English
往期目录
新闻公告
More
化学进展 2023, Vol. 35 Issue (10): 1505-1518 DOI: 10.7536/PC230318 前一篇   后一篇

• 综述 •

先进人工智能技术在新药研发中的应用

汪忠华1,2, 吴亦初1, 吴中山1, 朱冉冉1, 杨阳1, 吴范宏1,2,*()   

  1. 1 上海应用技术大学化学与环境工程学院 上海 201418
    2 上海绿色氟代制药工程技术研究中心 上海 201418
  • 收稿日期:2023-03-16 修回日期:2023-05-24 出版日期:2023-10-24 发布日期:2023-08-06
  • 作者简介:

    吴范宏 博士、教授。主要从事小分子靶向抗肿瘤新药设计合成、基于新药研发的绿色氟代技术研究及其工艺创新。主持完成多项国家、省部科研项目和企业重大横向项目。在Angew. Chem. Int. Ed.、Adv. Syn. Catal.和Chem. Comm.等刊物上发表论文100余篇,授权专利40多项。

  • 基金资助:
    中国国家自然科学基金项目(21672151); 中国国家自然科学基金项目(21602136)
Richhtml ( 23 ) 下载PDF ( 342 ) 引用
导出

Application of Advanced Artificial Intelligence Technology in New Drug Discovery

Zhonghua Wang1,2, Yichu Wu1, Zhongshan Wu1, Ranran Zhu1, Yang Yang1, Fanhong Wu1,2,*()   

  1. 1 School of Chemical and Environmental Engineering, Shanghai Institute of Technology,Shanghai 201418, China
    2 Shanghai Engineering Research Center of Green Fluoropharmaceutical Technology,Shanghai 201418, China
  • Received:2023-03-16 Revised:2023-05-24 Online:2023-10-24 Published:2023-08-06
  • Contact: *e-mail: wfh@sit.edu.cn
  • Supported by:
    National Natural Science Foundation of China(21672151); National Natural Science Foundation of China(21602136)

近年来,先进人工智能(Artificial intelligence,AI)技术驱动的新药研发备受关注。先进的人工智能算法(机器学习和深度学习)已逐渐应用于新药研发的各个场景,如表征学习任务(分子描述符)、预测任务(药靶结合亲和力预测、晶型结构预测和分子基本性质预测)以及生成任务(分子构象生成和药物分子生成)等。该技术可大大减少新药研发的成本和时间,提高药物研发效率,降低临床前和临床试验的相关成本和风险。本文归纳总结了近年来新药研发中先进人工智能技术的应用,帮助了解该领域的研究进展和未来发展趋势,助力创新药物的研发。

关键词： 人工智能, 新药研发, 深度学习, 表征学习, 任务应用

In recent years, the discovery of new drugs driven by advanced artificial intelligence (AI) has attracted much attention. Advanced artificial intelligence algorithms (machine learning and deep learning) have been gradually applied in various scenarios of new drug discovery, such as representation learning task (molecular descriptor), prediction task (drug target binding affinity prediction, crystal structure prediction and molecular basic properties prediction) and generation task (molecular conformation generation and drug molecular generation). This technology can significantly reduce the cost and time of new drug development, improve the efficiency of drug development, and reduce the costs and risks associated with preclinical and clinical trials. This review summarizes the application of advanced artificial intelligence technology in new drug discovery in recent years, to help understand the research progress and future development trend in this field, and to facilitate the discovery of innovative drugs.

