Do feature selection methods for selecting environmental covariables enhance genomic prediction accuracy?

Frontiers in Genetics

Genetics

Abelardo Montesinos-López¹  Roberto de la Rosa-Santamaria²  Osval A. Montesinos-López³  José Alejandro Ascencio-Laguna⁴  Afolabi Agbona⁵  Leonardo Crespo-Herrera⁶  Alison R. Bentley⁶  Carolina Saint Pierre⁶  Guillermo S. Gerard⁶  José Crossa⁷ 

[1] Centro Universitario de Ciencias Exactas e Ingenierías (CUCEI), Universidad de Guadalajara, Guadalajara, JA, Mexico;Colegio de Postgraduados, Campus Tabasco, Tabasco, Mexico;Facultad de Telemática, Universidad de Colima, Colima, Mexico;Instituto Mexicano del Transporte, Querétaro, Mexico;International Institute of Tropical Agriculture (IITA), Ibadan, Nigeria;Molecular & Environmental Plant Sciences, Texas A&M University, College Station, TX, United States;International Maize and Wheat Improvement Center (CIMMYT), El Battan, Mexico;International Maize and Wheat Improvement Center (CIMMYT), El Battan, Mexico;Colegio de Postgraduados, Campus Montecillos, Montecillos, Mexico;

关键词: genomic prediction;    feature selection;    environmental covariables;    genotype x environment interaction;    genomic selection;   

DOI  :  10.3389/fgene.2023.1209275

 received in 2023-04-20, accepted in 2023-07-03,  发布年份 2023

来源: Frontiers

【 摘 要 】

Genomic selection (GS) is transforming plant and animal breeding, but its practical implementation for complex traits and multi-environmental trials remains challenging. To address this issue, this study investigates the integration of environmental information with genotypic information in GS. The study proposes the use of two feature selection methods (Pearson’s correlation and Boruta) for the integration of environmental information. Results indicate that the simple incorporation of environmental covariates may increase or decrease prediction accuracy depending on the case. However, optimal incorporation of environmental covariates using feature selection significantly improves prediction accuracy in four out of six datasets between 14.25% and 218.71% under a leave one environment out cross validation scenario in terms of Normalized Root Mean Squared Error, but not relevant gain was observed in terms of Pearson´s correlation. In two datasets where environmental covariates are unrelated to the response variable, feature selection is unable to enhance prediction accuracy. Therefore, the study provides empirical evidence supporting the use of feature selection to improve the prediction power of GS.

【 授权许可】

Unknown   
Copyright © 2023 Montesinos-López, Crespo-Herrera, Saint Pierre, Bentley, de la Rosa-Santamaria, Ascencio-Laguna, Agbona, Gerard, Montesinos-López and Crossa.