Article
Biochemical Research Methods
Jing Jiang, Junlin Xu, Yuansheng Liu, Bosheng Song, Xiulan Guo, Xiangxiang Zeng, Quan Zou
Summary: Single-cell RNA sequencing (scRNA-seq) is a revolutionary breakthrough for studying gene expressions at the individual cell level and understanding cell heterogeneity. However, scRNA-seq data are noisy, leading to challenges in dimensionality reduction and visualization. In this study, we propose an improved variational autoencoder model called DREAM, which combines different techniques to accurately analyze scRNA-seq data and identify cell types. Benchmarking comparisons show that DREAM outperforms current methods and can capture gene expression dynamics in human embryonic development.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Genetics & Heredity
Jianping Zhao, Na Wang, Haiyun Wang, Chunhou Zheng, Yansen Su
Summary: This paper proposes a scRNA-seq data dimensionality reduction algorithm SCDRHA based on a hierarchical autoencoder, which consists of two core modules for denoising and projecting data into a low-dimensional space. Experimental results show that SCDRHA outperforms existing algorithms in dimension reduction and noise reduction on five real scRNA-seq datasets, and significantly improves data visualization and cell clustering performance.
FRONTIERS IN GENETICS
(2021)
Article
Computer Science, Information Systems
Shuchang Zhao, Li Zhang, Xuejun Liu
Summary: Single-cell RNA sequencing technology provides new insights into transcriptomic research, but technical noise and biological variation can lead to high dropout events, hindering downstream analysis. To address the characteristics of scRNA-seq data, a customized autoencoder model based on a two-part generalized gamma distribution is proposed, capturing the inherent relationship between genes and providing denoised imputation.
FRONTIERS OF COMPUTER SCIENCE
(2023)
Article
Biochemical Research Methods
Siqi Chen, Xuhua Yan, Ruiqing Zheng, Min Li
Summary: Single-cell RNA sequencing technology (scRNA-seq) has the drawback of large sparsity, which leads to dropout events and affects downstream analyses. To address this, we propose Bubble, which identifies and imputes dropout events using expression rate and coefficient of variation, and leverages bulk RNA-seq data as a constraint. Bubble improves recovery of missing values, correlations, and reduces false positive signals. It enhances differential expression analysis, clustering, visualization, and aids cellular trajectory inference. Moreover, Bubble provides fast and scalable imputation with minimal memory usage.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Siqi Chen, Xuhua Yan, Ruiqing Zheng, Min Li
Summary: Bubble is a method for identifying and imputing 'dropout events' in scRNA-seq data, using gene expression rate and coefficient of variation to identify zeros, and then utilizing an autoencoder for imputation. Bubble enhances the recovery of missing values, reduces the introduction of false positive signals, and improves the identification of differentially expressed genes and cell clustering and visualization.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Xiaoshu Zhu, Jian Li, Yongchang Lin, Liquan Zhao, Jianxin Wang, Xiaoqing Peng
Summary: This paper proposes a hybrid dimensionality reduction algorithm, ScEDA, for scRNA-seq data by integrating binning-based entropy and a denoising autoencoder. ScEDA effectively addresses the computational problems of high dimensionality, high sparseness, and high noise in scRNA-seq data. Experimental results demonstrate that ScEDA outperforms three other clustering methods on 16 real scRNA-seq datasets, especially in large-scale datasets.
JOURNAL OF COMPUTATIONAL BIOLOGY
(2022)
Article
Computer Science, Theory & Methods
Micheal Olaolu Arowolo, Marion Olubunmi Adebiyi, Charity Aremu, Ayodele A. Adebiyi
Summary: Researchers are increasingly using machine learning and bioinformatics techniques to address classification problems in genetic data analysis. Early detection of diseases and infections is a key focus for researchers in the field. Dimensionality reduction techniques and classification methods play important roles in advancing RNA-Sequencing approaches.
JOURNAL OF BIG DATA
(2021)
Article
Engineering, Electrical & Electronic
Ruisheng Rana, Jinping Wang, Bin Fang, Weiming Yang
Summary: This paper introduces an improved neighborhood preserving embedding method (NPEAE), which utilizes a linear autoencoder to achieve more accurate and effective data projection from high-dimensional space to low-dimensional space. NPEAE performs better in recognition accuracy compared to other comparative methods.
