Exploring the future of biopharmaceutical drug discovery: can advanced AI platforms overcome current challenges?

Abstract

Abstract Artificial intelligence (AI)-based drug discovery has not yet completely addressed the numerous and varied challenges posed by the inherent complexities and demands of achieving breakthroughs in drug discovery (DD). This review explores the promising role of advanced AI platforms in navigating the complex landscape of biopharmaceutical DD. A thorough examination of challenges, methodologies, and the pivotal role of AI outlines a vision for a more efficient, innovative, and transformative DD process. Using the cutting-edge Dompé Exscalate platform as a case study, this review describes how AI can address the diverse challenges that have long hampered progress in the field. By adopting a transformative approach in DD, the Exscalate platform exemplifies an AI-driven paradigm capable of not only streamlining the identification of promising molecular candidates but also improving prediction accuracy and the development of targeted therapeutics. Exploring the convergence of machine learning, deep learning, and high-performance computing, the article describes a landscape in which AI-integrated platforms blend technological and biological disciplines seamlessly. This synergy, encompassing physics-based simulations, generative modeling, and extensive molecular databases, has significant implications for both the scientific community and the pharmaceutical industry and will lead to notable improvements in both efficiency and innovation in biopharmaceutical DD.

Keywords

• Machine learning (ML)
• Artificial intelligence (AI)
• Deep learning (DL)
• Drug discovery (DD)
• Drug development