A5044328870- Single-cell and spatial transcriptomics
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Gene Regulatory Network Analysis
- Computational Drug Discovery Methods
- Machine Learning in Bioinformatics
- Extracellular vesicles in disease
- Cell Image Analysis Techniques
- MicroRNA in disease regulation
- Protein Structure and Dynamics
- Cancer-related molecular mechanisms research
- Advanced Fluorescence Microscopy Techniques
- Microbial Metabolic Engineering and Bioproduction
- Immune Cell Function and Interaction
- Viral Infectious Diseases and Gene Expression in Insects
- Functional Brain Connectivity Studies
- vaccines and immunoinformatics approaches
- RNA Research and Splicing
- Monoclonal and Polyclonal Antibodies Research
- Age of Information Optimization
- Molecular Communication and Nanonetworks
- Domain Adaptation and Few-Shot Learning
- Technology and Security Systems
- Wheat and Barley Genetics and Pathology
- Mental Health via Writing
Central South University
2014-2025
Guangxi University
2021
University of Calgary
2018-2019
Alberta Children's Hospital
2019
Institute of Cancer Research
2019
Shenzhen Maternity and Child Healthcare Hospital
2010-2014
Yichun University
2011
Ganzhou People's Hospital
2010
Longgang Central Hospital
2007
St Bartholomew's Hospital
1999
Abstract Motivation The development of single-cell RNA-sequencing (scRNA-seq) provides a new perspective to study biological problems at the level. One key issues in scRNA-seq analysis is resolve heterogeneity and diversity cells, which cluster cells into several groups. However, many existing clustering methods are designed analyze bulk RNA-seq data, it urgent develop methods. Moreover, high noise data also brings lot challenges computational Results In this study, we propose novel cell...
It is well known that most brain disorders are complex diseases, such as Alzheimer’s disease (AD) and schizophrenia (SCZ). In general, regions their interactions can be modeled network, which describe highly efficient information transmission in a brain. Therefore, network analysis plays an important role the study of diseases. With development noninvasive neuroimaging electrophysiological techniques, experimental data produced for constructing networks. recent years, researchers have found...
High-throughput screening technologies have provided a large amount of drug sensitivity data for panel cancer cell lines and hundreds compounds. Computational approaches to analyzing these can benefit anticancer therapeutics by identifying molecular genomic determinants developing new drugs. In this study, we developed deep learning architecture improve the performance prediction based on data. We integrated both features chemical information compounds predict half maximal inhibitory...
Abstract Genes that are thought to be critical for the survival of organisms or cells called essential genes. The prediction genes and their products (essential proteins) is great value in exploring mechanism complex diseases, study minimal required genome living development new drug targets. As laboratory methods often complicated, costly time-consuming, a many computational have been proposed identify genes/proteins from perspective network level with in-depth understanding biology rapid...
Abstract Increasing evidences have proved that circRNA plays a significant role in the development of many diseases. In addition, researches shown can be considered as potential biomarker for clinical diagnosis and treatment disease. Some computational methods been proposed to predict circRNA-disease associations. However, performance these is limited sparsity low-order interaction information. this paper, we propose new method (KGANCDA) associations based on knowledge graph attention...
Abstract Motivation Single-cell RNA sequencing has emerged as a powerful technology for studying gene expression at the individual cell level. Clustering cells into distinct subpopulations is fundamental in scRNA-seq data analysis, facilitating identification of types and exploration cellular heterogeneity. Despite recent development many deep learning-based single-cell clustering methods, few have effectively exploited correlations among genes, resulting suboptimal outcomes. Results Here,...
The clinical, pathological, and immunological similarities between Kawasaki disease the staphylococcal streptococcal toxic shock syndromes suggest that a superantigen toxin may be involved in pathogenesis of disease. V beta repertoire peripheral blood mononuclear cells from 21 children with disease, 28 other illnesses, 22 healthy controls were examined using monoclonal antibodies to 2, 5, 8, 12, 19. mean percentage 2 expressing T patients was increased when compared or illnesses. percentages...
Reconstructing gene regulatory networks (GRNs) based on expression profiles is still an enormous challenge in systems biology. Random forest-based methods have been proved a kind of efficient to evaluate the importance regulations. Nevertheless, accuracy traditional can be further improved. With time-series data, exploiting inherent time information and high order lag are promising strategies improve power GRNs inference.In this study, we propose scalable, flexible approach called BiXGBoost...
The rapid development of single-cell RNA sequencing (scRNA-Seq) technology provides strong technical support for accurate and efficient analyzing gene expression data. However, the analysis scRNA-Seq is accompanied by many obstacles, including dropout events curse dimensionality. Here, we propose scGMAI, which a new Gaussian mixture clustering method based on autoencoder networks fast independent component (FastICA). Specifically, scGMAI utilizes to reconstruct values from data FastICA used...
The rapid development of proteomics and high-throughput technologies has produced a large amount Protein-Protein Interaction (PPI) data, which makes it possible for considering dynamic properties protein interaction networks (PINs) instead static properties. Identification complexes from PINs becomes vital scientific problem understanding cellular life in the post genome era. Up to now, plenty models or methods have been proposed construction identify complexes. However, most constructed...