DIGITAL SIGNAL PROCESSING
(2024)
Article
Computer Science, Artificial Intelligence
Jianping Gou, Xia Yuan, Ya Xue, Lan Du, Jiali Yu, Shuyin Xia, Yi Zhang
Summary: Learning graph embeddings is crucial for reducing the dimensionality of high-dimensional data. This process aims to preserve both discriminative and geometric information by constructing graphs manually or automatically. However, relying solely on manual or automatic graph constructions cannot fully explore the underlying data structure. To address this, we propose a novel method called Discriminative and Geometry-Preserving Adaptive Graph Embedding (DGPAGE) that integrates manual and adaptive graph constructions in a unified framework. DGPAGE effectively injects essential information from predefined graphs into the learning of an adaptive graph, achieving both adaptability and specificity of the data. Experimental results on image datasets demonstrate that DGPAGE outperforms state-of-the-art graph-based dimensionality reduction methods. Ablation studies further show the advantages of the integrated framework provided by DGPAGE.
Article
Biology
Yongjie Xu, Zelin Zang, Jun Xia, Cheng Tan, Yulan Geng, Stan Z. Li
Summary: This paper proposes a general visualization method called deep visualization (DV) that can preserve the inherent structure of data and handle batch effects in various datasets. DV learns a structure graph to describe the relationships between data samples and transforms the data into a visualization space while preserving the geometric structure and correcting batch effects.
COMMUNICATIONS BIOLOGY
(2023)
Article
Biotechnology & Applied Microbiology
Saeedeh Akbari Rokn Abadi, Seyed Pouria Laghaee, Somayyeh Koohi
Summary: In this study, a clustering approach called SCEA is proposed for scRNA-seq data, which utilizes an encoder based on MLP and a graph attention auto-encoder to achieve low-dimensional representation and clustering of cells and genes. Experimental results demonstrate that SCEA generally outperforms several popular single-cell analysis methods in terms of clustering accuracy.
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
Multidisciplinary Sciences
Kai Battenberg, S. Thomas Kelly, Radu Abu Ras, Nicola A. Hetherington, Makoto Hayashi, Aki Minoda
Summary: Single-cell RNA-sequencing analysis has gained popularity, and UniverSC is a universal tool for processing single-cell RNA-seq data on any platform. It provides a command-line tool, docker image, and containerized graphical application for consistent and comprehensive integration, comparison, and evaluation of data from various platforms. Additionally, a cross-platform application with a graphical user interface is available to address the bottleneck of data processing for researchers without bioinformatics expertise.
NATURE COMMUNICATIONS
(2022)
Article
Biochemical Research Methods
Malte D. Luecken, M. Buettner, K. Chaichoompu, A. Danese, M. Interlandi, M. F. Mueller, D. C. Strobl, L. Zappia, M. Dugas, M. Colome-Tatche, Fabian J. Theis
Summary: This study benchmarked 68 method and preprocessing combinations on 85 batches of gene expression data, highlighting the importance of highly variable gene selection in improving method performance. When dealing with complex integration tasks, scANVI, Scanorama, scVI, and scGen consistently performed well, while the performance of single-cell ATAC-sequencing integration was strongly influenced by the choice of feature space.
Article
Biology
Shuchang Zhao, Li Zhang, Xuejun Liu
Summary: Single-cell RNA sequencing (scRNA-seq) is widely used in biomedical studies to reveal genetic differences at the single-cell level. However, the low RNA content in individual cells often leads to missing data and noise in scRNA-seq data. To address this, data normalization is crucial. In this study, a new method based on deep autoencoder and a two-part-gamma model is introduced for better handling of scRNA-seq data.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biochemical Research Methods
Wei Xu, Yi Wen, Yingying Liang, Qiushi Xu, Xuefei Wang, Wenfei Jin, Xi Chen
Summary: This protocol describes a fast and robust method for single-cell chromatin accessibility profiling using ATAC-seq, combining bulk tagging and flow cytometry. It provides critical information about cell type composition and variability within complex tissues. The experimental procedure can be completed within 1 or 2 days, generating high complexity data with excellent signal-to-noise ratio.
