The incorporation of artificial intelligence (AI) systems in drug discovery process augments pharmaceutical industry’s capabilities by enhancing efficiency along with accuracy of drug prediction. This review aims to summarize current state of the art concerning AI methodologies used for drug prediction, including important developments and future prospects. We analyze the roles of AI, including machine learning, in target identification, lead compound synthesis, and drug repurposing. By evaluating four seminal papers, we highlight the pervasive and distinctive features of AI that underscore transformative change. The most significant are still pending, such as data integrity, explainability, and ethical issues. Emerging technologies and interdisciplinary work that promise to create more value will be discussed in this paper. Based on the literature, we propose directions for research AI applications to increase the efficiency of innovative drug discovery.
Artificial Intelligence, Drug Discovery, Machine Learning, Deep Learning, DrugTarget Interaction, Drug Prediction, Neural Networks, Bioinformatics.