Quantum machine learning for drug discovery: taxonomy, research challenges, and the road ahead

The recent pandemic outbreak has posed significant challenges for medical research, particularly in drug discovery. Machine learning (ML) has become increasingly prevalent in various stages of drug discovery, aiming to support the advancement of new drug research while reducing time and cost investments. Furthermore, the emergence of quantum computing and quantum machine learning (QML) represents a significant advancement in this field, offering the ability to tackle the complex processes involved in drug discovery. This review provides a comprehensive perspective, comparing advanced QML to classical ML in drug discovery applications including drug design, virtual screening, and ADMET (absorption, distribution, metabolism, excretion) and toxicity prediction. Additionally, we summarize the current applications of QML algorithms to real-world data sets utilized in clinical research and drug discovery.