Revolutionizing Drug Discovery: A Systematic Review of AI and Machine Learning Application

Artificial intelligence (AI) and machine learning (ML) have transformed drug development, tackling issues like poor clinical trial success rates, high prices, and extended timescales. Target discovery, lead optimisation, drug repurposing, and toxicity prediction—among other aspects—of artificial intelligence and machine learning's influence across drug development phases. Examining more than 15 current investigations, the review emphasises new methods and constraints. Deep learning (DL) and reinforcement learning (RL) have raised target identification and virtual screening effectiveness, thus improving drug discovery efficiency. Companies like Sumitomo Dainippon Pharma and Insilico Medicine have shown how artificial intelligence can anticipate medicinal properties, speed lead drug discovery, and reuse already-existing medications. Platforms powered by artificial intelligence like Centaur Chemist and Atomwise have accelerated the search for treatments for illnesses like Ebola and schizophrenia. Still, artificial intelligence implementation must contend with issues like "black-box" constraints, model interpretability, and data quality. Furthermore covered in the research is how Explainable AI (XAI) could increase openness and confidence in AI-driven drug discovery methods.