Artificial intelligence (AI) as a catalyst for mechanistic target discovery: Integrating systems pharmacology and multimodal data.

Abstract

Artificial intelligence (AI) is evolving from a predictive tool into a foundational computational infrastructure for mechanism-driven pharmacology, fundamentally reshaping drug discovery. This review examines how this transformation addresses persistent challenges in target validation, including data biases and the need for model interpretability, by integrating network pharmacology with advanced deep learning architectures. Specifically, graph neural networks decipher the complex topology of biological systems and transformer models facilitate the fusion of multimodal data, from genomics to real-world clinical records. Coupled with physics-informed neural networks, this integrated framework operates as a predictive computational microscope. It enables comprehensive in silico simulations that span multiple biological scales, encompassing atomic-level molecular interactions and longitudinal patient trajectories. We demonstrate that this AI-driven paradigm is essential for advancing precision medicine, as it systematically translates vast and heterogeneous datasets into testable mechanistic hypotheses. Consequently, this approach accelerates the development of safer, more effective and patient-specific therapies, by de-risking target validation and elucidating novel therapeutic mechanisms. It directly addresses some of the most pressing inefficiencies in contemporary drug discovery and development, offering a pathway towards more rational and efficient therapeutic innovation.