Key points are not available for this paper at this time.
Plant phytohormone networks control growth, dormancy, and stress responses throughout plants’ long lifespans and heterogeneous tissues. While multi-omics approaches have advanced the understanding of these regulatory systems, their application remains constrained by low spatial resolution, static sampling strategies, and limited capacity to capture nonlinear, context-dependent interactions. These limitations are especially evident in forest tree species, where hormone gradients change dynamically across developmental stages, seasons, and environmental conditions. The emergence of Artificial Intelligence (AI), including its subsets deep learning (DL) and machine learning (ML), provides valuable solutions to overcome these barriers. These solutions involve integrating high-dimensional data, reconstructing spatiotemporal hormone architectures, and developing predictive network models that regulate stress resilience and growth. This review highlights recent research on integrative omics in forest hormone biology and discusses how AI technologies overcome the barriers in traditional multi-omics approaches. Additionally, it outlines future directions for developing translational tools to support sustainable forestry production and management.
Zhang et al. (Thu,) studied this question.