首页|Tongji University School of Medicine Reports Findings in PersonalizedMedicine ( Integrated approach of machine learning, Mendelianrandomization and experimenta l validation for biomarker discoveryin diabetic nephropathy)
Tongji University School of Medicine Reports Findings in PersonalizedMedicine ( Integrated approach of machine learning, Mendelianrandomization and experimenta l validation for biomarker discoveryin diabetic nephropathy)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Drugs and Therapies - Personalized Medicine is the subject of areport. According to news originating from Shanghai, People’s Republic of China, by NewsRx correspondents,research st ated, “To identify potential biomarkers and explore the mechanisms underlying di abeticnephropathy (DN) by integrating machine learning, Mendelian randomization (MR) and experimentalvalidation. Microarray and RNA-sequencing datasets (GSE47 184, GSE96804, GSE104948, GSE104954,GSE142025 and GSE175759) were obtained from the Gene Expression Omnibus database.”Financial support for this research came from Shanghai Municipal Health Commissi on.Our news journalists obtained a quote from the research from the Tongji Universi ty School of Medicine,“Differential expression analysis identified the differen tially expressed genes (DEGs) between patients withDN and controls. Diverse mac hine learning algorithms, including least absolute shrinkage and selectionopera tor, support vector machine-recursive feature elimination, and random forest, we re used to enhancegene selection accuracy and predictive power. We integrated s ummary-level data from genome-wideassociation studies on DN with expression qua ntitative trait loci data to identify genes with potentialcausal relationships to DN. The predictive performance of the biomarker gene was validated using rece iveroperating characteristic (ROC) curves. Gene set enrichment and correlation analyses were conducted toinvestigate potential mechanisms. Finally, the biomar ker gene was validated using quantitative real-timepolymerase chain reaction in clinical samples from patients with DN and controls. Based on identified 314DE Gs, seven characteristic genes with high predictive performance were identified using three integratedmachine learning algorithms. MR analysis revealed 219 gen es with significant causal effects on DN,ultimately identifying one co-expresse d gene, carbonic anhydrase II (CA2), as a key biomarker for DN.The ROC curves d emonstrated the excellent predictive performance of CA2, with area under the curve values consistently above 0.878 across all datasets. Additionally, our analys is indicated a significantassociation between CA2 and infiltrating immune cells in DN, providing potential mechanistic insights.This biomarker was validated u sing clinical samples, confirming the reliability of our findings in clinical practice. By integrating machine learning, MR and experimental validation, we succ essfully identified andvalidated CA2 as a promising biomarker for DN with excel lent predictive performance. The biomarkermay play a role in the pathogenesis a nd progression of DN via immune-related pathways.”
ShanghaiPeople’s Republic of ChinaAs iaBiomarkersCyborgsDiabetes ComplicationsDiabetes MellitusDiabetic Nep hropathyDiagnostics and ScreeningDrugs and TherapiesEmerging TechnologiesGeneticsHealth and MedicineKidney Diseases and ConditionsMachine LearningNephrologyNephropathyNutritional and Metabolic Diseases and ConditionsPe rsonalized MedicinePersonalized Therapy
NETL
NSTL
