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.

Lipid nanoparticle (LNP) is commonly used to deliver mRNA vaccines. Currently, LNP optimization primarily relies on screening ionizable lipids by traditional experiments which consumes intensive cost and time. Current study attempts to apply computational methods to accelerate the LNP development for mRNA vaccines. Firstly, 325 data samples of mRNA vaccine LNP formulations with IgG titer were collected. The machine learning algorithm, lightGBM, was used to build a prediction model with good performance (R ² > 0.87). More importantly, the critical substructures of ionizable lipids in LNPs were identified by the algorithm, which well agreed with published results. The animal experimental results showed that LNP using DLin-MC3-DMA (MC3) as ionizable lipid with an N/P ratio at 6:1 induced higher efficiency in mice than LNP with SM-102, which was consistent with the model prediction. Molecular dynamic modeling further investigated the molecular mechanism of LNPs used in the experiment. The result showed that the lipid molecules aggregated to form LNPs, and mRNA molecules twined around the LNPs. In summary, the machine learning predictive model for LNP-based mRNA vaccines was first developed, validated by experiments, and further integrated with molecular modeling. The prediction model can be used for virtual screening of LNP formulations in the future.

Current pharmaceutical formulation development still strongly relies on the traditional trial-and-error methods of pharmaceutical scientists. This approach is laborious, time-consuming and costly. Recently, deep learning has been widely applied in many challenging domains because of its important capability of automatic feature extraction. The aim of the present research is to apply deep learning methods to predict pharmaceutical formulations. In this paper, two types of dosage forms were chosen as model systems. Evaluation criteria suitable for pharmaceutics were applied to assess the performance of the models. Moreover, an automatic dataset selection algorithm was developed for selecting the representative data as validation and test datasets. Six machine learning methods were compared with deep learning. Results showed that the accuracies of both two deep neural networks were above 80% and higher than other machine learning models; the latter showed good prediction of pharmaceutical formulations. In summary, deep learning employing an automatic data splitting algorithm and the evaluation criteria suitable for pharmaceutical formulation data was developed for the prediction of pharmaceutical formulations for the first time. The cross-disciplinary integration of pharmaceutics and artificial intelligence may shift the paradigm of pharmaceutical research from experience-dependent studies to data-driven methodologies.

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.