전자통신동향분석 (Electronics and Telecommunications Trends)

한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

신규 약물 설계를 위한 인공지능 기술 동향

Technical Trends in Artificial Intelligence for De Novo Drug Design

  • 한영웅 (의료정보연구실) ;
  • 정호열 (의료정보연구실) ;
  • 박수준 (디지털바이오의료연구본부)
  • Y.W. Han ;
  • H.Y. Jung ;
  • S.J. Park
  • 발행 : 2023.06.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The value of living a long and healthy life without suffering has increased owing to aging populations, transition to welfare societies, and global interest in health deriving from the novel coronavirus disease pandemic. New drug development has gained attention as both a tool to improve the quality of life and high-value market, with blockbuster drugs potentially generating over 10 billion dollars in annual revenue. However, for newly discovered substances to be used as drugs, various properties must be verified over a long period in a time-consuming and costly process. Recently, the development of artificial intelligence technologies, such as deep and reinforcement learning, has led to significant changes in drug development by enabling the effective identification of drug candidates that satisfy desired properties. We explore and discuss trends in artificial intelligence for de novo drug design.

키워드

과제정보

본 연구는 한국전자통신연구원 내부연구과제(전략기술)의 일환으로 수행되었음[23YB1600/ETRI-KAIST ICT 미래기술 탐색].

참고문헌

  1. M. Steedman et al., "Intelligent biopharma: Forging the links across the value chain," Deloitte Insights, 2019, pp. 1-25, https://www2.deloitte.com/content/dam/Deloitte/ch/Documents/life-sciences-health-care/deloitte-ch-di-intelligent-biopharma.pdf
  2. https://openclipart.org/detail/340527/smiles-code-of-molecules
  3. D. Weininger, "SMILES, a chemical language and information systems. 1. introduction to methodology and encoding rules," J. Chem. Inf. Comput. Sci., vol. 28, no. 1, 1988, pp. 31-36. https://doi.org/10.1021/ci00057a005
  4. J. Arus-Pous et al., "Randomized SMILES strings improve the quality of molecular generative models," J. Cheminformatics, vol. 11, no. 71, 2019, pp. 1-13. https://doi.org/10.1186/s13321-018-0323-6
  5. W. Jin et al., "Junction tree variational auto encoder for molecular graph generation," in Proc. 35th Int. Conf. Mach. Learn. (ICML), (Stockholm, Sweden), Jul. 2018.
  6. M. Wang et al., "Deep learning approaches for de novo drug design: An overview," Current Opinion Struct. Biol., vol. 72, 2022, pp. 135-144. https://doi.org/10.1016/j.sbi.2021.10.001
  7. C.A. Lipinski, "Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings," Adv. Drug Deliv. Rev., vol. 46, no. 1-3, 2001, pp. 3-26. https://doi.org/10.1016/S0169-409X(00)00129-0
  8. J. Mao et al., "Comprehensive strategies of machine learning based quantitative structure activity relationship models," iScience, vol. 24, no. 9, 2021, p. 103052.
  9. M. Popova et al., "Deep reinforcement learning for de novo drug design," Sci. Adv., vol. 4, no. 7, 2018, eaap7885.
  10. A. Zhavoronkov et al., "Deep learning enables rapid identification of potent DDR1 kinase inhibitors," Nat. Biotechnol., vol. 37, 2019, pp. 1038-1040. https://doi.org/10.1038/s41587-019-0224-x
  11. J. Choi and J. Lee, "V-Dock: Fast generation of novel drug-like molecules using machine-learning-based docking score and molecular optimization," Int. J. Mol. Sci., vol. 22, no. 21, 2021, p. 11635.
  12. M. Olivecrona et al., "Molecular de-novo design through deep reinforcement learning," J. Cheminform., vol. 9, no. 1, 2017, p. 48.
  13. J. Guo et al., "DockStrem: A docking wrapper to enhance de novo molecular design," J. Cheminform., vol. 13, no. 1, 2021, p. 89.
  14. J. Jumper et al., "Highly accurate protein structure prediction with AlphaFold," Nature, vol. 596, no. 7873, 2021, pp. 583-589. https://doi.org/10.1038/s41586-021-03819-2
  15. P. Bryant et al., "Improved prediction of protein-protein interactions using AlphaFold2," Nat. Commun., vol. 13, no. 1, 2022, p. 1265.
  16. V. Chenthamarakshan et al., "CogMol: Target-specific and selective drug design for COVID-19 using deep generative models," Proceedings of the 34th Conference on Neural Information Processing System(NeurIPS), 2020.
  17. J. Born et al., "PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning," iScience, vol. 24, no. 4, 2021, p. 102269.
  18. 남호정 외, "가상인체와 심층학습을 이용한 약물표적 및 효능예측," 정보과학회지, vol. 40, no. 3, 2022, pp. 22-29.
  19. K. Lanevskij and R. Didziapetris, "Physicochemical QSAR analysis of passive permeability across Caco-2 monolayers," J. Pharm. Sci., vol. 108, no. 1, 2019, pp. 78-86. https://doi.org/10.1016/j.xphs.2018.10.006
  20. H. Sun, "Highly predictive and interpretable models for PAMPA permeability," Bioorg. Med. Chem., vol. 25, no. 3, 2017, pp. 1266-1276. https://doi.org/10.1016/j.bmc.2016.12.049
  21. F. Stefaniak, "Prediction of compounds activity in nuclear receptor signaling and stress pathway assays using machine learning algorithms and low-dimensional molecular descriptors," Front. Environ. Sci., vol. 3, 2015, p. 77.
  22. E. Kim and H. Nam, "Prediction models for drug-induced hepatotoxicity by using weighted molecular fingerprints," BMC Bioinformatics, vol. 18, no. 227, 2017, pp. 25-34. https://doi.org/10.1186/s12859-016-1437-3
  23. K. Ogura et al., "Support vector machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-II," Sci. Rep., vol. 9, no. 1, 2019, p. 12220.
  24. C. Cai et al., "Deep learning-based prediction of drug-induced cardiotoxicity," J. Chem. Inf. Model, vol. 59, no. 3, 2019, pp. 1073-1084.  https://doi.org/10.1021/acs.jcim.8b00769