计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (7): 280-288.doi: 10.11896/jsjkx.250900078

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

基于图结构感知的单细胞转录组嵌入聚类模型

杨行, 黄瑞章, 薛菁菁, 秦永彬, 陈艳平, 林川   

  1. 贵州大学计算机科学与技术学院 贵阳 550025
    贵州大学文本计算与认知智能教育部工程研究中心 贵阳 550025
    贵州大学公共大数据国家重点实验室 贵阳 550025
  • 收稿日期:2025-09-11 修回日期:2026-01-06 出版日期:2026-07-15 发布日期:2026-07-10
  • 通讯作者: 黄瑞章(cse.rzhuang@gzu.edu.cn)
  • 作者简介:(gs.yangxing24@gzu.edu.cn)
  • 基金资助:
    国家重点研发计划(2023YFC3304500);贵州省科学技术基金重点资助项目(黔科合重大专项字[2024]003);贵州省科技支撑计划资助项目(黔科合支撑[2023]一般448)

Graph-structure-aware Single-cell Transcriptomic Embedding Clustering Model

YANG Hang, HUANG Ruizhang, XUE Jingjing, QIN Yongbin, CHEN Yanping, LIN Chuan   

  1. College of Computer Science and Technology,Guizhou University,Guiyang 550025,China
    Text Computing and Cognitive Intelligence Engineering Research Center,Ministry of Education,Guizhou University,Guiyang 550025,China
    State Key Laboratory of Public Big Data,Guizhou University,Guiyang 550025,China
  • Received:2025-09-11 Revised:2026-01-06 Published:2026-07-15 Online:2026-07-10
  • About author:YANG Hang,born in 2000,postgra-duate.His main research interests include natural language processing and bio-clustering.
    HUANG Ruizhang,born in 1979,professor,Ph.D,is a member of CCF(No.52039M).Her main research interests include big data,data mining,information extraction.
  • Supported by:
    National Key Research and Development Program of China(2023YFC3304500),Key Funded Projects of the Science and Technology Foundation Program of Guizhou Province([2024]003) and Funded Projects of the Science-Technology Foundation Program of Guizhou Province([2023] 448).

PDF (PC)

19

摘要： 细胞聚类作为单细胞RNA测序(scRNA-seq)分析的核心任务,在scRNA-seq数据分析中起着至关重要的作用。近年来,单细胞深度嵌入表示模型因其能够同时学习特征表示和聚类而受到欢迎。然而,这些模型仍面临多种重大挑战,包括海量数据、普遍存在的丢弃事件以及转录谱中的复杂噪声模式。为此,提出基于图结构感知的单细胞转录组嵌入聚类模型(scGAEC)。该模型创新性地融合对比学习机制与自研图感知手段进行更深度嵌入的融合表示,同时基于零膨胀负二项模型(ZINB)设计解码器重建基因表达信息,通过联合互监督策略协同优化聚类损失、对比损失、ZINB损失和基因表达矩阵重建损失,实现聚类性能强化与潜在表征深度学习。实验结果表明,scGAEC在来自不同测序平台的4个单细胞RNA测序数据集上,相较于6个对比模型,在NMI和ARI核心评估指标上性能平均提升30.63%和52.17%,显著优于多种先进方法。

关键词: 聚类, 单细胞RNA聚类, 图结构感知, 对比学习, 零膨胀负二项模型

Abstract: Cell clustering,a core task in single-cell RNA sequencing(scRNA-seq) analysis,plays a crucial role in scRNA-seq data analysis.In recent years,single-cell deep embedding representation models have gained popularity due to their ability to simultaneously learn feature representation and perform clustering.However,these models still face several significant challenges,including massive data,widespread dropout events,and complex noise patterns in the transcriptome.This paper proposes a graph-structure-aware single-cell transcriptomic embedding clustering model(scGAEC).This model innovatively integrates a contrastive learning mechanism with a self-developed graph-aware approach for more in-depth embedding representation.It also designs a decoder based on the zero-inflated negative binomial(ZINB) model to reconstruct gene expression information.By employing a joint mutual supervision strategy,the model optimizes clustering loss,contrastive loss,ZINB loss,and gene expression matrix reconstruction loss in a coordinated manner,thereby enhancing clustering performance and deep learning of latent representation.Experimental results demonstrate that scGAEC achieves average performance improvements of 30.63% in NMI and 52.17% in ARI over six competing models across four single-cell RNA sequencing datasets from different sequencing platforms,significantly outperforming various state-of-the-art methods.

