Towards safer and efficient formulations: Machine learning approaches to predict drug-excipient compatibility.

Predicting drug-excipient compatibility is a critical aspect of pharmaceutical formulation design. In this study, we introduced an innovative approach that leverages machine learning techniques to improve the accuracy of drug-excipient compatibility predictions. Mol2vec and 2D molecular descriptors combined with the stacking technique were used to improve the performance of the model.

Development of taste-masking microcapsules containing azithromycin by fluid bed coating for powder for suspension and evaluation.

This research aims to develop bitter taste-masking microcapsules containing azithromycin (AZI) by a simpler and familiar method, fluid-bed coating technology, in comparison with Zithromax. Cores of microcapsules, AZI microparticles, were prepared by fluid-bed granulation, then taste-masking polymer was covered on by fluid-bed coating technique. Eudragit L100, Eudragit RL100, and ethyl cellulose in single and combined with Eudragit L100 and Eudragit E100 were used as taste-masking polymers.