Advances in high-throughput technologies have led to the acquisition of various types of -omic data on the same biological samples. Each data type gives independent and complementary information that can explain the biological mechanisms of interest. While several studies performing independent analyses of each dataset have led to significant results, a better understanding of complex biological mechanisms requires an integrative analysis of different sources of –omic data. The proposed approach allows the integration of various genomic data types at the gene level by considering biological relationships between the different molecular features. Several scenarios and a flexible modeling, based on penalized likelihood approaches and EM algorithms, are studied and tested. The method is applied to genomic datasets from Glioblastoma Multiforme samples collected as part of the Cancer Genome Atlas project in order to elucidate biological mechanisms of the disease and identify markers associated with patients' survival.