Systems pharmacology approaches to modeling immune training and tolerance

Trained immunity is defined as the epigenetic and metabolic reprogramming of innate immune cells, conferring enhanced or diminished responsiveness to secondary challenges following initial stimulation. Immune tolerance represents the state of immunological unresponsiveness to self-antigens or innocuous foreign antigens. Systems pharmacology approaches have emerged as essential tools for understanding and modulating these complex immunological processes. In this mini-review, we evaluate quantitative systems pharmacology (QSP) approaches which are predominantly based on ordinary differential equation (ODE) frameworks and artificial intelligence (AI)/machine learning (ML) applications in the context of trained immunity and immune tolerance. QSP models enable in silico clinical trials, thereby accelerating drug development and supporting cost-effective therapeutic decision-making. Recent advances have identified histone lactylation, particularly H3K18la, as a central epigenetic mark linking metabolic rewiring to long-term innate immune memory, revealing novel pharmacological targets including LDHA, EP300, and ACAT2. ML algorithms integrated with explainable AI frameworks have facilitated biomarker discovery and therapeutic target identification. Digital twin technology holds considerable promise for developing personalized immunomodulatory strategies. This review highlights the translational potential of systems pharmacology tools in pharmacological targeting of trained immunity and tolerance, emphasizing the convergence of computational modeling with precision medicine approaches.