Contents

1 Introduction

2 Artificial intelligence

2.1 Convolutional neural network

2.2 Recurrent neural network

2.3 Graph neural network

2.4 Generative adversarial network

2.5 Variational auto encoder

2.6 Diffusion model

2.7 Transformer model

3 The application of artificial intelligence in drug discovery

3.1 Data resources and open-source tools

3.2 Artificial intelligence technology drives molecular representation learning tasks

3.3 Artificial intelligence technology drives predictive tasks

3.4 Artificial intelligence technology drives generation tasks

4 Conclusion and outlook

Key words: artificial intelligence, new drug discovery, deep learning, representation learning, task application
()
图1 GPU与CPU的逻辑模式[10]
Fig.1 Logical mode of the GPU and CPU[10]
图2 卷积神经网络模型架构
Fig.2 Convolutional neural network model architecture
图3 递归神经网络模型架构
Fig.3 Recurrent neural network model architecture
图4 图神经网络模型架构
Fig.4 Graph neural network model architecture
图5 生成对抗网络模型架构
Fig.5 Generative adversarial network model architecture
图6 变分自编码器模型架构
Fig.6 Variational auto encoder model architecture
图7 扩散模型架构
Fig.7 Diffusion model architecture
图8 Transformer模型架构
Fig.8 Transformer model architecture
图9 (a)数据及开源工具;(b)模型架构;(c)分子描述形式;(d)执行任务
Fig.9 (a) Data and open-source tools. (b) Model architecture. (c) Molecular descriptions. (d) Performing tasks
图10 DTI示意图:首先将药物分子和蛋白分别表示,经过神经网络模型后两者向量拼凑进入MLP从而将结果执行分类任务判断药物对靶点是否有作用[76]
Fig.10 DTI schematic diagram: Firstly, drug molecules and proteins are represented respectively, and after neural network model, the vectors of the two are pieced together into MLP, so that the results can be classified to determine whether the drug has an effect on the target[76]
图11 DTI的注意力可视化。左:蛋白质距离图以热图的形式显示,相应目标的注意力栏显示出来。中:配体和预测的重要残基分别用绿色和粉色骨架表示,预测的重要配体原子用红色突出显示,已知的氢键用黄色虚线标出,局部目标结构被涂成灰色作为背景。右:配体用二维凯库勒公式表示,相应的预测的重要原子用浅红点突出显示[76]
Fig.11 Attention visualization of DTIs. Left: Protein distance maps are displayed in the form of heat maps. The corresponding targets’ attention bars are shown. Middle: Ligands and predicted important residues are represented as green and pink skeletons, respectively. Predicted important atoms of ligands are highlighted in red. Known hydrogen bonds are marked with yellow dashed lines. Local target structures are painted grey as the background. Right: Ligands are represented by 2D Kekule formula. The corresponding predicted important atoms are highlighted by light red dots[76]
图12 (a)预测的最低晶格能形式Z1(蓝色,rmsd15 = 0.091 ?)和形式X1(红色,rmsd15 = 0.141 ?)与实验单晶结构稳定形式AZD1305(绿色)的结构叠加。(b)形态A(黑色)的实验PXRD数据与预测形态Z8(蓝色)和X23(红色)的模拟PXRD图谱的比较。(c)AZD1305预测形式A(蓝色)和形式B(红色)的构象结构叠加。(d)XtalPi预测形式X1(形式B)、X2、X3、X4、X5和X23(形式A)相对自由能稳定性的温度依赖性[81]
Fig.12 (a)Structure overlay of the predicted lowest lattice energy form Z1 (in blue, rmsd15 = 0.091 ?) and form X1 (in red, rmsd15 = 0.141 ?) with experimental single crystal structure of the stable form B of AZD1305 (in green). (b)Comparison of experimental PXRD data for form A (black) and simulated PXRD patterns of predicted form Z8 (blue) and X23(red). (c)Structural overlay of conformers in predicted form A (blue) and form B (red) of AZD1305. (d)Temperature dependence of relative free-energy stabilities of forms X1 (form B), X2, X3, X4, X5, and X23 (form A) predicted by XtalPi[81]
表1 人工智能模型用于化合物性质预测的测试数据集
Table 1 The dataset for compound property prediction by artificial intelligence
Category Dataset Description
Physical chemistry ESOL Aqueous solubility
FreeSolv Hydration free energy
Lipophilicity Octanol/water distribution coefficient (LogD)
Biopyhsics MUV 17 tasks from PubChem BioAssay
HIV Ability to inhibit HIV replication
BACE Binding results for inhibitors of human BACE-1
Physiology BBBP Blood-brain barrier penetration
Tox21 Toxicity measurements
SIDER Adverse drug reactions on 27 system organs
ClinTox Clinical trail toxicity and FDA approval status
图13 Rdkit与聚类算法用于分子构象生成[95]
Fig.13 Rdkit and clustering algorithm are used for molecular conformation generation[95]
图14 分子生成旨在偌大的化学空间中生成具有特定性质的化合物[107]
Fig.14 Molecular formation aims to create compounds with specific properties in a large chemical space[107]
[1]
DiMasi J A, Grabowski H G, Hansen R W. J. Health Econ., 2016, 47: 20.

