The genomic selection (GS) methodology proposed over 20 years ago by Meuwissen et al. (Genetics, 2001) has revolutionized plant breeding. A predictive methodology that trains statistical machine learning algorithms with phenotypic and genotypic data of a reference population and makes predictions for genotyped candidate lines, GS saves significant resources in the selection of candidate individuals. However, its practical implementation is still challenging when the plant breeder is interested in the prediction of future seasons or new locations and/or environments, which is called the “leave one environment out” issue. Furthermore, because the distributions of the training and testing set do not match, most statistical machine learning methods struggle to produce moderate or reasonable prediction accuracies. For this reason, the main objective of this study was to explore the use of the multi-trait partial least square (MT-PLS) regression methodology for this specific task, benchmarking its performance with the Bayesian Multi-trait Genomic Best Linear Unbiased Predictor (MT-GBLUP) method. The benchmarking process was performed with five actual data sets. We found that in all data sets the MT-PLS method outperformed the popular MT-GBLUP method by 349.8% (under predictor E + G), 484.4% (under predictor E + G + GE; where E denotes environments, G genotypes and GE the genotype by environment interaction) and 15.9% (under predictor G + GE) across traits. Our results provide empirical evidence of the power of the MT-PLS methodology for the prediction of future seasons or new environments. Furthermore, the comparison between single univariate-trait (UT) versus MT for GBLUP and PLS gave an increase in prediction accuracy of MT-GBLUP versus UT-GBLUP, but not for MT-PLS versus UT-PLS.
In plant breeding, the need to improve the prediction of future seasons or new locations and/or environments, also denoted as “leave one environment out,” is of paramount importance to increase the genetic gain in breeding programs and contribute to food and nutrition security worldwide. Genomic selection (GS) has the potential to increase the accuracy of future seasons or new locations because it is a predictive methodology. However, most statistical machine learning methods used for the task of predicting a new environment or season struggle to produce moderate or high prediction accuracies. For this reason, in this study we explore the use of the partial least squares (PLS) regression methodology for this specific task, and we benchmark its performance with the Bayesian Genomic Best Linear Unbiased Predictor (GBLUP) method. The benchmarking process was done with 14 real datasets. We found that in all datasets the PLS method outperformed the popular GBLUP method by margins between 0% (in the Indica data) and 228.28% (in the Disease data) across traits, environments, and types of predictors. Our results show great empirical evidence of the power of the PLS methodology for the prediction of future seasons or new environments.
It has not been fully understood in real fields what environment stimuli cause the genotype-by-environment (G E) interactions, when they occur, and what genes react to them. Large-scale multi-environment data sets are attractive data sources for these purposes because they potentially experienced various environmental conditions. Here we developed a data-driven approach termed Environmental Covariate Search Affecting Genetic Correlations (ECGC) to identify environmental stimuli and genes responsible for the G E interactions from large-scale multi-environment data sets. ECGC was applied to a soybean (Glycine max) data set that consisted of 25,158 records collected at 52 environments. ECGC illustrated what meteorological factors shaped the G E interactions in six traits including yield, flowering time, and protein content and when these factors were involved in the interactions. For example, it illustrated the relevance of precipitation around sowing dates and hours of sunshine just before maturity to the interactions observed for yield. Moreover, genome-wide association mapping on the sensitivities to the identified stimuli discovered candidate and known genes responsible for the G E interactions. Our results demonstrate the capability of data-driven approaches to bring novel insights on the G E interactions observed in fields.