A Diagnostic Model for Alzheimer’s Disease Based on Blood Levels of Autophagy-Related Genes

Abstract

Alzheimer’s disease (AD) is a common neurodegenerative disease. The major problems that exist in the diagnosis of AD include the costly examinations and the high-invasive sampling tissue. Therefore, it would be advantageous to develop blood biomarkers. Because AD’s pathological process is considered tightly related to autophagy; thus, a diagnostic model for AD based on ATGs may have more predictive accuracy than other models. We obtained GSE63060 dataset from the GEO database, ATGs from the HADb and screened 64 differentially expressed autophagy-related genes (DE-ATGs). We then applied them to Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses as well as DisGeNET and PaGenBase enrichment analyses. By using the univariate analysis, least absolute shrinkage and selection operator (LASSO) regression method and the multivariable logistic regression, nine DE-ATGs were identified as biomarkers, which are ATG16L2, BAK1, CAPN10, CASP1, RAB24, RGS19, RPS6KB1, ULK2, and WDFY3. We combined them with sex and age to establish a nomogram model. To evaluate the model’s distinguishability, consistency, and clinical applicability, we applied the receiver operating characteristic (ROC) curve, C-index, calibration curve, and on the validation datasets GSE63061, GSE54536, GSE22255, and GSE151371 from GEO database. The results show that our model demonstrates good prediction performance. This AD diagnosis model may benefit both clinical work and mechanistic research.

A History of Repeated Alcohol Intoxication Promotes Cognitive Impairment and Gene Expression Signatures of Disease Progression in the 3xTg Mouse Model of Alzheimer’s Disease

“…Genes with decreased expression in astrocytes in 3xTg-AD mice exposed to alcohol versus WT controls but not in 3xTg-AD mice or WT mice exposed to alcohol versus WT controls included the following: the WD repeat-containing protein Wdr17, abundantly expressed in astrocytes and associated with macular degeneration ( Stöhr et al, 2002 ); Smim4, which may be involved in mitochondrial toxicity ( Dennerlein et al, 2021 ); and autophagy-related 16 like 2 (Atg16l2), a proposed peripheral marker of AD ( Qin et al, 2022 ) that has been shown to be a negative regulator of the NOD (nucleotide-binding oligomerization domain)-like receptor family, pyrin domain containing 3 (NLRP3) inflammasome ( Wang et al, 2022 ) and thus may contribute to neuroinflammation ( Fig. 4 B , Extended Data Fig.…”

Identification of cuproptosis-related gene clusters and immune cell infiltration in major burns based on machine learning models and experimental validation

“…In recent years, machine learning models based on demographic and imaging indicators have been increasingly used to predict disease prevalence. Studies have shown that a multifactor analysis, which considers the relationships between variables, has lower error rates and more reliable results than a single-factor analysis ( 39 ). In this study, we assessed and compared the predictive performance of four specifically chosen machine learning classifiers (RF, SVM, GLM, and XGB) based on cluster-specific GLM expression profiles and established a GLM-based predictive model that demonstrated the highest predictive capability (AUC = 0.989).…”

Identification of immune infiltration and cuproptosis-related molecular clusters in tuberculosis

“…In recent years, machine learning models based on demographic and imaging metrics have been increasingly used to predict disease prevalence. Some studies confirmed that multivariate analysis takes into account the relationship between variables and therefore has a lower error rate and more reliable results than single-factor analysis (50,51). Since TB is an infectious disease, there is an urgent need for accurate models to predict the prevalence of TB.…”