UM  > Institute of Chinese Medical Sciences
Affiliated with RCfalse
Status已發表Published
Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques
Zhao,Qianqian; Ye,Zhuyifan; Su,Yan; Ouyang,Defang
2019-11-01
Source PublicationActa Pharmaceutica Sinica B
ISSN2211-3835
Volume9Issue:6Pages:1241-1252
Abstract

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.

KeywordBinding Free Energy Cyclodextrin Deep Learning Ketoprofen Lightgbm Machine Learning Molecular Modeling Random Forest
DOI10.1016/j.apsb.2019.04.004
URLView the original
Indexed BySCIE
WOS Research AreaPharmacology & Pharmacy
WOS SubjectPharmacology & Pharmacy
WOS IDWOS:000500912700012
Scopus ID2-s2.0-85069591580
Fulltext Access
Citation statistics
Cited Times [WOS]:32   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionInstitute of Chinese Medical Sciences
Corresponding AuthorOuyang,Defang
AffiliationState Key Laboratory of Quality Research in Chinese Medicine,Institute of Chinese Medical Sciences (ICMS),University of Macau,Macau,China
First Author AffilicationInstitute of Chinese Medical Sciences
Corresponding Author AffilicationInstitute of Chinese Medical Sciences
Recommended Citation
GB/T 7714
Zhao,Qianqian,Ye,Zhuyifan,Su,Yan,et al. 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.
APA Zhao,Qianqian,Ye,Zhuyifan,Su,Yan,&Ouyang,Defang.(2019).Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques.Acta Pharmaceutica Sinica B,9(6),1241-1252.
MLA Zhao,Qianqian,et al."Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques".Acta Pharmaceutica Sinica B 9.6(2019):1241-1252.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao,Qianqian]'s Articles
[Ye,Zhuyifan]'s Articles
[Su,Yan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao,Qianqian]'s Articles
[Ye,Zhuyifan]'s Articles
[Su,Yan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao,Qianqian]'s Articles
[Ye,Zhuyifan]'s Articles
[Su,Yan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.