Miao Ya-Ru, Xia Mengxuan, Luo Mei, Luo Tao, Yang Mei, Guo An-Yuan
Center for Artificial Intelligence Biology, Hubei Bioinformatics and Molecular Imaging Key Laboratory, Department of Bioinformatics and Systems Biology, Key Laboratory of Molecular Biophysics of the Ministry of Education, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China.
Research Center of Clinical Medicine, Affiliated Hospital of Nantong University, Nantong 226001, China.
Bioinformatics. 2022 Jan 12;38(3):785-791. doi: 10.1093/bioinformatics/btab711.
Immune cells are important components of the immune system and are crucial for disease initiation, progression, prognosis and survival. Although several computational methods have been designed for predicting the abundance of immune cells, very few tools are applicable to mouse. Given that, mouse is the most widely used animal model in biomedical research, there is an urgent need to develop a precise algorithm for predicting mouse immune cells.
We developed a tool named Immune Cell Abundance Identifier for mouse (ImmuCellAI-mouse), for estimating the abundance of 36 immune cell (sub)types from gene expression data in a hierarchical strategy of three layers. Reference expression profiles and robust marker gene sets of immune cell types were curated. The abundance of cells in three layers was predicted separately by calculating the ssGSEA enrichment score of the expression deviation profile per cell type. Benchmark results showed high accuracy of ImmuCellAI-mouse in predicting most immune cell types, with correlation coefficients between predicted value and real cell proportion of most cell types being larger than 0.8. We applied ImmuCellAI-mouse to a mouse breast tumor dataset and revealed the dynamic change of immune cell infiltration during treatment, which is consistent with the findings of the original study but with more details. We also constructed an online server for ImmuCellAI-mouse, on which users can upload expression matrices for analysis. ImmuCellAI-mouse will be a useful tool for studying the immune microenvironment, cancer immunology and immunotherapy in mouse models, providing an indispensable supplement for human disease studies.
Software is available at http://bioinfo.life.hust.edu.cn/ImmuCellAI-mouse/.
Supplementary data are available at Bioinformatics online.
免疫细胞是免疫系统的重要组成部分，对疾病的发生、发展、预后和生存至关重要。尽管已经设计了几种计算方法来预测免疫细胞的丰度，但很少有工具适用于小鼠。鉴于小鼠是生物医学研究中使用最广泛的动物模型，迫切需要开发一种精确的算法来预测小鼠免疫细胞。
我们开发了一种名为小鼠免疫细胞丰度识别器（ImmuCellAI-mouse）的工具，用于从基因表达数据中以三层分层策略估计36种免疫细胞（亚）类型的丰度。整理了免疫细胞类型的参考表达谱和稳健的标记基因集。通过计算每种细胞类型的表达偏差谱的单样本基因集富集分析（ssGSEA）富集分数，分别预测三层中细胞的丰度。基准结果表明，ImmuCellAI-mouse在预测大多数免疫细胞类型方面具有很高的准确性，大多数细胞类型的预测值与实际细胞比例之间的相关系数大于0.8。我们将ImmuCellAI-mouse应用于一个小鼠乳腺肿瘤数据集，揭示了治疗过程中免疫细胞浸润的动态变化，这与原始研究的结果一致，但更详细。我们还为ImmuCellAI-mouse构建了一个在线服务器，用户可以在上面上传表达矩阵进行分析。ImmuCellAI-mouse将成为研究小鼠模型中免疫微环境、癌症免疫学和免疫治疗的有用工具，为人类疾病研究提供不可或缺的补充。
软件可在http://bioinfo.life.hust.edu.cn/ImmuCellAI-mouse/获取。
补充数据可在《生物信息学》在线获取。