doi: 10.1016/j.jhealeco.2016.01.012     URL    
[2]
Reddy A S, Zhang S X. Expert Rev. Clin. Pharmacol., 2013, 6(1): 41.

doi: 10.1586/ecp.12.74     URL    
[3]
Sachdev K, Gupta M K. J. Biomed. Inform., 2019, 93: 103159.

doi: 10.1016/j.jbi.2019.103159     URL    
[4]
Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, Li B, Madabhushi A, Shah P, Spitzer M, Zhao S R. Nat. Rev. Drug Discov., 2019, 18(6): 463.

doi: 10.1038/s41573-019-0024-5     pmid: 30976107
[5]
Kimber T B, Chen Y H, Volkamer A. Int. J. Mol. Sci., 2021, 22(9): 4435.

doi: 10.3390/ijms22094435     URL    
[6]
Lipinski C F, Maltarollo V G, Oliveira P R, da Silva A B F, Honorio K M. Front. Robot. AI, 2019, 6: 108.

doi: 10.3389/frobt.2019.00108     URL    
[7]
Rifaioglu A S, Atas H, Martin M J, Cetin-Atalay R, Atalay V, Doğan T. Brief Bioinform, 2019, 20(5): 1878.

doi: 10.1093/bib/bby061     pmid: 30084866
[8]
Ivanenkov Y A, Polykovskiy D, Bezrukov D, Zagribelnyy B, Aladinskiy V, Kamya P, Aliper A, Ren F, Zhavoronkov A. J. Chem. Inf. Model., 2023, 63(3): 695.

doi: 10.1021/acs.jcim.2c01191     pmid: 36728505
[9]
Janiesch C, Zschech P, Heinrich K. Electron. Mark., 2021, 31(3): 685.

doi: 10.1007/s12525-021-00475-2    
[10]
Wang M Z, Wang B, He Q, Liu X X, Zhu K S. arXiv preprint arXiv: 1505.06561, 2015.
[11]
LeCun Y, Bengio Y, Hinton G. Nature, 2015, 521(7553): 436.

doi: 10.1038/nature14539    
[12]
Simm J, Klambauer G, Arany A, Steijaert M, Wegner J K, Gustin E, Chupakhin V, Chong Y T, Vialard J, Buijnsters P, Velter I, Vapirev A, Singh S, Carpenter A E, Wuyts R, Hochreiter S, Moreau Y, Ceulemans H. Cell Chem. Biol., 2018, 25(5): 611.

doi: 10.1016/j.chembiol.2018.01.015     URL    
[13]
Hofmarcher M, Rumetshofer E, Clevert D A, Hochreiter S, Klambauer G. J. Chem. Inf. Model., 2019, 59(3): 1163.

doi: 10.1021/acs.jcim.8b00670     pmid: 30840449
[14]
Ramsundar B, Kearnes S, Riley P, Webster D, Konerding D, Pande V. arXiv preprint arXiv: 1502.02072, 2015.
[15]
Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J, G’omez-Bombarelli R, Hirzel T, Aspuru-Guzik A, P. Adams R. arXiv preprint arXiv: 1509.09292, 2015.
[16]
Goh G B, Siegel C, Vishnu A, Hodas N O, Baker N. arXiv preprint arXiv: 1706.06689, 2017.
[17]
Chen M Y, Chiang H S, Sangaiah A K, Hsieh T C. Neural Comput. Appl., 2020, 32(12): 7915.

