scIAC: clustering scATAC-seq data based on Student's t-distribution similarity imputation and denoising autoencoder

Wei Lan, Jin Ye, Xun Sun, Xiaoshu Zhu, Qingfeng Chen, Yi PanBIBM 2022 · OpenReview

Abstract

Assay of single cell transposase-accessible chromatin with high-throughput sequencing (scATAC-seq) have enabled massively profiling of the chromatin accessibility landscape at the single-cell level. The essential step in analyzing scATAC-seq data is to cluster the cells into different clusters and utilize the clustering information in the subsequent downstream analysis. However, there are some challenges in the clustering analysis of scATAC-seq data. For example, scATAC-seq data are often high-dimensional and extremely sparse, as well as featuring high loss rate or noise. In this study, we proposed the scIAC to address these challenges of scATACseq data. In particular, scIAC combines the Student’s t-distribution similarity imputation and the denoising autoencoder based on the Zero-inflated Negative Binomial (ZINB) distribution. The Student’s t-distribution similarity imputation is used to solve the problem of high sparsity and high loss rate. The denoising autoencoder is employ to extract features which are useful for clustering and to reduce data noises. In addition, the self-training soft K-means and pairwise constraints are utilized in the clustering phase to enhance clustering performance. The experimental validation on several datasets shows that the proposed method performed better than other state-of-the-art methods. In conclusion, scIAC is an effective method to accurately cluster and identify cell types in scATAC-seq data.
BibTeX
@inproceedings{lan2022sciac,
  author = {Wei Lan and Jin Ye and Xun Sun and Xiaoshu Zhu and Qingfeng Chen and Yi Pan},
  title = {{scIAC: clustering scATAC-seq data based on Student's t-distribution similarity imputation and denoising autoencoder}},
  booktitle = {BIBM},
  year = {2022},
  url = {https://openreview.net/forum?id=Rz4k7nLKik},
}

Loading related content...

Figure