ORIGINAL RESEARCH article
Front. Bioinform.
Sec. RNA Bioinformatics
This article is part of the Research TopicRNA-Protein Interaction NetworksView all articles
A Clustering Method for Single-Cell RNA Sequencing Data Based on Denoising and Masking Learning
Provisionally accepted
- Jilin University, Changchun, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Single-cell RNA sequencing (scRNA-seq) enables high-throughput analysis of gene expression at the single-cell level, playing a vital role in studying cellular heterogeneity, tissue development, and disease mechanisms. However, scRNA-seq data often suffer from high dimensionality, sparsity, technical noise, and dropout events, posing significant challenges to conventional clustering methods. To address these issues, this paper proposes a clustering method for single-cell RNA sequencing data based on denoising and masking learning (scDMAC), a novel clustering method that integrates a denoising autoencoder based on a zero-inflated negative binomial (ZINB) model with a masking autoencoder. The model first denoises the expression data using the ZINB-based autoencoder, then applies a tailored masking strategy to learn gene-wise correlations through reconstruction. By masking and reconstructing input data, scDMAC preserves essential features and enhances representation learning, leading to improved clustering performance. Experimental results demonstrate that scDMAC achieves superior accuracy and stability in cell clustering, outperforming on most benchmark datasets.
Keywords: Cell clustering, Denoising autoencoder, Maskedautoencoder, single-cell RNA sequencing, Zero-inflated negative binomial (ZINB)
Received: 01 Dec 2025; Accepted: 16 Feb 2026.
Copyright: © 2026 Xu, Yan, Zhang, Qi and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Kai Wang
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.