ORIGINAL RESEARCH article
Front. Aging Neurosci.
Sec. Alzheimer's Disease and Related Dementias
Volume 17 - 2025 | doi: 10.3389/fnagi.2025.1568337
This article is part of the Research TopicExploring the Applications of Artificial Intelligence in Disease Screening, Diagnosis, Treatment, and NursingView all articles
Identification and validation of pyroptosis-related genes in Alzheimer's disease based on multi-transcriptome and machine learning
Provisionally accepted
- North Sichuan Medical College, Nanchong, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Alzheimer'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.We integrated multiple transcriptomes of AD patients from the GEO database, and analyzed the PRGs expression in combined datasets. Machine learning algorithms and comprehensive bioinformatics analysis (including immune infiltration, receiver operating characteristic (ROC)) was 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.We identified 91 PRGs in AD using the 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, 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 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.This 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.
Keywords: Alzheimer's disease, pyroptosis, machine learning, bioinformatics, Immune infiltration, regulatory network
Received: 29 Jan 2025; Accepted: 29 Apr 2025.
Copyright: © 2025 Wu, Wang, Li, Zhou, Yuan, Liu, Zeng, Chen and He. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Zhuoze Wu, North Sichuan Medical College, Nanchong, China
Qi He, North Sichuan Medical College, Nanchong, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.