AUTHOR=Wang Yuntai , Li Yilin , Zhou Lu , Yuan Yihuan , Liu Chuanfei , Zeng Zimeng , Chen Yuanqi , He Qi , Wu Zhuoze 

TITLE=Identification and validation of pyroptosis-related genes in Alzheimer’s disease based on multi-transcriptome and machine learning

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 17 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2025.1568337

DOI=10.3389/fnagi.2025.1568337

ISSN=1663-4365

ABSTRACT=BackgroundAlzheimer’s disease (AD) progression is characterized by persistent neuroinflammation, where pyroptosis—an inflammatory programmed cell death mechanism—has emerged as a key pathological contributor. However, the molecular mechanisms through which pyroptosis-related genes (PRGs) drive AD pathogenesis remain incompletely elucidated.MethodsWe integrated multiple transcriptomes of AD patients from the GEO database and analyzed the expression of PRGs in combined datasets. Machine learning algorithms and comprehensive bioinformatics analysis (including immune infiltration and receiver operating characteristic (ROC)) were applied to identify the hub genes. Additionally, we validated the expression patterns of these key genes using the expression data from AD mice and constructed potential regulatory networks through time series and correlation analysis.ResultsWe identified 91 PRGs in AD using the weighted gene co-expression network analysis (WGCNA) and differentially expressed genes analysis. By application of the protein–protein interaction and machine learning algorithms, seven pyroptosis feature genes (CHMP2A, EGFR, FOXP3, HSP90B1, MDH1, METTL3, and PKN2) were identified. Crucially, MDH1 and PKN2 demonstrated superior performance in terms of immune cell infiltration, ROC curves, and experimental validation. Furthermore, we constructed the long non-coding RNA and mRNA (lncRNA-mRNA) regulatory network of these characteristic genes using the gene expression profiles from AD mice at varying ages, revealing the potential regulatory mechanism in AD.ConclusionThis study provides the first comprehensive characterization of pyroptosis-related molecular signatures in AD. Seven hub genes were identified, with particular emphasis on MDH1 and PKN2. Their superior performances were validated through comprehensive bioinformatic analysis in both patient and mouse transcriptomes, as well as the experimental data. Our findings establish foundational insights into pyroptosis mechanisms in AD that may inform novel treatment strategies targeting neuroinflammatory pathways.