Original articles
Qianqian Zhao, Zhuyifan Ye, Yan Su, Defang Ouyang. Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques[J]. Acta Pharmaceutica Sinica B, 2019, 9(6): 1241-1252

Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques
Qianqian Zhao, Zhuyifan Ye, Yan Su, Defang Ouyang
State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences (ICMS), University of Macau, Macau, China
Most pharmaceutical formulation developments are complex and ideal formulations are generally obtained after extensive experimentation. Machine learning is increasingly advancing many aspects in modern society and has achieved significant success in multiple subjects. Current research demonstrated that machine learning can be adopted to build up high-accurate predictive models in drugs/cyclodextrins (CDs) systems. Molecular descriptors of compounds and experimental conditions were employed as inputs, while complexation free energy as outputs. Results showed that the light gradient boosting machine provided significantly improved predictive performance over random forest and deep learning. The mean absolute error was 1.38 kJ/mol and squared correlation coefficient was 0.86. The evaluation of relative importance of molecular descriptors further demonstrated the key factors affecting molecular interactions in drugs/CD systems. In the specific ketoprofen-CD systems, machine learning model showed better predictive performance than molecular modeling calculation, while molecular simulation could provide structural, dynamic and energetic information. The integration of machine learning and molecular simulation could produce synergistic effect for interpreting and predicting pharmaceutical formulations. In conclusion, the developed predictive models were able to quickly and accurately predict the solubilizing capacity of CD systems. Current research has taken an important step toward the application of machine learning in pharmaceutical formulation design.
Key words:    Machine learning    Deep learning    LightGBM    Random forest    Cyclodextrin    Binding free energy    Molecular modeling    Ketoprofen   
Received: 2019-01-06     Revised: 2019-04-10
DOI: 10.1016/j.apsb.2019.04.004
Funds: We thank Mr. Weifeng Peng for the technical support in the research about the machine learning. The research was supported by the University of Macau Research Grants (MYRG2016-00038-ICMS-QRCM and MYRG2016-00040-ICMS-QRCM, Macau, China). This work was performed in part at the High-Performance Computing Cluster (HPCC) which is supported by Information and Communication Technology Office (ICTO) of the University of Macau, China.
Corresponding author: Defang Ouyang     Email:defangouyang@umac.mo
Author description:
PDF(KB) Free
Qianqian Zhao
Zhuyifan Ye
Yan Su
Defang Ouyang

1. Campisi B, Chicco D, Vojnovic D, Phan-Tan-Luu R. Experimental design for a pharmaceutical formulation: optimisation and robustness. J Pharm Biomed Anal 1998;18:57-65.
2. Hussain AS, Shivanand P, Johnson RD. Application of neural computing in pharmaceutical product development: computer aided formulation design. Drug Dev Ind Pharm 1994;20:1739-52.
3. Ouyang D, Smith SC. Computational pharmaceutics: application of molecular modeling in drug delivery. 1st ed. Chichester: Wiley; 2015.
4. Light DW, Lexchin JR. Pharmaceutical research and development: what do we get for all that money?. BMJ 2012;345:1-5.
5. Santanilla AB, Regalado EL, Pereira T, Shevlin M, Bateman K, Campeau L-C, et al. Nanomole-scale high-throughput chemistry for the synthesis of complex molecules. Science 2015;347:49-53.
6. Lewis GA, Mathieu D, Phan-Tan-Luu R. Pharmaceutical experimental design. 1st ed. Boca Raton: Taylor; 1998.
7. Zhao Q, Zhang W, Wang R, Wang Y, Ouyang D. Research advances in molecular modeling in cyclodextrins. Curr Pharm Des 2017;23: 522-31.
8. Lipkowitz KB. Applications of computational chemistry to the study of cyclodextrins. Chem Rev 1998;98:1829-74.
9. Jordan MI, Mitchell TM. Machine learning: trends, perspectives, and prospects. Science 2015;349:255-60.
10. Ahneman DT, Estrada JG, Lin S, Dreher SD, Doyle AG. Predicting reaction performance in CeN cross-coupling using machine learning. Science 2018;360:186-90.
