Journal of Pharmaceutical Research International

The drug discovery process has been time-consuming and expensive in the past. Also, previous drugs were not formulated as well as the drugs being expected and developed using AI and ML technologies. This article shall elaborate on the stages of drug discovery and development where AI and ML modelling have revolutionized the traditional methods of drug development. AI, in the broader context, has been taken up and implemented at each stage of drug discovery, from target identification and validation to hit finding and the progression from hit to lead optimization, with a vital role in streamlining the formerly time-consuming process of drug screening. Several methods based on machine learning are being used to predict drug targets, predict the structures of drug targets, predict binding sites, perform ligand-based similarity searches, design ligands with certain desired properties de novo, develop scoring functions for molecular docking, build Quantitative structure-activity relationship (QSAR) models for the prediction of biological activity, and predict the pharmacokinetic and pharmacodynamic properties of ligands.