Artificial Intelligence in Drug Formulation and Delivery: Benefits, Trends, and Future Perspectives | ||||
| Archives of Pharmaceutical Sciences Ain Shams University | ||||
| Article 13, Volume 9, Issue 1, June 2025, Page 209-222 PDF (760.78 K) | ||||
| Document Type: Editorial | ||||
| DOI: 10.21608/aps.2025.365472.1217 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Anupama Singh   1; Vikas A. Saharan 2; Rania M. Hathout 3
| ||||
| 1School of Pharmaceutical Sciences and Technology, Sardar Bhagwan Singh University, Balawala, Dehradun 248001, India | ||||
| 2Department of Pharmaceutical Technology (Formulations), National Institute of Pharmaceutical Education and Research (NIPER) Guwahati, Sila Katamur (Halugurisuk), P.O. Changsari 781101, District Kamrup, Assam, India | ||||
| 3Department of Pharmaceutics and Industrial Pharmacy, Faculty of Pharmacy, Ain Shams University, Cairo, 11566, Egypt | ||||
| Abstract | ||||
| Computational optimization and its integration with AI in formulation optimization, predictive modeling, and drug-excipient interactions have significantly reduced the conventional trial-and-error approaches. This editorial highlights the integration of artificial intelligence (AI) in optimization and predictive analysis in formulation development and delivery. Some other advancements such as those emerging at the interface of human-AI interaction are also briefly discussed with a focus on advancements in the last five years. Extensive data from the characterization of early formulations like cocrystals, solid dispersions, and drug-excipient complexes have led to prediction tools with the help of supervised machine learning algorithms. Robotic innovations have led to the automation of manufacturing operations which are predictive, self-optimizing, and self-correcting. Ligand-receptor interactions are now analyzed and predicted more effectively with the help of AI algorithms bringing rationality to innovations in drug delivery. All forms of AI like machine learning and deep learning are contributing at each step of the pharmaceutical drug discovery and development pathway. | ||||
| Keywords | ||||
| DoE; optimization; artificial intelligence; machine learning; preformulation; drug product; simulation; docking; pharmacokinetics | ||||
|
Statistics Article View: 714 PDF Download: 402 |
||||
