• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于自监督对比学习的整合单细胞 RNA-seq 数据分析。

Self-supervised contrastive learning for integrative single cell RNA-seq data analysis.

机构信息

Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE), Computational Bioscience Research Center (CBRC), King Abdullah University of Science and Technology (KAUST), Thuwal, 23955, Saudi Arabia.

Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Hong Kong SAR, China.

出版信息

Brief Bioinform. 2022 Sep 20;23(5). doi: 10.1093/bib/bbac377.

DOI:10.1093/bib/bbac377
PMID:36089561
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9487595/
Abstract

We present a novel self-supervised Contrastive LEArning framework for single-cell ribonucleic acid (RNA)-sequencing (CLEAR) data representation and the downstream analysis. Compared with current methods, CLEAR overcomes the heterogeneity of the experimental data with a specifically designed representation learning task and thus can handle batch effects and dropout events simultaneously. It achieves superior performance on a broad range of fundamental tasks, including clustering, visualization, dropout correction, batch effect removal, and pseudo-time inference. The proposed method successfully identifies and illustrates inflammatory-related mechanisms in a COVID-19 disease study with 43 695 single cells from peripheral blood mononuclear cells.

摘要

我们提出了一种新颖的基于对比学习的单细胞 RNA 测序 (CLEAR) 数据表示和下游分析的自监督框架。与当前的方法相比，CLEAR 通过专门设计的表示学习任务克服了实验数据的异质性，因此可以同时处理批次效应和丢包事件。它在广泛的基础任务上表现出色，包括聚类、可视化、丢包校正、批次效应去除和伪时间推断。该方法成功地识别并说明了 COVID-19 疾病研究中与炎症相关的机制，该研究使用了来自外周血单核细胞的 43695 个单细胞。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/60375d12a1bb/bbac377f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/f298898f2631/bbac377f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/60b1b492b9cc/bbac377f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/208e97decc6e/bbac377f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/2dc9e68d2556/bbac377f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/24e6287c6c1a/bbac377f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/60375d12a1bb/bbac377f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/f298898f2631/bbac377f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/60b1b492b9cc/bbac377f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/208e97decc6e/bbac377f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/2dc9e68d2556/bbac377f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/24e6287c6c1a/bbac377f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/81bf/9487595/60375d12a1bb/bbac377f6.jpg

相似文献

1
Self-supervised contrastive learning for integrative single cell RNA-seq data analysis.基于自监督对比学习的整合单细胞 RNA-seq 数据分析。
Brief Bioinform. 2022 Sep 20;23(5). doi: 10.1093/bib/bbac377.
2
Contrastive self-supervised clustering of scRNA-seq data.单细胞 RNA 测序数据的对比自监督聚类。
BMC Bioinformatics. 2021 May 27;22(1):280. doi: 10.1186/s12859-021-04210-8.
3
CL-Impute: A contrastive learning-based imputation for dropout single-cell RNA-seq data.CL-Impute：基于对比学习的 dropout 单细胞 RNA-seq 数据插补方法。
Comput Biol Med. 2023 Sep;164:107263. doi: 10.1016/j.compbiomed.2023.107263. Epub 2023 Jul 23.
4
scGCC: Graph Contrastive Clustering With Neighborhood Augmentations for scRNA-Seq Data Analysis.scGCC：基于邻域增强的图对比聚类在 scRNA-Seq 数据分析中的应用。
IEEE J Biomed Health Inform. 2023 Dec;27(12):6133-6143. doi: 10.1109/JBHI.2023.3319551. Epub 2023 Dec 5.
5
nsDCC: dual-level contrastive clustering with nonuniform sampling for scRNA-seq data analysis.nsDCC：基于非均匀采样的双层对比聚类算法，用于 scRNA-seq 数据分析。
Brief Bioinform. 2024 Sep 23;25(6). doi: 10.1093/bib/bbae477.
6
scZAG: Integrating ZINB-Based Autoencoder with Adaptive Data Augmentation Graph Contrastive Learning for scRNA-seq Clustering.scZAG：基于 ZINB 的自动编码器与自适应数据增强图对比学习在 scRNA-seq 聚类中的整合。
Int J Mol Sci. 2024 May 29;25(11):5976. doi: 10.3390/ijms25115976.
7
Deep enhanced constraint clustering based on contrastive learning for scRNA-seq data.基于对比学习的深度增强约束聚类算法在单细胞 RNA-seq 数据分析中的应用。
Brief Bioinform. 2023 Jul 20;24(4). doi: 10.1093/bib/bbad222.
8
scDCCA: deep contrastive clustering for single-cell RNA-seq data based on auto-encoder network.scDCCA：基于自动编码器网络的单细胞RNA测序数据深度对比聚类
Brief Bioinform. 2023 Jan 19;24(1). doi: 10.1093/bib/bbac625.
9
scNAME: neighborhood contrastive clustering with ancillary mask estimation for scRNA-seq data.scNAME：基于辅助掩模估计的 scRNA-seq 数据邻域对比聚类。
Bioinformatics. 2022 Mar 4;38(6):1575-1583. doi: 10.1093/bioinformatics/btac011.
10
scGCL: an imputation method for scRNA-seq data based on graph contrastive learning.scGCL：一种基于图对比学习的 scRNA-seq 数据插补方法。
Bioinformatics. 2023 Mar 1;39(3). doi: 10.1093/bioinformatics/btad098.