Key words: Clustering, Single-cell RNA clustering, Graph-structure aware, Contrastive learning, Zero-inflated negative binomial model

中图分类号: 

  • Q811
[1]SIMMONS S K,LITHWICK-YANAI G,ADICONIS X,et al.Mostly natural sequencing-by-synthesis for scRNA-seq using Ultima sequencing[J].Nature Biotechnology,2023,41(2):204-211.
[2]PAPALEXI E,SATIJA R.Single-cell RNA sequencing to explore immune cell heterogeneity[J].Nature Reviews Immunology,2018,18(1):35-45.
[3]SVENSSON V,NATARAJAN K N,LY L H,et al.Power ana-lysis of single-cell RNA-sequencing experiments[J].Nature Methods,2017,14(4):381-387.
[4]KISELEV V Y,ANDREWS T S,HEMBERG M.Challenges in unsupervised clustering of single-cell RNA-seq data[J].Nature Reviews Genetics,2019,20(5):273-282.
[5]MACQUEEN J.Some methods for classification and analysis of multivariate observations[C]//Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability.University of California Press,1967,5:281-298.
[6]JOHNSON S C.Hierarchical clustering schemes[J].Psy-chometrika,1967,32(3):241-254.
[7]GRÜN D,KESTER L,VAN O A.Validation of noise models for single-cell transcriptomics[J].Nature Methods,2014,11(6):637-640.
[8]LOPEZ R,REGIER J,COLE M B,et al.Deep generative mode-ling for single-cell transcriptomics[J].Nature Methods,2018,15(12):1053-1058.
[9]XIE J,GIRSHICK R,FARHADI A.Unsupervised deep embedding for clustering analysis[C]//International Conference on Machine Learning.PMLR,2016:478-487.
[10]TIAN T,WAN J,SONG Q,et al.Clustering single-cell RNA-seq data with a model-based deep learning approach[J].Nature Machine Intelligence,2019,1(4):191-198.
[11]TIAN T,ZHANG J,LIN X,et al.Model-based deep embedding for constrained clustering analysis of single cell RNA-seq data[J].Nature Communications,2021,12(1):1873.
[12]CHEN L,WANG W,ZHAI Y,et al.Deep soft K-means clustering with self-training for single-cell RNA sequence data[J].NAR Genomics and Bioinformatics,2020,2(2):lqaa039.
[13]LIU T,JIA C,BI Y,et al.scDFN:enhancing single-cell RNA-seq clustering with deep fusion networks[J].Briefings in Bioinformatics,2024,25(6):bbae486.
[14]YU Z,LU Y,WANG Y,et al.Zinb-based graph embedding autoencoder for single-cell rna-seq interpretations[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2022:4671-4679.
[15]CHENG Y,SU Y,YU Z,et al.Unsupervised deep embedded fusion representation of single-cell transcriptomics[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2023:5036-5044.
[16]JIA C.Kinetic foundation of the zero-inflated negative binomial model for single-cell RNA sequencing data[J].SIAM Journal on Applied Mathematics,2020,80(3):1336-1355.
[17]TU W,ZHOU S,LIU X,et al.Deep fusion clustering network[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:9978-9987.
[18]ZENG Y,ZHOU X,RAO J,et al.Accurately clustering single-cell RNA-seq data by capturing structural relations between cells through graph convolutional network[C]//2020 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).IEEE,2020:519-522.
[19]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.
[20]ERASLAN G,SIMON L M,MIRCEA M,et al.Single-cellRNA-seq denoising using a deep count autoencoder[J].Nature Communications,2019,10(1):390.
[21]CHEN L,WANG W,ZHAI Y,et al.Single-cell transcriptome data clustering via multinomial modeling and adaptive fuzzy k-means algorithm[J].Frontiers in Genetics,2020,11:295.
[22]LI X,WANG K,LYU Y,et al.Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq ana-lysis[J].Nature Communications,2020,11(1):2338.
[23]HU D,LIANG K,ZHOU S,et al.scDFC:a deep fusion clustering method for single-cell RNA-seq data[J].Briefings in Bioinformatics,2023,24(4):bbad216.
[24]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[25]WAN H,CHEN L,DENG M.scNAME:neighborhood contrastive clustering with ancillary mask estimation for scRNA-seq data[J].Bioinformatics,2022,38(6):1575-1583.
[26]WANG J,XIA J,WANG H,et al.scDCCA:deep contrastiveclustering for single-cell RNA-seq data based on auto-encoder network[J].Briefings in Bioinformatics,2023,24(1):bbac625.
[27]SCHAUM N,KARKANIAS J,NEFF N F,et al.Single-celltranscriptomics of 20 mouse organs creates a Tabula Muris:The Tabula Muris Consortium[J].Nature,2018,562(7727):367.
[28]CAMP J G,SEKINE K,GERBER T,et al.Multilineage communication regulates human liver bud development from pluripotency[J].Nature,2017,546(7659):533-538.
[29]YU J,CHEN N,GAO M,et al.Unsupervised gene-cell collective representation learning with optimal transport[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2024:356-364.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发