11. Ekins S. The next era: deep learning in pharmaceutical research. Pharm Res 2016;33:2594-603.
12. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521: 436-44.
13. Akbal-Delibas B, Farhoodi R, Pomplun M, Haspel N. Accurate refinement of docked protein complexes using evolutionary information and deep learning. J Bioinform Comput Biol 2016;14:1642002.
14. Cern A, Golbraikh A, Sedykh A, Tropsha A, Barenholz Y, Goldblum A. Quantitative structureeproperty relationship modeling of remote liposome loading of drugs. J Control Release 2012;160:147-57.
15. Han R, Yang Y, Li X, Ouyang D. Predicting oral disintegrating tablet formulations by neural network techniques. Asian J Pharm Sci 2018; 13:336-42.
16. Aliper A, Plis S, Artemov A, Ulloa A, Mamoshina P, Zhavoronkov A. Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data. Mol Pharm 2016;13:2524-30.
17. Yang Y, Ye Z, Su Y, Zhao Q, Li X, Ouyang D. Deep learning for in vitro prediction of pharmaceutical formulations. Acta Pharm Sin B 2019;9:177-85.
18. Akseli I, Xie J, Schultz L, Ladyzhynsky N, Bramante T, He X, et al. A practical framework toward prediction of breaking force and disintegration of tablet formulations using machine learning tools. J Pharm Sci 2017;106:234-47.
19. Loftsson T, Brewster ME. Cyclodextrins as functional excipients: methods to enhance complexation efficiency. J Pharm Sci 2012;101: 3019-32.
20. Xu Q, Wei C, Liu R, Gu S, Xu J. Quantitative structureeproperty relationship study of β-cyclodextrin complexation free energies of organic compounds. Chemometr Intell Lab Syst 2015;146:313-21.
21. Zhu Q, Guo T, Xia D, Li X, Zhu C, Li H, et al. Pluronic F127-modified liposome-containing tacrolimusecyclodextrin inclusion complexes: improved solubility, cellular uptake and intestinal penetration. J Pharm Pharmacol 2013;65:1107-17.
22. Merzlikine A, Abramov YA, Kowsz SJ, Thomas VH, Mano T. Development of machine learning models of β-cyclodextrin and sulfobutylether-β-cyclodextrin complexation free energies. Int J Pharm 2011;418:207-16.
23. Dodziuk H. Cyclodextrins and their complexes: chemistry, analytical methods, applications. 1st ed. Weinheim: Wiley; 2006.
24. Higuchi T. A phase solubility technique. Adv Anal Chem Instrum 1965;4:117-211.
25. Li S, Yuan L, Chen Y, Zhou W, Wang X. Studies on the inclusion complexes of daidzein with β-cyclodextrin and derivatives. Molecules 2017;22:1-18.
26. Tetko IV, Gasteiger J, Todeschini R, Mauri A, Livingstone D, Ertl P, et al. Virtual computational chemistry laboratoryedesign and description. J Comput Aided Mol Des 2005;19:453-63.
27. Meng Q, Ke G, Wang T, Chen W, Ye Q, Ma Z-M, et al. A communicationeefficient parallel algorithm for decision tree. Barcelona: NIPS; 2016. p. 1279-87.
28. WangD,ZhangY,ZhaoY.LightGBM:aneffectivemiRNAclassification method in breast cancer patients. Newark: ICCBB; 2017. p. 7-11.
29. Svetnik V, Liaw A, Tong C, Culberson JC, Sheridan RP, Feuston BP. Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci 2003;43: 1947-58.
30. Breiman L. Random forests. Mach Learn 2001;45:5-32.
31. Lv Y, Duan Y, Kang W, Li Z, Wang F-Y. Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 2015;16:865-73.
32. Wang J, Wolf RM, Caldwell JW, Kollman PA, Case DA. Development and testing of a general amber force field. J Comput Chem 2004;25: 1157-74.
