Integrating AI, mechanistic modelling and network approaches in systems biology for translational research

The field of systems biology is undergoing a profound transformation, driven by the need to move beyond reductionist views and understand biological systems in all their complexity. Our special issue exemplifies this evolution and presents computational approaches advancing our understanding of disease and cellular function ( https://www.nature.com/collections/chdbdhfibd ). The papers cover four themes that define the current research frontier: hybrid modeling and AI integration, single-cell resolution and spatial heterogeneity, network medicine and translational discovery, and mechanistic modeling and model refinement. Collectively, these studies contribute to bridging the gap between data abundance and mechanistic insight. Integrating artificial intelligence (AI) with traditional mechanistic models, especially through universal differential equations frameworks, can improve the estimation and prediction of parameters in the presence of noisy, sparse biological data 1 . Concurrently, focusing on single-cell and spatial systems biology can provide insights into the functional implications of cellular heterogeneity, which is a key challenge in basic and translational research 2 . Additionally, applying network-based models to multi-omics integration and developing Immune Digital Twins highlights the increasing dedication to translational outcomes and may facilitate the identification of biomarkers and repurposable drug targets 3 . Finally, foundational work in mechanistic modeling, including agent-based simulations and automated model refinement, continues to provide essential theory for the field 4 . Together, these studies provide examples of current directions in systems biology that may contribute to precision medicine and holistic biological understanding.