Discovery of a Trans-Omics Biomarker Signature that Predisposes High Risk Diabetic Patients to Diabetic Kidney Disease
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA889394 | ENA |
REPOSITORIES: ENA
Similar Datasets
Project description:Diabetic kidney disease is the leading cause of end-stage kidney disease worldwide; however, the integration of high-dimensional trans-omics data to predict this diabetic complication is rare. We develop artificial intelligence (AI)-assisted models using machine learning algorithms to identify a biomarker signature that predisposes high risk patients with diabetes mellitus (DM) to diabetic kidney disease based on clinical information, untargeted metabolomics, targeted lipidomics and genome-wide single nucleotide polymorphism (SNP) datasets. This involves 618 individuals who are split into training and testing cohorts of 557 and 61 subjects, respectively. Three models are developed. In model 1, the top 20 features selected by AI give an accuracy rate of 0.83 and an area under curve (AUC) of 0.89 when differentiating DM and non-DM individuals. In model 2, among DM patients, a biomarker signature of 10 AI-selected features give an accuracy rate of 0.70 and an AUC of 0.76 when identifying subjects at high risk of renal impairment. In model 3, among non-DM patients, a biomarker signature of 25 AI-selected features give an accuracy rate of 0.82 and an AUC of 0.76 when pinpointing subjects at high risk of chronic kidney disease. In addition, the performance of the three models is rigorously verified using an independent validation cohort. Intriguingly, analysis of the protein-protein interaction network of the genes containing the identified SNPs (RPTOR, CLPTM1L, ALDH1L1, LY6D, PCDH9, B3GNTL1, CDS1, ADCYAP and FAM53A) reveals that, at the molecular level, there seems to be interconnected factors that have an effect on the progression of renal impairment among DM patients. In conclusion, our findings reveal the potential of employing machine learning algorithms to augment traditional methods and our findings suggest what molecular mechanisms may underlie the complex interaction between DM and chronic kidney disease. Moreover, the development of our AI-assisted models will improve precision when diagnosing renal impairment in predisposed patients, both DM and non-DM. Finally, a large prospective cohort study is needed to validate the clinical utility and mechanistic implications of these biomarker signatures.
2022-10-12 | GSE215221 | GEO
Project description:Diabetic kidney disease is the leading cause of end-stage kidney disease worldwide; however, the integration of high-dimensional trans-omics data to predict this diabetic complication is rare. We develop artificial intelligence (AI)-assisted models using machine learning algorithms to identify a biomarker signature that predisposes high risk patients with diabetes mellitus (DM) to diabetic kidney disease based on clinical information, untargeted metabolomics, targeted lipidomics and genome-wide single nucleotide polymorphism (SNP) datasets. This involves 618 individuals who are split into training and testing cohorts of 557 and 61 subjects, respectively. Three models are developed. In model 1, the top 20 features selected by AI give an accuracy rate of 0.83 and an area under curve (AUC) of 0.89 when differentiating DM and non-DM individuals. In model 2, among DM patients, a biomarker signature of 10 AI-selected features gives an accuracy rate of 0.70 and an AUC of 0.76 when identifying subjects at high risk of renal impairment. In model 3, among non-DM patients, a biomarker signature of 25 AI-selected features gives an accuracy rate of 0.82 and an AUC of 0.76 when pinpointing subjects at high risk of chronic kidney disease. In addition, the performance of the three models is rigorously verified using an independent validation cohort. Intriguingly, analysis of the protein-protein interaction network of the genes containing the identified SNPs (RPTOR, CLPTM1L, ALDH1L1, LY6D, PCDH9, B3GNTL1, CDS1, ADCYAP and FAM53A) reveals that, at the molecular level, there seems to be interconnected factors that have an effect on the progression of renal impairment among DM patients. In conclusion, our findings reveal the potential of employing machine learning algorithms to augment traditional methods and our findings suggest what molecular mechanisms may underlie the complex interaction between DM and chronic kidney disease. Moreover, the development of our AI-assisted models will improve precision when diagnosing renal impairment in predisposed patients, both DM and non-DM. Finally, a large prospective cohort study is needed to validate the clinical utility and mechanistic implications of these biomarker signatures.
| S-EPMC9630270 | biostudies-literature
Project description:Diabetic retinopathy (DR) is the leading cause of blindness in the working-age population, and there are no diagnostic biomarkers and intervention methods for DR developed from glucose well-controlled diabetic patients (GW-DR) to date. Here, we established a prospective cohort of 2126 diabetic Chinese adults (DM) including1134 subjects without ocular diseases at baseline. After 2-year follow-up, 42 participants (21 new-onset GW-DR and 21 matched control) with HbA1c persistently less than 7% were enrolled to profile the serum metabolic features of GW-DR through targeted metabolomics. Among different levels of metabolites, the lower level of ethanolamine with an AUC of 0.954 was significantly associated with early-stage GW-DR risk compared to HbA1c with a 0.506 AUC. Moreover, ethanolamine attenuated diabetic retinal inflammation in STZ-induced diabetic rats with inactivating microglia and DAG-PKC pathway remodeling. In conclusion, ethanolamine, as a potential metabolic biomarker for early diagnosis of GW-DR, may provide a biomarker-based treatment for DR prevention. We then performed gene expression profiling analysis using data obtained from RNA-seq of 4 different cells at two time points.