引用本文的文献

1
GNODEVAE: a graph-based ODE-VAE enhances clustering for single-cell data.GNODEVAE：一种基于图的常微分方程变分自编码器增强了单细胞数据的聚类效果。
BMC Genomics. 2025 Aug 21;26(1):767. doi: 10.1186/s12864-025-11946-7.
2
Less is more: improving cell-type identification with augmentation-free single-cell RNA-Seq contrastive learning.少即是多：通过无增强单细胞RNA测序对比学习改进细胞类型识别
Bioinformatics. 2025 Sep 1;41(9). doi: 10.1093/bioinformatics/btaf437.
3
A technical review of multi-omics data integration methods: from classical statistical to deep generative approaches.

本文引用的文献

1
Single-cell multi-omics reveals dyssynchrony of the innate and adaptive immune system in progressive COVID-19.单细胞多组学揭示了进展期新冠肺炎中固有免疫系统和适应性免疫系统的不同步性。
Nat Commun. 2022 Jan 21;13(1):440. doi: 10.1038/s41467-021-27716-4.
2
scNAME: neighborhood contrastive clustering with ancillary mask estimation for scRNA-seq data.scNAME：基于辅助掩模估计的 scRNA-seq 数据邻域对比聚类。
Bioinformatics. 2022 Mar 4;38(6):1575-1583. doi: 10.1093/bioinformatics/btac011.
3
HDMC: a novel deep learning-based framework for removing batch effects in single-cell RNA-seq data.
多组学数据整合方法的技术综述：从经典统计方法到深度生成方法
Brief Bioinform. 2025 Jul 2;26(4). doi: 10.1093/bib/bbaf355.
4
CYCLONE: recycle contrastive learning for integrating single-cell gene expression data.CYCLONE：用于整合单细胞基因表达数据的循环对比学习
BMC Bioinformatics. 2025 Jul 30;26(1):202. doi: 10.1186/s12859-025-06214-0.
5
IGCLAPS: an interpretable graph contrastive learning method with adaptive positive sampling for scRNA-seq data analysis.IGCLAPS：一种用于单细胞RNA测序数据分析的具有自适应正样本采样的可解释图对比学习方法。
Bioinformatics. 2025 Jul 21. doi: 10.1093/bioinformatics/btaf411.
6
ConsAMPHemo: A computational framework for predicting hemolysis of antimicrobial peptides based on machine learning approaches.ConsAMPHemo：一种基于机器学习方法预测抗菌肽溶血作用的计算框架。
Protein Sci. 2025 Jul;34(7):e70087. doi: 10.1002/pro.70087.
7
Deep learning in single-cell and spatial transcriptomics data analysis: advances and challenges from a data science perspective.从数据科学视角看深度学习在单细胞和空间转录组学数据分析中的进展与挑战
Brief Bioinform. 2025 Mar 4;26(2). doi: 10.1093/bib/bbaf136.
8
HEDDI-Net: heterogeneous network embedding for drug-disease association prediction and drug repurposing, with application to Alzheimer's disease.HEDDI-Net：用于药物-疾病关联预测和药物再利用的异构网络嵌入，应用于阿尔茨海默病
J Transl Med. 2025 Feb 1;23(1):57. doi: 10.1186/s12967-024-05938-6.
9
A generative deep neural network for pan-digestive tract cancer survival analysis.用于全消化道癌症生存分析的生成式深度神经网络。
BioData Min. 2025 Jan 27;18(1):9. doi: 10.1186/s13040-025-00426-z.
10
Integration of unpaired single cell omics data by deep transfer graph convolutional network.通过深度迁移图卷积网络整合非配对单细胞组学数据
PLoS Comput Biol. 2025 Jan 16;21(1):e1012625. doi: 10.1371/journal.pcbi.1012625. eCollection 2025 Jan.
HDMC：一种用于去除单细胞 RNA-seq 数据中批次效应的新型深度学习框架。
Bioinformatics. 2022 Feb 7;38(5):1295-1303. doi: 10.1093/bioinformatics/btab821.
4
SMILE: mutual information learning for integration of single-cell omics data.SMILE：单细胞组学数据集成的互信息学习。
Bioinformatics. 2022 Jan 3;38(2):476-486. doi: 10.1093/bioinformatics/btab706.
5
scRAE: Deterministic Regularized Autoencoders With Flexible Priors for Clustering Single-Cell Gene Expression Data.scRAE：用于单细胞基因表达数据聚类的具有灵活先验的确定性正则化自动编码器
IEEE/ACM Trans Comput Biol Bioinform. 2022 Sep-Oct;19(5):2996-3007. doi: 10.1109/TCBB.2021.3098394. Epub 2022 Oct 10.
6
Contrastive self-supervised clustering of scRNA-seq data.单细胞 RNA 测序数据的对比自监督聚类。
BMC Bioinformatics. 2021 May 27;22(1):280. doi: 10.1186/s12859-021-04210-8.
7
Deep generative model embedding of single-cell RNA-Seq profiles on hyperspheres and hyperbolic spaces.基于超球和双曲空间的单细胞 RNA-Seq 图谱的深度生成模型嵌入。
Nat Commun. 2021 May 5;12(1):2554. doi: 10.1038/s41467-021-22851-4.
8
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.用于单细胞RNA测序分析中聚类和细胞类型分类的神经网络迭代迁移学习
Nat Mach Intell. 2020 Oct;2(10):607-618. doi: 10.1038/s42256-020-00233-7. Epub 2020 Oct 5.
9
scGNN is a novel graph neural network framework for single-cell RNA-Seq analyses.scGNN 是一种用于单细胞 RNA-Seq 分析的新型图神经网络框架。
Nat Commun. 2021 Mar 25;12(1):1882. doi: 10.1038/s41467-021-22197-x.
10
Model-based deep embedding for constrained clustering analysis of single cell RNA-seq data.基于模型的深度学习嵌入方法用于单细胞 RNA-seq 数据的约束聚类分析。
Nat Commun. 2021 Mar 25;12(1):1873. doi: 10.1038/s41467-021-22008-3.