Genomic prediction has become central to human, animal and plant biology, enabling quantitative inference of how genetic variation shapes complex traits. Although these domains share statistical foundations, such as linear mixed models, Bayesian regression and deep-learning frameworks, they have advanced largely in parallel. Here we synthesize their methodological evolution and highlight opportunities for integration and deeper collaborations. Agricultural genetics contributed to the mixed-model and Bayesian frameworks underlying modern polygenic scores, while human genomics has driven advances in nonlinear modeling, federated learning and biology-informed artificial intelligence. We propose a roadmap centered on interoperable data standards, shared benchmarks and cross-disciplinary training to unify predictive genomics across species. Together, these efforts establish genomic prediction as a comparative science capable of explaining how genetic information drives form and function across the diversity of life. We emphasize that shared biological architectures and knowledge transfer across species can directly improve the robustness, interpretability and generalizability of predictive models.
Arirangan et al. (Wed,) studied this question.