基于图神经网络的肺癌单细胞转录组数据细胞类型识别*

沈阳 ,  王彤 ,  刘改琴 ,  田雅昕 ,  房瑞玲 ,  罗艳虹 ,  曾平 ,  余红梅 ,  张岩波 ,  曹红艳

中国卫生统计 ›› 2026, Vol. 43 ›› Issue (5) : 674 -681.

PDF (3471KB)
中国卫生统计 ›› 2026, Vol. 43 ›› Issue (5) : 674 -681. DOI: 10.11783/j.issn.1002-3674.2026.05.006
论著

基于图神经网络的肺癌单细胞转录组数据细胞类型识别*

作者信息 +

Cell Type Identification of Single-cell RNA Sequencing Data in Lung Cancer based on Graph Neural Network

Author information +
文章历史 +
PDF (3553K)

摘要

目的 探讨单细胞图神经网络(single-cell graph neural network, scGNN)方法在肺癌单细胞转录组测序 (scRNA-seq)数据上的应用,识别肺癌细胞亚群,发现肺癌潜在靶点及特异性标志物。方法 采用scGNN 方法对肺癌 scRNA-seq数据进行聚类分析,并与经典的单细胞聚类方法SC3、Seurat以及谱聚类方法进行比较。进一步对scGNN方法 的细胞分型结果进行细胞注释、差异基因筛选、GO富集分析和细胞通讯等下游分析。结果 scGNN将肺癌scRNA-seq数 据细胞分为10类,并将其注释为五种主要细胞类型。筛选出841个差异基因,GO 富集分析得到715个富集项。细胞通讯 分析检测到 118 个重要的配体-受体对,14 条信号通路,并分析 MIF 信号通路网络中细胞类型间的相互作用。结论 scGNN方法能够有效地识别细胞亚型,其细胞分型准确性优于传统分型方法,通过筛选差异表达基因,探索细胞间相互作 用,识别潜在生物标志物,获取肺癌相关靶点,对肺癌靶向药物治疗策略具有重要意义。

Abstract

【Abstract】 Objective This study explores the application of graph neural networks (GNNs) on lung cancer scRNA- seq data to identify potential therapeutic targets and specific biomarkers, providing valuable insights for targeted therapy. Methods The scGNN method is used to analyze the data and is compared with three other approaches. Further downstream analyses, including cell annotation, differential gene screening, GO enrichment analysis, and cell-cell communication, are also performed.Results The scGNN method divides the sample data into 10 clusters and identifies them as five major cell types. A total of 841 differential expression genes are selected, with the top 15 visualized. GO enrichment analysis yielded 715 significant terms, with the top 15 most enriched terms presented graphically. Cell-cell communication analysis detects 118 important ligand-receptor pairs, which are further categorized into 14 signaling pathways. The MIF signaling pathway is analyzed in detail.Conclusion The scGNN method effectively identifies cell subtypes and outperforms traditional classification methods in terms of results. Subsequent analysis can help identify potential biomarkers and lung cancer-related targets, which is of great significance for tumor-targeted drug treatment strategies.

关键词

单细胞转录组 / 图神经网络 / 肺癌 / 细胞类型识别

Key words

Single-cell transcriptomics / Graph neural networks / Lung cancer / Cell type identification

引用本文

引用格式 ▾
沈阳,王彤,刘改琴,田雅昕,房瑞玲,罗艳虹,曾平,余红梅,张岩波,曹红艳. 基于图神经网络的肺癌单细胞转录组数据细胞类型识别*[J]. 中国卫生统计, 2026, 43(5): 674-681 DOI:10.11783/j.issn.1002-3674.2026.05.006

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

Smolarz B, Łukasiewicz H, Samulak D, et al. Lung cancer: epidemiology, pathogenesis, treatment and molecular aspect (review of literature)[J].International journal of molecular sciences, 2025, 26(5): 2049.

[2]

Thapa R, Gupta G, Bhat AA, et al. A review of Glycogen Synthase Kinase—3 (GSK3) inhibitors for cancers therapies[J].International Journal of Biological Macromolecules, 2023, 253(Pt7): 127375.

[3]

孙可欣,李荔,王少明,等. 2024年中国分地区恶性肿瘤流行情况分析[J].中华肿瘤杂志,2026,48(3):400-412.