doi: 10.1007/s00521-019-04301-x    
[18]
Hochreiter S, Schmidhuber J. Neural Comput., 1997, 9(8): 1735.

doi: 10.1162/neco.1997.9.8.1735     pmid: 9377276
[19]
Chung J, Gulcehre C, Cho K, Bengio K. arXiv preprint arXiv: 1412.3555, 2014.
[20]
Goh G B, Hodas N O, Siegel C, Vishnu A. arXiv preprint arXiv: 1712.02034, 2017.
[21]
Mayr A, Klambauer G, Unterthiner T, Steijaert M, Wegner J K, Ceulemans H, Clevert D A, Hochreiter S. Chem. Sci., 2018, 9(24): 5441.

doi: 10.1039/C8SC00148K     URL    
[22]
Wu Z H, Pan S R, Chen F W, Long G D, Zhang C Q, Yu P S. IEEE Trans. Neural Netw. Learn. Syst., 2021, 32(1): 4.

doi: 10.1109/TNNLS.5962385     URL    
[23]
Schütt K T, Kindermans P J, Sauceda H E, Chmiela S, Tkatchenko A, Müller K R. arXiv preprint arXiv: 1706.08566, 2017.
[24]
Feinberg E N, Sur D, Wu Z Q, Husic B E, Mai H H, Li Y, Sun S S, Yang J Y, Ramsundar B, Pande V S. ACS Cent. Sci., 2018, 4(11): 1520.

doi: 10.1021/acscentsci.8b00507     URL    
[25]
Gasteiger J, Grob J, Günnemann S. arXiv preprint arXiv:2003.03123, 2020.
[26]
Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, 2672.
[27]
Guimaraes G L, Sanchez-Lengeling B, Outerial C, Farias P L C, Aspuru-Guzik A. arXiv preprint arXiv: 1705.10843, 2017.
[28]
Sanchez-Lengeling B, Outeiral C, Guimaraes G L, Aspuru-Guzik A. chemRxiv preprint: 10.26434/chemrxiv.5309668.v3, 2017.
[29]
Kingma D P, Welling M. arXiv preprint arXiv: 1312.6114, 2013.
[30]
Kingma D P, Welling M. Found. Trends® Mach. Learn., 2019, 12(4): 307.
[31]
Kusner M J, Paige B, Hernández-Lobato J M. International Conference on Machine Learning. PMLR, 2017, 1945.
[32]
Dai H J, Tian Y T, Dai B, Skiena S, Song L. arXiv preprint arXiv: 1802.08786, 2018.
[33]
Saharia C, Chan W, Chang H, Lee C A, Ho J, Salimas T, Fleet D J, Norouzi M. arXiv preprint arXiv: 2111.05826, 2021.
[34]
Hoogeboom E, Satorras V G, Vignac C, Welling M. International Conference on Machine Learning. PMLR, 2022: 8867.
[35]
Luo S, Su Y, Peng X, Wang S, Peng J, Ma J. bioRxiv, 2022, 10.499510.
[36]
Tachibana H, Go M, Inahara M, Katayama Y, Watanabe Y. arXiv preprint arXiv: 2112.13339, 2021.
[37]
Watson J L, Juergens D, Bennett N R, Trippe B L, Yim J, Eisenach H E, Ahern W, Borst A J, Ragotte R J, Milles L F, Wicky B I M, Hanikel N, Pellock S J, Courbet A, Sheffler W, Wang J, Venkatesh P, Sappington I, Torres S V, Lauko A, De Bortoli V, Mathieu E, Ovchinnikov S, Barzilay R, Jaakkola T S, DiMaio F, Baek M, Baker D. Nature, 2023, 620: 1089.

