Identification of diagnostic biomarkers in Alzheimer’s disease by integrated bioinformatic analysis and machine learning strategies

Abstract

BackgroundAlzheimer’s disease (AD) is the most prevalent form of dementia, and is becoming one of the most burdening and lethal diseases. More useful biomarkers for diagnosing AD and reflecting the disease progression are in need and of significance.MethodsThe integrated bioinformatic analysis combined with machine-learning strategies was applied for exploring crucial functional pathways and identifying diagnostic biomarkers of AD. Four datasets (GSE5281, GSE131617, GSE48350, and GSE84422) with samples of AD frontal cortex are integrated as experimental datasets, and another two datasets (GSE33000 and GSE44772) with samples of AD frontal cortex were used to perform validation analyses. Functional Correlation enrichment analyses were conducted based on Gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and the Reactome database to reveal AD-associated biological functions and key pathways. Four models were employed to screen the potential diagnostic biomarkers, including one bioinformatic analysis of Weighted gene co-expression network analysis (WGCNA)and three machine-learning algorithms: Least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) analysis. The correlation analysis was performed to explore the correlation between the identified biomarkers with CDR scores and Braak staging.ResultsThe pathways of the immune response and oxidative stress were identified as playing a crucial role during AD. Thioredoxin interacting protein (TXNIP), early growth response 1 (EGR1), and insulin-like growth factor binding protein 5 (IGFBP5) were screened as diagnostic markers of AD. The diagnostic efficacy of TXNIP, EGR1, and IGFBP5 was validated with corresponding AUCs of 0.857, 0.888, and 0.856 in dataset GSE33000, 0.867, 0.909, and 0.841 in dataset GSE44770. And the AUCs of the combination of these three biomarkers as a diagnostic tool for AD were 0.954 and 0.938 in the two verification datasets.ConclusionThe pathways of immune response and oxidative stress can play a crucial role in the pathogenesis of AD. TXNIP, EGR1, and IGFBP5 are useful biomarkers for diagnosing AD and their mRNA level may reflect the development of the disease by correlation with the CDR scores and Breaking staging.

Insulin resistance induces earlier initiation of cognitive dysfunction mediated by cholinergic deregulation in a mouse model of Alzheimer's disease

“…Insulin signaling in the brain affects neuronal activity (Suzuki et al, 2010). Expression of EGR1 was also reported to decrease in the frontal cortex of AD patients (Hu et al, 2019; Jin et al, 2023). Considering that EGR1 is involved in cholinergic function (Jin et al, 2023; Quirin‐Stricker et al, 1997), reduced expression of Egr1 in APP/IR‐dKI could reflect cholinergic malfunction in these mice.…”

“…Expression of EGR1 was also reported to decrease in the frontal cortex of AD patients (Hu et al, 2019; Jin et al, 2023). Considering that EGR1 is involved in cholinergic function (Jin et al, 2023; Quirin‐Stricker et al, 1997), reduced expression of Egr1 in APP/IR‐dKI could reflect cholinergic malfunction in these mice. NPTX2, which expresses on GABAergic neurons inhibiting excitatory pyramidal neurons (Chang et al, 2010), was downregulated in the frontopolar cortex of AD patients (Xiao et al, 2017), which causes the excitatory/inhibitory imbalance of memory impairment (Xiao et al, 2017).…”

Improve the diagnosis of idiopathic normal pressure hydrocephalus by combining abnormal cortical thickness and ventricular morphometry

“…For the assessment of three different feature combination methods, the Least absolute shrinkage and selection operator with cross-validation (LassoCV) method was initially employed for feature selection. This method can handle potential correlations between features while reducing feature dimensions to minimize collinearity ( Ranstam and Cook, 2018 ; Jin et al, 2023 ). Next, eight state-of-the-art machine learning algorithms were utilized to build models based on three different feature combinations, respectively.…”