Artificial Intelligence and Multi-Omics for Anticancer Drug Development and Repurposing

The escalating complexity and financial burden associated with de novo drug development necessitate a transition toward more efficient therapeutic discovery models. Conventional pipelines often span over fifteen years with costs exceeding two billion dollars, yet they remain plagued by a ninety percent failure rate in clinical phases. Drug repurposing offers a viable alternative by identifying novel oncological applications for existing, safety-validated compounds, thereby bypassing early-stage toxicological bottlenecks. The integration of artificial intelligence (AI) has emerged as a transformative force in this domain, enabling the high-throughput analysis of vast chemical libraries and multi-omics biological datasets. Researchers can now predict drug-target interactions, model therapeutic outcomes, and prioritize lead candidates with unprecedented precision by utilizing sophisticated machine learning, deep neural networks, and network-based algorithms. Modern computational strategies leverage genomic, proteomic, and metabolic signatures to map the intricate interactions between pharmacological agents and the neoplastic microenvironment. This review provides the current state of AI-driven repositioning, emphasizing the transition from target-centered to disease-oriented models. Case studies involving antibiotics, cardiovascular agents, and psychotropic drugs show the clinical viability of repurposed therapies in reducing tumor proliferation and overcoming chemoresistance. Overcoming the challenges of data heterogeneity and algorithmic bias is essential for the future implementation of these technologies in precision oncology