基于集成学习的单细胞数据分类和参考图谱投射方法。
Ensemble learning for classifying single-cell data and projection across reference atlases.
机构信息
Department of Neurosurgery, University of California, San Francisco, CA 94158, USA.
出版信息
Bioinformatics. 2020 Jun 1;36(11):3585-3587. doi: 10.1093/bioinformatics/btaa137.
Abstract
SUMMARY
Single-cell data are being generated at an accelerating pace. How best to project data across single-cell atlases is an open problem. We developed a boosted learner that overcomes the greatest challenge with status quo classifiers: low sensitivity, especially when dealing with rare cell types. By comparing novel and published data from distinct scRNA-seq modalities that were acquired from the same tissues, we show that this approach preserves cell-type labels when mapping across diverse platforms.
AVAILABILITY AND IMPLEMENTATION
https://github.com/diazlab/ELSA.
CONTACT
SUPPLEMENTARY INFORMATION
Supplementary data are available at Bioinformatics online.
摘要
摘要
单细胞数据正在以前所未有的速度产生。如何最好地在单细胞图谱中投射数据是一个悬而未决的问题。我们开发了一种增强学习器，克服了现有分类器的最大挑战：低灵敏度，尤其是在处理稀有细胞类型时。通过比较来自同一组织的不同 scRNA-seq 模式的新颖和已发表的数据，我们表明，这种方法在跨多种平台映射时保留了细胞类型标签。
可用性和实现
https://github.com/diazlab/ELSA。
联系人
补充信息
补充数据可在生物信息学在线获得。
相似文献
1
Ensemble learning for classifying single-cell data and projection across reference atlases.基于集成学习的单细胞数据分类和参考图谱投射方法。
Bioinformatics. 2020 Jun 1;36(11):3585-3587. doi: 10.1093/bioinformatics/btaa137.
2
SCell: integrated analysis of single-cell RNA-seq data.SCell：单细胞RNA测序数据的综合分析
Bioinformatics. 2016 Jul 15;32(14):2219-20. doi: 10.1093/bioinformatics/btw201. Epub 2016 Apr 19.
3
CONICS integrates scRNA-seq with DNA sequencing to map gene expression to tumor sub-clones.CONICS 将单细胞 RNA-seq 与 DNA 测序相结合，将基因表达映射到肿瘤亚克隆。
Bioinformatics. 2018 Sep 15;34(18):3217-3219. doi: 10.1093/bioinformatics/bty316.
4
DECENT: differential expression with capture efficiency adjustmeNT for single-cell RNA-seq data.DECENT：用于单细胞 RNA-seq 数据的捕获效率调整的差异表达分析。
Bioinformatics. 2019 Dec 15;35(24):5155-5162. doi: 10.1093/bioinformatics/btz453.
5
scDetect: a rank-based ensemble learning algorithm for cell type identification of single-cell RNA sequencing in cancer.scDetect：一种基于排序的集成学习算法，用于癌症中单细胞RNA测序的细胞类型识别。
Bioinformatics. 2021 Nov 18;37(22):4115-4122. doi: 10.1093/bioinformatics/btab410.
6
scDoc: correcting drop-out events in single-cell RNA-seq data.scDoc：纠正单细胞 RNA-seq 数据中的 dropout 事件。
Bioinformatics. 2020 Aug 1;36(15):4233-4239. doi: 10.1093/bioinformatics/btaa283.
7
scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling.scPNMF：稀疏的单细胞基因编码，以方便选择用于靶向基因分析的基因。
Bioinformatics. 2021 Jul 12;37(Suppl_1):i358-i366. doi: 10.1093/bioinformatics/btab273.
8
scHinter: imputing dropout events for single-cell RNA-seq data with limited sample size.scHinter：利用有限的样本量对单细胞 RNA-seq 数据进行缺失事件推断。
Bioinformatics. 2020 Feb 1;36(3):789-797. doi: 10.1093/bioinformatics/btz627.
9
alona: a web server for single-cell RNA-seq analysis.alona：单细胞 RNA-seq 分析的 Web 服务器。
Bioinformatics. 2020 Jun 1;36(12):3910-3912. doi: 10.1093/bioinformatics/btaa269.
10
Falco: a quick and flexible single-cell RNA-seq processing framework on the cloud.Falco：一个在云端快速且灵活的单细胞RNA测序处理框架。
Bioinformatics. 2017 Mar 1;33(5):767-769. doi: 10.1093/bioinformatics/btw732.
引用本文的文献
1
Measles oncolytic virus as an immunotherapy for recurrent/refractory pediatric medulloblastoma and atypical teratoid rhabdoid tumor: results from PNOC005.麻疹溶瘤病毒作为复发性/难治性儿童髓母细胞瘤和非典型畸胎样横纹肌样瘤的免疫疗法：PNOC005研究结果
Clin Cancer Res. 2025 Jun 20. doi: 10.1158/1078-0432.CCR-24-3721.
