Jovan Tanevski, PhD of Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Germany

Spatial omics technologies provide unprecedented maps of tissue organization, but their complexity and heterogeneity pose major challenges for interpretation and clinical translation. My research develops computational frameworks that go beyond black-box predictions by embedding biological knowledge into AI systems, creating interpretable tools that systematically link data, mechanisms, and outcomes. We design specialist models that capture spatial relationships, molecular programs, and tissue-level organization linking to clinically relevant observations. These models also form a foundation for biology-informed orchestrator systems capable of automatically applying methods to biological tasks, ensuring reproducibility, adaptability, and clinical relevance.
I will present recent developments in three directions. First, relationship-based representation learning across samples and conditions, which captures persistent local patterns and provides interpretable embeddings predictive of disease progression and treatment response. Second, integration approaches that augment and align data across omics modalities, platforms, and conditions to reveal coherent molecular and cellular patterns, including their trajectories. Finally, graph-based modeling that associates tissue architecture with clinical outcomes, identifying spatial features that improve patient stratification.
These developments are flexible, communicable, and readily deployable. Their outputs can be combined to define clinically relevant tissue regions, cellular organizations, and molecular relationships, which can then be refined with more precise experimental technologies. In this way, we transform high-dimensional spatial data into mechanistic insight and compact spatial marker patterns and molecular panels, accelerating the translation of discoveries into clinical practice.

Biography:

Jovan Tanevski is a Group Leader at the Institute for Computational Biomedicine, Faculty of Medicine, Heidelberg University and Heidelberg University Hospital, Germany, where he also heads the computational platform of the Translational Spatial Profiling Center. His research lies at the intersection of systems sciences and machine learning, focusing on the development of explainable AI/ML and optimization-based methods for representation learning, integration, and alignment of single-cell, imaging, and spatial omics data. His work aims to uncover clinically relevant spatiotemporal patterns and mechanistic insights across molecular layers to better understand disease heterogeneity, progression, and response to treatment.