The following is a summary of “Unbiased kidney-centric molecular categorization of chronic kidney disease as a step towards precision medicine,” published in the January 2024 issue of Nephrology by Reznichenko et al.
The current staging of chronic kidney disease (CKD) based on estimated glomerular filtration rate (eGFR) and albuminuria needs to be more precise by neglecting the diverse molecular processes within the kidney, hindering advancements in precision medicine. To address this, researchers conducted an in-depth analysis of publicly available transcriptomic data from kidney biopsy tissue using a Self-Organizing Maps unsupervised artificial neural network machine-learning algorithm.
This approach led to the identification of four distinct molecular categories of CKD, labeled as CKD-Blue, CKD-Gold, CKD-Olive, and CKD-Plum. These categories were not only replicated in independent CKD and diabetic kidney disease datasets but are also available for validation on external data through kidneyclass.org. Transcending CKD stages and histopathological diagnoses, each molecular category exhibited the activation of unique biological pathways. Notably, disease progression rates significantly differed between the categories. CKD-Gold showed rapid progression, as indicated by a substantial eGFR-adjusted Cox regression hazard ratio for kidney failure and a composite endpoint of kidney failure or a 40% or more eGFR decline. Distinct patterns in urine proteomics further differentiated these molecular categories, and the investigators identified a 25-protein signature capable of distinguishing CKD-Gold from other categories.
This comprehensive patient stratification based on kidney tissue omics provides a non-invasive biomarker-driven categorization and holds the potential for future clinical implementation. This novel approach marks a crucial step toward realizing precision medicine in the field of CKD, offering a refined understanding of the molecular intricacies underlying the disease and paving the way for targeted therapeutic interventions.
Source: sciencedirect.com/science/article/pii/S0085253824000681
