Abstract
Peanut, as an important oil crop, has its oil content and quality directly determining its economic value and industrial application potential. With the rapid development of molecular biology and synthetic biology, researchers have gained a deeper understanding of the complex regulatory mechanisms underlying peanut oil metabolism. However, traditional research methods face limitations in deciphering and optimizing these intricate processes due to the multilayered gene networks and dynamic multifactorial regulation involved in lipid metabolism. The rapid rise of artificial intelligence (AI) technologies has provided novel perspectives and technical tools for this field. Through AI-driven gene network modeling and metabolic pathway analysis, researchers can accurately identify metabolic bottlenecks and key gene regulatory nodes, integrating large-scale and multidimensional experimental data for comprehensive analysis. These technologies not only significantly enhance the efficiency of gene editing target selection but also improve the scientific rigor and feasibility of metabolic pathway optimization. Moreover, AI-powered feedback optimization strategies further accelerate the iterative process of experimental validation and model refinement. This review comprehensively summarizes the current applications and recent advances of AI technologies in peanut oil metabolism research, systematically analyzing their practical implementations and potential challenges in gene selection, metabolic network optimization, and experimental validation. Additionally, future research directions are proposed to explore how AI can be fully leveraged to overcome bottlenecks in lipid metabolism optimization, providing theoretical support and technological solutions for peanut genetic improvement and efficient oil production.