[4]

Bai X, Li Y, Zeng X, et al. Single—cell sequencing technology in tumor research[J].Clinica Chimica Acta, 2021, 518: 101-109.

[5]

张凌谱,杨佳臻,唐东升,等. 靶向肿瘤进化的创新纳米药物[J].中国科学:化学,2022,52(12):2121-2155.

[6]

刘亚飞, 叶贯超, 黄岚, 等. 单细胞转录组在晚期肺腺癌患者个体化治疗中的应用[J].中华实验外科杂志, 2020, 37(5): 3.

[7]

Wang Z, Ding H, Zou Q. Identifying cell types to interpret scRNA—seq data: how, why and more possibilities[J].Briefings in Functional Genomics, 2020, 19(4): 286-291.

[8]

Hu J, Li X, Hu G, et al. Iterative transfer learning with neural network for clustering and cell type classification in single—cell RNA—seq analysis[J].Nature Machine Intelligence, 2020, 2(10): 607-618.

[9]

Park S, Zhao H. Spectral clustering based on learning similarity matrix[J].Bioinformatics, 2018, 34(12): 2069-2076.

[10]

Kiselev VY, Kirschner K, Schaub MT, et al. SC3: consensus clustering of single—cell RNA—seq data[J].Nature Methods, 2017, 14(5): 483-486.

[11]

Satija R, Farrell JA, Gennert D, et al. Spatial reconstruction of single—cell gene expression data[J].Nature Biotechnology, 2015, 33(5): 495-502.

[12]

何佳, 王文杰, 张刘超, 等. Specter 聚类方法在单细胞RNA 测序数据分析中的应用[J].中国卫生统计, 2023, 40(3): 354-357.

[13]

Wang J, Ma A, Chang Y, et al. scGNN is a novel graph neural network framework for single—cell RNA—Seq analyses[J].Nature Communications, 2021, 12(1): 1882.

[14]

Barrett T, Wilhite SE, Ledoux P, et al. NCBI GEO: archive for functional genomics data sets: update[J].Nucleic Acids Research, 2012, 41(D1): D991-D995.

[15]

Hao Y, Stuart T, Kowalski MH, et al. Dictionary learning for integrative, multimodal and scalable single—cell analysis[J].Nature Biotechnology, 2024, 42(2): 293-304.

[16]

Kipf TN, Welling M. Variational Graph Auto—Encoders[J].Stat, 2016, 1050: 21.

[17]

Wolf FA, Hamey FK, Plass M, et al. PAGA: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells[J].Genome Biology, 2019, 20(1): 59.

[18]

Liu FT, Ting KM, Zhou ZH. Isolation forest[C]//2008 eighth ieee international conference on data mining. IEEE, 2008: 413-422.

[19]

Blondel V, Guillaume JL, Lambiotte R. Fast unfolding of communities in large networks: 15 years later[J].Journal of Statistical Mechanics: Theory and Experiment, 2024, 2024(10): 10R001.

[20]

Linderman GC, Rachh M, Hoskins JG, et al. Fast interpolation—based t—SNE for improved visualization of single—cell RNA—seq data[J].Nature Methods, 2019, 16(3): 243-245.

[21]

Davies DL, Bouldin DW. A cluster separation measure[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1979(2): 224-227.

[22]

Caliński T, Harabasz J. A dendrite method for cluster analysis[J].Communications in Statistics—theory and Methods, 1974, 3(1): 1-27.

[23]

Aran D, Looney AP, Liu L, et al. Reference—based analysis of lung single—cell sequencing reveals a transitional profibrotic macrophage[J].Nature Immunology, 2019, 20(2): 163-172.

[24]

Mabbott NA, Baillie JK, Brown H, et al. An expression atlas of human primary cells: inference of gene function from coexpression networks[J].BMC Genomics, 2013, 14(1): 632.

[25]

Gene Ontology Consortium. The Gene Ontology resource: enriching a GOld mine[J].Nucleic Acids Research, 2021, 49(D1): D325-D334.

[26]

Wu T, Hu E, Xu S, et al. clusterProfiler 4.0: A universal enrichment tool for interpreting omics data[J].The Innovation, 2021, 2(3): 100141.

[27]

Huber W, Carey VJ, Gentleman R, et al. Orchestrating high—throughput genomic analysis with Bioconductor[J].Nature Methods, 2015, 12(2): 115-121.

