Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization

文献类型： 外文期刊

第一作者： Liang, Mang

作者： Liang, Mang;An, Bingxing;Li, Keanning;Du, Lili;Deng, Tianyu;Cao, Sheng;Du, Yueying;Xu, Lingyang;Gao, Xue;Zhang, Lupei;Li, Junya;Gao, Huijiang

作者机构：

关键词： hyperparameters optimization; tree-structured Parzen estimator; genomic prediction; machine learning

期刊名称：BIOLOGY-BASEL （ 影响因子：5.168； ）

ISSN：

年卷期： 2022 年 11 卷 11 期

页码：

收录情况： SCI

摘要： Simple Summary Machine learning has been a crucial implement for genomic prediction. However, the complicated process of tuning hyperparameters tremendously hindered its application in actual breeding programs, especially for people without experience tuning hyperparameters. In this study, we applied a tree-structured Parzen estimator (TPE) to tune the hyperparameters of machine learning methods. Overall, incorporating kernel ridge regression (KRR) with TPE achieved the highest prediction accuracy in simulation and real datasets. Depending on excellent prediction ability, machine learning has been considered the most powerful implement to analyze high-throughput sequencing genome data. However, the sophisticated process of tuning hyperparameters tremendously impedes the wider application of machine learning in animal and plant breeding programs. Therefore, we integrated an automatic tuning hyperparameters algorithm, tree-structured Parzen estimator (TPE), with machine learning to simplify the process of using machine learning for genomic prediction. In this study, we applied TPE to optimize the hyperparameters of Kernel ridge regression (KRR) and support vector regression (SVR). To evaluate the performance of TPE, we compared the prediction accuracy of KRR-TPE and SVR-TPE with the genomic best linear unbiased prediction (GBLUP) and KRR-RS, KRR-Grid, SVR-RS, and SVR-Grid, which tuned the hyperparameters of KRR and SVR by using random search (RS) and grid search (Gird) in a simulation dataset and the real datasets. The results indicated that KRR-TPE achieved the most powerful prediction ability considering all populations and was the most convenient. Especially for the Chinese Simmental beef cattle and Loblolly pine populations, the prediction accuracy of KRR-TPE had an 8.73% and 6.08% average improvement compared with GBLUP, respectively. Our study will greatly promote the application of machine learning in GP and further accelerate breeding progress.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序