Artificial Intelligence in Drug Discovery and Design: A Paradigm Shift Toward Faster, Smarter, and Targeted Therapeutics
Code: G-1786
Authors: Hossein Najafi *, Sana Rahimian ℗
Schedule: Not Scheduled!
Tag: Drug Discovery
Download: Download Poster
Abstract:
Abstract
Background and Aims: Drug discovery is traditionally a high-cost, time-intensive endeavor with a high failure rate. The recent integration of artificial intelligence (AI)—particularly machine learning (ML), deep learning (DL), and natural language processing (NLP)—has transformed this paradigm, enabling faster, data-driven, and more predictive workflows. This paper aims to comprehensively review AI’s impact across the entire drug development continuum, from target identification to clinical translation. Methods: We conducted a structured literature review of recent advances in AI-enhanced drug discovery platforms. Key focus areas include structure-based virtual screening, generative AI for de novo molecule design, synthesis prediction, and drug repurposing strategies. The study also evaluated real-world case studies and emerging commercial platforms applying AI in both early and late-stage pharmaceutical research. Results: AI-driven platforms such as RosettaVS have revolutionized structure-based drug discovery by enabling rapid, flexible receptor modeling and accurate binding affinity prediction. These systems successfully identified potent compounds from multi-billion entry libraries within days—validated through crystallographic analysis. Concurrently, generative AI models have shown promise in designing novel chemical entities with optimized pharmacokinetic and pharmacodynamic profiles, bypassing traditional compound libraries. Additionally, AI is facilitating downstream processes such as synthetic route planning, combinatorial drug design, and clinical trial optimization. Early clinical assets developed through AI-collaborative pipelines are emerging, reflecting real-world impact. However, challenges such as data standardization, explainability, and regulatory compliance remain central to successful integration. Conclusion: AI is fundamentally reshaping the future of drug discovery and design by streamlining workflows, accelerating timelines, and enhancing precision. The integration of AI with multi-omics data and real-time patient stratification models positions it as a cornerstone of next-generation pharmaceutical innovation. Future progress depends on continued interdisciplinary collaboration, ethical data practices, and the development of transparent, explainable AI systems aligned with regulatory standards.
Keywords
Artificial Intelligence, Drug Discovery, Drug Design