Only a small fraction of patients with cancer receiving immune checkpoint therapy (ICT) respond, which is associated tumor microenvironment (TIME) subtypes and tumor-infiltrating lymphocytes (TILs).To examine whether germline variants natural killer (NK) cells, key component the system, are TIME subtypes, abundance TILs, response to ICT, clinical outcomes, risk.This genetic association study explored examined genomic information prognosis, risk. Clinical information, RNA sequencing,...
Biological functions of a cell are typically carried out through protein complexes. The detection complexes is therefore great significance for understanding the cellular organizations and functions. In past decades, many computational methods have been proposed to detect However, most existing just search local topological information mine dense subgraphs as complexes, ignoring global information. To tackle this issue, we propose DPCMNE method via multi-level network embedding. It can...
Integration of multi-omics data can provide information on biomolecules from different layers to illustrate the complex biology systematically. Here, we build a atlas containing 132,570 transcripts, 44,473 proteins, 19,970 phosphoproteins, and 12,427 acetylproteins across wheat vegetative reproductive phases. Using this atlas, elucidate transcriptional regulation network, contributions post-translational modification (PTM) transcript level protein abundance, biased homoeolog expression PTM...
Recently, the emergence of single-cell RNA-sequencing (scRNA-seq) technology makes it possible to solve biological problems at resolution. One critical steps in cellular heterogeneity analysis is cell type identification. Diverse scRNA-seq clustering methods have been proposed partition cells into clusters. Among all methods, hierarchical and spectral are most popular approaches downstream with different preprocessing strategies such as similarity learning, dropout imputation, dimensionality...
Accurate identification of cell types from single-cell RNA sequencing (scRNA-seq) data plays a critical role in variety scRNA-seq analysis studies. This task corresponds to solving an unsupervised clustering problem, which the similarity measurement between cells affects result significantly. Although many approaches for type have been proposed, accuracy still needs be improved. In this study, we proposed novel framework based on learning, called SSRE. SSRE models relationships subspace...
The rapid development of single-cell transcriptome sequencing technology provides a cell-level perspective to study biological problems. Identification cell types is one the fundamental issues in computational analysis single data. Due large amount noise from technologies and high dimension expression profiles, traditional clustering methods are not so applicable solve it. To address problem, we design an adaptive sparse subspace method, called AdaptiveSSC, identify types. AdaptiveSSC based...
The prediction of genes related to diseases is important the study due high cost and time consumption biological experiments. Network propagation a popular strategy for disease-gene prediction. However, existing methods focus on stable solution dynamics while ignoring useful information hidden in dynamical process, it still challenge make use multiple types physical/functional relationships between proteins/genes effectively predict disease-related genes. Therefore, we proposed framework...
Abstract Gene regulatory network plays a crucial role in controlling the biological processes of living creatures. Deciphering complex gene networks from experimental data remains major challenge system biology. Recent advances single-cell RNA sequencing technology bring massive high-resolution data, enabling computational inference cell-specific (GRNs). Many relevant algorithms have been developed to achieve this goal past years. However, GRN is still less ideal due extra noises involved...
Abstract Clustering cells based on single-cell multi-modal sequencing technologies provides an unprecedented opportunity to create high-resolution cell atlas, reveal cellular critical states and study health diseases. However, effectively integrating different data for clustering remains a challenging task. Motivated by the successful application of Louvain in scRNA-seq data, we propose framework, called scMLC, tackle this problem. scMLC builds multiplex single- cross-modal cell-to-cell...
It is a fundamental challenge that identifying disease genes from large number of candidates for specific disease. As the biological experiment-based methods are generally timeconsuming and laborious, it has become new strategy to identify by using computational approaches. In this paper, we proposed an algorithm based on search engine ranking method, named PDGTR, prioritize candidates. Firstly, constructed weighted human network calculating topological similarity phenotype each pair...
Integration of single-cell transcriptome datasets from multiple sources plays an important role in investigating complex biological systems. The key to integration is batch effect removal. Recent methods attempt apply a contrastive learning strategy correct effects. Despite their encouraging performance, the optimal framework for removal still under exploration. We develop improved learning-based correction framework, GLOBE. GLOBE defines adaptive translation transformations each cell...
Abstract With the development of spatially resolved transcriptomics technologies, it is now possible to explore gene expression profiles single cells while preserving their spatial context. Spatial clustering plays a key role in transcriptome data analysis. In past 2 years, several graph neural network-based methods have emerged, which significantly improved accuracy clustering. However, accurately identifying boundaries domains remains challenging task. this article, we propose stAA, an...
Abstract With the advent of spatial multi-omics, we can mosaic integrate such datasets with partially overlapping modalities to construct higher dimensional views source tissue. SpaMosaic is a multi-omics integration tool that employs contrastive learning and graph neural networks modality-agnostic batch-corrected latent space suited for analyses like domain identification imputing missing omes. Using simulated experimentally acquired datasets, benchmarked against single-cell methods. The...