AI and ML in drug discovery: a comprehensive review related to virtual screening, molecular modelling & accelerating clinical trials.

Abstract

This chapter examines how Artificial Intelligence (AI) and Machine Learning (ML) have been transforming traditional drug discovery between 2019 and 2025, addressing the high costs, long timelines, and low success rates associated with this process. Highlighting recent advancements in AI/ML across the entire drug discovery pipeline, from target identification to clinical development. It explores various AI techniques, including deep learning, graph neural networks, and transformers, and their applications in key areas such as Target identification, Lead discovery, Hit optimization, and preclinical safety assessment. A comparative analysis of the advantages, limitations, and practical challenges of different AI approaches. It emphasizes crucial factors for successful implementation, including data quality, model validation, and ethical considerations. In this chapter, we study how we synthesize current applications, identify ongoing gaps (especially in data accessibility, interpretability, and clinical translation), and propose future directions. The ultimate goal is to unlock AI's full potential to create safer, more effective, and more accessible medicines by emphasizing transparent methodologies, robust validation, and ethical frameworks for responsible AI integration into pharmaceutical research and development.  Drug-target identification: AI can pinpoint potential drug targets more effectively by analysing complex datasets. Through virtual screening, we studied molecular properties and compound analysis, Drug development and quality assurance, and Drug toxicity assessment. The integration of AI and ML offers a promising strategy to overcome the complexities of the pharmaceutical industry, accelerating the entire process from research to clinical trials and ultimately bringing safer, more effective medicines to patients faster and at a lower cost. While facing challenges such as data quality, interpretability of models, and regulatory hurdles, the collaborative efforts and continuous advancements in AI technology promise to unlock its full potential in revolutionizing pharmaceutical research and development. CADD has significantly impacted this area of research. Further, the combination of CADD with Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) technologies to handle enormous amounts of biological data has reduced the time and cost associated with the drug development process. This review will discuss how CADD, AI, ML, and DL approaches help identify drug candidates and various other steps of the drug discovery process. It will also provide a detailed overview of the different in silico tools used and how these approaches interact