The Korean Journal of Physiology and Pharmacology

  • 제28권6호
  • /
  • Pages.527-537
  • /
  • 2024
  • /
  • 1226-4512(pISSN)
  • /
  • 2093-3827(eISSN)
대한약리학회 (The Korean Society of Pharmacology)
권호 표지
DOI QR코드

DOI QR Code

Predicting antioxidant activity of compounds based on chemical structure using machine learning methods

  • Jinwoo Jung (Department of Pharmacy, College of Pharmacy and Research Institute for Drug Development) ;
  • Jeon-Ok Moon (Department of Pharmacy, College of Pharmacy and Research Institute for Drug Development) ;
  • Song Ih Ahn (School of Mechanical Engineering, Pusan National University) ;
  • Haeseung Lee (Department of Pharmacy, College of Pharmacy and Research Institute for Drug Development)
  • 투고 : 2024.05.07
  • 심사 : 2024.07.12
  • 발행 : 2024.11.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Oxidative stress is a well-established risk factor for numerous chronic diseases, emphasizing the need for efficient identification of potent antioxidants. Conventional methods for assessing antioxidant properties are often time-consuming and resource-intensive, typically relying on laborious biochemical assays. In this study, we investigated the applicability of machine learning (ML) algorithms for predicting the antioxidant activity of compounds based solely on their molecular structure. We evaluated the performance of five ML algorithms, Support Vector Machine (SVM), Logistic Regression (LR), XGBoost, Random Forest (RF), and Deep Neural Network (DNN), using a dataset of over 1,900 compounds with experimentally determined antioxidant activity. Both RF and SVM achieved the best overall performance, exhibiting high accuracy (> 0.9) and effectively distinguishing active and inactive compounds with high structural similarity. External validation using natural product data from the BATMAN database confirmed the generalizability of the RF and SVM models. Our results suggest that ML models serve as powerful tools to expedite the discovery of novel antioxidant candidates, potentially streamlining the development of future therapeutic interventions.

키워드

과제정보

We would like to express our sincere gratitude to Professor Minhye Yang for her generous support throughout this project. We are also grateful to Dr. Changyong Lee for his invaluable supervision during the formal validation experiments.

