Revolutionizing Anti-cancer Drug Discovery With Artificial Intelligence: a New Era in Oncology
Year: 2025
Type: article
Abstract: Background: Cancer remains one of the leading causes of death worldwide, with conventional drug discovery methods proving time-consuming, costly, and often ineffective in tackling the complexity and heterogeneity of malignancies. Objective: This review aims to explore the transformative role of artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), in accelerating and refining anti-cancer drug discovery. Methods: The article examines how AI is integrated into various stages of the drug development pipeline, including target identification, virtual screening, structure prediction, and clinical trial design. Emphasis is placed on synergizing AI with natural product-based drug discovery and addressing key computational, ethical, and regulatory challenges. Findings: AI has significantly improved the prediction of molecular properties, reduced attrition rates, and enabled the repurposing of existing drugs for new cancer indications. Virtual screening of phytochemicals and AI-aided solubility predictions are streamlining the path from lab to clinic. Attention mechanisms and transformer models are enhancing interpretability, while AI is optimizing clinical trials and enabling personalized medicine approaches. Conclusion: Artificial intelligence is revolutionizing cancer therapeutics by enabling faster, cost-effective, and personalized drug development. However, integration into routine practice requires addressing data quality, model interpretability, and ethical concerns. Continued interdisciplinary collaboration will be vital to fully harness AI's potential in oncology drug discovery.
DOI: 10.62019/z6nr7048
Authors: Muhammad Akhlaq, Mehran sattar, Muhammad Akram, Syed Muhammad Kazim Abbas Shah, Sania Saeed, Muhammad Khaleeq Alum
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4414152343