Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization
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 pla...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/11/11/1647 |
| _version_ | 1797465833334636544 |
|---|---|
| author | Mang Liang Bingxing An Keanning Li Lili Du Tianyu Deng Sheng Cao Yueying Du Lingyang Xu Xue Gao Lupei Zhang Junya Li Huijiang Gao |
| author_facet | Mang Liang Bingxing An Keanning Li Lili Du Tianyu Deng Sheng Cao Yueying Du Lingyang Xu Xue Gao Lupei Zhang Junya Li Huijiang Gao |
| author_sort | Mang Liang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T18:28:11Z |
| format | Article |
| id | doaj.art-41e07fee139348bdae5abb1f9ab9497f |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-09T18:28:11Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-41e07fee139348bdae5abb1f9ab9497f2023-11-24T07:45:00ZengMDPI AGBiology2079-77372022-11-011111164710.3390/biology11111647Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters OptimizationMang Liang0Bingxing An1Keanning Li2Lili Du3Tianyu Deng4Sheng Cao5Yueying Du6Lingyang Xu7Xue Gao8Lupei Zhang9Junya Li10Huijiang Gao11Institute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaInstitute of Animal Sciences, Chinese Academy of Agricultural Sciences, Beijing 100193, ChinaDepending 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.https://www.mdpi.com/2079-7737/11/11/1647hyperparameters optimizationtree-structured Parzen estimatorgenomic predictionmachine learning |
| spellingShingle | Mang Liang Bingxing An Keanning Li Lili Du Tianyu Deng Sheng Cao Yueying Du Lingyang Xu Xue Gao Lupei Zhang Junya Li Huijiang Gao Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization Biology hyperparameters optimization tree-structured Parzen estimator genomic prediction machine learning |
| title | Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization |
| title_full | Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization |
| title_fullStr | Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization |
| title_full_unstemmed | Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization |
| title_short | Improving Genomic Prediction with Machine Learning Incorporating TPE for Hyperparameters Optimization |
| title_sort | improving genomic prediction with machine learning incorporating tpe for hyperparameters optimization |
| topic | hyperparameters optimization tree-structured Parzen estimator genomic prediction machine learning |
| url | https://www.mdpi.com/2079-7737/11/11/1647 |
| work_keys_str_mv | AT mangliang improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT bingxingan improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT keanningli improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT lilidu improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT tianyudeng improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT shengcao improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT yueyingdu improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT lingyangxu improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT xuegao improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT lupeizhang improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT junyali improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization AT huijianggao improvinggenomicpredictionwithmachinelearningincorporatingtpeforhyperparametersoptimization |