Artificial Intelligence in Drug Research—A New Wave of Innovation in Drug Discovery
Puja Ghosh, K. M. Muhasina, Akey Krishna Swaroop, M. Esakkimuthukumar, Rana Pratap Singh, Ramveer Singh, Antony Justin, Jubie Selvaraj, Duraiswamy Basavan · 2024
Artificial intelligence plays a prominent role in the drug discovery process, from the development of synthetic medications to the discovery of lead phytochemicals from plants. Through a strong interaction between network pharmacology (NetP) and reverse pharmacology (RevP), conventional knowledge can be turned into innovative targets. Today, we can create a complete virtual universe dedicated to drug discovery, including in silico experiments to choose the most promising targets. This work shows how recent and traditional data interact with each other, including access to improved or novel chemistry, novel biology, greater success rates, and much more efficient and cost-effective discovery techniques. For instance, the selection of genes involved in the pathophysiology and therapy of chronic diseases can be identified using the DrugBank databases, PROTEOME, DISEASES, DisGeNE, enrichment analysis of KEGG pathways, and the RevP technique based on PASS. Gene Ontology analysis can be used to choose new prospective drug targets. Based on the examination of the databases with gene-disease relationships, we will be able to discover some known genes related to the disease and choose new targets for the treatment. This chapter will be credited with a thorough overview of network pharmacology based on recent studies, highlighting various active components, associated methods, tools, and databases, as well as utilization in cost-effective drug discovery and development.