, while for number of piglets born alive, Adaboost.R2_KRR performed significantly better than ssGBLUP. Among ML methods, Adaboost.R2_KRR consistently performed well in our study. Our findings also demonstrated that optimal hyperparameters are useful for ML methods. After tuning hyperparameters in CV and in predicting genomic outcomes of younger individuals, the average improvement was 14.3% and 21.8% over those using default hyperparameters, respectively. Conclusion Our findings demonstrated that ML methods had better overall prediction performance than conventional genomic selection methods, and could be new options for genomic prediction. Among ML methods, Adaboost.R2_KRR consistently performed well in our study, and tuning hyperparameters is necessary for ML methods. The optimal hyperparameters depend on the character of traits, datasets etc. |
first_indexed | 2024-04-13T18:54:21Z |
format | Article |
id | doaj.art-24973a2e33f047cba503200044a0a46e |
institution | Directory Open Access Journal |
issn | 2049-1891 |
language | English |
last_indexed | 2024-04-13T18:54:21Z |
publishDate | 2022-05-01 |
publisher | BMC |
record_format | Article |
series | Journal of Animal Science and Biotechnology |
spelling | doaj.art-24973a2e33f047cba503200044a0a46e2022-12-22T02:34:19ZengBMCJournal of Animal Science and Biotechnology2049-18912022-05-0113111210.1186/s40104-022-00708-0Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigsXue Wang0Shaolei Shi1Guijiang Wang2Wenxue Luo3Xia Wei4Ao Qiu5Fei Luo6Xiangdong Ding7Key Laboratory of Animal Genetics and Breeding of Ministry of Agriculture and Rural Affairs, National Engineering Laboratory of Animal Breeding, College of Animal Science and Technology, China Agricultural UniversityKey Laboratory of Animal Genetics and Breeding of Ministry of Agriculture and Rural Affairs, National Engineering Laboratory of Animal Breeding, College of Animal Science and Technology, China Agricultural UniversityHebei Province Animal Husbandry and Improved Breeds Work StationHebei Province Animal Husbandry and Improved Breeds Work StationZhangjiakou Dahao Heshan New Agricultural Development Co., LtdKey Laboratory of Animal Genetics and Breeding of Ministry of Agriculture and Rural Affairs, National Engineering Laboratory of Animal Breeding, College of Animal Science and Technology, China Agricultural UniversityHebei Province Animal Husbandry and Improved Breeds Work StationKey Laboratory of Animal Genetics and Breeding of Ministry of Agriculture and Rural Affairs, National Engineering Laboratory of Animal Breeding, College of Animal Science and Technology, China Agricultural UniversityAbstract Background Recently, machine learning (ML) has become attractive in genomic prediction, but its superiority in genomic prediction over conventional (ss) GBLUP methods and the choice of optimal ML methods need to be investigated. Results In this study, 2566 Chinese Yorkshire pigs with reproduction trait records were genotyped with the GenoBaits Porcine SNP 50 K and PorcineSNP50 panels. Four ML methods, including support vector regression (SVR), kernel ridge regression (KRR), random forest (RF) and Adaboost.R2 were implemented. Through 20 replicates of fivefold cross-validation (CV) and one prediction for younger individuals, the utility of ML methods in genomic prediction was explored. In CV, compared with genomic BLUP (GBLUP), single-step GBLUP (ssGBLUP) and the Bayesian method BayesHE, ML methods significantly outperformed these conventional methods. ML methods improved the genomic prediction accuracy of GBLUP, ssGBLUP, and BayesHE by 19.3%, 15.0% and 20.8%, respectively. In addition, ML methods yielded smaller mean squared error (MSE) and mean absolute error (MAE) in all scenarios. ssGBLUP yielded an improvement of 3.8% on average in accuracy compared to that of GBLUP, and the accuracy of BayesHE was close to that of GBLUP. In genomic prediction of younger individuals, RF and Adaboost.R2_KRR performed better than GBLUP and BayesHE, while ssGBLUP performed comparably with RF, and ssGBLUP yielded slightly higher accuracy and lower MSE than Adaboost.R2_KRR in the prediction of total number of piglets born, while for number of piglets born alive, Adaboost.R2_KRR performed significantly better than ssGBLUP. Among ML methods, Adaboost.R2_KRR consistently performed well in our study. Our findings also demonstrated that optimal hyperparameters are useful for ML methods. After tuning hyperparameters in CV and in predicting genomic outcomes of younger individuals, the average improvement was 14.3% and 21.8% over those using default hyperparameters, respectively. Conclusion Our findings demonstrated that ML methods had better overall prediction performance than conventional genomic selection methods, and could be new options for genomic prediction. Among ML methods, Adaboost.R2_KRR consistently performed well in our study, and tuning hyperparameters is necessary for ML methods. The optimal hyperparameters depend on the character of traits, datasets etc.https://doi.org/10.1186/s40104-022-00708-0Genomic predictionMachine learningPigPrediction accuracy |
spellingShingle | Xue Wang Shaolei Shi Guijiang Wang Wenxue Luo Xia Wei Ao Qiu Fei Luo Xiangdong Ding Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs Journal of Animal Science and Biotechnology Genomic prediction Machine learning Pig Prediction accuracy |
title | Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
title_full | Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
title_fullStr | Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
title_full_unstemmed | Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
title_short | Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
title_sort | using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs |
topic | Genomic prediction Machine learning Pig Prediction accuracy |
url | https://doi.org/10.1186/s40104-022-00708-0 |
work_keys_str_mv | AT xuewang usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT shaoleishi usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT guijiangwang usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT wenxueluo usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT xiawei usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT aoqiu usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT feiluo usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs AT xiangdongding usingmachinelearningtoimprovetheaccuracyofgenomicpredictionofreproductiontraitsinpigs |