Differentially penalized regression to predict agronomic traits from metabolites and markers in wheat

Abstract

Background: Genomic prediction of agronomic traits as targets for selection in plant breeding programmes is increasingly common. The methods employed can also be applied to predict traits from other sources of covariates, such as metabolomics. However, prediction combining sets of covariates can be less accurate than using the best of the individual sets.

Results: We describe a method, termed Differentially Penalized Regression (DiPR), which uses standard ridge regression software to combine sets of covariates while applying independent penalties to each. In a dataset of wheat varieties, field traits are better predicted, on average, by seed metabolites than by genetic markers, but DiPR using both sets of predictors is best.

Conclusion: DiPR is a simple and accessible method of using existing software to combine multiple sets of covariates in trait prediction when there are more predictors than observations and the contribution to accuracy from each set differs.