2
CTISL: a dynamic stacking multi-class classification approach for identifying cell types from single-cell RNA-seq data.CTISL：一种动态堆叠多类分类方法，用于从单细胞 RNA-seq 数据中识别细胞类型。
Bioinformatics. 2024 Feb 1;40(2). doi: 10.1093/bioinformatics/btae063.
3
Lymph node and tumor-associated PD-L1 macrophages antagonize dendritic cell vaccines by suppressing CD8 T cells.淋巴结和肿瘤相关 PD-L1 巨噬细胞通过抑制 CD8 T 细胞来拮抗树突状细胞疫苗。
Cell Rep Med. 2024 Jan 16;5(1):101377. doi: 10.1016/j.xcrm.2023.101377.
4
A global database for modeling tumor-immune cell communication.用于肿瘤免疫细胞通讯建模的全球数据库。
Sci Data. 2023 Jul 12;10(1):444. doi: 10.1038/s41597-023-02342-5.
5
Transfer learning enables predictions in network biology.迁移学习可实现网络生物学预测。
Nature. 2023 Jun;618(7965):616-624. doi: 10.1038/s41586-023-06139-9. Epub 2023 May 31.
6
Cytohesin-4 Upregulation in Glioma-Associated M2 Macrophages Is Correlated with Pyroptosis and Poor Prognosis.胶质瘤相关M2巨噬细胞中细胞衔接蛋白4的上调与细胞焦亡及不良预后相关。
J Mol Neurosci. 2023 Mar;73(2-3):143-158. doi: 10.1007/s12031-023-02104-3. Epub 2023 Feb 7.
7
Integrated analysis of single-cell and bulk RNA sequencing data reveals a pan-cancer stemness signature predicting immunotherapy response.单细胞和批量 RNA 测序数据的综合分析揭示了一个泛癌干性特征，可预测免疫治疗反应。
Genome Med. 2022 Apr 29;14(1):45. doi: 10.1186/s13073-022-01050-w.
8
Vec2image: an explainable artificial intelligence model for the feature representation and classification of high-dimensional biological data by vector-to-image conversion.Vec2image：一种通过向量到图像的转换对高维生物数据进行特征表示和分类的可解释人工智能模型。
Brief Bioinform. 2022 Mar 10;23(2). doi: 10.1093/bib/bbab584.
9
Automated annotation of rare-cell types from single-cell RNA-sequencing data through synthetic oversampling.通过合成过采样对单细胞 RNA 测序数据中的稀有细胞类型进行自动注释。
BMC Bioinformatics. 2021 Nov 19;22(1):557. doi: 10.1186/s12859-021-04469-x.
10
ATRX regulates glial identity and the tumor microenvironment in IDH-mutant glioma.ATRX 调控 IDH 突变型 glioma 中的神经胶质细胞特性和肿瘤微环境。
Genome Biol. 2021 Nov 11;22(1):311. doi: 10.1186/s13059-021-02535-4.
本文引用的文献
1
The Phenotypes of Proliferating Glioblastoma Cells Reside on a Single Axis of Variation.增生性胶质母细胞瘤细胞的表型位于单一变化轴上。
Cancer Discov. 2019 Dec;9(12):1708-1719. doi: 10.1158/2159-8290.CD-19-0329. Epub 2019 Sep 25.
2
Supervised classification enables rapid annotation of cell atlases.监督分类可实现细胞图谱的快速标注。
Nat Methods. 2019 Oct;16(10):983-986. doi: 10.1038/s41592-019-0535-3. Epub 2019 Sep 9.
3
Challenges in unsupervised clustering of single-cell RNA-seq data.无监督单细胞 RNA-seq 数据聚类的挑战。
Nat Rev Genet. 2019 May;20(5):273-282. doi: 10.1038/s41576-018-0088-9.
4
scmap: projection of single-cell RNA-seq data across data sets.scmap：跨数据集的单细胞 RNA-seq 数据的投影。
Nat Methods. 2018 May;15(5):359-362. doi: 10.1038/nmeth.4644. Epub 2018 Apr 2.
5
Integrating single-cell transcriptomic data across different conditions, technologies, and species.整合不同条件、技术和物种的单细胞转录组数据。
Nat Biotechnol. 2018 Jun;36(5):411-420. doi: 10.1038/nbt.4096. Epub 2018 Apr 2.
6
A general and flexible method for signal extraction from single-cell RNA-seq data.一种从单细胞RNA测序数据中提取信号的通用且灵活的方法。
Nat Commun. 2018 Jan 18;9(1):284. doi: 10.1038/s41467-017-02554-5.
Zotero 插件