**5. Conclusions**

These results suggest that measurement of urinary proteome was more promising than albuminuria alone for predicting renal outcomes in patients with type 2 diabetes. A panel of five proteins had the potential for use as a biomarker in clinical practice.

**Supplementary Materials:** Supplementary materials can be found at http://www.mdpi.com/1422-0067/21/12/ 4236/s1. Figure S1. Prognostic probability of 54 patients by RF and SVM classifier divided into three groups by albumin-to-creatinine ratio.; Table S1. Demographic and clinical characteristics of the 54 patients with type 2 diabetes.; Table S2. Search result of MS/MS spectra of protein sequences obtained from the 54 urine samples in the Human Swissprot proteome database using the SequestHT search engine.; Table S3. Results of volcano plot analysis.; Table S4. Normalized abundance of 412 urinary proteins in the 54 patients with type 2 diabetes.; Table S5. Univariate receiver operating curve analysis of the areas under the curves of 412 urinary proteins.; Table S6. Prognostic probability by RF and SVM classifier of 54 patients.

**Author Contributions:** Conceptualization, J.H.K., S.H.S., S.S.K., I.J.K., and K.K.; methodology, H.J.; formal analysis, H.-S.A.; investigation, J.Y. (Jiyoung Yu); data curation, H.-S.A., S.S.K., and I.J.K.; writing—original draft preparation, H.-S.A. and K.K.; writing—review and editing, J.H.K., J.Y. (Jiyoung Yu), J.Y. (Jeonghun Yeom), S.H.S., S.S.K., and I.J.K; visualization, H.-S.A.; supervision, I.J.K and K.K.; funding acquisition, J.H.K. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was funded by a Biomedical Research Institute Grant (2017-20) from Pusan National University Hospital.

**Acknowledgments:** The authors thank the Department of Biostatistics, Clinical Trial Center, Biomedical Research Institute, Pusan National University Hospital.

**Conflicts of Interest:** The authors declare no conflict of interest.
