Artificial Intelligence-Assisted Discovery of Phytoconstituent: A New Era in Herbal Drug Development

Abstract

Herbal medicinal plants play an important role as a source of therapeutic agents due to the presence of bioactive phytoconstituents such as alkaloids, flavonoids, tannins, glycosides, and phenolic compounds. Traditional methods for discovering the phytoconstituents in herbal plants are time-consuming and require more experimental work. In recent years, AI (artificial intelligence) has been improving drug discovery and rapidly growing in the herbal industry. AI, integrated with powerful tools, can significantly accelerate the drug discovery process from herbal plants. AI techniques such as deep learning, machine learning, molecular docking, QSAR modelling and virtual screening, etc. AI can analyse the phytoconstituents datasets and predict the biological activity from plant-derived compounds. AI is identifying the potential of a drug and predicting the drug-protein interaction. AI can also detect the nature, such as primary or secondary metabolites. The integration of artificial intelligence into the discovery of phytoconstituents marks a transformative phase in the development of herbal medicines. AI predict the drug toxicity and safety before clinical trials. AI has a vast scope in the modern era. So, using AI with powerful tools in drug discovery and development is essential for future perspectives to make drug discovery easy and faster. There are some kinds of limitations and challenges of artificial intelligence

Keywords

Introduction

APPLICATIONS OF AI IN HERBAL DRUG DEVELOPMENT

• Identification of phytoconstituent (bioactive compound)
• Prediction of pharmacological activity
• Prediction of toxicity
• Analysis of plant database
• Prediction of drug-target interaction
• Analysis of herbal drug formulation
• study the therapeutic effect
• Identify the metabolites
• Analyse the medicinal data
• Virtual screening
• Molecular docking
• Data mining and protein engineering
• To know active phytoconstituents using various AI tools, etc.

CHALLENGES AND LIMITATIONS

• Limited phytochemical data- there are many medicinal plant phytoconstituent are not well documented in databases.
• Data quality issue – inconsistent or incomplete data can reduce the accuracy of the prediction
• Computational requirements- advanced AI tools require powerful software
• Need for experimental validation- after AI prediction, it will still require experimental validation
• Difficult to analyse- the plant contains many phytoconstituents, which make it difficult to identify and predict
• Difficulty with software handling – required trained person to handle the software and predict the data.

FUTURE PERSPECTIVES

• AI drug discovery- advanced AI helps to faster and more effective identification
• Safety and toxicity- AI predict the toxicity and safety before clinical testing.
• Analysis of phytoconstituent- AI helps to analyse the phytoconstituent in the herbal medicinal plant
• Detect the metabolite- AI Fastly detect the nature of the metabolite
• Predict the pharmacological activity- AI can predict the pharmacological action, depending on the chemical nature of the herbal drug medicine
• Research- AI bring automation in the research field
• Time- AI reduces the time of drug discovery research
• Acceptance- AI is rapidly growing in the modern era
• Therapeutic effect- AI can identify the therapeutic effect of a drug based on its biological activity
• Prediction- AI can predict the adverse effect using various AI tools

CONCLUSION

Artificial intelligence is the new era in drug development and drug discovery of phytoconstituents from plant-derived sources. AI helps to analyse the phytochemicals by using various tools. Such as molecular docking, QSAR modelling, virtual screening, and machine learning. Artificial intelligence predicts the toxicity and safety before clinical testing. All these AI tools are very helpful in the drug discovery of phytoconstituents. Artificial intelligence is one of the most valuable tools in modern pharmaceutical research, such as drug discovery and drug development. The integration of artificial intelligence with phytochemical research provides new opportunities for identifying novel plant-derived therapeutic agents. Some challenges and limitations of artificial intelligence, such as limited phytochemical data, difficulty with software handling, etc, but AI has great potential to accelerate herbal drug discovery and development. Therefore, the combination of artificial intelligence and herbal drug research play important role in the pharmaceutical industry for prospects.

