Integrating Artificial Intelligence Into Drug Discovery From Medicinal Plants: Current Applications and...

Area of Science:

• Phytochemistry
• Computational Chemistry
• Drug Discovery

Background:

• Medicinal plants offer diverse bioactive compounds for drug discovery.
• Significant bottlenecks hinder the translation of plant-derived metabolites into clinical drugs, including extract complexity and data challenges.

Purpose of the Study:

• To present a framework for integrating artificial intelligence (AI) into medicinal plant-based drug discovery (MPDD).
• To address specific challenges in phytomedicine research using AI tools.

Main Methods:

• AI applications are mapped across the MPDD pipeline: identification, extraction, metabolite analysis, ADMET prediction, virtual screening, network pharmacology, and de novo design.
• Emphasis on preparing phytochemical datasets for AI through harmonization, balancing, and structured data engineering.
• Exploration of advanced AI models like GNNs, GAI, and multi-omics network pharmacology.

Main Results:

• AI integration can tackle key bottlenecks in MPDD, from plant identification to drug design.
• Phytochemical dataset readiness is crucial for effective AI implementation.
• Emerging AI approaches show promise for accelerating the discovery of plant-derived therapeutics.

Conclusions:

• AI offers a transformative approach to medicinal plant drug discovery.
• Standardized, reproducible, and biologically grounded AI integration is essential for next-generation botanical drug development.
• Further research and infrastructural reform are needed to fully realize AI's potential in this field.