# Comparative analysis of genomic prediction approaches for multiple time-resolved traits in maize

## TL;DR

This paper compares different genomic prediction methods for predicting multiple traits over time in maize, finding that MegaLMM performs better in some cases, while dynamicGP can forecast traits beyond training data.

## Contribution

The study introduces hybrid genomic prediction models and evaluates their ability to handle time-resolved traits in maize.

## Key findings

- MegaLMM outperforms dynamicGP in snapshot and longitudinal Pearson correlation over time.
- dynamicGP is the only method capable of forecasting traits beyond training time points.
- Trait developmental trajectories influence predictive performance.

## Abstract

Ability to accurately predict multiple growth-related traits over plant developmental trajectories has the potential to revolutionize crop breeding and precision agriculture. Despite increased availability of time-resolved data for multiple traits from high-throughput phenotyping platforms of model plants and crops, genomic prediction is largely applied independently to a small number of traits, often neglecting their dynamics. Here, we compared and contrasted the performance of MegaLMM and dynamicGP as well as hybrid variants, using MegaLMM in place of RR-BLUP for component matrix prediction, which can handle high-dimensional temporal data for multi-trait genomic prediction. The comparative analysis made use of time series for 50 geometric, color, and texture traits in a maize multi-parent advanced generation inter-cross (MAGIC) population. The performance of the approaches was assessed using snapshot and longitudinal accuracy, quantified as the Pearson correlation (PCC) and mean squared error (MSE), thereby providing insight into the ability to predict multiple traits at a single time point or the dynamics of individual traits over the considered time domain, respectively. We found that MegaLMM outperforms dynamicGP in terms of both snapshot and longitudinal PCC over an observed time interval, but not in terms of snapshot MSE. We also analyzed the characteristics of trait developmental trajectories associated with predictive performance. This study goes further to demonstrate that dynamicGP is the only time-dependent genomic prediction approach which can forecast multiple traits beyond the set of training time points and paves the way for careful investigation of factors that affect the capacity to predict dynamics of multiple traits from genetic markers alone.

The online version contains supplementary material available at 10.1007/s00122-026-05162-4.