Quantum intelligence in drug discovery: Advancing insights with quantum machine learning

Abstract

Over recent decades, the pharmaceutical industry has undergone a major transformation with the integration of machine learning (ML) across various stages of the drug discovery pipeline. Although ML has accelerated molecular screening and drug development, it faces critical challenges, such as dependence on large, high-quality datasets, limited interpretability, and increased computational complexity for large systems. Quantum machine learning (QML) has emerged as a powerful alternative, combining quantum computing with artificial intelligence to address these limitations. By harnessing the ability of quantum systems to process high-dimensional data efficiently, QML promises improved accuracy and scalability. This review explores the contributions of QML to drug discovery, focusing on molecular property prediction, docking simulations, de novo design, limitations, ethics, and future directions.