Background: Artificial Intelligence (AI) and Machine Learning (ML) have transformed computer-aided drug design (CADD) by leveraging big data and advanced algorithms to accelerate drug design. These technologies enhance the exploration of chemical spaces, prediction of drug-target interactions, and development of personalized therapeutics, particularly for complex diseases like cancer.
Objectives: This review aims to evaluate the role of AI and ML in CADD, focusing on their applications in high-throughput screening (HTS), three-dimensional (3D) protein structure prediction, and drug-target identification, while addressing challenges and future prospects.
Methods: A comprehensive analysis of recent literature (2005–2024) was conducted using scientometric tools like VOSviewer to identify trends and keywords in CADD. AI-driven methods, including deep learning frameworks (e.g., TensorFlow, AlphaFold2) and computational techniques (e.g., molecular dynamics simulations), were reviewed for their contributions to drug design.
Results: AI and ML have streamlined HTS, improved 3D protein structure prediction, and enhanced drug-target identification, reducing development timelines and costs. Tools like AlphaFold 2 and QuoteTarget have identified novel drug targets with high accuracy. However, challenges such as data quality, model interpretability, and ethical concerns persist. Interdisciplinary collaboration has driven innovation in personalized therapeutics.
Conclusion: AI and ML have revolutionized CADD, offering efficient and precise solutions for drug design. Overcoming data and ethical challenges through interdisciplinary efforts and advanced algorithms will further enhance the development of targeted therapies, reshaping therapeutic paradigms for complex diseases.