A parameter-free deep embedded clustering method for single-cell RNA-seq data. Issue 5 (6th May 2022)

• Record Type: Journal Article
• Authors: Zeng, Yuansong; Wei, Zhuoyi; Zhong, Fengqi; Pan, Zixiang; Lu, Yutong; Yang, Yuedong
• Is Part Of: Briefings in bioinformatics. Volume 23:Issue 5(2022)
• Publication Date: 2022-05-06
• Subjects: deep embedded clustering -- dip-test -- estimating the number of cell clusters -- single-cell clustering -- single-cell RNA sequencing; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbac172
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: Clustering analysis is widely used in single-cell ribonucleic acid (RNA)-sequencing (scRNA-seq) data to discover cell heterogeneity and cell states. While many clustering methods have been developed for scRNA-seq analysis, most of these methods require to provide the number of clusters. However, it is not easy to know the exact number of cell types in advance, and experienced determination is not always reliable. Here, we have developed ADClust, an automatic deep embedding clustering method for scRNA-seq data, which can accurately cluster cells without requiring a predefined number of clusters. Specifically, ADClust first obtains low-dimensional representation through pre-trained autoencoder and uses the representations to cluster cells into initial micro-clusters. The clusters are then compared in between by a statistical test, and similar micro-clusters are merged into larger clusters. According to the clustering, cell representations are updated so that each cell will be pulled toward centers of its assigned cluster and similar clusters, while cells are separated to keep distances between clusters. This is accomplished through jointly optimizing the carefully designed clustering and autoencoder loss functions. This merging process continues until convergence. ADClust was tested on 11 real scRNA-seq datasets and was shown to outperform existing methods in terms of both clustering performance and the accuracy on the number of the determined clusters. More importantly, our model provides high speed and scalability for large datasets.