The workshop aims to strengthen the dialogue between computational scientists, bioinformaticians, and clinicians by focusing on the role of network science and graph neural networks (GNNs) in modeling complex biological and medical systems. It seeks to highlight methodological innovations, promote interdisciplinary collaboration, and identify emerging challenges that must be addressed to translate graph-based models into clinically meaningful insights. The scope of the workshop encompasses both theoretical and applied research on network modeling and GNNs across biological and clinical domains. Topics of interest include network-based representations of omics and multi-omics data, the design and application of GNN architectures for molecular, cellular, and patient-level data, and the development of explainable and interpretable models tailored to biomedical applications. The workshop also invites studies demonstrating translational potential in disease characterization, drug discovery, and precision medicine, as well as practical case studies linking computational pipelines to diagnostic or therapeutic interpretation. By bridging graph learning techniques with biomedical research, the workshop will foster a deeper integration of computational models into clinical and translational workflows. It aims to catalyze collaborations, strengthen the community around graph-based bioinformatics, and stimulate the adoption of AI-driven network methodologies within precision health.