Discovery of Distinct Immune Phenotypes Using Machine Learning in Pulmonary Arterial Hypertension
Discovery of Distinct Immune Phenotypes Using Machine Learning in Pulmonary Arterial Hypertension
复制标题
DOI：
10.1161/circresaha.118.313911
复制
发表时间：
2019-03-15
影响因子：
20.1
通讯作者：
Zamanian, Roham T.
中科院分区：
文献类型：
--
作者：
Sweatt, Andrew J.;Hedlin, Haley K.;Zamanian, Roham T.
理由：越来越多的证据表明肺动脉高压 (PAH) 存在炎症，针对免疫的疗法正在研究中，但是否存在不同的免疫表型仍不清楚。目的：基于血液蛋白质组谱的无监督分析来识别 PAH 免疫表型。方法和结果：在斯坦福大学（发现队列；n=281）和谢菲尔德大学（验证队列；n=281）对第 1 组 PAH 患者进行的一项前瞻性观察研究中进行了评估。 n=104）在 2008 年至 2014 年间，我们使用多重免疫测定法测量了 48 种细胞因子、趋化因子和因子的循环蛋白质组组。在两个队列中独立应用无监督机器学习（共识聚类），将患者分类为蛋白质组免疫簇，无需临床特征的指导。为了识别每个簇中的中心蛋白质，我们进行了部分相关网络分析。随后对不同群体的临床特征和结果进行比较。在发现队列中发现了四个具有不同蛋白质组免疫特征的多环芳烃簇。簇 2 (n=109) 的细胞因子水平与对照相似，较低。其他簇具有免疫网络中心的独特上调蛋白质组 - 簇 1（n = 58；TRAIL [肿瘤坏死因子相关凋亡诱导配体]、CCL5 [C-C 基序趋化因子配体 5]、CCL7、CCL4、MIF [巨噬细胞迁移抑制因子]）、簇 3（n = 77；IL [白细胞介素]-12、IL-17、IL-10、IL-7、VEGF [血管内皮生长因子]）和簇 4（n=37；IL-8、IL-4、PDGF-β [血小板衍生生长因子 β]、IL-6、CCL11）。各集群的人口统计特征、PAH 临床亚型、合并症和药物治疗相似。临床风险的无创和血流动力学替代指标将组 1 确定为高风险组，将组 3 确定为低风险组。五年无移植生存率对组 1 不利（47.6%；95% CI，35.4%-64.1%），对组 3 有利（82.4%；95% CI，72.0%-94.3%；跨组 P
Rationale: Accumulating evidence implicates inflammation in pulmonary arterial hypertension (PAH) and therapies targeting immunity are under investigation, although it remains unknown if distinct immune phenotypes exist.Objective: Identify PAH immune phenotypes based on unsupervised analysis of blood proteomic profiles.Methods and Results: In a prospective observational study of group 1 PAH patients evaluated at Stanford University (discovery cohort; n=281) and University of Sheffield (validation cohort; n=104) between 2008 and 2014, we measured a circulating proteomic panel of 48 cytokines, chemokines, and factors using multiplex immunoassay. Unsupervised machine learning (consensus clustering) was applied in both cohorts independently to classify patients into proteomic immune clusters, without guidance from clinical features. To identify central proteins in each cluster, we performed partial correlation network analysis. Clinical characteristics and outcomes were subsequently compared across clusters. Four PAH clusters with distinct proteomic immune profiles were identified in the discovery cohort. Cluster 2 (n=109) had low cytokine levels similar to controls. Other clusters had unique sets of upregulated proteins central to immune networks-cluster 1 (n=58; TRAIL [tumor necrosis factor-related apoptosis-inducing ligand], CCL5 [C-C motif chemokine ligand 5], CCL7, CCL4, MIF [macrophage migration inhibitory factor]), cluster 3 (n=77; IL [interleukin]-12, IL-17, IL-10, IL-7, VEGF [vascular endothelial growth factor]), and cluster 4 (n=37; IL-8, IL-4, PDGF-beta [platelet-derived growth factor beta], IL-6, CCL11). Demographics, PAH clinical subtypes, comorbidities, and medications were similar across clusters. Noninvasive and hemodynamic surrogates of clinical risk identified cluster 1 as high-risk and cluster 3 as low-risk groups. Five-year transplant-free survival rates were unfavorable for cluster 1 (47.6%; 95% CI, 35.4%-64.1%) and favorable for cluster 3 (82.4%; 95% CI, 72.0%-94.3%; across-cluster P