Affiliated with RCfalse
TitleIntegrated in Silico Formulation Design of Lipid-based Drug Delivery Systems
CreatorHaoshi Gao; Li HF(李海峰); Defang Ouyang
Date Issued2022-07
Degree GrantorUniversity of Macau
Place of ConferralUniversity of Macau

Lipid-based drug delivery system (LBDDS) has shown great potential in
pharmaceutical formulation. LBDDS is a dosage form with lipid as the main excipient, which increases the solubility and in vivo absorption of APIs, thus improving bioavailability. Growing evidence suggests that the molecular mechanism of LBDDS is still indefinite. Therefore, a novel method for formulations screening, the structure of formulations, and interactions between drug and excipient needed to be developed.
Machine learning (ML) methods were applied to predict the complex properties of
phospholipid complexes. Then, 341 drug-phospholipid complexes were collected from the literature. The datasets were trained by the LightGBM method. The berberine was used as the model drug to be prepared the complexes with phospholipids to validate the prediction modeling. Molecular dynamics (MD) simulation was used to investigate the molecular mechanism for self-aggregation of berberine in solution and BBRphospholipid complex complexation, which well explained the experimental results.
The integrated computational methodology, including ML, experiments, and MD
simulation, was utilized in the self-emulsifying drug delivery system (SEDDS) design. 4495 SEDDS formulation datasets were collected to predict the pseudo-ternary phase diagram by the ML methods. Random forest (RF) showed the best prediction performance with 91.3% accuracy, 92.0% sensitivity, and 90.7% specificity in 5-fold cross-validation. The pseudo-ternary phase diagrams of meloxicam SEDDS were experimentally developed to validate the RF prediction model and achieved an excellent prediction accuracy (89.51%). The central composite design was used to screen the best ratio of oil-surfactant-cosurfactant. Finally, MD simulation investigated the molecular interaction between excipients and drugs, which revealed the diffusion behavior in water and the role of cosurfactants.
The ML algorithm LightGBM was built to predict the knockdown efficiency of
siRNA-LNP in vitro and in vivo delivery and reached good accuracy with 80% and
78.89% in the validation set. Further siRNA experiments well validated the ML model. Moreover, MD simulation was utilized to investigate the molecular structure of siRNA-LNP.
In summary, three typical LBDDS formulation phospholipid complex, selfemulsifying drug delivery systems, and siRNA-LNPs were developed by integrated computational methodologies. This research is a crucial step in developing an LBDDS that integrates ML, MD simulation, and experimental methods.

Fulltext Access
Document TypeThesis
CollectionUniversity of Macau
Corresponding AuthorLi HF(李海峰); Defang Ouyang
AffiliationInstitute of Applied Physics and Materials Engineering, University of Macau, Macau, China
Recommended Citation
GB/T 7714
Haoshi Gao,Li HF,Defang Ouyang. Integrated in Silico Formulation Design of Lipid-based Drug Delivery Systems[D]. University of Macau. University of Macau,2022.
Files in This Item: Download All
File Name/Size Publications Version Access License
7 Finalized Thesis -(10110KB)Thesis 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Haoshi Gao]'s Articles
[Li HF(李海峰)]'s Articles
[Defang Ouyang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Haoshi Gao]'s Articles
[Li HF(李海峰)]'s Articles
[Defang Ouyang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Haoshi Gao]'s Articles
[Li HF(李海峰)]'s Articles
[Defang Ouyang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 7 Finalized Thesis - Haoshi GAO.pdf
Format: Adobe PDF
All comments (0)
No comment.

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