Integrated in silico formulation design of self-emulsifying drug delivery systems

Abstract

The drug formulation design of self-emulsifying drug delivery systems (SEDDS) often requires numerous experiments, which are time- and money-consuming. This research aimed to rationally design the SEDDS formulation by the integrated computational and experimental approaches. 4495 SEDDS formulation datasets were collected to predict the pseudo-ternary phase diagram by the machine learning methods. Random forest (RF) showed the best prediction performance with 91.3% for accuracy, 92.0% for sensitivity and 90.7% for 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 (CCD) was used to screen the best ratio of oil-surfactant-cosurfactant. Finally, molecular dynamic (MD) simulation was used to investigate the molecular interaction between excipients and drugs, which revealed the diffusion behavior in water and the role of cosurfactants. In conclusion, this research combined machine learning, central composite design, molecular modeling and experimental approaches for rational SEDDS formulation design. The integrated computer methodology can decrease traditional drug formulation design works and bring new ideas for future drug formulation design.

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

“…This approach is helpful in formulation prediction. Previous studies have successfully applied ML to predict the drug delivery systems, such as nanocrystals 36 , solid dispersion 37 , cyclodextrin complex 38 , and self-emulsifying drug delivery systems (SEDDS) 39 . In the case of SEDDS, the trained ML model predicted the molar composition of oils, surfactants, and cosurfactant where they can form self-emulsion, based on their physicochemical properties input, which helped to choose proper excipients for SEDDS formulation.…”

Improved oral bioavailability of poorly water-soluble vorinostat by self-microemulsifying drug delivery system

“…Different types of formulation techniques have been developed to enhance the oral bioavailability of poorly soluble drugs. These include solid dispersions, permeation enhancers, complexation with cyclodextrins, emulsions, liposomes, lipid-based formulations, micronization, and nanoparticles [3][4][5]. These approaches have a few challenges, such as the need for specialized equipment, complicated manufacturing processes, longer processing times, and regulatory complexity.…”

“…Fig 4. Comparison of the percentage in vitro drug release between pure drug (vorinostat powder) and vorinostat-loaded optimized SMEDDS formulation (F7)…”

Computational and Experimental Models of Type III Lipid-Based Formulations of Loratadine Containing Complex Nonionic Surfactants

“…Although the application of MD simulation formulation design to the study of LBFs is still quite limited (for recent reviews, see Boyd et al and Hasmukh et al), most published studies are restricted to simple formulations: oily blends that do not contain surfactants such as the Kolliphors or polysorbates, which are widely used in LBFs. One recent study reports simulations of self-emulsifying drug delivery systems containing poly­(ethylene glycol) and, additionally, papers investigate the behavior of LBFs in the presence of bile components. − More recently, a prediction of the pseudo-ternary phase diagram for self-emulsifying drug delivery system formulation using machine learning methods was carried out by Gao et al in 2021 with its experimental validation . In this study, MD simulations were performed to investigate the molecular interaction between excipients and drugs.…”

“…16−19 More recently, a prediction of the pseudoternary phase diagram for self-emulsifying drug delivery system formulation using machine learning methods was carried out by Gao et al in 2021 with its experimental validation. 27 In this study, MD simulations were performed to investigate the molecular interaction between excipients and drugs. Although this study modeled surfactant Kolliphor RH40 and the cosolvent Transcutol HP, the MD simulation component is not an extensive and systematic investigation.…”