doi: 10.1038/s41586-023-06415-8    
[38]
Yeh A H W, Norn C, Kipnis Y, Tischer D, Pellock S J, Evans D, Ma P C, Lee G R, Zhang J Z, Anishchenko I, Coventry B, Cao L X, Dauparas J, Halabiya S, DeWitt M, Carter L, Houk K N, Baker D. Nature, 2023, 614(7949): 774.

doi: 10.1038/s41586-023-05696-3    
[39]
Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, Davison J, Shleifer S, Platen P, Ma C, Jernite Y, Plu J, Xu C W, Scao T L, Gugger S, Drame M, Lhoest Q, Rush A M. arXiv preprint arXiv: 1910.03771, 2019.
[40]
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L, Polosukhin I. arXiv preprint arXiv: 1706.03762, 2017.
[41]
Radford A, Narasimhan K, Salimans T, Sutskever I. OpenAI: https://openai.com/blog/language-unsupervised/, 2018.
[42]
Devlin J, Chang M W, Lee K, Toutanova. Proceedings of NAACL-HLT, 2019, 4171-4186.
[43]
Thorp H H. Science, 2023, 379(6630): 313.

doi: 10.1126/science.adg7879     URL    
[44]
OpenAI. arXiv preprint arXiv: 2303.08774, 2023.
[45]
Wang S, Guo Y Z, Wang Y H, Sun H M, Huang J Z. Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Niagara Falls NY USA. New York, NY, USA: ACM, 2019, 429.
[46]
Honda S, Shi S, Ueda H R. arXiv preprint arXiv: 1911.04738, 2019.
[47]
Kim S, Chen J, Cheng T J, Gindulyte A, He J, He S Q, Li Q L, Shoemaker B A, Thiessen P A, Yu B, Zaslavsky L, Zhang J, Bolton E E. Nucleic Acids Res., 2021, 49(D1): D1388.

doi: 10.1093/nar/gkaa971     URL    
[48]
Gaulton A, Hersey A, Nowotka M, Bento A P, Chambers J, Mendez D, Mutowo P, Atkinson F, Bellis L J, Cibrián-Uhalte E, Davies M, Dedman N, Karlsson A, Magariños M P, Overington J P, Papadatos G, Smit I, Leach A R. Nucleic Acids Res., 2017, 45(D1): D945.

doi: 10.1093/nar/gkw1074     URL    
[49]
Irwin J J, Tang K G, Young J, Dandarchuluun C, Wong B R, Khurelbaatar M, Moroz Y S, Mayfield J, Sayle R A. J. Chem. Inf. Model., 2020, 60(12): 6065.

doi: 10.1021/acs.jcim.0c00675     pmid: 33118813
[50]
Schneider N, Sayle R A, Landrum G A. J. Chem. Inf. Model., 2015, 55(10): 2111.

doi: 10.1021/acs.jcim.5b00543     pmid: 26441310
[51]
Ramsundar B, Eastman P, Walters P, Pande V. Drug Discovery and More. 1st ed. CA; O’Reilly Media: Sebastopol, 2019.
[52]
Schneider N, Fechner N, Landrum G A, Stiefl N. J. Chem. Inf. Model., 2017, 57(8): 1816.

doi: 10.1021/acs.jcim.7b00249     pmid: 28715190
[53]
Czodrowski P, Bolick W G. J. Chem. Inf. Model., 2016, 56(10): 2013.

pmid: 27668814
[54]
Xue L, Bajorath J. Comb. Chem. High Throughput Screen., 2000, 3(5): 363.

pmid: 11032954
[55]
Redkar S, Mondal S, Joseph A, Hareesha K S. Mol. Inform., 2020, 39(5): 1900062.

doi: 10.1002/minf.v39.5     URL    
[56]
Rifaioglu A S, Nalbat E, Atalay V, Martin M J, Cetin-Atalay R, Doğan T. Chem. Sci., 2020, 11(9): 2531.

