Revolution of Computer-assisted Drug Design: The Transformative Role of Artificial Intelligence
Uma Rawat, Anita SinghAbstract:
Artificial intelligence (AI) is transforming computer-aided drug design (CADD) by enabling more rapid, efficient, and data-driven approaches to drug discovery. This narrative review examines recent applications of AI, machine learning (ML), deep learning (DL), reinforcement learning (RL), natural language processing (NLP), and generative AI across major stages of the drug discovery pipeline. Literature published primarily between 2021 and 2026 was reviewed to describe advances in AI-assisted target identification, protein structure and protein- protein interaction prediction, virtual screening, molecular docking, quantitative structure– activity relationship (QSAR) modelling, drug repurposing, ADMET prediction, biomarker discovery, lead optimization, and de novo molecular design. The review also highlights AI-enabled computational tools, databases, and predictive models that support the analysis of large chemical and biological datasets. AI-based approaches can improve prediction accuracy, accelerate candidate identification and optimization, and reduce the time and cost associated with conventional drug discovery workflows. However, widespread implementation remains limited by challenges including data quality and bias, limited model generalizability, insufficient interpretability and reproducibility, computational demands, and regulatory and ethical concerns. AI should therefore be considered a complementary technology that supports, rather than replaces, experimental and clinical validation. Future research should focus on developing standardized and diverse datasets, explainable and transparent AI models, robust external validation strategies, and improved integration of multimodal and multi-omics data. Furthermore, the convergence of AI with emerging technologies, including quantum computing, generative models, automated laboratories, and precision medicine, may further advance CADD. Collaborative efforts among computational scientists, medicinal chemists, biologists, clinicians, and regulatory agencies will be essential to translate AI-driven discoveries into safe, effective, and clinically relevant therapeutic candidates.