Applied Computer-Aided Drug Design: Models and Methods

FBDD & De Novo Drug Design

Author(s): Anwesha Das, Arijit Nandi, Vijeta Kumari and Mallika Alvala * .

Pp: 159-201 (43)

DOI: 10.2174/9789815179934123010008

* (Excluding Mailing and Handling)

Abstract

Fragment-based drug or lead discovery (FBDD or FBLD) refers to as one of the most significant approaches in the domain of current research in the pharmaceutical industry as well as academia. It offers a number of advantages compared to the conventional drug discovery approach, which include – 1) It needs the lesser size of chemical databases for the development of fragments, 2) A wide spectrum of biophysical methodologies can be utilized for the selection of the best fit fragments against a particular receptor, and 3) It is far more simpler, feasible, and scalable in terms of the application when compared to the classical high-throughput screening methods, making it more popular day by day. For a fragment to become a drug candidate, they are analyzed and evaluated on the basis of numerous strategies and criteria, which are thoroughly explained in this chapter. One important term in the field of FBDD is de novo drug design (DNDD), which means the design and development of new ligand molecules or drug candidates from scratch using a wide range of in silico approaches and algorithmic tools, among which AI-based platforms are gaining large attraction. A principle segment of AI includes DRL that finds numerous applicabilities in the DNDD sector, such as the discovery of novel inhibitors of BACE1 enzyme, identification and optimization of new antagonists of DDR1 kinase enzyme, and development and design of ligand molecules specific to target adenosine A2A, etc. In this book chapter, several aspects of both FBDD and DNDD are briefly discussed. 


Keywords: Artificial Intelligence, Autoencoder, Deep Learning, De Novo Drug Design, Drug Development, Drug Discovery, Evaluation Criteria, Expansion, Fragment-based Fragment to Lead, Hotspot analysis, In silico, Lead Optimization, Machine Learning, Molecular Docking, Optimization, Pharmacokinetic Properties, Property Prediction, Synthetic Accessibility.

Related Journals
Related Books
© 2024 Bentham Science Publishers | Privacy Policy