Oral cancer incidence is rising and is the now the 8th most common form of cancer. Prognosis is poor; at least 50% of patients die within five years of diagnosis. Lysyl oxidase (LOX) is a critically important extracellular matrix protein and enzyme. LOX is synthesized as a 50 kDa pre-proenzyme (Pro-LOX) that is secreted, and then processed extracellularly by procollagen C-proteinases to form active 30 kDa lysyl oxidase enzyme, and the 18 kDa lysyl oxidase propeptide (LOX-PP). The tumor suppressor activity originally attributed to LOX enzyme depends instead on LOX-PP. LOX-PP is a naturally occurring extracellular matrix protein, and likely has limited toxicity while having important anti-cancer activities. Different regions of LOX-PP bind to different targets in its inhibition of RAS-dependen cancer pathways. Some targets are intracellular (c-RAF and tubulin for example), while others are extracellular (FGFR1, for example). It is currently unknown which location and targets of LOX-PP are most important for its tumor suppressor activity. Knowledge regarding the functional location (intracellular or extracellular) is important for formulation of therapeutics based on rLOX-PP. The proposed research will establish which location of rLOX-PP is functional in its ability to inhibit oral cancer phenotype in vitro (Aim 1), and orthotopic oral tuor growth in mice in vivo (Aim 2). Particular attention will be paid to the HSP70 cancer cell marker which is a rLOX-PP binding partner and occurs both extracellularly and intracellularly and participates in RAS-dependent signal transduction and cell transformation. Fusion protein derivatives which are designed to either remain extracellular by fusion with the Fc-domain of IgG4, or are designed for increased cell uptake by fusion with cell penetrating peptide sequences, or palmitic acid, will be created and tested for anti-cancer activities and extracellular/intracellular location in vitro. These rLOX-PP derivatives are expected to have increased in vivo stability. The most active derivative will be systemically administered to mice i which tongue orthotopic tumors have been implanted using UMSCC2 (aggressive) and CAL 27 (less aggressive) oral cancer cell lines and tumor growth and expression of tumor markers and active RAS activity effectors will be determined. It is expected that at least one rLOX-PP derivative with both increased stability and anti-oral tumor growth effectiveness will be identifie. The importance of extracellular compared to intracellular interactions of the HSP70-binding domain of rLOX-PP in particular will be evaluated. Important information will be gained to further refine the design of anti-tumor molecules.