2022-11-13 | GSE217573 | GEO
Project description:Current diagnostic methods for diabetic nephropathy (DN) lack precision, especially in early stages and monitoring progression. This study aims to find potential biomarkers for DN progression and evaluate their accuracy. Using serum samples from healthy controls (NC), diabetic patients (DM), early-medium stage DN (DN-EM), and late-stage DN (DN-L), researchers employed quantitative proteomics and Mfuzz clustering analysis revealed 15 proteins showing increased expression during DN progression, hinting at their biomarker potential. Combining Mfuzz clustering with weighted gene co-expression network analysis (WGCNA) highlighted five candidates (HMGB1, CD44, FBLN1, PTPRG, and ADAMTSL4). HMGB1 emerged as a promising biomarker, closely correlated with renal function changes. Experimental validation supported HMGB1’s upregulation under high glucose conditions, reinforcing its potential as an early detection biomarker for DN. This research advances DN understanding and identifies five potential biomarkers, notably HMGB1, as a promising early monitoring target. These findings set the stage for future clinical diagnostic applications in DN.
2023-12-28 | PXD047872 | Pride
Project description:Elaidic acid is an abundant industrial produced trans fatty acid in foodstuffs. Trans fatty acid intake has been correlated to an unfavorable plasma lipoprotein profile and an increased cardiovascular disease risk. The present study aimed to identify a plasma protein biomarker panel related to human intake of elaidic acid. The human liver cell line HepG2-SF was used as a model system, and the cells were maintained for seven days in serum-free medium containing 100 µM elaidic acid (trans∆9-C18:1), oleic acid (cis∆9-C18:1) or stearic acid (C18:0). The secretomes were analyzed by stable isotope labeling of amino acids in cell culture (SILAC), difference in gel electrophoresis (DIGE) and gene expression microarray analysis. Twelve proteins were found to be differentially regulated based on SILAC data (>1.3 fold change, P-value < 0.05), 13 proteins were found to be differentially regulated based on DIGE analysis (>1.3 fold change, P-value < 0.05), and 17 mRNA transcripts encoding extracellular proteins were determined to be affected (>1.3 fold change, P-value < 0.01) following the addition of elaidic acid compared to oleic acid or stearic acid. The results revealed that 37 proteins were regulated specifically in response to elaidic acid exposure, and nine of these proteins were confirmed to be regulated in this manner by using selected reaction monitoring mass spectrometry. HepG2 cells kept used in serum free conditions. The cells were incubated for seven days in either 100 µM oleic, elaidic or stearic acid, before total RNA was extracted. For each group four biological replicates were made and from the each RNA extraction two technical replicates were made. There is a control group without fatty acid incubation.
2011-11-30 | E-GEOD-34045 | biostudies-arrayexpress
Project description:Identification of ethanolamine as a biomarker and therapeutic potential for diabetic retinopathy in glucose well-controlled diabetic patients
| PRJNA899563 | ENA
Project description:Elaidic acid is an abundant industrial produced trans fatty acid in foodstuffs. Trans fatty acid intake has been correlated to an unfavorable plasma lipoprotein profile and an increased cardiovascular disease risk. The present study aimed to identify a plasma protein biomarker panel related to human intake of elaidic acid. The human liver cell line HepG2-SF was used as a model system, and the cells were maintained for seven days in serum-free medium containing 100 µM elaidic acid (trans∆9-C18:1), oleic acid (cis∆9-C18:1) or stearic acid (C18:0). The secretomes were analyzed by stable isotope labeling of amino acids in cell culture (SILAC), difference in gel electrophoresis (DIGE) and gene expression microarray analysis. Twelve proteins were found to be differentially regulated based on SILAC data (>1.3 fold change, P-value < 0.05), 13 proteins were found to be differentially regulated based on DIGE analysis (>1.3 fold change, P-value < 0.05), and 17 mRNA transcripts encoding extracellular proteins were determined to be affected (>1.3 fold change, P-value < 0.01) following the addition of elaidic acid compared to oleic acid or stearic acid. The results revealed that 37 proteins were regulated specifically in response to elaidic acid exposure, and nine of these proteins were confirmed to be regulated in this manner by using selected reaction monitoring mass spectrometry.
2011-11-30 | GSE34045 | GEO
Project description:Cell state determination is apparent within the endometrium during the mid-luteal window of implantation. Using previously identified biomarkers of cell states (SCARA5 and DIO2) we performed bulk RNA sequencing on 6 pairs of endometrial biopsies characterised by either normal biomarker expression in both biopsies, or abnormal biomarker expression in one biopsy (low SCARA5 and high DIO2) and normal expression in a second biopsy. We demonstrate that “abnormal cycles” are associated with a distinct gene expression profile when compared to “normal cycles” and have utilised this dataset for biomarker discovery.
2024-10-21 | GSE245963 | GEO
Project description:Biomarker discovery in pre-menstrual endometrial biopsies
| PRJNA1033578 | ENA
Project description:The Trans-omics Landscape of COVID-19
| PRJEB43380 | ENA