Data_Sheet_2_Identification of anoikis-related genes classification patterns and immune infiltration characterization in ischemic stroke based on machine learning.ZIP

IntroductionIschemic stroke (IS) is a type of stroke that leads to high mortality and disability. Anoikis is a form of programmed cell death. When cells detach from the correct extracellular matrix, anoikis disrupts integrin junctions, thus preventing abnormal proliferating cells from growing or attaching to an inappropriate matrix. Although there is growing evidence that anoikis regulates the immune response, which makes a great contribution to the development of IS, the role of anoikis in the pathogenesis of IS is rarely explored.
MethodsFirst, we downloaded GSE58294 set and GSE16561 set from the NCBI GEO database. And 35 anoikis-related genes (ARGs) were obtained from GSEA website. The CIBERSORT algorithm was used to estimate the relative proportions of 22 infiltrating immune cell types. Next, consensus clustering method was used to classify ischemic stroke samples. In addition, we used least absolute shrinkage and selection operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms to screen the key ARGs in ischemic stroke. Next, we performed receiver operating characteristics (ROC) analysis to assess the accuracy of each diagnostic gene. At the same time, the nomogram was constructed to diagnose IS by integrating trait genes. Then, we analyzed the correlation between gene expression and immune cell infiltration of the diagnostic genes in the combined database. And gene ontology (GO) and kyoto encyclopedia of genes and genomes (KEGG) analysis were performed on these genes to explore differential signaling pathways and potential functions, as well as the construction and visualization of regulatory networks using NetworkAnalyst and Cytoscape. Finally, we investigated the expression pattern of ARGs in IS patients across age or gender.
ResultsOur study comprehensively analyzed the role of ARGs in IS for the first time. We revealed the expression profile of ARGs in IS and the correlation with infiltrating immune cells. And The results of consensus clustering analysis suggested that we can classify IS patients into two clusters. The machine learning analysis screened five signature genes, including AKT1, BRMS1, PTRH2, TFDP1 and TLE1. We also constructed nomogram models based on the five risk genes and evaluated the immune infiltration correlation, gene-miRNA, gene-TF and drug-gene interaction regulatory networks of these signature genes. The expression of ARGs did not differ by sex or age.
DiscussionThis study may provide a beneficial reference for further elucidating the pathogenesis of IS, and render new ideas for drug screening, individualized therapy and immunotherapy of IS.

引言
缺血性脑卒中（Ischemic stroke, IS）是一类具有高病死率与致残率的脑卒中类型。失巢凋亡（anoikis）是一种程序性细胞死亡形式，当细胞脱离正常细胞外基质时，失巢凋亡会破坏整合素连接通路，从而阻止异常增殖的细胞在不适宜的基质上生长或附着。尽管越来越多的证据表明失巢凋亡可调控免疫应答，这对缺血性脑卒中的发生发展具有重要作用，但目前鲜有研究探讨失巢凋亡在缺血性脑卒中发病机制中的作用。

方法
首先，我们从NCBI GEO数据库下载了GSE58294数据集与GSE16561数据集，并从GSEA网站获取了35个失巢凋亡相关基因（anoikis-related genes, ARGs）。采用CIBERSORT算法评估22种浸润免疫细胞的相对占比；随后使用共识聚类法对缺血性脑卒中样本进行分型。此外，我们通过最小绝对收缩和选择算子（least absolute shrinkage and selection operator, LASSO）、支持向量机-递归特征消除（support vector machine-recursive feature elimination, SVM-RFE）以及随机森林（random forest, RF）算法筛选缺血性脑卒中的关键ARGs。继而通过受试者工作特征（receiver operating characteristics, ROC）分析评估各诊断基因的诊断效能，同时整合特征基因构建列线图（nomogram）以辅助缺血性脑卒中的诊断。进而在整合数据库中分析诊断基因的表达与免疫细胞浸润的相关性，并对这些基因开展基因本体（gene ontology, GO）与京都基因与基因组百科全书（kyoto encyclopedia of genes and genomes, KEGG）富集分析，以探究差异信号通路与潜在功能；此外通过NetworkAnalyst和Cytoscape完成调控网络的构建与可视化。最后，我们分析了不同年龄、性别分层的缺血性脑卒中患者中ARGs的表达模式。

结果
本研究首次全面解析了ARGs在缺血性脑卒中中的作用：明确了ARGs在缺血性脑卒中中的表达谱及其与浸润免疫细胞的相关性；共识聚类分析结果显示，可将缺血性脑卒中患者划分为两个亚型。机器学习分析筛选出5个特征基因，分别为AKT1、BRMS1、PTRH2、TFDP1与TLE1。本研究还基于这5个风险基因构建了列线图模型，并评估了这些特征基因的免疫浸润相关性、基因-miRNA、基因-TF以及药物-基因相互作用调控网络。此外，ARGs的表达水平在不同性别、年龄的患者中无显著差异。

讨论
本研究可为进一步阐明缺血性脑卒中的发病机制提供有益参考，同时为其药物筛选、个体化治疗以及免疫治疗提供全新的思路。