Systematic Review of Integrating Artificial Intelligence and Machine Learning in Predicting Drought-Tolerance-Associated Genes in Agricultural Crops

Amid the escalating global drought crisis driven by climate change—which directly threatens the sustainability of agricultural systems and food security—the development of crop varieties with high water-deficit tolerance and optimal water-use efficiency has become more critical than ever. This systematic review aimed to investigate and analyze how artificial intelligence (AI) and machine learning (ML) are integrated to accelerate plant breeding processes, with a particular focus on the accurate prediction of drought-tolerance-associated genes in agricultural crops. The research adopted a descriptive-analytical approach involving a systematic review of scientific literature and state-of-the-art computational frameworks. The results revealed that AI and ML—particularly through deep learning algorithms—exhibit unparalleled capability in managing and analyzing multi-omics big data (genomics, transcriptomics, and phenomics), enabling the discovery of gene regulatory networks (GRNs) and hub genes that were previously undetectable using conventional methods. This convergence ultimately enhances the precision of breeding value prediction and optimizes targeting in precise genetic engineering (e.g., CRISPR/Cas۹). Consequently, integrating AI with genomics transforms the development of resilient and adaptable crop varieties from a time-consuming, trial-and-error process into a rapid, accurate, and data-driven engineering paradigm—one that is essential for ensuring agricultural sustainability in a future marked by increasing environmental stresses.

کلیدواژه ها:

Drought tolerance ، Artificial intelligence (AI) ، Machine learning (ML) ، Genome-wide studies ، Smart plant breeding