Drug delivery, serving as a pivotal link between pharmaceutical innovation and clinical implementation, faces numerous challenges in achieving optimal therapeutic outcomes. With the advancement of computational methodologies and technological tools, artificial intelligence (AI) has been increasingly applied in pharmaceutical sciences, ranging from target discovery to product management. In recent years, AI has been extensively used in drug delivery to tailor formulation design, enhance therapeutic efficacy, and reduce side effects. However, limitations in data quality and model interpretability frequently restrict AI's predictive performance and hinder its clinical applicability. This overview highlights the applications of AI in drug delivery, focusing on AI-designed drug formulations, AI-driven prediction of ADMET properties, and AI-assisted drug delivery devices, which support the development of precision medicine. Additionally, the translation challenges and future perspectives in this field are discussed.
Xinmin Yu, Xinyun Jiang, Tao Sheng et al.· ACS Nano· 0 citations
The Comprehensive VS Platform with AI Engine (CVSP-AIE) for drug discovery from compound libraries integrates three AI models: KarmaDock, a fast docking model that directly updates atomic coordinates; CarsiDock, an accurate docking model that predicts protein-ligand distances and reconstructs binding poses; and RTMScore, an accurate scoring model that learns residue-atom distance distributions for affinity prediction.