{"title":"结合生物信息学和机器学习,确定与免疫细胞浸润相关的结核病诊断生物标志物","authors":"","doi":"10.1016/j.tube.2024.102570","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>The asymptomatic nature of tuberculosis (TB) during its latent phase, combined with limitations in current diagnostic methods, makes accurate diagnosis challenging. This study aims to identify TB diagnostic biomarkers by integrating gene expression screening with machine learning, evaluating their diagnostic potential and correlation with immune cell infiltration.</div></div><div><h3>Methods</h3><div>We analyzed GSE19435, GSE19444, and GSE54992 datasets to identify differentially expressed genes (DEGs). GO and KEGG enrichment characterized gene functions. Three machine learning algorithms identified potential biomarkers, validated with GSE83456, GSE62525, and RT-qPCR on clinical samples. Immune cell infiltration was analyzed and verified with blood data.</div></div><div><h3>Results</h3><div>249 DEGs were identified, with PDE7A and DOK3 emerging as potential biomarkers. RT-qPCR confirmed their expression, showing AUCs above 0.75 and a combined AUC of 0.926 for TB diagnosis. Immune infiltration analysis revealed strong correlations between PDE7A, DOK3, and immune cells.</div></div><div><h3>Conclusion</h3><div>PDE7A and DOK3 show strong diagnostic potential for TB, closely linked to immune cell infiltration, and may serve as promising biomarkers and therapeutic targets.</div></div>","PeriodicalId":23383,"journal":{"name":"Tuberculosis","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Combining bioinformatics and machine learning to identify diagnostic biomarkers of TB associated with immune cell infiltration\",\"authors\":\"\",\"doi\":\"10.1016/j.tube.2024.102570\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objective</h3><div>The asymptomatic nature of tuberculosis (TB) during its latent phase, combined with limitations in current diagnostic methods, makes accurate diagnosis challenging. This study aims to identify TB diagnostic biomarkers by integrating gene expression screening with machine learning, evaluating their diagnostic potential and correlation with immune cell infiltration.</div></div><div><h3>Methods</h3><div>We analyzed GSE19435, GSE19444, and GSE54992 datasets to identify differentially expressed genes (DEGs). GO and KEGG enrichment characterized gene functions. Three machine learning algorithms identified potential biomarkers, validated with GSE83456, GSE62525, and RT-qPCR on clinical samples. Immune cell infiltration was analyzed and verified with blood data.</div></div><div><h3>Results</h3><div>249 DEGs were identified, with PDE7A and DOK3 emerging as potential biomarkers. RT-qPCR confirmed their expression, showing AUCs above 0.75 and a combined AUC of 0.926 for TB diagnosis. Immune infiltration analysis revealed strong correlations between PDE7A, DOK3, and immune cells.</div></div><div><h3>Conclusion</h3><div>PDE7A and DOK3 show strong diagnostic potential for TB, closely linked to immune cell infiltration, and may serve as promising biomarkers and therapeutic targets.</div></div>\",\"PeriodicalId\":23383,\"journal\":{\"name\":\"Tuberculosis\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-10-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tuberculosis\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1472979224000969\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"IMMUNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tuberculosis","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1472979224000969","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMMUNOLOGY","Score":null,"Total":0}
Combining bioinformatics and machine learning to identify diagnostic biomarkers of TB associated with immune cell infiltration
Objective
The asymptomatic nature of tuberculosis (TB) during its latent phase, combined with limitations in current diagnostic methods, makes accurate diagnosis challenging. This study aims to identify TB diagnostic biomarkers by integrating gene expression screening with machine learning, evaluating their diagnostic potential and correlation with immune cell infiltration.
Methods
We analyzed GSE19435, GSE19444, and GSE54992 datasets to identify differentially expressed genes (DEGs). GO and KEGG enrichment characterized gene functions. Three machine learning algorithms identified potential biomarkers, validated with GSE83456, GSE62525, and RT-qPCR on clinical samples. Immune cell infiltration was analyzed and verified with blood data.
Results
249 DEGs were identified, with PDE7A and DOK3 emerging as potential biomarkers. RT-qPCR confirmed their expression, showing AUCs above 0.75 and a combined AUC of 0.926 for TB diagnosis. Immune infiltration analysis revealed strong correlations between PDE7A, DOK3, and immune cells.
Conclusion
PDE7A and DOK3 show strong diagnostic potential for TB, closely linked to immune cell infiltration, and may serve as promising biomarkers and therapeutic targets.
期刊介绍:
Tuberculosis is a speciality journal focusing on basic experimental research on tuberculosis, notably on bacteriological, immunological and pathogenesis aspects of the disease. The journal publishes original research and reviews on the host response and immunology of tuberculosis and the molecular biology, genetics and physiology of the organism, however discourages submissions with a meta-analytical focus (for example, articles based on searches of published articles in public electronic databases, especially where there is lack of evidence of the personal involvement of authors in the generation of such material). We do not publish Clinical Case-Studies.
Areas on which submissions are welcomed include:
-Clinical TrialsDiagnostics-
Antimicrobial resistance-
Immunology-
Leprosy-
Microbiology, including microbial physiology-
Molecular epidemiology-
Non-tuberculous Mycobacteria-
Pathogenesis-
Pathology-
Vaccine development.
This Journal does not accept case-reports.
The resurgence of interest in tuberculosis has accelerated the pace of relevant research and Tuberculosis has grown with it, as the only journal dedicated to experimental biomedical research in tuberculosis.