Artificial intelligence (AI) is becoming a revolutionary force in the field of pharma research and technology, radically reshaping drug discovery, development, and healthcare practices. This literature review provides a comprehensive overview of the application of AI across the pharma value chain, across areas such as target discovery, lead optimisation, clinical trials, personalised medicine, and manufacturing. Advances brought about through machine learning, deep learning, and natural language processing have enabled quicker and more precise predictions about drug-target interactions, toxicity profiles, and clinical activity. AI-based virtual screening and generative modeling have accelerated the detection and optimisation of lead candidates, whereas AI-boosted clinical trial design and participant stratification have resulted in superior success rates and minimised costs. AI has, in addition, propelled personalised medicine through the incorporation of multi-omics data and support in the identification of biomarkers. In pharma manufacturing, AI is a driving force in the optimisation of process operations, quality control, and predictive maintenance. Despite this, ethical concerns, regulatory hurdles, and the need for transparent and interpretable models remain key challenges. Future directions identify the future possibility of next-generation AI algorithms, quantum computing, and collaborative environments in driving precision medicine and responsible innovation. Successful pharma applications of AI require intersectoral collaborations, harmonized regulations, and a delicate balance between technological innovation and ethical considerations in providing widespread benefits for all stakeholders.

Abhishek Dukale, Harsha Kathpalia

AI; Pharma Value Chain; Virtual Screening; Generative Modeling; Predictive Maintenance.