Related Experiment Video
Updated: Dec 15, 2025
Comparative Proteomic Analysis of Whole Kidney, Medulla, and Cortical Tubules in Diabetic Pathogenesis of Kidney Injury in Mice
Published on: May 2, 2025
Proteomics-Based Machine Learning Approach as an Alternative to Conventional Biomarkers for Differential Diagnosis of
Yury E Glazyrin1,2, Dmitry V Veprintsev2, Irina A Ler3
1Laboratory for Biomolecular and Medical Technologies, Krasnoyarsk State Medical University Named after Prof. V.F. Voyno-Yasenetsky, 660022 Krasnoyarsk, Russia.
Insights
Machine learning algorithms effectively differentiate chronic kidney disease (CKD) origins using proteomic data. The k-nearest-neighbors algorithm shows high accuracy in distinguishing diabetic nephropathy and glomerulonephritis from plasma, and hypertensive nephropathy from urine.
Area of Science:
- Nephrology
- Proteomics
- Machine Learning
Background:
- Diabetic nephropathy, hypertension, and glomerulonephritis are leading causes of chronic kidney disease (CKD).
- Early diagnosis is crucial as CKD often progresses unnoticed until significant kidney function impairment.
- Conventional biomarkers lack sufficient discriminatory power for early CKD subtyping.
Purpose of the Study:
- To evaluate machine learning algorithms for the differential diagnosis of CKD from three common origins.
- To assess the utility of plasma and urine proteomic data in distinguishing these CKD subtypes.
- To explore the potential of proteomic analysis for early and non-invasive CKD diagnosis.
Main Methods:
- Whole proteomic data from plasma and urine samples of 34 CKD patients were analyzed using mass spectrometry and label-free quantification.
- Several machine learning algorithms, including k-nearest-neighbors, were applied to the proteomic datasets.
- The k-nearest-neighbors algorithm was tested for differentiating healthy individuals from CKD patients and for distinguishing between specific CKD origins.
Main Results:
- The k-nearest-neighbors algorithm achieved 97.8% accuracy in separating healthy individuals from renal patients using plasma proteomic data.
- Plasma proteomic data allowed for 96.3% accurate differentiation between diabetic nephropathy and glomerulonephritis using the k-nearest-neighbors algorithm.
- Hypertensive nephropathy was not reliably separated from plasma data, but was distinguished from all other renal patients with 100% accuracy using urine proteomic data with a 'one against all' k-nearest-neighbors approach.
Conclusions:
- Machine learning applied to proteomic data shows significant potential for early differential diagnosis of CKD subtypes.
- Proteomic analysis of plasma and urine offers a promising non-invasive alternative to invasive procedures for CKD subtyping.
- The k-nearest-neighbors algorithm demonstrates robust performance in classifying CKD origins based on proteomic profiles.
Abstract:
Diabetic nephropathy, hypertension, and glomerulonephritis are the most common causes of chronic kidney diseases (CKD). Since CKD of various origins may not become apparent until kidney function is significantly impaired, a differential diagnosis and an appropriate treatment are needed at the very early stages. Conventional biomarkers may not have sufficient separation capabilities, while a full-proteomic approach may be used for these purposes. In the current study, several machine learning algorithms were examined for the differential diagnosis of CKD of three origins. The tested dataset was based on whole proteomic data obtained after the mass spectrometric analysis of plasma and urine samples of 34 CKD patients and the use of label-free quantification approach. The k-nearest-neighbors algorithm showed the possibility of separation of a healthy group from renal patients in general by proteomics data of plasma with high confidence (97.8%). This algorithm has also be proven to be the best of the three tested for distinguishing the groups of patients with diabetic nephropathy and glomerulonephritis according to proteomics data of plasma (96.3% of correct decisions). The group of hypertensive nephropathy could not be reliably separated according to plasma data, whereas analysis of entire proteomics data of urine did not allow differentiating the three diseases. Nevertheless, the group of hypertensive nephropathy was reliably separated from all other renal patients using the k-nearest-neighbors classifier "one against all" with 100% of accuracy by urine proteome data. The tested algorithms show good abilities to differentiate the various groups across proteomic data sets, which may help to avoid invasive intervention for the verification of the glomerulonephritis subtypes, as well as to differentiate hypertensive and diabetic nephropathy in the early stages based not on individual biomarkers, but on the whole proteomic composition of urine and blood.
Related Concept Videos
01:28Chronic Kidney Disease III: Interprofessional Care
01:25Chronic Kidney Disease I: Introduction
01:33Proteomics
Proteomics is the study of proteomes' function. It involves the large-scale systematic study of the proteome to denote the protein complement expressed by a genome. Scientist Mark Wilkins coined the term...
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration