Boosting scRNA-seq data clustering by cluster-aware feature weighting.
Boosting scRNA-seq data clustering by cluster-aware feature weighting.
复制标题
通过聚类感知特征加权增强 scRNA-Seq 数据聚类
DOI：
10.1186/s12859-021-04033-7
复制
发表时间：
2021-06-02
影响因子：
3
通讯作者：
Zhou S
中科院分区：
文献类型：
--
作者：
Li RY;Guan J;Zhou S
背景单细胞RNA测序（scRNA-seq）的快速发展使得细胞异质性的探索成为可能，这通常是通过scRNA-seq数据聚类来完成的。 scRNA-seq数据聚类的本质是通过测量细胞基因/转录本之间的相似性来对细胞进行分组。细胞相似性评估的特征选择非常重要，这将显着影响聚类的有效性和效率。结果在本文中，我们提出了一种称为CaFew的新方法，用于基于聚类感知特征权重选择基因。通过优化聚类目标函数，CaFew得到特征权重矩阵，进一步用于特征选择。选择至少在一个簇中权重较大的基因或者在不同簇中权重变化较大的基因。在8个真实scRNA-seq数据集上的实验表明，CaFew可以明显提高现有scRNA-seq数据聚类方法的聚类性能。特别是，CaFew 与 SC3 的结合实现了最先进的性能。此外，CaFew还有利于scRNA-seq数据的可视化。结论CaFew是一种有效的scRNA-seq数据聚类方法，由于其基于聚类感知特征权重的基因选择机制，是scRNA-seq数据分析的有用工具。
BackgroundThe rapid development of single-cell RNA sequencing (scRNA-seq) enables the exploration of cell heterogeneity, which is usually done by scRNA-seq data clustering. The essence of scRNA-seq data clustering is to group cells by measuring the similarities among genes/transcripts of cells. And the selection of features for cell similarity evaluation is of great importance, which will significantly impact clustering effectiveness and efficiency.ResultsIn this paper, we propose a novel method called CaFew to select genes based on cluster-aware feature weighting. By optimizing the clustering objective function, CaFew obtains a feature weight matrix, which is further used for feature selection. The genes have large weights in at least one cluster or the genes whose weights vary greatly in different clusters are selected. Experiments on 8 real scRNA-seq datasets show that CaFew can obviously improve the clustering performance of existing scRNA-seq data clustering methods. Particularly, the combination of CaFew with SC3 achieves the state-of-art performance. Furthermore, CaFew also benefits the visualization of scRNA-seq data.ConclusionCaFew is an effective scRNA-seq data clustering method due to its gene selection mechanism based on cluster-aware feature weighting, and it is a useful tool for scRNA-seq data analysis.
登录
查看更多内容
影响因子：
64.5
作者：
Goolam M;Scialdone A;Graham SJL;Macaulay IC;Jedrusik A;Hupalowska A;Voet T;Marioni JC;Zernicka-Goetz M
通讯作者：
Zernicka-Goetz M
影响因子：
46.9
作者：
Becht, Etienne;McInnes, Leland;Newell, Evan W.
通讯作者：
Newell, Evan W.
影响因子：
48
作者：
Kiselev, Vladimir Yu;Kirschner, Kristina;Hemberg, Martin
通讯作者：
Hemberg, Martin
影响因子：
48
作者：
Kharchenko, Peter V.;Silberstein, Lev;Scadden, David T.
通讯作者：
Scadden, David T.
影响因子：
12.3
作者：
Jiang L;Chen H;Pinello L;Yuan GC
通讯作者：
Yuan GC