Deep learning on electronic medical records identifies distinct subphenotypes of diabetic kidney disease driven by genetic variations in the Rho pathway.
Ishan ParanjpeXuan WangNanditha AnandakrishnanJonathan C HaydakTielman Van VleckStefanie DeFronzoZhengzhe LiAnthony MendozaRuijie LiuJia FuIain S ForrestWeibin ZhouKyung LeeRoss O'HaganSergio DellepianeKartikeya M MenonFaris GulamaliSamir KamatGabriele Luca GusellaAlexander W CharneyIra HoferJudy H ChoRon DoBenjamin S GlicksbergJohn C HeGirish N NadkarniEvren U AzelogluPublished in: medRxiv : the preprint server for health sciences (2023)
Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease. Exome-wide associations identify a novel variant in ARHGEF18, a Rho guanine exchange factor specifically expressed in glomeruli. Overexpression of ARHGEF18 in human podocytes leads to impairments in focal adhesion architecture, cytoskeletal dynamics, cellular motility, and RhoA/Rac1 activation. Mutant GEF18 is resistant to ubiquitin mediated degradation leading to pathologically increased protein levels. Our findings uncover the first known disease-causing genetic variant that affects protein stability of a cytoskeletal regulator through impaired degradation, a potentially novel class of expression quantitative trait loci that can be therapeutically targeted.
Keyphrases
- genome wide
- electronic health record
- deep learning
- copy number
- dna methylation
- end stage renal disease
- machine learning
- type diabetes
- single cell
- endothelial cells
- clinical decision support
- binding protein
- ejection fraction
- chronic kidney disease
- biofilm formation
- protein protein
- artificial intelligence
- wound healing
- cell proliferation
- peritoneal dialysis
- protein kinase
- high resolution
- skeletal muscle
- patient reported outcomes
- prognostic factors
- risk factors
- metabolic syndrome
- amino acid
- smooth muscle
- cell migration
- big data
- high glucose
- gene expression
- induced pluripotent stem cells
- cancer therapy
- adipose tissue
- diabetic nephropathy
- wild type
- candida albicans