Article
Cell Biology
Nonthaphat Kent Wong, Shumeng Luo, Eudora Y. D. Chow, Fei Meng, Adenike Adesanya, Jiahong Sun, Herman M. H. Ma, Wenfei Jin, Wan-Chun Li, Shea Ping Yip, Chien-Ling Huang
Summary: Recent research has identified novel lncRNAs and miRNA axis that play a role in modulating drug response and the tumor microenvironment in myeloproliferative neoplasms (MPNs). The newly identified LNC000093 serves as a competitive endogenous RNA for miR-675-5p and reverses imatinib resistance in CML cells.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2021)
Article
Immunology
Xuefei Wang, Xiangru Shen, Shan Chen, Hongyi Liu, Ni Hong, Hanbing Zhong, Xi Chen, Wenfei Jin
Summary: Classic T cell subsets are defined by cell surface markers, while single-cell RNA sequencing clusters cells based on gene expression profiles. Multiple T cell subsets can be assigned to one cluster with similar expression patterns. Higher levels of ISAGs may contribute to quick immune responses.
JOURNAL OF IMMUNOLOGY
(2022)
Article
Immunology
Haoda Wu, Ruiqing Fu, Yu-Hong Zhang, Zhiming Liu, Zhen-Hua Chen, Jingkai Xu, Yongji Tian, Wenfei Jin, Samuel Zheng Hao Wong, Qing-Feng Wu
Summary: This study reveals both inter- and intratumoral heterogeneity in Ependymoma (EPN) and provides a framework for studying transcriptomic signatures of individual subclones at single-cell resolution.
FRONTIERS IN IMMUNOLOGY
(2022)
Article
Biochemical Research Methods
Wei Xu, Weilong Yang, Yunlong Zhang, Yawen Chen, Ni Hong, Qian Zhang, Xuefei Wang, Yukun Hu, Kun Song, Wenfei Jin, Xi Chen
Summary: ISSAAC-seq is a highly sensitive and flexible single-cell multi-omics method that allows for joint profiling of chromatin accessibility and gene expression. It provides critical information about cell types and cell states, revealing heterogeneity at the chromatin level within cell types defined by gene expression.
Article
Multidisciplinary Sciences
Junliang Wang, Wei Chen, Wenjun Yue, Wenhong Hou, Feng Rao, Hanbing Zhong, Yuanming Qi, Ni Hong, Ting Ni, Wenfei Jin
Summary: This study developed a single-cell polyadenylation sequencing method to investigate the landscape of alternative polyadenylation (APA) at the single-cell level. The results showed that genes with multiple polyA sites in bulk data tend to use only one site in each single cell. Cell cycle genes were found to have high variation in polyA site usages. Furthermore, polyA site usage switch played an important role in cell cycle regulation.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Computer Science, Information Systems
Zhichao Liang, Zixiang Luo, Keyin Liu, Jingwei Qiu, Quanying Liu
Summary: Electrical neuromodulation is commonly used for palliative treatment in epilepsy control, but it lacks the capability of self-adaptively adjusting stimulation inputs. This study proposes a Koopman-MPC framework that integrates a deep Koopman operator based dynamical model and a model predictive control module for real-time closed-loop electrical neuromodulation in epilepsy. The proposed framework shows better predictive capability and computational efficiency compared to baseline models, and opens up new possibilities for model-based closed-loop neuromodulation and nonlinear neurodynamics.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Review
Plant Sciences
Md. Alamin, Most. Humaira Sultana, Xiangyang Lou, Wenfei Jin, Haiming Xu
Summary: This review paper provides an overview of LMMs-based methods for GWAS, including different methods, software packages, and open-source applications. The advantages and weaknesses of LMMs in GWAS are discussed, along with future perspectives and conclusions.
