Utilization of machine learning approach for production of optimized PLGA nanoparticles for drug delivery applications

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 14, 2025

This study investigates utilization of machine learning for the regression task predicting size PLGA (Poly lactic-co-glycolic acid) nanoparticles. Various inputs including category and numeric were considered building model to predict optimum conditions preparation nanosized particles drug delivery applications. The proposed methodology employs Leave-One-Out (LOO) categorical feature transformation, Local Outlier Factor (LOF) outlier detection, Bat Optimization Algorithm (BA) hyperparameter optimization. A comparative analysis compares K-Nearest Neighbors (KNN), ensemble methods such as Bagging Adaptive Boosting (AdaBoost), novel Small-Size Bat-Optimized KNN Regression (SBNNR) model, which uses generative adversarial networks deep extraction improve performance on sparse datasets. Results demonstrate that ADA-KNN outperforms other models Particle Size prediction with a test R² 0.94385, while SBNNR achieves superior accuracy in Zeta Potential 0.97674. These findings underscore efficacy combining advanced preprocessing, optimization, techniques robust modeling. contributions this work include development validation BA's optimization capabilities, comprehensive evaluation methods. method provides reliable framework using material science applications, particularly nanoparticle characterization.

Язык: Английский

Advances in Nanoparticles in Targeted Drug Delivery- A Review

Results in Surfaces and Interfaces, Год журнала: 2025, Номер unknown, С. 100529 - 100529

Опубликована: Апрель 1, 2025

Язык: Английский