Genomics studies large-scale interactions of genes and proteins, and thus is a key driver of systems medicine. In this context, the new engineering discipline of Genomic Signal Processing (GSP) is the analysis, processing, and use of genomic signals for gaining biological knowledge and the translation of that knowledge into systems-based applications. An important goal of translational genomics is to discover families of genes whose signals can be used for molecular-based diagnosis and prognosis for instance, predicting the effect of a cancer drug so that a patient can receive the drug best suited to their genetic make-up. The long-term goal is to characterize genetic regulation, thereby gaining a functional understanding of disease, and to use this understanding to develop systems-based medical solutions. Prognosis depends to a great extent on pattern classification and regulation-based therapy depends on modeling gene regulatory networks and developing control policies to beneficially guide their dynamics. In this presentation we discuss the roles of these engineering paradigms in translational genomics, illustrate some applications, and point out critical obstacles that must be overcome to achieve success.