Journal
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
Volume 14, Issue 4, Pages 917-928Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s12539-022-00536-w
Keywords
scATAC-seq; Clustering; Deep learning; Variational autoencoder; Bayesian Gaussian-mixture model
Categories
Funding
- National Natural Science Foundation of China [61902216, 61972236, 61972226]
- Natural Science Foundation of Shandong Province [ZR2018MF013]
Ask authors/readers for more resources
The development of single-cell technologies has led to a surge in research, particularly in the analysis of chromatin accessibility differences at the single-cell level using scATAC-seq. However, challenges in distinguishing cell types have emerged due to the increasing number of cells and data characteristics. We propose a method called scVAEBGM, which combines a Variational Autoencoder (VAE) with a Bayesian Gaussian-mixture model (BGM) to process and analyze scATAC-seq data. This method can estimate the number of cell types without prior knowledge and is more robust to noise and better represents single-cell data in lower dimensions.
A surge in research has occurred because of current developments in single-cell technologies. Above all, single-cell Assay for Transposase-Accessible Chromatin with high throughput sequencing (scATAC-seq) is a popular approach of analyzing chromatin accessibility differences at the level of single cell, either within or between groups. As a result, it is critical to examine cell heterogeneity at a previously unseen level and to identify both recognized and unknown cell types. However, with the ever-increasing number of cells engendered by technological development and the characteristics of the data, such as high noise, sparsity and dimension, challenges in distinguishing cell types have emerged. We propose scVAEBGM, which integrates a Variational Autoencoder (VAE) with a Bayesian Gaussian-mixture model (BGM) to process and analyze scATAC-seq data. This method combines and takes benefits of a Bayesian Gaussian mixture model to estimate the number of cell types without determining the cluster number in a beforehand. In other words, the size of the clusters is inferred from the data, thus avoiding biases introduced by subjective assessments when manually determining the size of the clusters. Additionally, the method is more robust to noise and can better represent single-cell data in lower dimensions. We also create a further clustering strategy. It is indicated by experiments that further clustering based on the already completed clustering can improve the clustering accuracy again. We test on six public datasets, and scVAEBGM outperforms various dimension reduction baselines. In downstream applications, scVAEBGM can reveal biological cell types. [GRAPHICS] .
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available