Predicting plant trait dynamics from genetic markers

Molecular and physiological changes across crop developmental stages shape the plant phenome and render its prediction from genetic markers challenging. Here we present dynamicGP, an efficient computational approach that combines genomic prediction with dynamic mode decomposition to characterize the temporal changes and to predict genotype-specific dynamics for multiple morphometric, geometric and colourimetric traits scored by high-throughput phenotyping. Using genetic markers and data from high-throughput phenotyping of a maize multiparent advanced generation inter-cross population and an Arabidopsis thaliana diversity panel, we show that dynamicGP outperforms a baseline genomic prediction approach for the multiple traits. We demonstrate that the developmental dynamics of traits whose heritability varies less over time can be predicted with higher accuracy. The approach paves the way for interrogating and integrating the dynamical interactions between genotype and environment over plant development to improve the prediction accuracy of agronomically relevant traits. This study presents a computational approach that effectively uses time-resolved multi-trait data from a high-throughput phenotyping platform for the genomic prediction of morphometric, geometric and colourimetric traits of Arabidopsis and maize lines.