首页|First Affiliated Hospital of Shenzhen University Reports Findings in Bioinformat ics (Identification of novel biomarkers and immune infiltration characteristics of ischemic stroke based on comprehensive bioinformatic analysis and machine lea rning)
First Affiliated Hospital of Shenzhen University Reports Findings in Bioinformat ics (Identification of novel biomarkers and immune infiltration characteristics of ischemic stroke based on comprehensive bioinformatic analysis and machine lea rning)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Biotechnology - Bioinf ormatics is the subject of a report. According to news reporting originating in Shenzhen, People's Republic of China, by NewsRx journalists, research stated, "I schemic stroke (IS) is one of most common causes of disability in adults worldwi de. However, there is still a lack of effective and reliable diagnostic markers and therapeutic targets in IS." The news reporters obtained a quote from the research from the First Affiliated Hospital of Shenzhen University, "Furthermore, immune cell dysfunction plays an important role in the pathogenesis of IS. Hence, in-depth research on immune-rel ated targets in progressive IS is urgently needed. Expression profile data from patients with IS were downloaded from the Gene Expression Omnibus (GEO) database . Then, differential expression analysis and weighted gene coexpression network analysis (WGCNA) were performed to identify the significant modules and differen tially expressed genes (DEGs). Key genes were obtained and used in functional en richment analyses by overlapping module genes and DEGs. Next, hub candidate gene s were identified by utilizing three machine learning algorithms: least absolute shrinkage and selection operator (LASSO), random forest, and support vector mac hine-recursive feature elimination (SVM-RFE). Subsequently, a diagnostic model w as constructed based on the hub genes, and receiver operating characteristic (RO C) curves were constructed to validate the performances of the predictive models and candidate genes. Finally, the immune cell infiltration landscape of IS was explored with the CIBERSORT deconvolution algorithm. A total of 40 key DEGs were identified based on the intersection of the DEGs and module genes, and we found that these genes were mainly enriched in the regulation of lipolysis in adipocy tes, neutrophil extracellular trap formation and complement and coagulation casc ades. Based on the results from three advanced machine learning algorithms, we o btained 7 hub candidate genes (ABCA1, ARG1, C5AR1, CKAP4, HMFN0839, SDCBP and TL N1) as diagnostic biomarkers of IS and developed a reliable nomogram with high p redictive performance (AUC = 0.987). In addition, immune cell infiltration dysre gulation was implicated in IS, and compared with those in the normal group, IS p atients had increased fractions of gamma delta T cells, monocytes, M0 macrophage s, M2 macrophages and neutrophils and clearly lower percentages of naive B cells , CD8 T cells, CD4 memory T cells, follicular helper T cells, regulatory T cells (Tregs) and resting dendritic cells. Furthermore, correlation analysis indicate d a significant correlation between the hub genes and immune cells in progressiv e IS. In conclusion, our study identified 7 hub genes as diagnostic biomarkers a nd established a reliable model to predict the occurrence of IS. Meanwhile, we e xplored the immune cell infiltration pattern and investigated the relationship b etween candidate genes and immune cells in the pathogenesis of IS."
ShenzhenPeople's Republic of ChinaAs iaBioengineeringBioinformaticsBiotechnologyCerebrovascular Diseases and ConditionsCyborgsEmerging TechnologiesGeneticsHealth and MedicineInfor mation TechnologyMachine LearningStroke