Citation: Dezhi Yang, Li Wang, Penghui Yuan, Qi An, Bin Su, Mingchao Yu, Ting Chen, Kun Hu, Li Zhang, Yang Lu, Guanhua Du. Cocrystal virtual screening based on the XGBoost machine learning model[J]. Chinese Chemical Letters, ;2023, 34(8): 107964. doi: 10.1016/j.cclet.2022.107964 shu

Cocrystal virtual screening based on the XGBoost machine learning model

Dezhi Yang ^{a, 1} ,
Li Wang ^{a, 1} ,
Penghui Yuan ^a ,
Qi An ^a ,
Bin Su ^b ,
Mingchao Yu ^a ,
Ting Chen ^a ,
Kun Hu ^a ,
Li Zhang ^{a, *,} ,
Yang Lu ^{a, *,} ,
Guanhua Du ^{c, *,}

a.
Beijing City Key Laboratory of Polymorphic Drugs, Center of Pharmaceutical Polymorphs, Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100050, China
b.
Shandong Soteria Pharmaceutical Co., Ltd., Laiwu 271100, China
c.
Beijing City Key Laboratory of Drug Target and Screening Research, National Center for Pharmaceutical Screening, Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100050, China

zhangl@imm.ac.cn

luy@imm.ac.cn

dugh@imm.ac.cn

Received Date: 19 July 2022
Revised Date: 18 August 2022
Accepted Date: 28 October 2022
Available Online: 31 October 2022

Figures(6)

