Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm
BackgroundAlthough an intracranial aneurysm (IA) is widespread and fatal, few drugs can be used to prevent its rupture. This study explored the molecular mechanism and potential targets of IA rupture through bioinformatics methods.MethodsThe gene expression matrices of GSE13353, GSE122897, and GSE15...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1487224/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558690307506176 |
|---|---|
| author | Qi Wu Chunli Yang Cuilan Huang Zhiying Lin |
| author_facet | Qi Wu Chunli Yang Cuilan Huang Zhiying Lin |
| author_sort | Qi Wu |
| collection | DOAJ |
| description | BackgroundAlthough an intracranial aneurysm (IA) is widespread and fatal, few drugs can be used to prevent its rupture. This study explored the molecular mechanism and potential targets of IA rupture through bioinformatics methods.MethodsThe gene expression matrices of GSE13353, GSE122897, and GSE15629 were downloaded. Differentially expressed genes (DEGs) were screened using the limma package. Functional enrichment analysis was performed, and a PPI network was constructed. Furthermore, candidate key genes were identified using the least absolute shrinkage and selection operator (LASSO) regression model, support vector machine-recursive feature elimination (SVM-RFE) analysis, and PPI network analysis. ROC analysis was conducted to further verify the diagnostic value of the key genes.ResultsA total of 334 DEGs were screened, including 175 upregulated genes and 159 downregulated genes. Further functional analysis suggested that the DEGs were enriched in inflammation and immune response pathways. Fourteen hub genes were identified using the two algorithms. The PPI networks of the hub genes were analyzed using the Cytoscape plugin CytoNCA to obtain two key genes (IL10 and Integrin α5 (ITGA5)). The ROC curve analysis showed that the AUC values of IL10 and ITGA5 were 0.801, and 0.786, respectively. In addition, the two key genes were significantly positively correlated with macrophages and Treg (T) cells. The immune score and ESTIMATE score of the ruptured IA group were significantly higher than those of the unruptured IA group.ConclusionThe increase in IL-10 and ITGA5 may weaken the vascular wall by promoting inflammation in blood vessels and immune cells, which could have a harmful effect on the rupture of IAs. |
| format | Article |
| id | doaj-art-54335b1a3c314fb9b68c0ed7d1034ff1 |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-54335b1a3c314fb9b68c0ed7d1034ff12025-01-06T06:59:13ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-01-011110.3389/fmed.2024.14872241487224Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithmQi WuChunli YangCuilan HuangZhiying LinBackgroundAlthough an intracranial aneurysm (IA) is widespread and fatal, few drugs can be used to prevent its rupture. This study explored the molecular mechanism and potential targets of IA rupture through bioinformatics methods.MethodsThe gene expression matrices of GSE13353, GSE122897, and GSE15629 were downloaded. Differentially expressed genes (DEGs) were screened using the limma package. Functional enrichment analysis was performed, and a PPI network was constructed. Furthermore, candidate key genes were identified using the least absolute shrinkage and selection operator (LASSO) regression model, support vector machine-recursive feature elimination (SVM-RFE) analysis, and PPI network analysis. ROC analysis was conducted to further verify the diagnostic value of the key genes.ResultsA total of 334 DEGs were screened, including 175 upregulated genes and 159 downregulated genes. Further functional analysis suggested that the DEGs were enriched in inflammation and immune response pathways. Fourteen hub genes were identified using the two algorithms. The PPI networks of the hub genes were analyzed using the Cytoscape plugin CytoNCA to obtain two key genes (IL10 and Integrin α5 (ITGA5)). The ROC curve analysis showed that the AUC values of IL10 and ITGA5 were 0.801, and 0.786, respectively. In addition, the two key genes were significantly positively correlated with macrophages and Treg (T) cells. The immune score and ESTIMATE score of the ruptured IA group were significantly higher than those of the unruptured IA group.ConclusionThe increase in IL-10 and ITGA5 may weaken the vascular wall by promoting inflammation in blood vessels and immune cells, which could have a harmful effect on the rupture of IAs.https://www.frontiersin.org/articles/10.3389/fmed.2024.1487224/fullLASSO regressionSVM-RFE algorithmintracranial aneurysmROC curvePPI network |
| spellingShingle | Qi Wu Chunli Yang Cuilan Huang Zhiying Lin Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm Frontiers in Medicine LASSO regression SVM-RFE algorithm intracranial aneurysm ROC curve PPI network |
| title | Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm |
| title_full | Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm |
| title_fullStr | Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm |
| title_full_unstemmed | Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm |
| title_short | Screening key genes for intracranial aneurysm rupture using LASSO regression and the SVM-RFE algorithm |
| title_sort | screening key genes for intracranial aneurysm rupture using lasso regression and the svm rfe algorithm |
| topic | LASSO regression SVM-RFE algorithm intracranial aneurysm ROC curve PPI network |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1487224/full |
| work_keys_str_mv | AT qiwu screeningkeygenesforintracranialaneurysmruptureusinglassoregressionandthesvmrfealgorithm AT chunliyang screeningkeygenesforintracranialaneurysmruptureusinglassoregressionandthesvmrfealgorithm AT cuilanhuang screeningkeygenesforintracranialaneurysmruptureusinglassoregressionandthesvmrfealgorithm AT zhiyinglin screeningkeygenesforintracranialaneurysmruptureusinglassoregressionandthesvmrfealgorithm |