免疫性血小板减少症治疗反应的代谢组学特征与机器学习预测:一项前瞻性队列研究
该前瞻性队列研究对91例免疫性血小板减少症(ITP)患者的骨髓活检样本进行代谢组学分析,共定量4494种代谢物,发现新诊断与慢性ITP组间代谢模式显著不同,涉及876种差异代谢物和181条代谢通路;基于五种治疗方案的应答,利用Boruta算法筛选代谢物并以随机森林算法排序重要性,脂质及其代谢有助于区分药物治疗反应。
要点
- 新诊断与慢性ITP组间代谢模式显著不同,涉及876种差异代谢物和181条代谢通路。
- 代谢富集最显著的 pathway 包括鞘脂代谢、鞘脂信号通路、泛醌及其他萜类-醌生物合成等。
- 脂质及其代谢(长链脂肪酸、氧化脂质、甘油磷脂等)有助于区分药物治疗反应。
核心结论
- 本研究揭示了ITP患者骨髓上清中与疾病相关的代谢改变,并发现预测ITP治疗反应的潜在生物标志物。
研究设计与样本
- 前瞻性队列研究,样本来自国家血液病纵向队列研究,采集ITP患者入院时的骨髓活检样本进行代谢组学分析。
- 共纳入91例ITP患者的骨髓活检样本,定量4494种代谢物(正离子模式1456种,负离子模式3038种)。
- 采用机器学习算法(Boruta算法筛选、随机森林算法排序)发现预测ITP治疗反应的生物标志物。
主要发现
- 新诊断与慢性ITP组间代谢模式显著不同,共876种差异代谢物涉及181条独特代谢通路。
- 富集因子和p值显示代谢富集最显著的 pathway 为鞘脂代谢、鞘脂信号通路、泛醌及其他萜类-醌生物合成、硫胺素代谢、色氨酸代谢与辅因子生物合成、磷脂酶D信号通路及磷脂酰肌醇信号系统。
- 基于患者对五种治疗方案的应答,脂质及其代谢(包括长链脂肪酸、氧化脂质、甘油磷脂、磷脂酰胆碱和磷脂酰乙醇胺生物合成)有助于区分药物治疗反应。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Immune thrombocytopenia (ITP) is an autoimmune disease characterized by antibody-mediated platelet destruction and impaired platelet production. The mechanisms underlying ITP and biomarkers predicting the response of drug treatments are elusive. We performed a metabolomic profiling of bone marrow biopsy samples collected from ITP patients admission in a prospective study of the National Longitudinal Cohort of Hematological Diseases. Machine learning algorithms were conducted to discover novel biomarkers to predict ITP patient treatment responses. From the bone marrow biopsies of 91 ITP patients, we quantified a total of 4494 metabolites, including 1456 metabolites in the positive mode and 3038 metabolites in the negative mode. Metabolic patterns varied significantly between groups of newly diagnosed and chronic ITP, with a total of 876 differential metabolites involved in 181 unique metabolic pathways. Enrichment factors and p-values revealed the top metabolically enriched pathways to be sphingolipid metabolism, the sphingolipid signalling pathway, ubiquinone and other terpenoid-quinone biosynthesis, thiamine metabolism, tryptophan metabolism and cofactors biosynthesis, the phospholipase D signalling pathway and the phosphatidylinositol signalling system. Based on patient responses to five treatment options, we screened several metabolites using the Boruta algorithm and ranked their importance using the random forest algorithm. Lipids and their metabolism, including long-chain fatty acids, oxidized lipids, glycerophospholipids, phosphatidylcholine and phosphatidylethanolamine biosynthesis, helped differentiate drug treatment responses. In conclusion, this study revealed metabolic alterations associated with ITP in bone marrow supernatants and a potential biomarker predicting the response to ITP.
引用
- Li Y, Sun T, Chen J, et al. Metabolomics profile and machine learning prediction of treatment responses in immune thrombocytopenia: A prospective cohort study. Br J Haematol. 2024. PMID: 38438130. doi:10.1111/bjh.19391
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。