REFERENCES

1. Jing Y, Bian Y, Hu Z, Wang L, Xie XQ. Deep learning for drug design: an artificial intelligence paradigm for drug discovery. Acta Pharm Sin B. 2021;11(3): 803-821.
2. Saldívar-González FI, Aldas-Bandera A, Gómez-García A, Medina-Franco JL. Natural product drug discovery in the artificial intelligence era. Chem Sci. 2022;13(6):1526-1546.
3. Vamathevan J, Clark D, Czodrowski P, et al. Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery. 2019;18(6):463–477.
4. Paul D, Sanap G, Shenoy S, Kalyane D, Kalia K, Tekade RK. Artificial intelligence in drug discovery and development. Drug Discov Today. 2021;26(1):80-93.
5. Schneider P, Walters WP, Plowright AT, et al. Rethinking drug design in the artificial intelligence era. Nature Reviews Drug Discovery. 2020;19:353–364.
6. Chen H, Engkvist O, Wang Y, Olivecrona M, Blaschke T. The rise of deep learning in drug discovery. Drug Discovery Today. 2018;23(6):1241–1250.
7. Rodrigues T, Reker D, Schneider P, Schneider G. Counting on natural products for drug design. Nature Chemistry. 2016;8:531–541.
8. Ekins S. The next era: Deep learning in pharmaceutical research. Pharmaceutical Research. 2016;33:2594–2603
9. Atanasov AG, Waltenberger B, Pferschy-Wenzig EM, et al. Discovery and resupply of pharmacologically active plant-derived natural products. Biotechnology Advances. 2015;33:1582–1614.
10. Jing Y, Bian Y, Hu Z, Wang L, Xie X. Deep learning for drug design: an artificial intelligence paradigm for drug discovery. Acta Pharmaceutica Sinica B. 2018;8(6):911–922.
11. Zhavoronkov A, Ivanenkov YA, Aliper A, et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nature Biotechnology. 2019;37:1038–1040.
12. Ekins S, Puhl AC, Zorn KM, et al. Exploiting machine learning for end-to-end drug discovery and development. Nature Materials. 2019;18:435–441.
13. Stokes JM, Yang K, Swanson K, et al. A deep learning approach to antibiotic discovery. Cell. 2020;180(4):688–702.
14. Mullowney MW, et al. Artificial intelligence for natural product drug discovery. Nat Rev Drug Discov. 2023;22:1-21.
15. Walters WP, Murcko MA. Assessing the impact of generative AI on medicinal chemistry. Nature Biotechnology. 2020;38:143–145.
16. Sliwoski G, Kothiwale S, Meiler J, Lowe EW. Computational methods in drug discovery. Pharmacological Reviews. 2014;66:334–395.
17. Kitchen DB, Decornez H, Furr JR, Bajorath J. Docking and scoring in virtual screening for drug discovery. Nature Reviews Drug Discovery. 2004;3:935–949.
18. Trott O, Olson AJ. AutoDock Vina: Improving the speed and accuracy of docking. Journal of Computational Chemistry. 2010;31(2):455–461.
19. Ferreira LG, dos Santos RN, Oliva G, Andricopulo AD. Molecular docking and structure-based drug design strategies. Molecules. 2015;20:13384–13421.
20. 20.https://www.researchgate.net/figure/Role-of-AI-technology-in-different-phases-of-drug-discovery_fig8_352692045
21. https://pmc.ncbi.nlm.nih.gov/articles/PMC9716588/
22. https://www.researchgate.net/figure/Schematic-illustration-of-the-anti-COVID-19-discover-procedure-of-virtual-screening_fig1_345101777
23. Morris GM, Huey R, Olson AJ. Using AutoDock for ligand–receptor docking. Current Protocols in Bioinformatics. 2008;24:8.14.1–8.14.40.
24. Pagadala NS, Syed K, Tuszynski J. Software for molecular docking: A review. Biophysical Reviews. 2017;9:91–102.
25. Lionta E, Spyrou G, Vassilatis DK, Cournia Z. Structure-based virtual screening for drug discovery. Current Topics in Medicinal Chemistry. 2014;14:1923–1938.
26. Sliwoski G, Kothiwale S, Meiler J, Lowe EW. Computational methods in drug discovery. Pharmacological Reviews. 2014;66:334–395.
27. Yuriev E, Holien J, Ramsland PA. Improvements, trends, and new ideas in molecular docking. Journal of Molecular Recognition. 2015;28:581–604.
28. Gorgulla C, Boeszoermenyi A, Wang ZF. An open-source drug discovery platform using molecular docking. Nature Protocols. 2020;15:4059–4085
29. Sousa SF, Ribeiro AJM, Coimbra JT, Neves RP, Martins SA. Protein–ligand docking: Current status and future challenges. Proteins. 2013;81:15–26
30. Schneider G, Walters WP, Plowright AT, Sieroka N, Listgarten J, Goodnow RA, et al. Rethinking drug design in the artificial intelligence era. Nat Rev Drug Discov. 2020;19(5):353-364.
31. Walters WP, Murcko MA. Assessing the impact of generative AI on medicinal chemistry. Nat Biotechnol. 2020;38(2):143-145.
32. Chen Y, Butkiewicz M, Fenner J, et al. Prediction of drug-target interactions using machine learning. J Chem Inf Model. 2019;59(4):1391-1400.