[28]

Jin S, Guerrero—Juarez CF, Zhang L, et al. Inference and analysis of cell—cell communication using CellChat[J].Nature Communications, 2021, 12(1): 1088.

[29]

Fan J, Slowikowski K, Zhang F. Single—cell transcriptomics in cancer: computational challenges and opportunities[J].Experimental & Molecular Medicine, 2020, 52(9): 1452-1465.

[30]

Rooney C, Sethi T. The epithelial cell and lung cancer: the link between chronic obstructive pulmonary disease and lung cancer[J].Respiration, 2011, 81(2): 89-104.

[31]

Pak MG, Shin DH, Lee CH, et al. Significance of EpCAM and TROP2 expression in non—small cell lung cancer[J].World Journal of Surgical Oncology, 2012, 10: 1-8.

[32]

Barkal AA, Brewer RE, Markovic M, et al. CD24 signalling through macrophage Siglec—10 is a target for cancer immunotherapy[J].Nature, 2019, 572(7769): 392-396.

[33]

Xu J, Guo Y. FCGR1A serves as a novel biomarker and correlates with immune infiltration in four cancer types[J].Frontiers in Molecular Biosciences, 2020, 7: 581615.

[34]

Salem A, Alotaibi M, Mroueh R, et al. CCR7 as a therapeutic target in Cancer[J].Biochimica et Biophysica Acta (BBA) —Reviews on Cancer, 2021, 1875(1): 188499.

[35]

Yue Z, Ningning D, Lin Y, et al. Correlation between CXCR4, CXCR5 and CCR7 expression and survival outcomes in patients with clinical T1N0M0 non—small cell lung cancer[J].Thoracic Cancer, 2020, 11(10): 2955-2965.

[36]

Wang H, Sahu A, Chuong MD, et al. TCF4 as a potential prognostic biomarker and an anticancer target in gastric cancer[J].Translational Cancer Research, 2024, 13(9): 5073.

[37]

He Y, Yu F, Tian Y, et al. Single—cell RNA sequencing unravels distinct tumor microenvironment of different components of lung adenocarcinoma featured as mixed ground—glass opacity[J].Frontiers in Immunology, 2022, 13: 903513.

[38]

Deng Y, Xia L, Zhang J, et al. Multicellular ecotypes shape progression of lung adenocarcinoma from ground—glass opacity toward advanced stages[J].Cell Reports Medicine, 2024, 5(4): 101489.

[39]

Calandra T, Bucala R. Macrophage migration inhibitory factor (MIF): a glucocorticoid counter—regulator within the immune system[J].Critical Reviews™ in Immunology, 1997, 17(1): 77-88.

[40]

Tilstam PV, Schulte W, Holowka T, et al. MIF but not MIF—2 recruits inflammatory macrophages in an experimental polymicrobial sepsis model[J].The Journal of Clinical Investigation, 2021, 131(23): e127171.

[41]

Han JM, Jung HJ. Cyclophilin A/CD147 interaction: A promising target for anticancer therapy[J].International Journal of Molecular Sciences, 2022, 23(16): 9341.

[42]

Chen Y, Wang D, Li Y, et al. Spatiotemporal single—cell analysis decodes cellular dynamics underlying different responses to immunotherapy in colorectal cancer[J].Cancer Cell, 2024, 42(7): 1268-1285.

[43]

Ye F, Yuan Z, Tang Y, et al. Endocytic activation and exosomal secretion of matriptase stimulate the second wave of EGF signaling to promote skin and breast cancer invasion[J].Cell Reports, 2024, 43(4): 114002.

[44]

Batlle E, Massagué J. Transforming growth factor—β signaling in immunity and cancer[J].Immunity, 2019, 50(4): 924-940.

[45]

Liu C, Wu K, Li C, et al. SPP1+ macrophages promote head and neck squamous cell carcinoma progression by secreting TNF—α and IL—1β[J].Journal of Experimental & Clinical Cancer Research, 2024, 43(1): 332.

基金资助

国家自然科学基金(82473739;82273742)

山西省基础研究计划(202303021211130)

山西省回国留学人员科研资助项目(2024-081)

山西省高等教育“百亿工程”科技引导专项()

煤炭环境致病与防治教育部重点实验室(山西医科大学)开放课题基金(MEKLCEPP/SXMU-202415)

AI Summary AI Mindmap
PDF (3471KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