The convergence of artificial intelligence (AI) and nanomedicine has transformed cancer vaccine development, particularly in optimizing RNA-loaded lipid nanoparticles (LNPs). Stability and targeted delivery are major obstacles to the clinical translation of promising RNA-LNP vaccines for cancer immunotherapy. This systematic review analyzes the AI’s impact on LNP engineering through machine learning-driven predictive models, generative adversarial networks (GANs) for novel lipid design, and neural network-enhanced biodistribution prediction. AI reduces the therapeutic development timeline through accelerated virtual screening of millions of lipid combinations, compared to conventional high-throughput screening. Furthermore, AI-optimized LNPs demonstrate improved tumor targeting. GAN-generated lipids show structural novelty while maintaining higher encapsulation efficiency; graph neural networks predict RNA-LNP binding affinity with high accuracy vs. experimental data; digital twins reduce lyophilization optimization from years to months; and federated learning models enable multi-institutional data sharing. We propose a framework to address key technical challenges: training data quality (min. 15,000 lipid structures), model interpretability (SHAP > 0.65), and regulatory compliance (21CFR Part 11). AI integration reduces manufacturing costs and makes personalized cancer vaccine affordable. Future directions need to prioritize quantum machine learning for stability prediction and edge computing for real-time formulation modifications.

The solubility of glibenclamide was evaluated in DMSO, NMP, 1,4-dioxane, PEG 400, Transcutol^® HP, water, and aqueous mixtures (T = 293.15~323.15 K). It was then recrystallized to solvate and compressed into tablets, of which 30-day stability and dissolution was studied. It had a higher solubility in 1,4-dioxane, DMSO, NMP (X_exp = 2.30 × 10³, 3.08 × 10⁴, 2.90 × 10⁴) at 323.15 K, its mixture (X_exp = 1.93 × 10³, 1.89 × 10⁴, 1.58 × 10⁴) at 298.15 K, and 1,4-dioxane (w) + water (1−w) mixture ratio of w = 0.8 (X_exp = 3.74 × 10³) at 323.15 K. Modified Apelblat (RMSD ≤ 0.519) and CNIBS/R-K model (RMSD ≤ 0.358) suggested good comparability with the experimental solubility. The minimum value of ΔG° vs ΔH° at 0.70 < x₂ < 0.80 suggested higher solubility at that molar concentration. Based on the solubility, it was recrystallized into the solvate, which was granulated and compressed into tablets. Among the studied solvates, the tablets of glibenclamide dioxane solvate had a higher initial (95.51%) and 30-day (93.74%) dissolution compared to glibenclamide reference (28.93%). There was no stability issue even after granulation, drying, or at pH 7.4. Thus, glibenclamide dioxane solvate could be an alternative form to improve the molecule’s properties.