Developments in Computer-Aided Drug Design for Antiviral Research

Computer-aided drug design (CADD) is a powerful tool for the rational design of new antivirals, allowing for the optimization of drug candidates based on their predicted interactions with target proteins and their expected behavior in the body. In antiviral research, CADD has greatly benefited from machine learning (ML). Large datasets of chemical compounds and their corresponding biological activity can be analyzed using ML algorithms, which enables researchers to forecast a compound’s antiviral potential. As a result, the process of discovering new drugs can be substantially accelerated. This enables scientists to select which compounds to test and improve further. In order to maximize the likelihood that a possible antiviral medication would be successful in preclinical and clinical studies, ML can also be used to optimize its physicochemical properties, such as its solubility and stability. The way we identify and create new antiviral treatments may be completely changed by the use of machine learning in the field of antiviral design. In this chapter, we outline various machine learning tools that are being used in the field of computer-aided drug design with specific examples.