The widespread adoption of next-generation sequencing and comprehensive genomic profiling in biomedical research and diagnostics has generated large-scale, heterogeneous, and highly complex genomic datasets. While technological advances have greatly improved data production, major challenges remain in data integration, interpretation, and transformation into actionable molecular knowledge. This Special Session aims to bring together researchers working on computational intelligence methods applied to advanced genomic diagnostics, with a focus on the development of robust, interpretable, and scalable analytical frameworks. The session will emphasize approaches that move beyond single-variant analysis toward system-level and phenotype-oriented interpretations of genomic data. Topics of interest include, but are not limited to: machine learning and artificial intelligence for variant prioritization and functional annotation; network-based and graph-learning approaches for molecular stratification; multi-omics data integration; computational identification of molecular signatures and endophenotypes; and frameworks for real-world genomic data analysis. Particular attention will be given to methodological rigor, reproducibility, and translational applicability, ensuring that proposed approaches can be effectively transferred to real diagnostic and research settings. The session is designed to foster interdisciplinary interaction among bioinformaticians, data scientists, and computational biologists, promoting innovative solutions at the interface between computational intelligence and genomic medicine.