doi: 10.1039/c9sc03414e     pmid: 33209251
[57]
Stokes J M, Yang K, Swanson K, Jin W G, Cubillos-Ruiz A, Donghia N M, MacNair C R, French S, Carfrae L A, Bloom-Ackermann Z, Tran V M, Chiappino-Pepe A, Badran A H, Andrews I W, Chory E J, Church G M, Brown E D, Jaakkola T S, Barzilay R, Collins J J. Cell, 2020, 181(2): 475.

doi: 10.1016/j.cell.2020.04.001     URL    
[58]
Shin B, Park S, Kang K, C. Ho J. arXiv preprint arXiv: 1908.06760, 2019.
[59]
Öztürk H, Özgür A, Ozkirimli E. Bioinformatics, 2018, 34(17): i821.

doi: 10.1093/bioinformatics/bty593     URL    
[60]
Abnousi A, Broschat S L, Kalyanaraman A. BMC Bioinform., 2018, 19(1): 83.

doi: 10.1186/s12859-018-2080-y    
[61]
Lee I, Keum J, Nam H. PLoS Comput. Biol., 2019, 15(6): e1007129.

doi: 10.1371/journal.pcbi.1007129     URL    
[62]
Zhao Q, Xing F, Tao Y Y, Liu H L, Huang K, Peng Y, Feng N P, Liu C H. Front. Pharmacol., 2020, 11: 1.

doi: 10.3389/fphar.2020.00001     URL    
[63]
Gao K F, Nguyen D D, Sresht V, Mathiowetz A M, Tu M H, Wei G W. Phys. Chem. Chem. Phys., 2020, 22(16): 8373.

doi: 10.1039/D0CP00305K     URL    
[64]
Wang Y B, You Z H, Yang S, Yi H C, Chen Z H, Zheng K. BMC Med. Inform. Decis. Mak., 2020, 20(2): 49.

doi: 10.1186/s12911-020-1052-0    
[65]
David L, Thakkar A, Mercado R, Engkvist O. J. Cheminformatics, 2020, 12(1): 56.

doi: 10.1186/s13321-020-00460-5    
[66]
Bian Y, Xie X Q. J. Chem. Inf. Model., 2021, 27(3): 1.
[67]
Xiong Z P, Wang D Y, Liu X H, Zhong F S, Wan X Z, Li X T, Li Z J, Luo X M, Chen K X, Jiang H L, Zheng M Y. J. Med. Chem., 2020, 63(16): 8749.

doi: 10.1021/acs.jmedchem.9b00959     URL    
[68]
Ren T, Zhang H D, Shi Y, Luo X M, Zhou S Q. J. Mol. Graph. Model., 2023, 119: 108401.

doi: 10.1016/j.jmgm.2022.108401     URL    
[69]
Liu Y W, Zhang R S, Li T F, Jiang J, Ma J, Wang P. J. Mol. Graph. Model., 2023, 118: 108344.

doi: 10.1016/j.jmgm.2022.108344     URL    
[70]
Vipul M, Karoline B, Rafiqul G, Venkat V. Fluid Phase Equilib., 2022, 561: 113531.

doi: 10.1016/j.fluid.2022.113531     URL    
[71]
Lv Q J, Chen G X, Zhao L, Zhong W H, Chen C Y C. Brief Bioinform., 2021, 22(6): bbab317.
[72]
Ji Z W, Shi R H, Lu J R, Li F, Yang Y. J. Chem. Inf. Model., 2022, 62(22): 5361.

doi: 10.1021/acs.jcim.2c00798     URL    
[73]
Vázquez J, LÓpez M, Gibert E, Herrero E, Luque F J. Molecules, 2020, 25(20): 4723.

doi: 10.3390/molecules25204723     URL    
[74]
Yuan W, Chen G, Chen C Y C. Briefings Bioinf., 2022, 23(1): bbab506.

doi: 10.1093/bib/bbab506     URL    
[75]
Shao K H, Zhang Y H, Wen Y Q, Zhang Z N, He S, Bo X C. Brief Bioinform., 2022, 23(3): bbac109.

