Genomic prediction using machine learning - a comparison of the performance of regularized regression, ensemble, instance-based and deep learning methods

Aug 5, 2026

Accurate prediction of genomic breeding values underpins genomic selection in plant and animal breeding, where thousands of whole-genome molecular markers create high-dimensional modeling challenges. This study compares supervised machine-learning method groups—regularized regression, deep learning, ensemble learning, and instance-based learning—using one simulated animal dataset and three empirical maize datasets from a commercial breeding program. Results show predictive performance and computational cost vary by data and target traits, and increased complexity does not always raise accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Abstract

Background

Results

Conclusions

Keywords

Background

Lourenço etal. BMC Genomics (2024) 25:152 [https://doi.org/10.1186/s12864-023-09933-x](https://doi.org/10.1186/s12864-023-09933-x) BMC Genomics RESEARCH Open Access Genomic prediction using machine learning: a comparison of the performance of regularized regression, ensemble, instance-based and deep learning methods on synthetic and empirical data Vanda M. Lourenço 1*, Joseph O. Ogutu2*, Rui A. P. Rodrigues 1, Alexandra Posekany3 and Hans‑Peter Piepho2 Abstract Background The accurate prediction of genomic breeding values is central to genomic selection in both plant and animal breeding studies. Genomic prediction involves the use of thousands of molecular markers spanning the entire genome and therefore requires methods able to efficiently handle high dimensional data. Not surpris‑ ingly, machine learning methods are becoming widely advocated for and used in genomic prediction studies. These methods encompass different groups of supervised and unsupervised learning methods. Although several studies have compared the predictive performances of individual methods, studies comparing the predictive performance of different groups of methods are rare. However, such studies are crucial for identifying (i) groups of methods with superior genomic predictive performance and assessing (ii) the merits and demerits of such groups of methods relative to each other and to the established classical methods. Here, we comparatively evaluate the genomic predic‑ tive performance and informally assess the computational cost of several groups of supervised machine learning methods, specifically, regularized regression methods, deep, ensemble and instance-based learning algorithms, using one simulated animal breeding dataset and three empirical maize breeding datasets obtained from a commercial breeding program. Results Our results show that the relative predictive performance and computational expense of the groups of machine learning methods depend upon both the data and target traits and that for classical regularized methods, increasing model complexity can incur huge computational costs but does not necessarily always improve predic‑ tive accuracy. Thus, despite their greater complexity and computational burden, neither the adaptive nor the group regularized methods clearly improved upon the results of their simple regularized counterparts. This rules out selec‑ tion of one procedure among machine learning methods for routine use in genomic prediction. The results also show that, because of their competitive predictive performance, computational efficiency, simplicity and therefore relatively few tuning parameters, the classical linear mixed model and regularized regression methods are likely to remain strong contenders for genomic prediction. *Correspondence: Vanda M. Lourenço[vmml@fct.unl.pt](vmml@fct.unl.pt)[ ](vmml@fct.unl.pt)Joseph O. Ogutu [jogutu2007@gmail.com](jogutu2007@gmail.com) Full list of author information is available at the end of the article © The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver ()[.

FAQs

What is the main goal of this genomic prediction study?

To evaluate and compare the predictive performance of different groups of supervised machine-learning methods for genomic breeding value prediction, and to assess their computational burden.

Which machine-learning method groups are compared?

Regularized regression methods, deep learning methods, ensemble learning methods, and instance-based learning algorithms.

What do the results indicate about model complexity and accuracy?

Higher model complexity can greatly increase computational costs without necessarily improving predictive accuracy, and more complex adaptive or grouped regularized methods may not outperform simpler regularized counterparts.

Aug 5, 2026

Upload by Emma Wilson