APPLICATIONS OF GENERATIVE AI IN NOVERL DRUG DESIGN: FROM MOLECULE TO LABORATORY SIMULATION

The emergence of generative artificial intelligence (AI) has profoundly transformed the field of novel drug design, offering new approaches that extend from molecular creation to experimental validation. This review systematically explores how generative models such as Generative Adversarial Networks (GANs), Diffusion Models, and Large Language Models (LLMs) have enabled more efficient and precise drug discovery processes. We highlight their applications in molecule generation, property optimization, retrosynthesis prediction, and simulation of laboratory experiments. A critical analysis of current challenges — including data quality, computational costs, interpretability issues, and ethical considerations — is provided, with real-world case studies such as Exscientia’s AI-designed OCD drug illustrating practical successes and limitations. Furthermore, comparative tables present performance metrics of major AI models in drug discovery tasks. The review concludes by discussing future perspectives on integrating generative AI with robotics, high-throughput screening, and personalized medicine to revolutionize pharmaceutical research and development.