AI-driven integration and optimization of medicinal plant multi-omics metabolic networks
Issued Date
2026-03-31
Resource Type
eISSN
1664462X
Scopus ID
2-s2.0-105038017382
Journal Title
Frontiers in Plant Science
Volume
17
Rights Holder(s)
SCOPUS
Bibliographic Citation
Frontiers in Plant Science Vol.17 (2026)
Suggested Citation
Chen J., Cai J., To Quyen Duong H., Bunsupa S., Han R., Tong X. AI-driven integration and optimization of medicinal plant multi-omics metabolic networks. Frontiers in Plant Science Vol.17 (2026). doi:10.3389/fpls.2026.1756809 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/116745
Title
AI-driven integration and optimization of medicinal plant multi-omics metabolic networks
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Natural products from medicinal plants are vital sources for medicines, but understanding their complex production pathways within the plant is challenging. This review explores how artificial intelligence (AI), defined here as a suite of computational techniques including Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), and network analysis—is transforming this field of research. We describe how AI technologies, particularly machine and deep learning, are used to integrate large, heterogeneous biological datasets, extract features and identify key components in the biosynthesis of valuable compounds, and model how these metabolic networks behave over time. The review demonstrates that AI technologies effectively integrate large biological datasets to model dynamic metabolic behaviors. Furthermore, AI facilitates the optimization of the entire production chain, from cultivation conditions to extraction parameters. Ultimately, these technologies are shifting the research paradigm from conventional methods to precise, data-driven approaches, accelerating the sustainable bioproduction of plant-based natural products.