Co-crystal formation can improve the physicochemical properties of a compound, thus enhancing its druggability. Therefore, artificial intelligence-based co-crystal virtual screening in the early stage of drug development has attracted extensive attention from researchers. However, the complexity of developing and applying algorithms hinders it wide application. This study presents a data-driven co-crystal prediction method based on the XGBoost machine learning model of the scikit-learn package. The simplified molecular input line entry specification (SMILES) information of two compounds is simply inputted to determine whether a co-crystal can be formed. The data set includs the co-crystal records presented in the Cambridge Structural Database (CSD) and the records of no co-crystal formation from extant literature and experiments. RDKit molecular descriptors are adopted as the features of a compound in the data set. The developed model shows excellent performance in the proposed co-crystal training and validation sets with high accuracy, sensitivity, and F1 score. The prediction success rate of the model exceeds 90%. The model therefore provides a simple and feasible scheme for designing and screening co-crystal drugs efficiently and accurately.
- Cocrystal,
- Machine learning,
- XGBoost,
- Molecular descriptor,
- Praziquantel,
- Nefiracetam
1. [1]
  S.H. Mithu, S.A. Ross, A.P. Hurt, et al., J. Drug Deliv. Sci. Technol. 63 (2021) 102508–102518. doi: 10.1016/j.jddst.2021.102508
2. [2]
  V.N. Saladi, B.R. Kammari, P.R. Mandad, et al., Cryst. Growth Des. 22 (2022) 1130–1142. doi: 10.1021/acs.cgd.1c01087
3. [3]
  D. Yang, H. Wang, Q. Liu, et al., Chin. Chem. Lett. 33 (2022) 3207–3211. doi: 10.1016/j.cclet.2021.10.012
4. [4]
  F. Martin, M. Pop, I. Kacso, et al., Mol. Pharm. 17 (2020) 919–932. doi: 10.1021/acs.molpharmaceut.9b01178
5. [5]
  L.S. Reddy, B.R. Bhogala, A. Nangia, CrystEngComm 7 (2005) 206–209. doi: 10.1039/b500829h
6. [6]
  A.J. Cruz-Cabeza, M. Lusi, H.P. Wheatcroft, et al., Faraday Discuss. 235 (2022) 446–466. doi: 10.1039/D1FD00081K
7. [7]
  C.M. Hansen, K. Skaarup, J. Paint Technol. 39 (1967) 511–520.
8. [8]
  A. Salem, S. Nagy, S. Pal, et al., Int. J. Pharm. 558 (2019) 319–327. doi: 10.1016/j.ijpharm.2019.01.007
9. [9]
  P.S. Panzade, G.R. Shendarkar, Curr. Drug Deliv. 14 (2017) 1097–1105.
10. [10]
  M.A. Mohammad, A. Alhalaweh, S.P. Velaga, Int. J. Pharm. 407 (2011) 63–71. doi: 10.1016/j.ijpharm.2011.01.030
11. [11]
  D. Musumeci, C.A. Hunter, R. Prohens, et al., Chem. Sci. 2 (2011) 883–890. doi: 10.1039/c0sc00555j
12. [12]
  Y.S. Mary, Y.S. Mary, Polycycl. Aromat. Compd. (2021) 1–12.
13. [13]
  R. Barbas, M. Font-Bardia, A. Paradkar, et al., Cryst. Growth Des. 18 (2018) 7618–7627. doi: 10.1021/acs.cgd.8b01413
14. [14]
  B.K. Mehta, S.S. Singh, S. Chaturvedi, et al., Cryst. Growth Des. 18 (2018) 1581–1592. doi: 10.1021/acs.cgd.7b01537
15. [15]
  H. Wu, Y. Sun, L. Sun, et al., Chin. Chem. Lett. 32 (2021) 3007–3010. doi: 10.1016/j.cclet.2021.03.045
16. [16]
  M.U. Faroque, A. Mehmood, Noureen, et al., J. Mol. Struct. 1214 (2020) 128183. doi: 10.1016/j.molstruc.2020.128183
17. [17]
  D. Yang, J. Cao, T. Heng, et al., Cryst. Growth Des. 21 (2021) 2292–2300. doi: 10.1021/acs.cgd.0c01706
18. [18]
  T. Heng, D. Yang, R. Wang, et al., ACS Omega 6 (2021) 15543–15550. doi: 10.1021/acsomega.1c01330
19. [19]
  M. Przybyek, T. Jeliński, J. Sabuszewska, et al., Cryst. Growth Des. 19 (2019) 3876–3887. doi: 10.1021/acs.cgd.9b00318
20. [20]
  B. Chabalenge, S. Korde, A.L. Kelly, et al., Cryst. Growth Des. 20 (2020) 4540–4549. doi: 10.1021/acs.cgd.0c00338
21. [21]
  J.J. Devogelaer, H. Meekes, P. Tinnemans, et al., Angew. Chem. Int. Ed. 59 (2020) 21711–21718. doi: 10.1002/anie.202009467
22. [22]
  A. Vriza, A.B. Canaj, R. Vismara, et al., Chem. Sci. 12 (2021) 1702–1719. doi: 10.1039/D0SC04263C
23. [23]
  M. Przybyłek, P. Cysewski, Cryst. Growth Des. 18 (2018) 3524–3534. doi: 10.1021/acs.cgd.8b00335
24. [24]
  Y. Jiang, Z. Yang, J. Guo, et al., Nat. Commun. 12 (2021) 1–14. doi: 10.1038/s41467-020-20314-w
25. [25]
  T. Chen, C. Guestrin, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