doi: 10.1093/bib/bbac109     URL    
[76]
Li F, Zhang Z Q, Guan J H, Zhou S G. Bioinformatics, 2022, 38(14): 3582.

doi: 10.1093/bioinformatics/btac377     URL    
[77]
Gardner C R, Walsh C T, Almarsson Ö. Nat. Rev. Drug Discov., 2004, 3(11): 926.

pmid: 15520815
[78]
Tung H H. Org. Process Res. Dev., 2013, 17(3): 445.

doi: 10.1021/op3002323     URL    
[79]
Waknis V, Chu E, Schlam R, Sidorenko A, Badawy S, Yin S, Narang A S. Pharm. Res., 2014, 31(1): 160.
[80]
Dandekar P, Kuvadia Z B, Doherty M F. Annu. Rev. Mater. Res., 2013, 43: 359.

doi: 10.1146/matsci.2013.43.issue-1     URL    
[81]
Sun G X, Liu X T, Abramov Y A, Nilsson Lill S O, Chang C, Burger V, Broo A. Cryst. Growth Des., 2021, 21(4): 1972.

doi: 10.1021/acs.cgd.0c01266     URL    
[82]
Bhardwaj R M, Johnston A, Johnston B F, Florence A J. CrystEngComm, 2015, 17(23): 4272.

doi: 10.1039/C4CE02403F     URL    
[83]
Wicker J G P, Cooper R I. CrystEngComm, 2015, 17(9): 1927.

doi: 10.1039/C4CE01912A     URL    
[84]
Pillong M, Marx C, Piechon P, Wicker J G P, Cooper R I, Wagner T. CrystEngComm, 2017, 19(27): 3737.

doi: 10.1039/C7CE00738H     URL    
[85]
Yang M J, Dybeck E, Sun G X, Peng C W, Samas B, Burger V M, Zeng Q, Jin Y D, Bellucci M A, Liu Y, Zhang P Y, Ma J, Alan Jiang Y, Hancock B C, Wen S H, Wood G P F. Cryst. Growth Des., 2020, 20(8): 5211.

doi: 10.1021/acs.cgd.0c00422     URL    
[86]
Wilkinson M R, Martinez-Hernandez U, Huggon L K, Wilson C C, Castro Dominguez B. CrystEngComm, 2022, 24(43): 7545.

doi: 10.1039/D2CE00992G     URL    
[87]
Mater A C, Coote M L. J. Chem. Inf. Model., 2019, 59(6): 2545.

doi: 10.1021/acs.jcim.9b00266     pmid: 31194543
[88]
Wu Z Q, Ramsundar B, Feinberg E N, Gomes J, Geniesse C, Pappu A S, Leswing K, Pande V. Chem. Sci., 2018, 9(2): 513.

doi: 10.1039/C7SC02664A     URL    
[89]
Jiang J, Zhang R S, Yuan Y N, Li T F, Li G L, Zhao Z L, Yu Z X. J. Mol. Graph. Model., 2023, 121: 108454.

doi: 10.1016/j.jmgm.2023.108454     URL    
[90]
Li C Y, Feng J H, Liu S H, Yao J F. Comput. Intell. Neurosci., 2022, 2022: 8464452.
[91]
Maziarka Ł, Danel T, Mucha S, Rataj K, Tabor J, Jastrzębski S. arXiv preprint arXiv: 2002.08264, 2020.
[92]
Liu H, Huang Y B, Liu X J, Deng L. Brief. Bioinform., 2022, 23(5): bbac303.

doi: 10.1093/bib/bbac303     URL    
[93]
Liu C Y, Sun Y, Davis R, Cardona S T, Hu P Z. J. Cheminformatics, 2023, 15(1): 29.

doi: 10.1186/s13321-023-00698-9    
[94]
Hawkins P C D. J. Chem. Inf. Model., 2017, 57(8): 1747.

doi: 10.1021/acs.jcim.7b00221     pmid: 28682617
[95]
Zhou G M, Gao Z F, Wei Z W, Zheng H, Ke G L. arXiv preprint arXiv: 2302.07061, 2023.
[96]
Mansimov E, Mahmood O, Kang S, Cho K. Sci. Rep., 2019, 9: 20381.