33. Trott O, Olson AJ. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem 2010;31:455-61.
34. Solovev A, Solov’ev V. 3D molecular fragment descriptors for structureeproperty modeling: predicting the free energies for the complexation between antipodal guests and β-cyclodextrins. J Incl Phenom Macrocycl Chem 2017;89:167-75.
35. Szejtli J. Introduction and general overview of cyclodextrin chemistry. Chem Rev 1998;98:1743-54.
36. Klein CT, Polheim D, Viernstein H, Wolschann P. A method for predicting the free energies of complexation between β-cyclodextrin and guest molecules. J Incl Phenom Macrocycl Chem 2000;36:409-23.
37. Katritzky AR, Fara DC, Yang H, Karelson M, Suzuki T, Solov’ev VP, et al. Quantitative structureeproperty relationship modeling of bcyclodextrin complexation free energies. J Chem Inf Comput Sci 2004; 44:529-41.
38. Klein CT, Polheim D, Viernstein H, Wolschann P. Predicting the free energies of complexation between cyclodextrins and guest molecules: linear versus nonlinear models. Pharm Res 2000;17:358-65.
39. Suzuki T, Ishida M, Fabian WM. Classical QSAR and comparative molecular field analyses of the hosteguest interaction of organic molecules with cyclodextrins. J Comput Aided Mol Des 2000;14: 669-78.
40. Pérez-Garrido A, Helguera AM, Cordeiro MND, Escudero AG. QSPR modelling with the topological substructural molecular design approach: β-cyclodextrin complexation. J Pharm Sci 2009;98: 4557-76.
41. Faucci MT, Melani F, Mura P. Computer-aided molecular modeling techniques for predicting the stability of drugecyclodextrin inclusion complexes in aqueous solutions. Chem Phys Lett 2002;358:383-90.
42. Hawkins DM. The problem of overfitting. J Chem Inf Comput Sci 2004;44:1-12.
43. Devasari N, Dora CP, Singh C, Paidi SR, Kumar V, Sobhia ME, et al. Inclusion complex of erlotinib with sulfobutyl ether-β-cyclodextrin: preparation, characterization, in silico, in vitro and in vivo evaluation. Carbohydr Polym 2015;134:547-56.
44. Zhao Q, Miriyala N, Su Y, Chen W, Gao X, Shao L, et al. Computeraided formulation design for a highly soluble luteinecyclodextrin multiple-component delivery system. Mol Pharm 2018;15:1664-73.
45. Sherje AP, Kulkarni V, Murahari M, Nayak UY, Bhat P, Suvarna V, et al. Inclusion complexation of etodolac with hydroxypropyl-betacyclodextrin and auxiliary agents: formulation characterization and molecular modeling studies. Mol Pharm 2017;14:1231-42.
46. Connors KA. The stability of cyclodextrin complexes in solution. Chem Rev 1997;97:1325-58.
47. Hilschmann J, Kali G, Wenz G. Rotaxanation of polyisoprene to render it soluble in water. Macromolecules 2017;50:1312-8.
48. López CA, de Vries AH, Marrink SJ. Molecular mechanism of cyclodextrin mediated cholesterol extraction. PLoS Comput Biol 2011; 7:e1002020.
49. Brewster ME, Loftsson T. Cyclodextrins as pharmaceutical solubilizers. Adv Drug Deliv Rev 2007;59:645-66.
Similar articles:
1.Yuanzhi He, Wei Zhang, Tao Guo, Guoqing Zhang, Wei Qin, Liu Zhang, Caifen Wang, Weifeng Zhu, Ming Yang, Xiaoxiao Hu, Vikramjeet Singh, Li Wu, Ruxandra Gref, Jiwen Zhang.Drug nanoclusters formed in confined nano-cages of CD-MOF: dramatic enhancement of solubility and bioavailability of azilsartan[J]. Acta Pharmaceutica Sinica B, 2019,9(1): 97-106