摘要
单细胞质谱分析能够获得单个细胞的代谢图谱,揭示细胞之间的异质性,在肿瘤学研究中具有重要价值。该文采用单细胞质谱和机器学习技术,建立了膀胱癌细胞亚型的鉴别方法。基于所采集的单细胞代谢数据,分别使用线性判别分析、随机森林、支持向量机、逻辑回归建立了机器学习分类模型,并进行了模型的性能评估。结果表明,各机器学习模型均具有良好的膀胱癌细胞分型能力,分类准确率≥94.9%,灵敏度≥88.6%,特异度≥93.3%。其中,随机森林算法的分类准确率达100%,模型的受试者工作特征曲线下面积达1。该方法实现了膀胱癌单细胞的代谢物检测及细胞亚型区分,也为更广泛的单细胞代谢组学研究提供了参考。
Single-cell mass spectrometry analysis enables metabolic profiling of individual cells,helps to reveal the heterogeneity among cells,which is of great significance in oncology research.Bladder cancer is the most common malignant tumor in the urinary system at present.Accurate iden⁃tification on the types of bladder cancer cells has an important value in life science and clinical appli⁃cation in the selection of treatment plan,prognosis judgment and drug resistance evaluation of pa⁃tients.In this paper,single-cell mass spectrometry combined with machine learning was used to identify bladder cancer cells.The metabolic profiles for different bladder cancer cell subtypes were investigated by single-cell mass spectrometry analysis system,and classification algorithms were studied.Based on the collected single cell metabolic data,t-distributed stochastic neighbor embed⁃ding(t-SNE)clustering algorithm was used for dimensionality reduction analysis on the data,and the difference between the single cell metabolic profile was visualized in the two-dimensional space.In order to accurately identify different types of bladder cancer cells,linear discriminant analysis,ran⁃dom forest,support vector machine and logistic regression were respectively used to establish ma⁃chine learning classification models,and grid search method and 5-fold cross-validation were used to optimize the model parameters.Then,five repeats of 10-fold cross-validation were performed on all data sets,and the averaged statistical result was taken as the final result.Accuracy,sensitivity,specificity,receiver operating characteristic(ROC)analysis and other indicators were used to comprehensively evaluate the performance of the model.The results showed that the metabolites of a sin⁃gle bladder cancer cell,such as ADP,ATP,glutamic acid,pyroglutamic acid,glutathione,etc,were successfully detected by the single-cell mass spectrometry system.There were significant differ⁃ences among different types of bladder cancer cells,as well as large differences among single cells of the same type,indicating the high heterogeneity of single cell in the tumor.In addition,the four machine learning models all had good typing ability for bladder cancer cells,with a comprehensive accuracy not less than 94.9%,a sensitivity not less than 88.6%and a specificity not less than 93.3%.Compared with other methods,the random forest algorithm has the highest classification ac⁃curacy,sensitivity and specificity,which are all up to 100%,and the area under the ROC curve(AUC)of the model is up to 1,indicating that this method has obvious advantages in classification performance.The method presented in this paper realized the detection of metabolites and differentia⁃tion of cell subtypes at single cell level of bladder cancer,paving the way for more single cell metabo⁃lomics research in future.
作者
孙佳琪
陈安琪
闫明月
傅广候
李刚强
金百冶
陈腊
闻路红
SUN Jia-qi;CHEN An-qi;YAN Ming-yue;FU Guang-hou;LI Gang-qiang;JIN Bai-ye;CHEN La;WEN Lu-hong(The Research Institute of Advanced Technology,Ningbo University,Ningbo 315211,China;China Innovation Instrument Co.Ltd.,Ningbo 315100,China;Hua Yue Enterprise Holdings Ltd,Guangzhou 511400,China;The First Affiliated Hospital of Zhejiang University School of Medicine,Hangzhou 310009,China)
出处
《分析测试学报》
CAS
CSCD
北大核心
2023年第5期621-627,共7页
Journal of Instrumental Analysis
基金
国家重点研发计划资助项目(2022YFF0705002)
国家自然科学基金资助项目(81902604)
浙江省重点研发计划项目(2020C03026,2020C02023)
宁波市3315创新团队项目(2017A-17-C)
宁波市重点研发计划项目(2022Z130)
广州市番禺区创新创业领军团队资助项目(2017-R01-5)
宁波大学王宽诚幸福基金项目。
关键词
单细胞质谱分析
膀胱癌
代谢物检测
细胞分型
single-cell mass spectrometry
bladder cancer
metabolite detection
cell typing
