The application of weighted gene co-expression network analysis and support vector machine learning in the screening of Parkinson's disease biomarkers and construction of diagnostic models.
Parkinson
biomarkers
immune microenvironment
support vector machine
weighted gene co-expression network analysis
Journal
Frontiers in molecular neuroscience
ISSN: 1662-5099
Titre abrégé: Front Mol Neurosci
Pays: Switzerland
ID NLM: 101477914
Informations de publication
Date de publication:
2023
2023
Historique:
received:
08
08
2023
accepted:
29
09
2023
medline:
1
11
2023
pubmed:
1
11
2023
entrez:
1
11
2023
Statut:
epublish
Résumé
This study aims to utilize Weighted Gene Co-expression Network Analysis (WGCNA) and Support Vector Machine (SVM) algorithm for screening biomarkers and constructing a diagnostic model for Parkinson's disease. Firstly, we conducted WGCNA analysis on gene expression data from Parkinson's disease patients and control group using three GEO datasets (GSE8397, GSE20163, and GSE20164) to identify gene modules associated with Parkinson's disease. Then, key genes with significantly differential expression from these gene modules were selected as candidate biomarkers and validated using the GSE7621 dataset. Further functional analysis revealed the important roles of these genes in processes such as immune regulation, inflammatory response, and cell apoptosis. Based on these findings, we constructed a diagnostic model by using the expression data of FLT1, ATP6V0E1, ATP6V0E2, and H2BC12 as inputs and training and validating the model using SVM algorithm. The prediction model demonstrated an AUC greater than 0.8 in the training, test, and validation sets, thereby validating its performance through SMOTE analysis. These findings provide strong support for early diagnosis of Parkinson's disease and offer new opportunities for personalized treatment and disease management. In conclusion, the combination of WGCNA and SVM holds potential in biomarker screening and diagnostic model construction for Parkinson's disease.
Sections du résumé
Background
UNASSIGNED
This study aims to utilize Weighted Gene Co-expression Network Analysis (WGCNA) and Support Vector Machine (SVM) algorithm for screening biomarkers and constructing a diagnostic model for Parkinson's disease.
Methods
UNASSIGNED
Firstly, we conducted WGCNA analysis on gene expression data from Parkinson's disease patients and control group using three GEO datasets (GSE8397, GSE20163, and GSE20164) to identify gene modules associated with Parkinson's disease. Then, key genes with significantly differential expression from these gene modules were selected as candidate biomarkers and validated using the GSE7621 dataset. Further functional analysis revealed the important roles of these genes in processes such as immune regulation, inflammatory response, and cell apoptosis. Based on these findings, we constructed a diagnostic model by using the expression data of FLT1, ATP6V0E1, ATP6V0E2, and H2BC12 as inputs and training and validating the model using SVM algorithm.
Results
UNASSIGNED
The prediction model demonstrated an AUC greater than 0.8 in the training, test, and validation sets, thereby validating its performance through SMOTE analysis. These findings provide strong support for early diagnosis of Parkinson's disease and offer new opportunities for personalized treatment and disease management.
Conclusion
UNASSIGNED
In conclusion, the combination of WGCNA and SVM holds potential in biomarker screening and diagnostic model construction for Parkinson's disease.
Identifiants
pubmed: 37908486
doi: 10.3389/fnmol.2023.1274268
pmc: PMC10614158
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1274268Informations de copyright
Copyright © 2023 Cai, Tang, Liu, Zhang and Yang.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Cell Rep Med. 2022 Jun 21;3(6):100661
pubmed: 35732154
Hereditas. 2023 Apr 21;160(1):17
pubmed: 37085930
BMC Cancer. 2022 Mar 26;22(1):330
pubmed: 35346107
Clin Neurophysiol. 2020 Jul;131(7):1444-1452
pubmed: 32388155
Genes Dis. 2019 Feb 27;6(2):120-128
pubmed: 31193965
Brain. 2022 Sep 14;145(9):3058-3071
pubmed: 35722765
Pharmacol Res. 2019 Dec;150:104515
pubmed: 31707035
Phys Ther. 2022 Apr 1;102(4):
pubmed: 34963139
Curr Opin Neurobiol. 2022 Feb;72:72-79
pubmed: 34653835
Dtsch Arztebl Int. 2016 Feb 5;113(5):61-9
pubmed: 26900156
Front Mol Biosci. 2022 Apr 25;9:816939
pubmed: 35547391
BMC Cancer. 2022 Apr 14;22(1):406
pubmed: 35421944
Front Oncol. 2022 Oct 25;12:966817
pubmed: 36387186
J Neuroinflammation. 2022 Jun 6;19(1):135
pubmed: 35668422
Front Immunol. 2021 Jul 16;12:724741
pubmed: 34335635
Neurosci Biobehav Rev. 2021 Jan;120:470-478
pubmed: 33068556
Front Neurosci. 2023 Mar 02;17:1113216
pubmed: 36937665
Mov Disord. 2020 Jan;35(1):20-33
pubmed: 31680318
Mov Disord. 2021 Jan;36(1):25-36
pubmed: 33314312
Brain Res. 2022 Jun 15;1785:147879
pubmed: 35278479
Semin Immunopathol. 2022 Sep;44(5):649-657
pubmed: 35505128
J Neuroinflammation. 2021 Jan 5;18(1):4
pubmed: 33402167
Mol Aspects Med. 2021 Dec;82:100972
pubmed: 34130867
Nat Rev Immunol. 2022 Nov;22(11):657-673
pubmed: 35246670
Front Genet. 2021 Mar 19;12:639160
pubmed: 33815473
Neurochem Int. 2012 Nov;61(6):907-12
pubmed: 22265874
J Physiol Sci. 2017 Jan;67(1):11-17
pubmed: 27289535
Brain Pathol. 2016 May;26(3):410-8
pubmed: 26940058
Med Clin North Am. 2019 Mar;103(2):337-350
pubmed: 30704685