Frontiers in genetics · 2026
Beyond QTL and GWAS: how deep learning, graph models, and multi-omics are reshaping plant genomic prediction analysis.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Tong, Tong Ran, Yuan Zheng, Li Yue
Аннотация
BACKGROUND: Traditional genetic mapping has advanced plant trait studies but struggles to capture epistasis, pleiotropy, and genotype-environment (G × E) interactions in genomic prediction (GP). Recently, artificial intelligence (AI) has provided innovative methods.
MAIN BODY: This review outlines the transition from traditional frameworks to AI-enabled approaches for plant trait analysis. Specifically, major statistical and AI methods are summarized; current strategies for combining genomic, transcriptomic, metabolomic, phenotypic, and environmental data are described; and examinations are carried out over how graph-based and Transformer models represent regulatory networks and higher-order interactions. This paper further explores developments in multi-task learning, cross-population and cross-species transfer, and emerging foundation-style models. Key issues related to interpretability, reproducibility, data quality, and evaluation practices are considered in the context of practical deployment.
CONCLUSION: AI-driven models are reshaping plant trait analysis by extending traditional association methods toward scalable, biologically informed prediction. Continued efforts in data standardization, transparent models, and validation across time and environments will determine the broader impact of these approaches in crop improvement.
MAIN BODY: This review outlines the transition from traditional frameworks to AI-enabled approaches for plant trait analysis. Specifically, major statistical and AI methods are summarized; current strategies for combining genomic, transcriptomic, metabolomic, phenotypic, and environmental data are described; and examinations are carried out over how graph-based and Transformer models represent regulatory networks and higher-order interactions. This paper further explores developments in multi-task learning, cross-population and cross-species transfer, and emerging foundation-style models. Key issues related to interpretability, reproducibility, data quality, and evaluation practices are considered in the context of practical deployment.
CONCLUSION: AI-driven models are reshaping plant trait analysis by extending traditional association methods toward scalable, biologically informed prediction. Continued efforts in data standardization, transparent models, and validation across time and environments will determine the broader impact of these approaches in crop improvement.