Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis
Introduction: An inflammatory condition of the periodontium is called periodontitis (PD). A prevalent chronic autoimmune condition known as rheumatoid arthritis (RA) is characterized by synovial membrane inflammation. Gene interactome analysis offers crucial insights into gene functional relationshi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2024-07-01
|
| Series: | Journal of Orofacial Sciences |
| Subjects: | |
| Online Access: | https://journals.lww.com/10.4103/jofs.jofs_242_23 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560263278460928 |
|---|---|
| author | Sri Shivasankari Thilagar Pradeep Kumar Rathinavelu Pradeep Kumar Yadalam |
| author_facet | Sri Shivasankari Thilagar Pradeep Kumar Rathinavelu Pradeep Kumar Yadalam |
| author_sort | Sri Shivasankari Thilagar |
| collection | DOAJ |
| description | Introduction: An inflammatory condition of the periodontium is called periodontitis (PD). A prevalent chronic autoimmune condition known as rheumatoid arthritis (RA) is characterized by synovial membrane inflammation. Gene interactome analysis offers crucial insights into gene functional relationships, enabling researchers to comprehend biological processes and molecular mechanisms within a genomic dataset. Here, we used bioinformatics analysis to predict the interactomic hub genes involved in RA and PD and their relationships to peripheral mononuclear cells. This study aimed to predict peripheral mononuclear cells based on interactomic hub genes in PD and RA by machine learning algorithms. Method: Gene Expression Omnibus datasets were used to identify the genes linked to RA (GSE224842) and PD (GSE156993). We used the R software packages for Cytoscape Genemania, Gene Ontology (GO) enrichment, and Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathway enrichment for annotation of biological processes and pathways to validate biological functions of the hub differential gene expression observed, and machine learning was used to identify hub genes from interactomic differential gene dataset. Result: Decision tree, AdaBoost, and Random Forest had an area under the receiver operating characteristic curve (AUC) in the receiver operating characteristic curve of 0.967, 1.000, and 0.973, respectively. The AdaBoost model had the best accuracy (1.000). These findings imply that the AdaBoost model had a good diagnostic value and may aid in the early detection of PD in association with RS. As a result, the genes with p value <0.05 and AUC >0.90 showed excellent diagnostic value for PD and RS and thus were considered for the prediction of hub genes. Conclusion: In summary, this study’s identified differential expression analysis and hub genes provide valuable insights into the molecular mechanisms of R.A. and periodontal disease progression. These genes have the potential to serve as biomarkers and offer innovative treatments for these chronic inflammatory diseases. |
| format | Article |
| id | doaj-art-3e86221baa4540c88354b8221b3054de |
| institution | Kabale University |
| issn | 0975-8844 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | Journal of Orofacial Sciences |
| spelling | doaj-art-3e86221baa4540c88354b8221b3054de2025-01-04T15:09:51ZengWolters Kluwer Medknow PublicationsJournal of Orofacial Sciences0975-88442024-07-01162829010.4103/jofs.jofs_242_23Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid ArthritisSri Shivasankari ThilagarPradeep Kumar RathinaveluPradeep Kumar YadalamIntroduction: An inflammatory condition of the periodontium is called periodontitis (PD). A prevalent chronic autoimmune condition known as rheumatoid arthritis (RA) is characterized by synovial membrane inflammation. Gene interactome analysis offers crucial insights into gene functional relationships, enabling researchers to comprehend biological processes and molecular mechanisms within a genomic dataset. Here, we used bioinformatics analysis to predict the interactomic hub genes involved in RA and PD and their relationships to peripheral mononuclear cells. This study aimed to predict peripheral mononuclear cells based on interactomic hub genes in PD and RA by machine learning algorithms. Method: Gene Expression Omnibus datasets were used to identify the genes linked to RA (GSE224842) and PD (GSE156993). We used the R software packages for Cytoscape Genemania, Gene Ontology (GO) enrichment, and Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathway enrichment for annotation of biological processes and pathways to validate biological functions of the hub differential gene expression observed, and machine learning was used to identify hub genes from interactomic differential gene dataset. Result: Decision tree, AdaBoost, and Random Forest had an area under the receiver operating characteristic curve (AUC) in the receiver operating characteristic curve of 0.967, 1.000, and 0.973, respectively. The AdaBoost model had the best accuracy (1.000). These findings imply that the AdaBoost model had a good diagnostic value and may aid in the early detection of PD in association with RS. As a result, the genes with p value <0.05 and AUC >0.90 showed excellent diagnostic value for PD and RS and thus were considered for the prediction of hub genes. Conclusion: In summary, this study’s identified differential expression analysis and hub genes provide valuable insights into the molecular mechanisms of R.A. and periodontal disease progression. These genes have the potential to serve as biomarkers and offer innovative treatments for these chronic inflammatory diseases.https://journals.lww.com/10.4103/jofs.jofs_242_23bioinformaticshub geneimmunityinflammationperiodontal diseaserheumatoid arthritissynovial tissue |
| spellingShingle | Sri Shivasankari Thilagar Pradeep Kumar Rathinavelu Pradeep Kumar Yadalam Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis Journal of Orofacial Sciences bioinformatics hub gene immunity inflammation periodontal disease rheumatoid arthritis synovial tissue |
| title | Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis |
| title_full | Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis |
| title_fullStr | Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis |
| title_full_unstemmed | Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis |
| title_short | Machine Learning Prediction of Peripheral Mononuclear Cells Based on Interactomic Hub Genes in Periodontitis and Rheumatoid Arthritis |
| title_sort | machine learning prediction of peripheral mononuclear cells based on interactomic hub genes in periodontitis and rheumatoid arthritis |
| topic | bioinformatics hub gene immunity inflammation periodontal disease rheumatoid arthritis synovial tissue |
| url | https://journals.lww.com/10.4103/jofs.jofs_242_23 |
| work_keys_str_mv | AT srishivasankarithilagar machinelearningpredictionofperipheralmononuclearcellsbasedoninteractomichubgenesinperiodontitisandrheumatoidarthritis AT pradeepkumarrathinavelu machinelearningpredictionofperipheralmononuclearcellsbasedoninteractomichubgenesinperiodontitisandrheumatoidarthritis AT pradeepkumaryadalam machinelearningpredictionofperipheralmononuclearcellsbasedoninteractomichubgenesinperiodontitisandrheumatoidarthritis |