The pathogenesis of progressive renal allograft injury, which is termed chronic allograft nephropathy (CAN), remains obscure and is currently defined by histology. Prospective protocol‐biopsy trials have demonstrated that clinical and standard laboratory tests are insufficiently sensitive indicators of the development and progression of CAN. The study aim was to determine if CAN could be characterized by urinary proteomic data and identify the proteins associated with disease. The urinary proteome of 75 renal transplant recipients and 20 healthy volunteers was analyzed using surface enhanced laser desorption and ionization MS. Patients could be classified into subgroups with normal histology and Banff CAN grades 2‐3 with a sensitivity of 86% and a specificity of 92% by applying the classification algorithm Adaboost to urinary proteomic data. Several urinary proteins associated with advanced CAN were identified including α1‐microglobulin, β2‐microglobulin, prealbumin, and endorepellin, the antiangiogenic C‐terminal fragment of perlecan. Increased urinary endorepellin was confirmed by ELISA and increased tissue expression of the endorepellin/perlecan ratio by immunofluoresence analysis of renal biopsies. In conclusion, analysis of urinary proteomic data has further characterized the more severe CAN grades and identified urinary endorepellin, as a potential biomarker of advanced CAN.