AI-Driven Exploration of Plant Specialized Metabolism: From Genes to Bioactive Natural Products

Plants produce an extraordinary diversity of natural products—such as alkaloids, terpenoids, flavonoids, and phenylpropanoids—that support ecological interactions and provide valuable resources for medicine, agriculture, and industry. However, traditional natural product discovery remains labor-intensive, low-throughput, and often biased toward known compounds. Meanwhile, much of the chemical diversity encoded in plant genomes is still uncharacterized due to complex biosynthetic pathways, low metabolite abundance, and limited functional annotation of biosynthetic genes. Artificial intelligence (AI) and machine learning (ML) are emerging as powerful tools to reveal this hidden metabolic landscape, enabling higher-throughput metabolite annotation, prediction of biosynthetic gene clusters, pathway reconstruction, and even design of improved biosynthetic routes.This Research Topic aims to advance the integration of AI-driven strategies into plant metabolism research, with the goal of accelerating natural product discovery and deepening our mechanistic understanding of metabolic networks. The initiative seeks to highlight pioneering work in applying machine learning and computational algorithms to annotate, predict, and engineer gene-to-metabolite relationships in plants.The scope of this Research Topic encompasses original research, methods, resources, and review articles that drive the AI-powered exploration of plant metabolism. We are particularly interested in contributions that leverage computational tools to bridge genomics, transcriptomics, metabolomics, and synthetic biology. Potential themes include, but are not limited to:• AI-guided discovery of plant natural products, biosynthetic genes and pathways• Machine learning for plant metabolite annotation and structural elucidation• Predictive modeling of plant metabolic regulation and responses to environmental stimuli• Generative and interpretable AI for plant metabolic engineering• Open-source tools, databases, and benchmark datasets available for the plant science community Topic editors: Jun Li, Wanshan Li, Prasat Kittakoop Source: https://www.frontiersin.org/research-topics/78755/ai-driven-exploration-of-plant-specialized-metabolism-from-genes-to-bioactive-natural-products