Artificial Intelligence in Computer- Aided Drug Design: A Comprehensive Review

Drug discovery and design are difficult, expensive, and time-consuming procedures. Drug discovery in the past was based on trial and error. Traditional drug development methods often involve screening chemicals that are either naturally occurring or created in laboratories at random. However, there are a number of serious problems with this strategy, such as expensive and time-consuming design cycles. After the 20th century, modern techniques are applied. The goal of drug design is to identify a chemical compound that can physically and chemically fit into a certain protein target cavity. Computer engineering and software development advances have improved rational drug design to save time and money, making computer-aided drug design (CADD) a viable substitute. CADD applications are widely used at various stages of design and discovery, and ligand-based approaches are widely recognized as powerful and successful techniques in drug development and discovery. Several CADD approaches are evaluated as promising techniques in all structure-based drug design. It still takes years for a treatment to be discovered, despite the amazing use of CADD; therefore, new methods to improve the design and discovery processes should be put into place. Machine learning, deep learning, and artificial intelligence are given special consideration in order to increase the efficacy and efficiency of creating new pharmaceutical medicines.