26. [26]
  J. Dong, D.S. Cao, H.Y. Miao, et al., J. Cheminform. 7 (2015) 1–10. doi: 10.1186/s13321-014-0049-z
27. [27]
  M.E. Mswahili, M.J. Lee, G.L. Martin, et al., Appl. Sci. 11 (2021) 1323. doi: 10.3390/app11031323
28. [28]
  D.S. Cao, Q.S. Xu, Q.N. Hu, et al., Bioinformatics 29 (2013) 1092–1094. doi: 10.1093/bioinformatics/btt105
29. [29]
  C. Steinbeck, Y. Han, S. Kuhn, et al., J. Chem. Inf. Comput. Sci. 43 (2003) 493–500. doi: 10.1021/ci025584y
30. [30]
  G. Landrum, URL http://www.rdkit.org/, https://github.com/rdkit/rdkit.149 (2016) 150.
31. [31]
  N.M. O'Boyle, C. Morley, G.R. Hutchison, Chem. Cent. J. 2 (2008) 1–7. doi: 10.1186/1752-153X-2-1
32. [32]
  University of Tübingen: BlueDesc. http://www.ra.cs.uni-tuebingen.de/software/bluedesc/.
33. [33]
  C.W. Yap, J. Comput. Chem. 32 (2011) 1466–1474. doi: 10.1002/jcc.21707
34. [34]
  F. Pedregosa, G. Varoquaux, A. Gramfort, et al., J. Mach. Learn. Res. 12 (2011) 2825–2830.
35. [35]
  K.B. Lipkowitz, D.B. Boyd, Reviews in Computational Chemistry, 2, Wiley-VCH, Hoboken, 1996, pp. 367–422. Volume.
36. [36]
  S.H. Bertz, J. Am. Chem. Soc. 103 (1981) 3599–3601. doi: 10.1021/ja00402a071
37. [37]
  J. Ellson, E. Gansner, L. Koutsofios, et al., in: Proceedings of the International Symposium on Graph Drawing, Springer, 2001, pp. 483–484.
38. [38]
  I.E. Kumar, S. Venkatasubramanian, C. Scheidegger, et al., in: Proceedings of the International Conference on Machine Learning, PMLR, 2020, pp. 5491–5500.
39. [39]
  P.T. LoVerde, Adv. Exp. Med. Biol. 1154 (2019) 45–70.
40. [40]
  D. Cioli, L. Pica-Mattoccia, Parasitol. Res. 90 (2003) S3–S9. doi: 10.1007/s00436-002-0751-z
41. [41]
  P.H.H. Schneeberger, J.T. Coulibaly, G. Panic, et al., Parasites Vectors 11 (2018) 1–12. doi: 10.1186/s13071-017-2573-y
42. [42]
  X. Buol, K. Robeyns, C. C Garrido, et al., Pharmaceutics 12 (2020) 653. doi: 10.3390/pharmaceutics12070653
43. [43]
  X. Buol, C. C Garrido, K. Robeyns, et al., Cryst. Growth Des. 20 (2020) 7979–7988. doi: 10.1021/acs.cgd.0c01236
44. [44]
  S. Yang, Q. Liu, W. Ji, et al., Molecules 27 (2022) 2022. doi: 10.3390/molecules27062022
45. [45]
  Q. Liu, D. Yang, T. Chen, et al., Cryst. Growth Des. 21 (2021) 6321–6331. doi: 10.1021/acs.cgd.1c00785
1. [1]
  Hongmei Yu , Baoxi Zhang , Meiju Liu , Cheng Xing , Guorong He , Li Zhang , Ningbo Gong , Yang Lu , Guanhua Du . Theoretical and experimental cocrystal screening of temozolomide with a series of phenolic acids, promising cocrystal coformers. Chinese Chemical Letters, 2024, 35(5): 109032-. doi: 10.1016/j.cclet.2023.109032
2. [2]
  Zixing Xu , Ruiying Chen , Chuanming Hao , Qionghong Xie , Chunhui Deng , Nianrong Sun . Peptidome data-driven comprehensive individualized monitoring of membranous nephropathy with machine learning. Chinese Chemical Letters, 2024, 35(5): 108975-. doi: 10.1016/j.cclet.2023.108975
3. [3]
  Yuting Wu , Haifeng Lv , Xiaojun Wu . Design of two-dimensional porous covalent organic framework semiconductors for visible-light-driven overall water splitting: A theoretical perspective. Chinese Journal of Structural Chemistry, 2024, 43(11): 100375-100375. doi: 10.1016/j.cjsc.2024.100375
4. [4]
  Chengde Wang , Liping Huang , Shanshan Wang , Lihao Wu , Yi Wang , Jun Dong . A distinction of gliomas at cellular and tissue level by surface-enhanced Raman scattering spectroscopy. Chinese Chemical Letters, 2024, 35(5): 109383-. doi: 10.1016/j.cclet.2023.109383
5. [5]
  Xiaochen Zhang , Fei Yu , Jie Ma . 多角度数理模拟在电容去离子中的前沿应用. Acta Physico-Chimica Sinica, 2024, 40(11): 2311026-. doi: 10.3866/PKU.WHXB202311026
6. [6]
  Fang-Yuan Chen , Wen-Chao Geng , Kang Cai , Dong-Sheng Guo . Molecular recognition of cyclophanes in water. Chinese Chemical Letters, 2024, 35(5): 109161-. doi: 10.1016/j.cclet.2023.109161
7. [7]
  Caihong Mao , Yanfeng He , Xiaohan Wang , Yan Cai , Xiaobo Hu . Synthesis and molecular recognition characteristics of a tetrapodal benzene cage. Chinese Chemical Letters, 2024, 35(8): 109362-. doi: 10.1016/j.cclet.2023.109362
8. [8]
