Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 25, 2026MoleculesOpen Access

Transcriptomic Profiling Combined with Machine Learning and Mendelian Randomization Identifies Diagnostic Biomarkers and Immune Infiltration Patterns in Diabetic Kidney Disease

View Full Paper
Ask AI
Bookmark
Share

Authors

HLHaiwen LiuQFQiang FuJCJing Chen

Discussion

Loading...

Member takes

Overview

Randomized trial identifies diagnostic biomarkers in diabetic kidney disease, suggesting new therapeutic targets.

Key Points

  • This research aims to identify reliable diagnostic biomarkers and immune infiltration patterns in diabetic kidney disease (DKD).
  • Integrated transcriptomic data from the GEO database with machine learning and Mendelian randomization.
  • Applied four machine learning methods: LASSO, random forest, SVM-RFE, and XGBoost for feature selection.
  • Conducted immune infiltration analysis using CIBERSORT for DKD samples.
  • Identified five hub genes: SPP1, CD44, VCAM1, C3, and TIMP1 related to DKD.
  • Achieved a cross-validated area under the receiver operating characteristic curve (CV-AUC) of 0.938 for the diagnostic model.
  • Estimated elevated M1 macrophage and activated CD4+ T cell proportions in DKD samples, correlating hub genes with macrophage infiltration.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69ec5b8a88ba6daa22dad046https://doi.org/10.3390/molecules31091390
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Integrative transcriptomic and genomic insights into diabetic kidney disease: evidence from multi-omics analysis and experimental validation2025 · 1 citations
  2. 2Identification of diagnostic markers for diabetic kidney disease by weighted gene co‑expression network analysis and machine learning2026
  3. 3Integrating bioinformatics and machine learning to elucidate the role of protein glycosylation-related genes in the pathogenesis of diabetic kidney disease2025 · 4 citations
  4. 4Identification and validation of immune and cuproptosis - related genes for diabetic nephropathy by WGCNA and machine learning2024 · 43 citations
  5. 5Immune Infiltration and Mitochondrial Function in Diabetic Kidney Disease: WGCNA and Machine Learning Identified Hub Genes with Clinical Validation2026