doi: 10.1038/s41598-019-56773-5     pmid: 31892716
[97]
Xu M K, Luo S T, Bengio Y, Peng J, Tang J. arXiv preprint arXiv: 2102.10240, 2021.
[98]
Xu M K, Wang W J, Luo S T, Shi C, Bengio Y, Gomez-Bombarelli R, Tang J. International Conference on Machine Learning. PMLR, 2021: 11537-11547.
[99]
Zhu J H, Xia Y C, Liu C, Wu L J, Xie S F, Wang T, Wang Y S, Zhou W G, Qin T, Li H Q, Liu T Y. arXiv preprint arXiv: 2202.01356, 2022.
[100]
Xu M K, Yu L T, Song Y, Shi C, Ermon S, Tang J. arXiv preprint arXiv: 2203.02923, 2022.
[101]
Polishchuk P G, Madzhidov T I, Varnek A. J. Comput. Aided Mol. Des., 2013, 27(8): 675.

doi: 10.1007/s10822-013-9672-4     URL    
[102]
Kim S, Thiessen P A, Bolton E E, Chen J, Fu G, Gindulyte A, Han L Y, He J, He S Q, Shoemaker B A, Wang J Y, Yu B, Zhang J, Bryant S H. Nucleic Acids Res., 2016, 44(D1): D1202.

doi: 10.1093/nar/gkv951     URL    
[103]
Segler M H S, Kogej T, Tyrchan C, Waller M P. ACS Cent. Sci., 2018, 4(1): 120.

doi: 10.1021/acscentsci.7b00512     URL    
[104]
Yang Y X, Zhang R K, Li Z J, Mei L H, Wan S L, Ding H, Chen Z F, Xing J, Feng H J, Han J, Jiang H L, Zheng M Y, Luo C, Zhou B. J. Med. Chem., 2020, 63(3): 1337.

doi: 10.1021/acs.jmedchem.9b01721     URL    
[105]
Bagal V, Aggarwal R, Vinod P K, Priyakumar U D. chemRxiv preprint: 10.26434/chemrxiv.14561901.v1, 2021.
[106]
Bagal V, Aggarwal R, Vinod P K, Deva Priyakumar U. J. Chem. Inf. Model., 2022, 62(9): 2064.

doi: 10.1021/acs.jcim.1c00600     URL    
[107]
Wang W L, Wang Y, Zhao H G, Sciabola S. arXiv preprint arXiv: 2210.08749, 2022.
[108]
You J X, Liu B W, Ying R, Pande V, Leskovec J. arXiv preprint arXiv: 1806.02473, 2018.
[109]
Samanta B, De A, Jana G, Chattaraj P K, Ganguly N, Gomez-Rodriguez M. arXiv preprint arXiv: 1802.05283, 2018.
[110]
Li X S, Liu X, Lu L, Hua X S, Chi Y, Xia K L. Brief Bioinform., 2022, 23(4): bbac231.

doi: 10.1093/bib/bbac231     URL    
[1] 刘煦阳, 段潮舒, 蔡文生, 邵学广. 可解释深度学习在光谱和医学影像分析中的应用[J]. 化学进展, 2022, 34(12): 2561-2572.
[2] 曹军文, 张文强, 李一枫, 赵晨欢, 郑云, 于波. 中国制氢技术的发展现状[J]. 化学进展, 2021, 33(12): 2215-2244.
[3] 梅以成, 杨宝卫. 酰胺电子等排体在先导化合物优化中的应用[J]. 化学进展, 2016, 28(9): 1406-1416.
[4] 朱大元. 中药活性成分研究是中药现代化的重要组成部分[J]. 化学进展, 2009, 21(01): 24-29.
[5] 黄赣辉,邓少平. 人工智能味觉系统：概念、结构与方法[J]. 化学进展, 2006, 18(04): 494-500.