Rethinking Nature's Pharmacy: AI Era and Natural Product Drug Discovery.

Area of Science:

• Pharmaceutical Science
• Computational Chemistry
• Drug Discovery

Background:

• Natural products (NPs) are crucial in drug discovery, accounting for ~50% of FDA-approved drugs.
• Traditional NP discovery is hampered by laborious isolation, biodiversity limits, and low screening hit rates, leading to long development times and high costs.

Purpose of the Study:

• To review advancements in AI applications for natural product drug discovery.
• To highlight AI's potential to overcome traditional challenges and accelerate therapeutic development.

Main Methods:

• Leveraging machine learning (ML), deep learning (DL), and generative AI (Gen. AI).
• Utilizing AI for virtual screening of chemical libraries and predicting molecular interactions.
• Employing AI for designing novel NP-inspired scaffolds.

Main Results:

• AI can potentially reduce NP drug discovery timelines by up to 70%.
• AI may increase success rates from <1% to over 10% compared to traditional methods.
• AI facilitates the development of innovative and eco-friendly therapeutics.

Conclusions:

• AI is a transformative force in revitalizing natural product drug discovery.
• Addressing challenges like data representation, model interpretability, and ethical bioprospecting is crucial for AI integration.