基于多源域适应的单细胞智能分类

doi:10.19678/j.issn.1000-3428.0067378

摘要/Abstract

摘要： 单细胞核糖核酸(RNA)测序技术被成功应用于产生人体组织和器官的高分辨率细胞图谱,这加深了研究者们对人类疾病组织中细胞异质性的理解。细胞注释是单细胞RNA测序数据分析中非常关键的一步,许多典型的模型利用一个有标签的单细胞参考数据集去注释目标数据集,但目标数据集中部分细胞类型可能不在参考数据集中。整合多个参考数据集可以更好地覆盖目标数据集中的细胞类型,然而多个参考数据集和目标数据集之间存在因测序技术差异等原因造成的批次效应。为此,提出一种基于多源域适应的单细胞分类模型,利用多个已标注细胞类型的参考数据集分别与未标注细胞类型的目标数据集进行对抗训练,消除了批次效应。采用虚拟对抗训练,进一步提升模型预测结果对数据点周围局部微小扰动或噪声的鲁棒性,防止过拟合。在多个单细胞数据集上的实验结果表明,该模型比目前主流模型的细胞识别精度至少提升了5个百分点,为新测序的单细胞身份鉴定提供了新的选择和参考。

关键词: 单细胞核糖核酸测序, 单细胞分类, 多源域适应, 对抗训练, 深度学习

Abstract: Single-cell Ribonucleic Acid (RNA) sequencing technology has proven effective in generating high-resolution cell maps of human tissues and organs, thereby enhancing researchers' comprehension of cellular heterogeneity in human disease tissues. Cell annotation stands as a crucial step in single-cell RNA sequencing data analysis. While many conventional models rely on a labeled single-cell reference dataset to annotate the target dataset, certain cell types within the target dataset may not be represented in the reference dataset. Consequently, integrating multiple reference datasets can offer broader coverage of cell types in the target dataset. Nevertheless, batch effects arise between multiple reference datasets and the target dataset due to disparities in sequencing technologies and other factors. To mitigate this issue, this study introduces a single-cell classification model based on multisource domain adaptation. This model leverages multiple reference datasets, each annotated with cell types, to undergo adversarial training with an unlabeled target dataset, thereby mitigating batch effects. Additionally, virtual adversarial training is employed to bolster the model's predictive robustness against minor perturbations or noise around data points, thus preventing overfitting. Experimental findings across multiple single-cell datasets demonstrate that this model enhances cell recognition accuracy by a minimum of 5 percentage points compared to current mainstream models, offering new avenues and benchmarks for identifying newly sequenced single-cell identities.

Key words: single-cell Ribonucleic Acid(RNA) sequencing, single-cell classification, multisource domain adaptation, adversarial training, deep learning

中图分类号:

TP183

魏琢艺, 罗迈, 李文兵, 曾远松, 余伟江, 杨跃东. 基于多源域适应的单细胞智能分类[J]. 计算机工程, 2024, 50(6): 48-55.

WEI Zhuoyi, LUO Mai, LI Wenbing, ZENG Yuansong, YU Weijiang, YANG Yuedong. Intelligent Single-Cell Classification Based on Multisource Domain Adaptation[J]. Computer Engineering, 2024, 50(6): 48-55.

