Integrated approach of machine learning, Mendelian randomization and experimental validation for biomarker discovery in diabetic nephropathy
Authors' conclusion
By integrating machine learning, MR and experimental validation, we successfully identified and validated CA2 as a promising biomarker for DN with excellent predictive performance. The biomarker may play a role in the pathogenesis and progression of DN via immune-related pathways. These findings provide important insights into the molecular mechanisms underlying DN and may inform the development of personalized treatment strategies for this disease.
Study context
- Population
- Microarray and RNA-seq datasets from Gene Expression Omnibus (GSE47184, GSE96804, GSE104948, GSE104954, GSE142025, GSE175,759); clinical samples from patients with diabetic nephropathy (DN) and controls
- Comparison
- DN vs controls
- Outcome
- Biomarker identification for DN
Methodological detailsbioinformatic analysis with Mendelian randomization and experimental validation, machine learning (LASSO, SVM-RFE, random forest), ROC validation, qRT-PCR validation in clinical samples
- Bioinformatic analysis with Mendelian randomization and experimental validation
- Machine learning (LASSO, SVM-RFE, random forest)
- ROC validation
- qRT-PCR validation in clinical samples
Performance
As reported in the abstract
- Differentially expressed genes (DEGs) between DN and controls
- 314
- Characteristic genes from 3 machine learning algorithms
- seven
- Genes with significant causal effects on DN (Mendelian randomization (MR))
- 219
- Key biomarker (co-expressed gene)
- carbonic anhydrase II (CA2)
- AUC of CA2 across all datasets
- above 0.878
Further findings
Immune cell infiltration
- Significant association between CA2 and infiltrating immune cells in DN
Clinical validation (qRT-PCR)
- CA2 validated using clinical samples
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Integrated approach of machine learning, Mendelian randomization and experimental validation for biomarker discovery in diabetic nephropathy. Diabetes Obes Metab. Published 6 October 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →