Wanning Zheng, Dongdong Lin, Shunan Shi, Jiayi Ren, Jiong Wu, Ming Wang, Shu Wan
{"title":"通过生物信息学和机器学习识别血管性痴呆和阿尔茨海默病的共享诊断基因和机制。","authors":"Wanning Zheng, Dongdong Lin, Shunan Shi, Jiayi Ren, Jiong Wu, Ming Wang, Shu Wan","doi":"10.1177/25424823241289804","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Alzheimer's disease (AD) and vascular dementia (VaD) share overlapping pathophysiological characteristics, yet comparative genetic studies are rare. Understanding these overlaps may aid in identifying common diagnostic markers and therapeutic targets.</p><p><strong>Objective: </strong>This study identifies shared diagnostic genes and mechanisms linking AD and VaD.</p><p><strong>Methods: </strong>Datasets GSE5281 and GSE122063 from the GEO database were used to identify differentially expressed genes (DEGs). Intersection DEGs were analyzed using KEGG and GO enrichment to explore signaling pathways. A PPI network was constructed, and LASSO and SVM-RFE were applied to identify core genes. CIBERSORT assessed immune cell composition and their relationship with core genes. Diagnostic efficacy was evaluated using ROC curves, nomogram, and Decision Curve Analysis (DCA). Core genes were used to identify characteristic genes in various brain regions of AD patients.</p><p><strong>Results: </strong>The analysis identified 9021 DEGs for AD and 373 DEGs for VaD, with 74 co-expressed genes and 8 core genes. ROC curves, nomogram, and DCA indicated high diagnostic accuracy. Core gene analysis revealed differential expression of characteristic genes in various brain regions of AD patients.</p><p><strong>Conclusions: </strong>This research identified 74 co-expressed genes and 8 pivotal diagnostic genes. These genes likely play roles in signal transduction, neuroinflammation, and autophagy in both AD and VaD. The findings offer potential targets for future research and clinical interventions. Further research should use larger, more diverse datasets and incorporate custom NGS panels to identify novel genetic variants, enhancing precise diagnostic and therapeutic strategies.</p>","PeriodicalId":73594,"journal":{"name":"Journal of Alzheimer's disease reports","volume":"8 1","pages":"1558-1572"},"PeriodicalIF":2.8000,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863729/pdf/","citationCount":"0","resultStr":"{\"title\":\"Identifying shared diagnostic genes and mechanisms in vascular dementia and Alzheimer's disease via bioinformatics and machine learning.\",\"authors\":\"Wanning Zheng, Dongdong Lin, Shunan Shi, Jiayi Ren, Jiong Wu, Ming Wang, Shu Wan\",\"doi\":\"10.1177/25424823241289804\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Alzheimer's disease (AD) and vascular dementia (VaD) share overlapping pathophysiological characteristics, yet comparative genetic studies are rare. Understanding these overlaps may aid in identifying common diagnostic markers and therapeutic targets.</p><p><strong>Objective: </strong>This study identifies shared diagnostic genes and mechanisms linking AD and VaD.</p><p><strong>Methods: </strong>Datasets GSE5281 and GSE122063 from the GEO database were used to identify differentially expressed genes (DEGs). Intersection DEGs were analyzed using KEGG and GO enrichment to explore signaling pathways. A PPI network was constructed, and LASSO and SVM-RFE were applied to identify core genes. CIBERSORT assessed immune cell composition and their relationship with core genes. Diagnostic efficacy was evaluated using ROC curves, nomogram, and Decision Curve Analysis (DCA). Core genes were used to identify characteristic genes in various brain regions of AD patients.</p><p><strong>Results: </strong>The analysis identified 9021 DEGs for AD and 373 DEGs for VaD, with 74 co-expressed genes and 8 core genes. ROC curves, nomogram, and DCA indicated high diagnostic accuracy. Core gene analysis revealed differential expression of characteristic genes in various brain regions of AD patients.</p><p><strong>Conclusions: </strong>This research identified 74 co-expressed genes and 8 pivotal diagnostic genes. These genes likely play roles in signal transduction, neuroinflammation, and autophagy in both AD and VaD. The findings offer potential targets for future research and clinical interventions. Further research should use larger, more diverse datasets and incorporate custom NGS panels to identify novel genetic variants, enhancing precise diagnostic and therapeutic strategies.</p>\",\"PeriodicalId\":73594,\"journal\":{\"name\":\"Journal of Alzheimer's disease reports\",\"volume\":\"8 1\",\"pages\":\"1558-1572\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-11-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11863729/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Alzheimer's disease reports\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1177/25424823241289804\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"NEUROSCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Alzheimer's disease reports","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/25424823241289804","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
Identifying shared diagnostic genes and mechanisms in vascular dementia and Alzheimer's disease via bioinformatics and machine learning.
Background: Alzheimer's disease (AD) and vascular dementia (VaD) share overlapping pathophysiological characteristics, yet comparative genetic studies are rare. Understanding these overlaps may aid in identifying common diagnostic markers and therapeutic targets.
Objective: This study identifies shared diagnostic genes and mechanisms linking AD and VaD.
Methods: Datasets GSE5281 and GSE122063 from the GEO database were used to identify differentially expressed genes (DEGs). Intersection DEGs were analyzed using KEGG and GO enrichment to explore signaling pathways. A PPI network was constructed, and LASSO and SVM-RFE were applied to identify core genes. CIBERSORT assessed immune cell composition and their relationship with core genes. Diagnostic efficacy was evaluated using ROC curves, nomogram, and Decision Curve Analysis (DCA). Core genes were used to identify characteristic genes in various brain regions of AD patients.
Results: The analysis identified 9021 DEGs for AD and 373 DEGs for VaD, with 74 co-expressed genes and 8 core genes. ROC curves, nomogram, and DCA indicated high diagnostic accuracy. Core gene analysis revealed differential expression of characteristic genes in various brain regions of AD patients.
Conclusions: This research identified 74 co-expressed genes and 8 pivotal diagnostic genes. These genes likely play roles in signal transduction, neuroinflammation, and autophagy in both AD and VaD. The findings offer potential targets for future research and clinical interventions. Further research should use larger, more diverse datasets and incorporate custom NGS panels to identify novel genetic variants, enhancing precise diagnostic and therapeutic strategies.