创新药物设计——从计算机辅助到人工智能

doi:10.3969/j.issn.0253-9608.2025.01.001

摘要/Abstract

摘要：

计算科学的高速发展不断为药物发现领域带来革新与机遇。伴随着生命科学领域数据的持续增长和计算硬件设备的迭代更新，计算化学以及化学信息学在临床前药物设计领域的支撑作用日益凸显。本文围绕计算机辅助药物设计(computer-aided drug design, CADD)和人工智能药物设计(artificial intelligence-driven drug design, AIDD)两大主题，简要阐述计算科学和药物发现在学科交叉中的探索和创新，以及针对临床前小分子药物的应用和进展。

关键词:

计算机辅助药物设计, 人工智能药物设计, 药物发现, 机器学习, 深度学习

Abstract:

The rapid advancement of computational science continues to drive innovation and create opportunities in the field of drug discovery. With the ongoing expansion of data in the life sciences and the iterative improvement of computational hardware, computational chemistry and cheminformatics have been indispensable tools for researchers in preclinical drug design. This article focuses on two key themes — computer-aided drug design (CADD) and artifificial intelligence-driven drug design (AIDD) — to provide a concise overview of the interdisciplinary exploration and innovation at the intersection of computational science and drug discovery, as well as the applications and progress related to preclinical small-molecule drug development.

卞月珉.

创新药物设计——从计算机辅助到人工智能

[J]. 自然杂志, 0, (): 1-10.

BIAN Yuemin.

From computer-aided drug design to artificial intelligence-driven drug design

[J]. Chinese Journal of Nature, 0, (): 1-10.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.nature.shu.edu.cn/CN/10.3969/j.issn.0253-9608.2025.01.001

参考文献

[1] WOUTERS O J, MCKEE M, LUYTEN J. Estimated research and development investment needed to bring a new medicine to market, 2009-2018 [J]. JAMA, 2020, 323(9): 844-853.

[2] DIMASI J A, GRABOWSKI H G, HANSEN R W. Innovation in the pharmaceutical industry: new estimates of R&D costs [J]. Journal of Health Economics, 2016, 47: 20-33.

[3] YASI E A, KRUYER N S, PERALTA-YAHYA P. Advances in G protein-coupled receptor high-throughput screening [J]. Current Opinion in Biotechnology, 2020, 64: 210-217.

[4] BLAY V, TOLANI B, HO S P, et al. High-throughput screening: today’s biochemical and cell-based approaches [J]. Drug Discovery Today, 2020, 25(10): 1807-1821.

[5] BLUNDELL T L. Structure-based drug design [J]. Nature, 1996, 384(6604): 23.

[6] BACILIERI M, MORO S. Ligand-based drug design methodologies in drug discovery process: an overview [J]. Current Drug Discovery Technologies, 2006, 3(3): 155-165.

[7] BIAN Y-M, HE X-B, JING Y-K, et al. Computational systems pharmacology analysis of cannabidiol: a combination of

chemogenomics-knowledgebase network analysis and integrated in silico modeling and simulation [J]. Acta Pharmacologica Sinica, 2019, 40(3): 374-386.

[8] BIAN Y, FENG Z, YANG P, et al. Integrated in silico fragment-based drug design: case study with allosteric modulators on

metabotropic glutamate receptor 5 [J]. The AAPS Journal, 2017, 19: 1235-1248.

[9] WANG J, WOLF R M, CALDWELL J W, et al. Development and testing of a general amber force fifield [J]. Journal of Computational Chemistry, 2004, 25(9): 1157-1174.

[10] GE H, BIAN Y, HE X, et al. Significantly different effects of tetrahydroberberrubine enantiomers on dopamine D1/D2 receptors revealed by experimental study and integrated in silico simulation [J]. Journal of Computer-Aided Molecular Design, 2019, 33: 447-459.

[11] WANG Z-Z, SHI X-X, HUANG G-Y, et al. Fragment-based drug discovery supports drugging ‘undruggable’ protein-protein

interactions [J]. Trends in Biochemical Sciences, 2023, 48(6): 539-552.

[12] BIAN Y, XIE X-Q. Computational fragment-based drug design: current trends, strategies, and applications [J]. The AAPS Journal, 2018, 20: 1-11.

[13] BIAN Y. Computational fragment-based discovery of allosteric modulators on metabotropic glutamate receptor 5 [D]. Pittsburgh, PA: University of Pittsburgh, 2017.

[14] SHARMA P, SHARMA S, YADAV Y, et al. Current pharmacophore based approaches for the development of new anti-Alzheimer’s agents [J]. Bioorganic & Medicinal Chemistry, 2024: 117926.

[15] ACHARYA A, YADAV M, NAGPURE M, et al. Molecular medicinal insights into scaffold hopping-based drug discovery success [J]. Drug Discovery Today, 2024, 29(1): 103845.

