دانلود کتاب کشف و طراحی دارو به کمک رایانه

For several decades, Computer-Aided Drug Design (CADD) and Machine Learning have been applied in drug discovery projects, and now there are several drugs in the market developed with the aid of such techniques. Computational techniques, methods, and concepts such as quantitative structure-activity relationships (QSAR), molecular docking, molecular dynamics, free-energy perturbation and quantum mechanics, and virtual screening of compounds databases, among several others, have been cornerstones in several drug discovery projects. These methods have now been boosted by data-driven artificial intelligence (AI) methods. Although it is anticipated that drugs cannot be designed and developed solely by computers, novel computational approaches are emerging, and existing techniques continue to evolve rapidly. Therefore, the scientific community must keep up to date with the most recent developments and practical applications. The CADD research field comprises several different knowledge areas, and often, researchers are only familiar or experienced with a small fraction of them. Indeed, pharmaceutical industries and large academic groups rely on a broad range of professionals, including chemists, biologists, pharmacists, computer scientists, and other related ones. In this sense, being an expert in every CADD approach is challenging. Furthermore, well-established methods are constantly revisited, and novel approaches and modifications are introduced, such as machine-learning- based scoring functions for molecular docking. The book “Computer-Aided and Machine Learning-Driven Drug Design” dis- cusses theoretical and successful practical applications of computational techniques. The book, written by authors from diverse countries and geographical regions, is expected to serve the scientific community by providing an overview and solid concepts related to chemoinformatic, bioinformatics, and molecular modeling in the context of AI; key considerations at the interface between computational and the required experimental validation; and practical and recent applications of such technique to real-world drug discovery campaigns. The book can be used as a textbook for courses that include or are focused on CADD and as reference material for researchers and practitioners of current CADD and machine learning. The editor and all contributor authors are very grateful to the Springer editorial staff for their support in developing and publishing the book