Artificial intelligence and anti-cancer drugs: advancing discovery, personalization, and precision oncology

Artificial intelligence (AI) is changing the way we discover anticancer drugs. It tackles the problems of traditional methods, such as prolonged timelines for drug development, higher costs, and substantial inter-patient heterogeneity. This review explains how AI is applied throughout the cancer drug pipeline. This includes target identification, virtual screening of compounds, molecular docking, and predicting pharmacokinetics. We explore how machine learning models speed up hit-to-lead optimization, improve clinical trial design by stratifying patients, and allow for real-time toxicity monitoring. A key focus is on integrating AI with multi-omics data, including proteomics, genomics, transcriptomics, and metabolomics, to support precision oncology and personalized treatments. We address important validation challenges, like model interpretability, data quality, and regulatory issues that must be solved before AI can be widely used in clinics. By summarizing current evidence and targeting research gaps, this review offers a clear view of how AI is enhancing the discovery, personalization, and validation of anticancer treatments.