[16] NASSER M, YUSOF U K, SALIM N. Deep learning based methods for molecular similarity searching: a systematic review [J]. Processes, 2023, 11(5): 1340.

[17] BIAN Y, HOU G, XIE X-Q. Artificial intelligence generative chemistry design of target-specific scaffold-focused small molecule drug libraries [M]//JAGADEESH G, BALAKUMAR P, SENATORE F (eds). The Quintessence of Basic and Clinical Research and Scientifific Publishing. Singapore: Springer, 2023: 503-521.

[18] JING Y, BIAN Y, HU Z, et al. Deep learning for drug design: an artifificial intelligence paradigm for drug discovery in the big data era [J]. The AAPS Journal, 2018, 20: 1-10.

[19] BIAN Y, XIE X-Q. Generative chemistry: drug discovery with deep learning generative models [J]. Journal of Molecular Modeling, 2021, 27: 1-18.

[20] IVANENKOV Y, ZAGRIBELNYY B, MALYSHEV A, et al. The hitchhiker’s guide to deep learning driven generative chemistry [J]. ACS Medicinal Chemistry Letters, 2023, 14(7): 901-915.

[21] BIAN Y, JUN J J, CUYLER J, et al. Covalent allosteric modulation: An emerging strategy for GPCRs drug discovery [J]. European Journal of Medicinal Chemistry, 2020, 206: 112690.

[22] CHEN Y, BIAN Y, WANG J-W, et al. Effects of α-mangostin derivatives on the Alzheimer’s disease model of rats and their mechanism: A combination of experimental study and computational systems pharmacology analysis [J]. ACS Omega, 2020, 5(17): 9846-9863.

[23] KWON J J, HAJIAN B, BIAN Y, et al. Structure-function analysis of the SHOC2-MRAS-PP1C holophosphatase complex [J]. Nature, 2022, 609(7926): 408-415.

[24] SHANKAR S, PAN J, YANG P, et al. Viral DNA polymerase structures reveal mechanisms of antiviral drug resistance [J]. Cell, 2024, 187(20): 5572-5586. e15.

[25] BIAN Y, JING Y, WANG L, et al. Prediction of orthosteric and allosteric regulations on cannabinoid receptors using supervised machine learning classifiers [J]. Molecular Pharmaceutics, 2019, 16(6): 2605-2615.

[26] HOU T, BIAN Y, MCGUIRE T, et al. Integrated multi-class classification and prediction of GPCR allosteric modulators by machine learning intelligence [J]. Biomolecules, 2021, 11(6): 870.

[27] GENTILE F, YAACOUB J C, GLEAVE J, et al. Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking [J]. Nature Protocols, 2022, 17(3): 672-697.

[28] BIAN Y, KWON J J, LIU C, et al. Target-driven machine learning-enabled virtual screening (TAME-VS) platform for early-stage hit identification [J]. Frontiers in Molecular Biosciences, 2023, 10: 1163536.

[29] BIAN Y. The research and development of an artifificial intelligence integrated fragment-based drug design platform for small molecule drug discovery [D]. Pittsburgh, PA: University of Pittsburgh, 2021.

[30] WANG M, WANG Z, SUN H, et al. Deep learning approaches for de novo drug design: An overview [J]. Current Opinion in Structural Biology, 2022, 72: 135-144.

[31] ABOUCHEKEIR S, VU A, MUKAIDAISI M, et al. Adversarial deep evolutionary learning for drug design [J]. Biosystems, 2022, 222: 104790.

[32] ALI F, KHALID M, ALMUHAIMEED A, et al. IP-GCN: A deep learning model for prediction of insulin using graph convolutional network for diabetes drug design [J]. Journal of Computational Science, 2024, 81: 102388.

[33] RAMESH A, RAO A S, MOUDGALYA S, et al. GAN based approach for drug design [C]// 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA). Pasadena, CA: IEEE, 2021: 825-828. DOI: 10.1109/ICMLA52953.2021.00136.

[34] GUPTA A, MÜLLER A T, HUISMAN B J, et al. Generative recurrent networks for de novo drug design [J]. Molecular Informatics, 2018, 37(1/2): 1700111.

[35] ALAKHDAR A, POCZOS B, WASHBURN N. Diffusion models in de novo drug design [J]. Journal of Chemical Information and Modeling, 2024, 64(19): 7238-7256.

[36] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks [J]. Communications of the ACM,

2020, 63(11): 139-144.

[37] BIAN Y, WANG J, JUN J J, et al. Deep convolutional generative adversarial network (dcGAN) models for screening and design of small molecules targeting cannabinoid receptors [J]. Molecular Pharmaceutics, 2019, 16(11): 4451-4460.

[38] BIAN Y, XIE X-Q. Artificial intelligent deep learning molecular generative modeling of scaffold-focused and cannabinoid CB2 target-specific small-molecule sublibraries [J]. Cells, 2022, 11(5): 915