  Cheng-Da Zhao , Huan Yao , Shi-Yao Li , Fangfang Du , Li-Li Wang , Liu-Pan Yang . Amide naphthotubes: Biomimetic macrocycles for selective molecular recognition. Chinese Chemical Letters, 2024, 35(4): 108879-. doi: 10.1016/j.cclet.2023.108879
9. [9]
  Zhimin Sun , Xin-Hui Guo , Yue Zhao , Qing-Yu Meng , Li-Juan Xing , He-Lue Sun . Dynamically switchable porphyrin-based molecular tweezer for on−off fullerene recognition. Chinese Chemical Letters, 2024, 35(6): 109162-. doi: 10.1016/j.cclet.2023.109162
10. [10]
  Li Lin , Song-Lin Tian , Zhen-Yu Hu , Yu Zhang , Li-Min Chang , Jia-Jun Wang , Wan-Qiang Liu , Qing-Shuang Wang , Fang Wang . Molecular crowding electrolytes for stabilizing Zn metal anode in rechargeable aqueous batteries. Chinese Chemical Letters, 2024, 35(7): 109802-. doi: 10.1016/j.cclet.2024.109802
11. [11]
  Minghao Hu , Tianci Xie , Yuqiang Hu , Longjie Li , Ting Wang , Tongbo Wu . Allosteric DNAzyme-based encoder for molecular information transfer. Chinese Chemical Letters, 2024, 35(7): 109232-. doi: 10.1016/j.cclet.2023.109232
12. [12]
  Chuan-Zhi Ni , Ruo-Ming Li , Fang-Qi Zhang , Qu-Ao-Wei Li , Yuan-Yuan Zhu , Jie Zeng , Shuang-Xi Gu . A chiral fluorescent probe for molecular recognition of basic amino acids in solutions and cells. Chinese Chemical Letters, 2024, 35(10): 109862-. doi: 10.1016/j.cclet.2024.109862
13. [13]
  Qihan Lin , Jiabin Xing , Yue-Yang Liu , Gang Wu , Shi-Jia Liu , Hui Wang , Wei Zhou , Zhan-Ting Li , Dan-Wei Zhang . taBOX: A water-soluble tetraanionic rectangular molecular container for conjugated molecules and taste masking for berberine and palmatine. Chinese Chemical Letters, 2024, 35(5): 109119-. doi: 10.1016/j.cclet.2023.109119
14. [14]
  Zhikang Wu , Guoyong Dai , Qi Li , Zheyu Wei , Shi Ru , Jianda Li , Hongli Jia , Dejin Zang , Mirjana Čolović , Yongge Wei . POV-based molecular catalysts for highly efficient esterification of alcohols with aldehydes as acylating agents. Chinese Chemical Letters, 2024, 35(8): 109061-. doi: 10.1016/j.cclet.2023.109061
15. [15]
  Jinyan Zhang , Fen Liu , Qian Jin , Xueyi Li , Qiong Zhan , Mu Chen , Sisi Wang , Zhenlong Wu , Wencai Ye , Lei Wang . Discovery of unusual phloroglucinol–triterpenoid adducts from Leptospermum scoparium and Xanthostemon chrysanthus by building blocks-based molecular networking. Chinese Chemical Letters, 2024, 35(6): 108881-. doi: 10.1016/j.cclet.2023.108881
16. [16]
  Zixi Zou , Jingyuan Wang , Yian Sun , Qian Wang , Da-Hui Qu . Controlling molecular assembly on time scale: Time-dependent multicolor fluorescence for information encryption. Chinese Chemical Letters, 2024, 35(7): 108972-. doi: 10.1016/j.cclet.2023.108972
17. [17]
  Ruonan Guo , Heng Zhang , Changsheng Guo , Ningqing Lv , Beidou Xi , Jian Xu . Degradation of neonicotinoids with different molecular structures in heterogeneous peroxymonosulfate activation system through different oxidation pathways. Chinese Chemical Letters, 2024, 35(9): 109413-. doi: 10.1016/j.cclet.2023.109413
18. [18]
  Wei-Yu Zhou , Zi-Han Xi , Ning-Ning Du , Li Ye , Ming-Hao Jiang , Jin-Le Hao , Bin Lin , Guo-Dong Yao , Xiao-Xiao Huang , Shao-Jiang Song . Rapid discovery of two unprecedented meroterpenoids from Daphne altaica Pall. using molecular networking integrated with MolNetEnhancer and Network Annotation Propagation. Chinese Chemical Letters, 2024, 35(8): 109030-. doi: 10.1016/j.cclet.2023.109030
19. [19]
  Hualei Xu , Manman Han , Haiqiang Liu , Liang Qin , Lulu Chen , Hao Hu , Ran Wu , Chenyu Yang , Hua Guo , Jinrong Li , Jinxiang Fu , Qichen Hao , Yijun Zhou , Jinchao Feng , Xiaodong Wang . 4-Nitrocatechol as a novel matrix for low-molecular-weight compounds in situ detection and imaging in biological tissues by MALDI-MSI. Chinese Chemical Letters, 2024, 35(6): 109095-. doi: 10.1016/j.cclet.2023.109095
20. [20]
  Keke Han , Wenjun Rao , Xiuli You , Haina Zhang , Xing Ye , Zhenhong Wei , Hu Cai . Two new high-temperature molecular ferroelectrics [1,5-3.2.2-Hdabcni]X (X = ClO₄⁻, ReO₄⁻). Chinese Chemical Letters, 2024, 35(6): 108809-. doi: 10.1016/j.cclet.2023.108809

Get Citation

PDF

XML

Metrics

PDF Downloads(2)
Abstract views(150)
HTML views(4)

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142