2. Preface

The design of novel therapeutics is an inventive process which involves assimilation and analysis of available experimental data in conjunction with traditional and novel molecular modeling techniques. It can be an extremely complex, long, and expensive process. The application of artificial intelligence (AI) and machine learning (ML) approaches promises to revolutionize the design-make-test-analyze (DMTA) cycle, accelerating the drug design process and therefore reducing cost. Over the past few years, the field of AI/ML has moved from largely theoretical studies to real-world applications. Much of that explosive growth has been enabled by the availability of graphical processing units (GPUs) and advances in AI/ML algorithms, such as deep learning (DL). The use of neural networks in deep learning algorithms enables computers to imitate human intelligence by learning from data. The application of these approaches can be exploited across multiple aspects of drug design.

This book provides an overview of the state of the art in the development and applica- tion of AI/ML/DL methods in drug design. Topics covered include: how the application of these methods can be implemented to accelerate and revolutionise traditional drug design approaches such as structure- and ligand-based, augmented and multi-objective de novo drug design, SAR and big data analysis, prediction of binding/activity, ADMET, pharma- cokinetics and drug-target residence time, precision medicine and favorable chemical syn- thetic routes prediction. Also included is discussion of how broadly these approaches are applied and where they maximally impact productivity both today and, potentially, in the near future. The review of these topics will allow a diverse audience, including computa- tional and medicinal chemists, pharmacologists and drug designers, to navigate through the existing techniques and challenges and gain an enhanced appreciation of the new directions under development.

Oxfordshire, UK

Alexander Heifetz