期刊
KNOWLEDGE-BASED SYSTEMS
卷 248, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.knosys.2022.108767
关键词
scRNA-seq; Clustering; Next generation sequencing; Computational biology; Bioinformatics
This paper proposes an effective clustering method for scRNA-seq data, which integrates preprocessing steps and robust cell group identification. The method requires no user input, except for setting thresholds, and outperforms most other existing methods.
Clustering unleashes the power of scRNA-seq through identification of appropriate cell groups. Most existing clustering methods applied on or developed for scRNA-seq data require user inputs. A few also require rigorous external preprocessing. In this paper, we propose an effective clustering method, which integrates required preprocessing steps for data cleaning, followed by robust cell group identification method from scRNA-seq data. The method is completely free of user input, although it requires threshold setting. We compare our method with 14 recent clustering methods on 12 real world scRNA-seq datasets in terms of internal cluster evaluation matrices, and running time. Our method outperforms most other methods. Sensitivity and robustness analyses of the proposed method are also carried out extensively to understand the effect of the thresholds, followed by benchmarking. Our method is available as an R package at https://sites.google.com/view/hussinchowdhury/software for download. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据