Article
Oncology
Jie Zhou, Guanming Chen, Jiuling Wang, Bo Zhou, Xuemin Sun, Jinsong Wang, Shu Tang, Xiangju Xing, Xiaofei Hu, Yang Zhao, Yu Peng, Wenjiong Shi, Tingting Zhao, Yuzhang Wu, Hanbing Zhong, Ni Hong, Zhihua Ruan, Yi Zhang, Wenfei Jin
Summary: Anti-PD-1 therapy shows effective outcomes in both liver cancer patients and non-liver cancer patients infected with HBV. Through a retrospective multicenter study, it is found that HBV+ non-liver cancer patients have better responses to anti-PD-1 therapy compared to HBV- non-liver cancer patients. Additionally, in HBV+ ESCC patients, the cytotoxicity score of T cells and MHC score of B cells significantly increase after anti-PD-1 therapy. CX3CR1(high) T-EFF, a subset of CD8(+) T-EFF, is also associated with better clinical outcomes in HBV+ ESCC patients.
Article
Biochemical Research Methods
Huiguang Yi, Yanling Lin, Qing Chang, Wenfei Jin
Summary: Alignment-based RNA-seq quantification methods involve time-consuming alignment process, while alignment-free RNA-seq quantification methods bypass this step and achieve significant speed improvements. However, existing alignment-free methods relying on EM algorithm only provide locally optimal solutions, leaving room for further accuracy improvement. In this study, we introduce TQSLE, the first alignment-free RNA-seq quantification method providing a globally optimal solution for transcript abundances estimation. TQSLE outperforms other alignment-free methods in terms of accuracy, while maintaining comparable speed. TQSLE is freely available.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemistry & Molecular Biology
Yang Su, Yifan Luo, Peitao Zhang, Hong Lin, Weijie Pu, Hongyun Zhang, Huifang Wang, Yi Hao, Yihang Xiao, Xiaozhe Zhang, Xiayun Wei, Siyue Nie, Keren Zhang, Qiuyu Fu, Hao Chen, Niu Huang, Yan Ren, Mingxuan Wu, Billy Kwok Chong Chow, Xing Chen, Wenfei Jin, Fengchao Wang, Li Zhao, Feng Rao
Summary: This article describes a post-translational modification cascade induced by glucose, which enhances glucose uptake and glycolysis to promote tumor growth and progression. This cascade leads to the degradation of p53 protein, thereby promoting cancer cell proliferation. The disruption of the glucose-CK2-CSN2-CRL4COP1 axis inhibits glucose-induced p53 degradation and cancer cell proliferation.
Article
Endocrinology & Metabolism
Di Wu, Zongxian Li, Yime Zhang, Yinlian Zhang, Guanqun Ren, Yanyu Zeng, Huiying Liu, Weiqiang Guan, Xingyu Zhao, Peng Li, Luni Hu, Zhiyuan Hou, Jingjing Gong, Jun Li, Wenfei Jin, Zeping Hu, Changtao Jiang, Houhua Li, Chao Zhong
Summary: This study reveals the importance of proline uptake in the activation of innate lymphoid cells and its contribution to gut homeostasis. Deficiency in proline uptake impairs lymphoid tissue inducer cell activation and worsens colitis. The study highlights the role of proline metabolism in specific subsets of lymphoid cells and its involvement in the regulation of reactive oxygen species and interleukin-22.
Article
Biochemistry & Molecular Biology
Tailin He, Bo Zhou, Guohuan Sun, Qinnan Yan, Sixiong Lin, Guixing Ma, Qing Yao, Xiaohao Wu, Yiming Zhong, Donghao Gan, Shaochuan Huo, Wenfei Jin, Di Chen, Xiaochun Bai, Tao Cheng, Huiling Cao, Guozhi Xiao
Summary: The novel Pinch-Cxcl12-Mbl2 signaling pathway promotes the interactions between bone and liver to modulate immunity and hematopoiesis, which may provide a useful therapeutic target for immune and infectious diseases.
CELL DEATH AND DIFFERENTIATION
(2023)
Article
Biotechnology & Applied Microbiology
Huiguang Yi, Yanling Lin, Chengqi Lin, Wenfei Jin
Summary: The Kssd technique is faster and more accurate than current methods, able to be used for large-scale dataset comparisons and identifying thousands of misidentifications or contaminations in real data.