*Article* **Di**ff**erential Urinary Proteome Analysis for Predicting Prognosis in Type 2 Diabetes Patients with and without Renal Dysfunction**

**Hee-Sung Ahn 1,**†**, Jong Ho Kim 2,**†**, Hwangkyo Jeong 3, Jiyoung Yu 1, Jeonghun Yeom 4, Sang Heon Song 2, Sang Soo Kim 2, In Joo Kim 2,\* and Kyunggon Kim 1,3,5,6,\***


Received: 3 April 2020; Accepted: 12 June 2020; Published: 14 June 2020

**Abstract:** Renal dysfunction, a major complication of type 2 diabetes, can be predicted from estimated glomerular filtration rate (eGFR) and protein markers such as albumin concentration. Urinary protein biomarkers may be used to monitor or predict patient status. Urine samples were selected from patients enrolled in the retrospective diabetic kidney disease (DKD) study, including 35 with good and 19 with poor prognosis. After removal of albumin and immunoglobulin, the remaining proteins were reduced, alkylated, digested, and analyzed qualitatively and quantitatively with a nano LC-MS platform. Each protein was identified, and its concentration normalized to that of creatinine. A prognostic model of DKD was formulated based on the adjusted quantities of each protein in the two groups. Of 1296 proteins identified in the 54 urine samples, 66 were differentially abundant in the two groups (area under the curve (AUC): *p*-value < 0.05), but none showed significantly better performance than albumin. To improve the predictive power by multivariate analysis, five proteins (ACP2, CTSA, GM2A, MUC1, and SPARCL1) were selected as significant by an AUC-based random forest method. The application of two classifiers—support vector machine and random forest—showed that the multivariate model performed better than univariate analysis of mucin-1 (AUC: 0.935 vs. 0.791) and albumin (AUC: 1.0 vs. 0.722). The urinary proteome can reflect kidney function directly and can predict the prognosis of patients with chronic kidney dysfunction. Classification based on five urinary proteins may better predict the prognosis of DKD patients than urinary albumin concentration or eGFR.

**Keywords:** urine; diabetic kidney disease; kidney function; proteomics; mass spectrometry; statistical clinical model; machine learning

#### **1. Introduction**

About 30% of people with diabetes develop diabetic kidney disease (DKD), and the spread of diabetes is increasing worldwide [1,2]. Complications of type 2 diabetes (T2D) mainly cause end-stage renal disease, which is related to high heart disease incidence and mortality [2,3]. Early detection and screening of patients at risk for DKD is important, which may reduce the global burden of T2D.

Because the kidneys filter waste from blood and discharge it as urine, urine can directly reflect kidney function. Unlike plasma, urine can be easily collected non-invasively, with proteins in urine being stable and not vulnerable to sudden degradation [4]. Albuminuria and estimated glomerular filtration rate (eGFR), have been generally used to assess kidney function [2,5]. However, albuminuria is only evaluated after glomerular damage has occurred, and sometimes kidney disease develops before the outbreak of albuminuria [6,7]. Better markers are required to help delay progression to DKD.

Multiple-biomarker approaches based on proteomics, including urinary proteomics, may overcome the limitations of markers diagnostic for DKD [4,8]. This study was designed to identify a urinary multi-protein panel that could predict progression to DKD in patients with T2D.

#### **2. Results**
