Immune-related/mediated disorders (IDs) comprise a very diverse group of diseases affecting millions worldwide. The complexity and heterogeneity of IDs, coupled with individual variability in immune system responses, create multiple challenges for developing targeted therapies. These challenges often result in prolonged diagnostic timelines, higher treatment costs, and frequent failures in clinical trials. Recent advances in artificial intelligence (AI) and digital twin (DT) technology offer promising solutions to support and accelerate drug discovery and development for these conditions, with anticipated substantial improvement in success rates. As virtual replicas of biological systems, DTs can be constructed using multimodal data sources, including multi-omics, molecular profiling, imaging and clinical records. These in silico tools can accelerate precision medicine by identifying relevant drug targets, designing personalised treatments and predicting individual immune responses to drug candidates. Here, we review the current landscape of DTs supporting drug development for IDs. We describe the concepts behind mixed reality approaches combining AI-based models, traditional mathematical and computational models based on low-throughput experiments and empirical studies. We highlight concrete examples of precision medicine strategies for IDs informed by computational modelling. We also address the benefits, limitations, and ethical considerations of these approaches, and outline future directions for research and clinical translation. Impact statement This manuscript addresses the use of digital twins (DT) to accelerate drug discovery and development for Immune-mediated Disorders. It provides a comprehensive overview of the field and helps clarify complex concepts. Furthermore, it provides concrete examples of DT applications on immune-mediated disorders, and discusses perspectives, and current challenges.
Niarakis et al. (Mon,) studied this question.