참고문헌

  1. Lobo V, Patil A, Phatak A, Chandra N. Free radicals, antioxidants and functional foods: impact on human health. Pharmacogn Rev. 2010;4:118-126.
  2. Ashok A, Andrabi SS, Mansoor S, Kuang Y, Kwon BK, Labhasetwar V. Antioxidant therapy in oxidative stress-induced neurodegenerative diseases: role of nanoparticle-based drug delivery systems in clinical translation. Antioxidants (Basel). 2022;11:408.
  3. Kim J, Lee C, Noh SG, Kim S, Chung HY, Lee H, Moon JO. Integrative transcriptomic analysis reveals upregulated apoptotic signaling in wound-healing pathway in rat liver fibrosis models. Antioxidants (Basel). 2023;12:1588.
  4. Kedare SB, Singh RP. Genesis and development of DPPH method of antioxidant assay. J Food Sci Technol. 2011;48:412-422.
  5. Re R, Pellegrini N, Proteggente A, Pannala A, Yang M, Rice-Evans C. Antioxidant activity applying an improved ABTS radical cation decolorization assay. Free Radic Biol Med. 1999;26:1231-1237.
  6. Du Z, Wang D, Li Y. Comprehensive evaluation and comparison of machine learning methods in QSAR modeling of antioxidant tripeptides. ACS Omega. 2022;7:25760-25771.
  7. Shao L, Gao H, Liu Z, Feng J, Tang L, Lin H. Identification of antioxidant proteins with deep learning from sequence information. Front Pharmacol. 2018;9:1036.
  8. Jelicic ML, Kovacic J, Cvetnic M, Mornar A, Amidzic Klaric D. Antioxidant activity of pharmaceuticals: predictive QSAR modeling for potential therapeutic strategy. Pharmaceuticals (Basel). 2022;15:791.
  9. Wiriyarattanakul A, Xie W, Toopradab B, Wiriyarattanakul S, Shi L, Rungrotmongkol T, Maitarad P. Comparative study of machine learning-based QSAR modeling of anti-inflammatory compounds from durian extraction. ACS Omega. 2024;9:7817-7826.
  10. Mao J, Akhtar J, Zhang X, Sun L, Guan S, Li X, Chen G, Liu J, Jeon HN, Kim MS, No KT, Wang G. Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models. iScience. 2021;24:103052.
  11. Carocho M, Ferreira IC. A review on antioxidants, prooxidants and related controversy: natural and synthetic compounds, screening and analysis methodologies and future perspectives. Food Chem Toxicol. 2013;51:15-25.
  12. Bajusz D, Racz A, Heberger K. Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J Cheminform. 2015;7:20.
  13. Kruger F, Stiefl N, Landrum GA. rdScaffoldNetwork: the scaffold network implementation in RDKit. J Chem Inf Model. 2020;60:3331-3335.
  14. Sordon S, Poplonski J, Milczarek M, Stachowicz M, Tronina T, Kucharska AZ, Wietrzyk J, Huszcza E. Structure-antioxidant-antiproliferative activity relationships of natural C7 and C7-C8 hydroxylated flavones and flavanones. Antioxidants (Basel). 2019;8:210.
  15. Kong X, Liu C, Zhang Z, Cheng M, Mei Z, Li X, Liu P, Diao L, Ma Y, Jiang P, Kong X, Nie S, Guo Y, Wang Z, Zhang X, Wang Y, Tang L, Guo S, Liu Z, Li D. BATMAN-TCM 2.0: an enhanced integrative database for known and predicted interactions between traditional Chinese medicine ingredients and target proteins. Nucleic Acids Res. 2024;52:D1110-D1120.
  16. Sakurai S, Kawakami Y, Kuroki M, Gotoh H. Structure-antioxidant activity (oxygen radical absorbance capacity) relationships of phenolic compounds. Struct Chem. 2022;33:1055-1062.
  17. Noda Y, Kaneyuki T, Mori A, Packer L. Antioxidant activities of pomegranate fruit extract and its anthocyanidins: delphinidin, cyanidin, and pelargonidin. J Agric Food Chem. 2002;50:166-171.
  18. Wang W, Xu H, Chen H, Tai K, Liu F, Gao Y. In vitro antioxidant, anti-diabetic and antilipemic potentials of quercetagetin extracted from marigold (Tagetes erecta L.) inflorescence residues. J Food Sci Technol. 2016;53:2614-2624.
  19. Materska M, Konopacka M, Rogolinski J, Slosarek K. Antioxidant activity and protective effects against oxidative damage of human cells induced by X-radiation of phenolic glycosides isolated from pepper fruits Capsicum annuum L. Food Chem. 2015;168:546-553.
  20. Yousfi M, Djeridane A, Bombarda I; Chahrazed-Hamia; Duhem B, Gaydou EM. Isolation and characterization of a new hispolone derivative from antioxidant extracts of Pistacia atlantica. Phytother Res. 2009;23:1237-1242.
  21. Kim SM, Kang K, Jho EH, Jung YJ, Nho CW, Um BH, Pan CH. Hepatoprotective effect of flavonoid glycosides from Lespedeza cuneata against oxidative stress induced by tert-butyl hyperoxide. Phytother Res. 2011;25:1011-1017.
  22. Ding L, Zhang X, Zhang J. Antioxidant activity in vitro guided screening and identification of flavonoids antioxidants in the extract from Tetrastigma hemsleyanum Diels et Gilg. Int J Anal Chem. 2021;2021:7195125.
  23. Estevez L, Mosquera RA. Molecular structure and antioxidant properties of delphinidin. J Phys Chem A. 2008;112:10614-10623.
  24. Wagner AB. SciFinder Scholar 2006: an empirical analysis of research topic query processing. J Chem Inf Model. 2006;46:767-774.
  25. Kilic I, Yesiloglu Y, Bayrak Y. Spectroscopic studies on the antioxidant activity of ellagic acid. Spectrochim Acta A Mol Biomol Spectrosc. 2014;130:447-452.
  26. Tzen JTC. Strictinin: a key ingredient of tea. Molecules. 2023;28:3961.
  27. Hossain H, Rahman SE, Akbar PN, Khan TA, Rahman MM, Jahan IA. HPLC profiling, antioxidant and in vivo anti-inflammatory activity of the ethanol extract of Syzygium jambos available in Bangladesh. BMC Res Notes. 2016;9:191.
  28. Tu EC, Hsu WL, Tzen JTC. Strictinin, a major ingredient in Yunnan Kucha tea possessing inhibitory activity on the infection of mouse hepatitis virus to mouse L cells. Molecules. 2023;28:1080.