Ai-Assisted Drug Design

Erscheinungsjahr 2026
ISBN: 978-981-958363-8
Verlag: Springer Nature Singapore

Buch, Englisch, 386 Seiten, Format (B × H): 155 mm x 235 mm

Drug discovery is a data-driven, knowledge-intensive, and labor-intensive field. Artificial intelligence (AI) has emerged as a powerful technology, capable of processing vast datasets and uncovering complex interactions. AI's application in pharmaceutical research and development (R&D) dates back to 1964, when Hansch introduced quantitative structure-activity relationships (QSAR). Since 2012, AI-assisted drug design has rapidly advanced with the rise of deep learning, now widely used across drug development stages, including target discovery, compound screening, lead optimization, drug-likeness analysis, and peptide design. AI-assisted drug design is increasingly seen as a key strategy in pharmaceutical R&D.

Despite its potential, applying AI in pharmaceutical R&D requires integrating expertise from AI and drug research, posing challenges for newcomers due to its interdisciplinary nature. To address these challenges and meet the growing demand for educational resources, the authors wrote this book.

The book consists of 18 chapters, organized into three sections:

1. Basic Methods of Artificial Intelligence — This section covers core AI concepts, focusing on machine learning and deep learning methods such as support vector machines, decision trees, ensemble learning, random forests, k-nearest neighbors, and neural networks. The goal is to provide readers with foundational AI knowledge.
2. Programming Development Environment — This section introduces Python and focuses on practical applications in pharmaceutical R&D. Readers will learn to set up deep learning frameworks like TensorFlow and PyTorch for AI-driven drug research.
3. Fundamentals of AI-Assisted Drug Design — This section explores drug and protein databases, QSAR models, drug screening methods, molecular feature extraction, property prediction, and protein-ligand binding predictions, with practical examples illustrating AI's role in drug design.

Zielgruppe

Research

Autoren/Hrsg.

Chang, Shan

Xie, Liangxu

Fachgebiete

• Technische Wissenschaften Technik Allgemein Computeranwendungen in der Technik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik EDV | Informatik Angewandte Informatik Computeranwendungen in Wissenschaft & Technologie

Inhaltsverzeichnis

"Chapter 1: Introduction".- "Chapter 2: Machine Learning in Drug Design".- "Chapter 3: Support Vector Machines".- "Chapter 4: Decision Trees".- "Chapter 5: Random Forests".- "Chapter 6: k-Nearest Neighbors Algorithm".- "Chapter 7: Neural Networks".- "Chapter 8: Convolutional Neural Networks".- "Chapter 9: Generative Deep Learning".- "Chapter 10: Basics of Python Programming and Setting Up the Computing Environment".- "Chapter 11: Introduction to Common Databases".- "Chapter 12: Molecular Docking".- "Chapter 13: New Applications of QSAR in Deep Learning".- "Chapter 14: Feature Engineering of Molecules".- "Chapter 15: Predicting Drug Molecular Properties".- "Chapter 16: De Novo Molecular Generation".- "Chapter 17: Protein Structure Prediction".- "Chapter 18: Deep Learning Prediction of Protein-Molecule Binding".

Über Autor(innen)

Shan Chang currently serves as the Director of the Institute of Bioinformatics and Pharmaceutical Engineering. He was the Postdoctoral Fellow at the University of Missouri, Columbia, and promoted to be the Professor at Jiangsu University of Technology. His main research areas include AI-assisted drug design, machine learning, and high-performance computing. In recent years, he has published over 120 academic papers in international journals, with more than 100 indexed by SCI. His work has been cited over 1,700 times according to Google Scholar with an H-index of 22. He holds 14 software copyrights and has applied for 35 invention patents (9 granted). He has published 3 monographs and 1 translated book. He is leading one General Project of the National Natural Science Foundation and completed two projects funded by the National Natural Science Foundation, as well as one sub-project of the NSFC-Guangdong Joint Fund, along with more than 10 other provincial and corporate projects. He has participated multiple times in the international challenge named Critical Assessment of Protein Structure Prediction (CASP), consistently ranking among the top internationally. Notably, his group (CoDock) ranked No. 1 in the ligand prediction category of the CASP15 challenge held in 2022.

Liangxu Xie is currently an Associate Professor at Jiangsu University of Technology. He obtained his PhD degree from the University of Hong Kong. He has conducted research at the University of Hong Kong and the Hong Kong University of Science and Technology as Research Assistant and Research Associate. He is a member of the Chinese Chemical Society and a lifetime member of the Chinese Association for Artificial Intelligence. He has been selected for “Mass Innovation and Entrepreneurship” (Shuang Chuang) program in Jiangsu Province, the Youth Talent Support Program in Changzhou, and the Doctoral Innovation Alliance of the Jiangsu-Israel Research Institute. He serves as a section editor for Current Topics in Medicinal Chemistry. His research focuses on AI-assisted drug screening and exploring the molecular mechanisms of important biological processes. In recent years, he has published over 40 SCI papers and participated in winning the Third Prize for Science and Technology Progress Award of Jiangsu Province. He has also led projects funded by the National Natural Science Foundation and the Jiangsu Provincial Natural Science Foundation.