Artificial Intelligence for Drug Design

The use of artificial intelligence in drug research and development plays an increasingly important role in evaluating the interaction between biological targets and drug molecules, optimizing drug design paths, etc., helping to accelerate the process of drug research and development and reduce the cost of research and development risks.

This book is aimed at researchers or technicians who are interested in cross-research in the field of life sciences and drug research and development. The content is mainly divided into four parts: 1. Fundamentals of artificial intelligence algorithms; 2. Data foundation and representation; 3. Artificial intelligence and drug design; 4. Program code. It systematically introduces artificial intelligence algorithms, focuses on key data resources in biomedicine, especially some data mining methods based on artificial intelligence. With the drug research and development process as the main line, for each key step where the artificial intelligence algorithm is integrated, it first introduces the basic principles and existing challenges of drug design, and then systematically reviews the progress of artificial intelligence (AI) algorithms in this research direction. Introduce existing cross-application examples.

Honglin Li, from Innovation Center for AI and Drug Discovery, East China Normal University. Dr. Honglin Li has dedicated significant time to addressing challenging, cutting-edge scientific problems in drug design and target discovery. He has developed more than ten drug design methods and software primarily focusing on methodological development and applied them to discover new targets and design promising compounds. The representative drug design methods and software suites include the graphical drug design software eSHAFTS and ePharmer, pioneered in China. Target discovery methods like PharmMapper and ChemMapper are popular, boasting a global user base of over 35,000. He has also developed several AI-based drug design methods, such as disease-target knowledge graph e-TSN, near-drug space exploration method CIRS, macrocyclic drug design method MacFormer, and online drug design platform iDrug. He has published over 210 papers in prestigious journals such as Nat. Commun., NAR, Adv. Sci., PNAS, STTT, Engineering, JMC, and other professional publications, accumulating more than 8,000 citations; filed applications for more than 118 invention patents (including 54 domestic authorizations and 13 foreign authorizations) and 15 software copyrights. He has transferred six drug candidates to pharmaceutical companies for pre-clinical research, and three of these drugs progressed to clinical trials.

Mingyue Zheng, from Shanghai Institute of Materia Medica, Chinese Academy of Sciences. Dr. Mingyue Zheng received his Ph.D. degree from Shanghai Institute of Materia Medica (SIMM), Chinese Acadamy of Sciences in 2006, majoring in computational drug design. He currently works as a Professor in State Key Laboratory of Drug Research at SIMM, where he focuses on artificial intelligence approaches for rational drug design and discovery. His research interests also encompass multidisciplinary studies in the fields of medicinal chemistry, cheminformatics, and computational biology. He has been engaged in the machine-learning based methodology development around the discovery and structural optimization of lead compounds, the assessment of drug ADME/T properties, as well as the application of the methods in practical drug design and discovery process. Till now, he has published more than 200 papers in Nat Comput Sci, Immunity, Nat Commun, Trends Pharmacol Sci, Circ Res, Protein & Cell, Nucleic Acids Res, etc.