Current advancement in AI-integrated drug discovery: Methods and applications

Abstract

Artificial intelligence (AI) has grown in prominence over the decade and continues to advance frighteningly. With additional research in the computer hardware field, the accuracy and precision of AI models will increase exponentially. The interdisciplinary nature of AI expands the possibility of application in every field of study. The use of AI in human healthcare has also been on the rise, with the involvement of interactive models. Since drug development is a prominent part of the field, there are bound to be AI models capable of improving parameters and predictions for various techniques. This review explores the recent developments in the applications of AI in the scope of drug discovery. Focusing on the workflow of a standard interdisciplinary drug discovery approach, this review aims to provide information about various AI-enabled tools in the field. We begin with an in-depth overview of the different AI models and architectures frequently employed in the field. Next, we reviewed the applications of AI in drug discovery, discussing the state-of-the-art models and tools employed for topics such as data analysis, functional annotation, virtual screening, clinical trial optimization, and much more. Discussing the prospects, challenges, and limitations that the field faces, this review attempts to encompass the essence of AI-based drug discovery. We anticipate this review will aid the innovation of more brilliant AI tools for various subtopics of the drug discovery and development field.