A REVIEW OF THE INTEGRATION OF AI IN MODERN DRUG DISCOVERY AND DEVELOPMENT

Dr. T. Vinciya* and P. Senthil Kumar

Drug discovery and development is going through a revolution with artificial intelligence (AI) which gives faster and cheaper solutions than traditional methods. AI-driven active learning is becoming more and more common in drug development as it finds important information inside large chemical spaces even with very little labeled data. By screening compounds and improving lead molecules, AI can find potential drug candidates by reducing the time and resources needed to get from hit to lead. CADD has greatly impacted this field. Another advantage of using CADD with AI, ML, and DL to manage large biological data is the time and cost of drug development has decreased. Deep learning and AI are necessary to organize and evaluate the data generated by combinatorial chemistry. This helps de novo, virtual screening, and structure-based drug design. Because active learning can find useful information even with minimal labelled data it’s a great approach for drug development. This approach addresses the challenges posed by data in the broad realm of chemistry. The article delves into the role of learning in drug development across stages such as predicting compound interactions, conducting screenings, designing and optimizing molecules, and forecasting properties. It also explores the obstacles and future potential of learning in drug development. Notably, structure-based drug design is gaining importance as a method to accelerate and streamline lead discovery compared to traditional methods. Moreover, artificial intelligence and deep learning technologies are employed to analyze and organize data sets in the drug discovery domain. Additionally, advanced machine learning tools driven by AI significantly influence the drug discovery process including areas of medicinal chemistry.