https://www.ecice06.com/CN/Y2024/V50/I6/48

参考文献

[1] 张淼,孙祥瑞,徐春明.单细胞RNA测序数据分析方法研究进展[J].生物技术通报, 2021, 37(1):52-59. ZHANG M, SUN X R, XU C M. Research progress of approaches in single cell RNA sequencing data analysis[J]. Biotechnology Bulletin, 2021, 37(1):52-59.(in Chinese)
[2] AZIZI E, CARR A J, PLITAS G, et al. Single-cell map of diverse immune phenotypes in the breast tumor microenvironment[J]. Cell, 2018, 174(5):1293-1308.
[3] CUSANOVICH D A, HILL A J, AGHAMIRZAIE D, et al. A single-cell atlas of in vivo mammalian chromatin accessibility[J]. Cell, 2018, 174(5):1309-1324.
[4] HASHIMSHONY T, SENDEROVICH N, AVITAL G, et al. CEL-seq2:sensitive highly-multiplexed single-cell RNA-seq[J]. Genome Biology, 2016, 17:77.
[5] NATARAJAN K N, MIAO Z C, JIANG M M, et al. Comparative analysis of sequencing technologies for single-cell transcriptomics[J]. Genome Biology, 2019, 20(1):70.
[6] 张永卓,傅博强,牛春艳,等.单细胞测序技术的发展[J].计量学报, 2023, 44(1):149-156. ZHANG Y Z, FU B Q, NIU C Y, et al. The development of single cell sequencing[J]. Acta Metrologica Sinica, 2023, 44(1):149-156.(in Chinese)
[7] NAVIN N E. The first five years of single-cell cancer genomics and beyond[J]. Genome Research, 2015, 25(10):1499-1507.
[8] SUVÀ M L, TIROSH I. Single-cell RNA sequencing in cancer:lessons learned and emerging challenges[J]. Molecular Cell, 2019, 75(1):7-12.
[9] JAITIN D A, KENIGSBERG E, KEREN-SHAUL H, et al. Massively parallel single-cell RNA-seq for marker-free decomposition of tissues into cell types[J]. Science, 2014, 343(6172):776-779.
[10] SAUNDERS A, MACOSKO E Z, WYSOKER A, et al. Molecular diversity and specializations among the cells of the adult mouse brain[J]. Cell, 2018, 174(4):1015-1030.
[11] REN X W, WEN W, FAN X Y, et al. COVID-19 immune features revealed by a large-scale single-cell transcriptome atlas[J]. Cell, 2021, 184(23):1895-1913.
[12] HAN X P, ZHOU Z M, FEI L J, et al. Construction of a human cell landscape at single-cell level[J]. Nature, 2020, 581:303-309.
[13] FLORES M, LIU Z T, ZHANG T H, et al. Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis[J]. Briefings in Bioinformatics, 2022, 23(1):531.
[14] LÄHNEMANN D, KÖSTER J, SZCZUREK E, et al. Eleven grand challenges in single-cell data science[J]. Genome Biology, 2020, 21(1):31.
[15] LUECKEN M D, THEIS F J. Current best practices in single-cell RNA-seq analysis:a tutorial[J]. Molecular Systems Biology, 2019, 15(6):e8746.
[16] HAN X P, WANG R Y, ZHOU Y C, et al. Mapping the mouse cell atlas by microwell-seq[J]. Cell, 2018, 172(5):1091-1107.
[17] ARAN D, LOONEY A P, LIU L Q, et al. Reference-based analysis of lung single-cell sequencing reveals a transitional profibrotic macrophage[J]. Nature Immunology, 2019, 20:163-172.
[18] DE KANTER J K, LIJNZAAD P, CANDELLI T, et al. CHETAH:a selective, hierarchical cell type identification method for single-cell RNA sequencing[J]. Nucleic Acids Research, 2019, 47(16):e95.
[19] KISELEV V Y, YIU A, HEMBERG M. scmap:projection of single-cell RNA-seq data across data sets[J]. Nature Methods, 2018, 15:359-362.
[20] BUTLER A, HOFFMAN P, SMIBERT P, et al. Integrating single-cell transcriptomic data across different conditions, technologies, and species[J]. Nature Biotechnology, 2018, 36:411-420.
[21] XU C L, LOPEZ R, MEHLMAN E, et al. Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models[J]. Molecular Systems Biology, 2021, 17(1):e9620.
[22] LIN Y X, CAO Y, KIM H J, et al. scClassify:sample size estimation and multiscale classification of cells using single and multiple reference[J]. Molecular Systems Biology, 2020, 16(6):e9389.
[23] DING J R, ADICONIS X, SIMMONS S K, et al. Systematic comparison of single-cell and single-nucleus RNA-sequencing methods[J]. Nature Biotechnology, 2020, 38:737-746.
[24] TAN Y Q, CAHAN P. SingleCellNet:a computational tool to classify single cell RNA-seq data across platforms and across species[J]. Cell Systems, 2019, 9(2):207-213.
[25] BARON M, VERES A, WOLOCK S L, et al. A single-cell transcriptomic map of the human and mouse pancreas reveals inter-and intra-cell population structure[J]. Cell Systems, 2016, 3(4):346-360.
[26] XIN Y R, KIM J, OKAMOTO H, et al. RNA sequencing of single human islet cells reveals type 2 diabetes genes[J]. Cell Metabolism, 2016, 24(4):608-615.
[27] MURARO M J, DHARMADHIKARI G, GRVN D, et al. A single-cell transcriptome atlas of the human pancreas[J]. Cell Systems, 2016, 3(4):385-394.
[28] VENKAT N, KUNDU J N, SINGH D, et al. Your classifier can secretly suffice multi-source domain adaptation[EB/OL].[2023-03-11]. https://arxiv.org/abs/2103.11169v1.
[29] GANIN Y, LEMPITSKY V. Unsupervised domain adaptation by backpropagation[EB/OL].[2023-03-11].https://cseweb.ucsd.edu//classes/sp18/cse252C-a/CSE252C_20180430.pdf.
[30] MIYATO T, MAEDA S I, KOYAMA M, et al. Virtual adversarial training:a regularization method for supervised and semi-supervised learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(8):1979-1993.
[31] GAO J, HUANG X, LI J D. Unsupervised graph alignment with Wasserstein distance discriminator[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery&Data Mining. New York, USA:ACM Press, 2021:426-435.

选择文件类型/文献管理软件名称

选择包含的内容