Identification of Type 2 Diabetes Based on a Ten-Gene Biomarker Prediction Model Constructed Using a Support Vector Machine Algorithm.
Journal
BioMed research international
ISSN: 2314-6141
Titre abrégé: Biomed Res Int
Pays: United States
ID NLM: 101600173
Informations de publication
Date de publication:
2022
2022
Historique:
received:
30
08
2021
revised:
24
11
2021
accepted:
20
02
2022
entrez:
14
3
2022
pubmed:
15
3
2022
medline:
9
4
2022
Statut:
epublish
Résumé
Type 2 diabetes is a major health concern worldwide. The present study is aimed at discovering effective biomarkers for an efficient diagnosis of type 2 diabetes. Differentially expressed genes (DEGs) between type 2 diabetes patients and normal controls were identified by analyses of integrated microarray data obtained from the Gene Expression Omnibus database using the Limma package. Functional analysis of genes was performed using the R software package clusterProfiler. Analyses of protein-protein interaction (PPI) performed using Cytoscape with the CytoHubba plugin were used to determine the most sensitive diagnostic gene biomarkers for type 2 diabetes in our study. The support vector machine (SVM) classification model was used to validate the gene biomarkers used for the diagnosis of type 2 diabetes. GSE164416 dataset analysis revealed 499 genes that were differentially expressed between type 2 diabetes patients and normal controls, and these DEGs were found to be enriched in the regulation of the immune effector pathway, type 1 diabetes mellitus, and fatty acid degradation. PPI analysis data showed that five MCODE clusters could be considered as clinically significant modules and that 10 genes ( Our results indicate that the SVM-based model developed by us can facilitate accurate diagnosis of type 2 diabetes.
Sections du résumé
Background
UNASSIGNED
Type 2 diabetes is a major health concern worldwide. The present study is aimed at discovering effective biomarkers for an efficient diagnosis of type 2 diabetes.
Methods
UNASSIGNED
Differentially expressed genes (DEGs) between type 2 diabetes patients and normal controls were identified by analyses of integrated microarray data obtained from the Gene Expression Omnibus database using the Limma package. Functional analysis of genes was performed using the R software package clusterProfiler. Analyses of protein-protein interaction (PPI) performed using Cytoscape with the CytoHubba plugin were used to determine the most sensitive diagnostic gene biomarkers for type 2 diabetes in our study. The support vector machine (SVM) classification model was used to validate the gene biomarkers used for the diagnosis of type 2 diabetes.
Results
UNASSIGNED
GSE164416 dataset analysis revealed 499 genes that were differentially expressed between type 2 diabetes patients and normal controls, and these DEGs were found to be enriched in the regulation of the immune effector pathway, type 1 diabetes mellitus, and fatty acid degradation. PPI analysis data showed that five MCODE clusters could be considered as clinically significant modules and that 10 genes (
Conclusion
UNASSIGNED
Our results indicate that the SVM-based model developed by us can facilitate accurate diagnosis of type 2 diabetes.
Identifiants
pubmed: 35281591
doi: 10.1155/2022/1230761
pmc: PMC8916865
doi:
Substances chimiques
Genetic Markers
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1230761Informations de copyright
Copyright © 2022 Jiabin Li et al.
Déclaration de conflit d'intérêts
The authors declare that they have no competing interests.
Références
OMICS. 2012 May;16(5):284-7
pubmed: 22455463
Bioinformatics. 2006 Feb 1;22(3):278-84
pubmed: 16332713
Biomolecules. 2020 Aug 24;10(9):
pubmed: 32847136
Biology (Basel). 2021 Oct 12;10(10):
pubmed: 34681130
Nucleic Acids Res. 2021 Jan 8;49(D1):D605-D612
pubmed: 33237311
Inflammation. 2015 Apr;38(2):710-7
pubmed: 25085744
J Bone Miner Res. 2008 May;23(5):644-54
pubmed: 18433299
Ann Transl Med. 2020 Aug;8(16):997
pubmed: 32953797
BMC Syst Biol. 2014;8 Suppl 4:S11
pubmed: 25521941
J Bone Miner Res. 2018 Nov;33(11):1980-1989
pubmed: 29924424
Periodontol 2000. 2018 Oct;78(1):59-97
pubmed: 30198134
J Diabetes Investig. 2019 Jul;10(4):972-984
pubmed: 30536626
PLoS One. 2012;7(9):e45142
pubmed: 23028809
Bioinformatics. 2021 Aug 31;:
pubmed: 34463706
Diabetologia. 2014 Sep;57(9):1884-8
pubmed: 24965964
Cancer Genomics Proteomics. 2018 Jan-Feb;15(1):41-51
pubmed: 29275361
J Cell Mol Med. 2019 Oct;23(10):6690-6699
pubmed: 31373168
Diabetes. 2009 Jun;58(6):1292-301
pubmed: 19223596
Comput Methods Programs Biomed. 2018 Nov;166:123-135
pubmed: 30415712
Expert Rev Mol Diagn. 2007 Mar;7(2):207-17
pubmed: 17331067
Med Biol Eng Comput. 2021 Sep;59(9):1773-1783
pubmed: 34302269
Diabetes Res Clin Pract. 2019 Nov;157:107843
pubmed: 31518657
Nucleic Acids Res. 2015 Apr 20;43(7):e47
pubmed: 25605792
Sensors (Basel). 2021 Mar 26;21(7):
pubmed: 33810211
Nucleic Acids Res. 2013 Jan;41(Database issue):D991-5
pubmed: 23193258
Expert Rev Mol Diagn. 2011 Nov;11(8):775-92
pubmed: 22022939
Endocr J. 2019 Aug 29;66(8):691-699
pubmed: 31105125
Diabetol Metab Syndr. 2019 Dec 30;11:113
pubmed: 31892956
Genome Res. 2003 Nov;13(11):2498-504
pubmed: 14597658
Diabetes Care. 2020 Jun;43(6):1319-1325
pubmed: 32295805
Ann Transl Med. 2021 Feb;9(4):316
pubmed: 33708943
Cardiovasc Diabetol. 2020 Jan 30;19(1):12
pubmed: 32000781
PLoS One. 2019 Dec 11;14(12):e0219636
pubmed: 31826018
Mol Metab. 2019 Jun;24:98-107
pubmed: 30956117
Talanta. 2022 Jan 15;237:122901
pubmed: 34736716
BMC Med Imaging. 2012 Jan 16;12:1
pubmed: 22248480
Cell Metab. 2019 Jan 8;29(1):202-210.e6
pubmed: 30293775
Mol Med Rep. 2019 Feb;19(2):1065-1073
pubmed: 30569177
Nurs Stand. 2022 Jan 5;37(1):61-66
pubmed: 34708622
Best Pract Res Clin Endocrinol Metab. 2016 Jun;30(3):331-43
pubmed: 27432069
J Clin Endocrinol Metab. 2007 Sep;92(9):3705-11
pubmed: 17595242
Diabetologia. 2017 Oct;60(10):2033-2041
pubmed: 28660492