Article
Biochemical Research Methods
Yanglan Gan, Yuhan Chen, Guangwei Xu, Wenjing Guo, Guobing Zou
Summary: scRNA-seq is a technique that measures genome-wide gene expression at the single-cell level. In this study, a novel deep enhanced constraint clustering algorithm named scDECL is proposed for scRNA-seq data analysis, which combines contrastive learning and pairwise constraints. Experimental results demonstrate the superior performance of the scDECL algorithm on six real scRNA-seq datasets.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Tianyuan Lei, Ruoyu Chen, Shaoqiang Zhang, Yong Chen
Summary: This study introduces a novel single-cell hierarchical clustering tool called DeepScena, which demonstrates outstanding accuracy on multiple large-scale scRNA-seq datasets, particularly in detecting rare cell populations within large datasets.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Medicine, Research & Experimental
Xiang Zhou, Shuchen Zhang, Yiheng Zhao, Wenjing Wang, Hao Zhang
Summary: This study utilized a multi-omics approach to compare the transcriptomic, miRNA expression, and chromatin accessibility profiles between HF and control mice, providing mechanistic insights into the pathogenesis of pressure overload-induced HF.
Article
Biochemical Research Methods
Tian Tian, Martin Renqiang Min, Zhi Wei
Summary: Research shows that there is still limited exploration in imputing discrete data, the proposed ZINB model-based autoencoder in this paper effectively improves imputation accuracy and can be applied in pre-processing scRNA-seq data. Analysis of extensive experimental data reveals that zero-inflated reconstruction can effectively enhance cell type separation and improve the accuracy of differential expression analysis.
Article
Biochemical Research Methods
Zile Wang, Haiyun Wang, Jianping Zhao, Chunhou Zheng
Summary: This study proposes a semi-supervised clustering model called scSemiAAE for scRNA sequence analysis. Through the use of deep generative neural networks, scSemiAAE significantly improves clustering performance compared to other unsupervised and semi-supervised algorithms, promoting downstream analysis.
BMC BIOINFORMATICS
(2023)
Article
Computer Science, Information Systems
Jie Xu, Yazhou Ren, Guofeng Li, Lili Pan, Ce Zhu, Zenglin Xu
Summary: This paper proposes a deep embedded multi-view clustering with collaborative training (DEMVC) to address the issues of high computation complexity and lack of representation capability in existing multi-view clustering methods. The DEMVC learns embedded representations of multiple views individually by deep autoencoders and takes into account the consensus and complementary of multiple views with a novel collaborative training scheme. Experimental results show that DEMVC achieves significant improvements over state-of-the-art methods on popular multi-view datasets.
INFORMATION SCIENCES
(2021)
Article
Biochemistry & Molecular Biology
Ryosuke Saigusa, Jenifer Vallejo, Rishab Gulati, Sujit Silas Armstrong Suthahar, Vasantika Suryawanshi, Ahmad Alimadadi, Jeffrey Makings, Christopher P. Durant, Antoine Freuchet, Payel Roy, Yanal Ghosheh, William Pandori, Tanyaporn Pattarabanjird, Fabrizio Drago, Angela Taylor, Coleen A. McNamara, Avishai Shemesh, Lewis L. Lanier, Catherine C. Hedrick, Klaus Ley
Summary: This study investigated the relationship between CD4+ T cells and coronary artery disease (CAD) in relation to sex and diabetes mellitus (DM). The researchers used single-cell RNA sequencing and antibody sequencing techniques to analyze CD4+ T cells and found significant differences in cell proportions and gene expression between men and women, as well as between subjects with and without DM. The study concluded that CAD and DM have distinct effects on CD4+ T cells and that there are significant differences between genders.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biochemical Research Methods
Jing Wang, Junfeng Xia, Haiyun Wang, Yansen Su, Chun-Hou Zheng
Summary: The advances in single-cell ribonucleic acid sequencing (scRNA-seq) have enabled the exploration of cellular heterogeneity and human diseases at the cellular level. However, the high dimensionality, noise, and sparsity of scRNA-seq data pose a challenge for cell clustering. In this study, we propose a new deep contrastive clustering algorithm scDCCA, which incorporates a denoising autoencoder and a dual contrastive learning module to extract valuable features and improve cell clustering performance.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Jing Zhao, Bowen Zhao, Xiaotong Song, Chujun Lyu, Weizhi Chen, Yi Xiong, Dong-Qing Wei
Summary: The Subtype-DCC method, which integrates multi-omics data, is proposed for cancer subtyping and demonstrates superior performance compared to existing clustering methods. It has potential applications in cancer diagnosis, prognosis, and treatment.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Wenkai Han, Yuqi Cheng, Jiayang Chen, Huawen Zhong, Zhihang Hu, Siyuan Chen, Licheng Zong, Liang Hong, Ting-Fung Chan, Irwin King, Xin Gao, Yu Li
Summary: This study presents a novel self-supervised Contrastive LEArning framework for processing single-cell RNA-sequencing data representation and downstream analysis. The method effectively addresses the heterogeneity of experimental data and achieves superior performance on various fundamental tasks.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Ren Qi, Jin Wu, Fei Guo, Lei Xu, Quan Zou
Summary: The paper proposes a new clustering method using multiple kernel combination to directly discover groupings in scRNA-seq data. By automatically learning similarity information from data, it helps transform candidate solutions into better approximations of discrete solutions.
BRIEFINGS IN BIOINFORMATICS
(2021)
Review
Biochemical Research Methods
Xiaobo Sun, Xiaochu Lin, Ziyi Li, Hao Wu
Summary: The study compared the performances of supervised and unsupervised cell type identification methods using multiple factors and found that supervised methods generally outperformed unsupervised methods, except for identifying unknown cell types. However, undesired dataset properties could make unsupervised methods comparable to supervised methods. The study offers insights on method selection based on scientific goals and dataset properties, and provides an evaluation pipeline for future method assessments.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Yanglan Gan, Xingyu Huang, Guobing Zou, Shuigeng Zhou, Jihong Guan
Summary: Single-cell RNA sequencing is a critical technique for studying cell heterogeneity and diversity. However, clustering analysis of scRNA-seq data is challenging due to noise, high dimensionality, and dropout events. In this study, a new deep structural clustering method called scDSC is proposed, which incorporates structural information to improve clustering accuracy and scalability.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Xun Wang, Chaogang Zhang, Lulu Wang, Pan Zheng
Summary: Single-cell RNA sequencing is a proven method for quantifying gene-expression heterogeneity, and batch effect correction is commonly used for analyzing multiple datasets. We propose a novel deep learning model named IMAAE, which utilizes single-cell cluster labeling information to correct batch effects in complex dataset scenarios. Experimental results demonstrate that IMAAE outperforms existing methods in qualitative measures and quantitative evaluation, and it also retains both corrected dimension reduction data and corrected gene expression data.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Biochemical Research Methods
Qi Yang, Zhaochun Xu, Wenyang Zhou, Pingping Wang, Qinghua Jiang, Liran Juan
Summary: Single-cell RNA sequencing (scRNA-seq) is powerful for determining cell-to-cell differences and investigating the functional characteristics of various cell types. In this study, a scRNA-seq analysis method based on the latent Dirichlet allocation (LDA) model was proposed, which incorporates a three-layer framework capable of discovering latent and complex gene expression patterns and obtaining biologically meaningful results.
BRIEFINGS IN BIOINFORMATICS
(2023)