A5045828187- Single-cell and spatial transcriptomics
- Gene expression and cancer classification
- Cell Image Analysis Techniques
- Molecular Biology Techniques and Applications
- AI in cancer detection
- Genomics and Phylogenetic Studies
- Immune cells in cancer
- Atherosclerosis and Cardiovascular Diseases
- Cancer-related molecular mechanisms research
- Neutrophil, Myeloperoxidase and Oxidative Mechanisms
- Neuroinflammation and Neurodegeneration Mechanisms
- CRISPR and Genetic Engineering
- Robotics and Sensor-Based Localization
- Land Use and Ecosystem Services
- Customer churn and segmentation
- Bioinformatics and Genomic Networks
- Advanced Vision and Imaging
- Genetics, Bioinformatics, and Biomedical Research
- Image Processing Techniques and Applications
- Advanced Text Analysis Techniques
- Web Data Mining and Analysis
- RNA and protein synthesis mechanisms
- RNA Research and Splicing
- Radiomics and Machine Learning in Medical Imaging
BGI Group (China)
2023-2025
Sun Yat-sen University
2025
Sun Yat-sen University Cancer Center
2025
BGI Research
2024-2025
Technical University of Denmark
2023-2024
Botswana Geoscience Institute
2024
Rice University
2024
The basic analysis steps of spatial transcriptomics require obtaining gene expression information from both space and cells. existing tools for these analyses incur performance issues when dealing with large datasets. These involve computationally intensive localization, RNA genome alignment, excessive memory usage in chip scenarios. problems affect the applicability efficiency analysis. Here, a high-performance accurate data workflow, called Stereo-seq Analysis Workflow (SAW), was developed...
Abstract Background Cell clustering is a pivotal aspect of spatial transcriptomics (ST) data analysis as it forms the foundation for subsequent mining. Recent advances in domain identification have leveraged graph neural network (GNN) approaches conjunction with data. However, such GNN-based methods suffer from representation collapse, wherein all spots are projected onto singular representation. Consequently, discriminative capability individual feature limited, leading to suboptimal...
Abstract Background Owing to recent advances in resolution and field-of-view, spatially resolved transcriptomics sequencing, such as Stereo-seq, has emerged a cutting-edge technology for the interpretation of large tissues at single-cell level. To generate accurate spatial gene expression profiles from high-resolution omics data, powerful computational tool is required. Findings We present CellBin, an image-facilitated one-stop pipeline field-of-view transcriptomic data Stereo-seq. CellBin...
Abstract Background The emergence of high-resolved spatial transcriptomics (ST) has facilitated the research novel methods to investigate biological development, organism growth, and other complex processes. However, whole ST datasets require customized imputation improve signal-to-noise ratio data quality. Findings We propose an efficient adaptive Gaussian smoothing (EAGS) method for ST. 2-factor EAGS creates patterns based on expression information cells, weights cells in same pattern,...
Abstract Background Integrative analysis of spatially resolved transcriptomics datasets empowers a deeper understanding complex biological systems. However, integrating multiple tissue sections presents challenges for batch effect removal, particularly when the are measured by various technologies or collected at different times. Findings We propose spatiAlign, an unsupervised contrastive learning model that employs expression all genes and spatial location cells, to integrate sections. It...
Understanding complex biological systems requires tracing cellular dynamic changes across conditions, time, and space. However, integrating multi-sample data in a unified way to explore heterogeneity remains challenging. Here, we present Stereopy, flexible framework for modeling dissecting comparative spatiotemporal patterns spatial transcriptomics with interactive visualization. To optimize this framework, devise universal container, scope controller, an integrative transformer tailored...
Gene expression in the brain is typically evaluated using invasive biopsy or postmortem histology. Serum markers provide an alternative way to monitor brain, but relatively few such exist. Additionally, origin of serum often cannot be localized a specific cell population, and monitoring dynamic changes their gene compromised by same factor that makes detectable - long half-life. Here we propose paradigm improve sensi-tivity marker measurement modifying vivo, called erasable markers, ESM. As...
In spatially resolved transcriptomics, Stereo-seq facilitates the analysis of large tissues at single-cell level, offering subcellular resolution and centimeter-level field-of-view. Our previous work on StereoCell introduced a one-stop software using cell nuclei staining images statistical methods to generate high-confidence spatial gene expression profiles for data. With advancements allowing acquisition boundary information, such as membrane/wall images, we updated our new version,...
Abstract Background Spatial transcriptome (ST) technologies are emerging as powerful tools for studying tumor biology. However, existing analyzing ST data limited, they mainly rely on algorithms developed single-cell RNA sequencing and do not fully utilize the spatial information. While some have been data, often designed specific tasks, lacking a comprehensive analytical framework leveraging Results In this study, we present StereoSiTE, an that combines open-source bioinformatics with...
As genomic sequencing technology continues to advance, it becomes increasingly important perform joint analyses of multiple datasets transcriptomics. However, batch effect presents challenges for dataset integration, such as data measured on different platforms, and collected at times. Here, we report the development BatchEval Pipeline, a workflow used evaluate integration. The Pipeline generates comprehensive report, which consists series HTML pages assessment findings, including main page,...
Abstract The basic analysis steps of spatial transcriptomics involve obtaining gene expression information from both space and cells. This process requires a set tools to be completed, existing face performance issues when dealing with large data sets. These include computationally intensive localization, RNA genome alignment, excessive memory usage in chip scenarios. problems affect the applicability efficiency process. To address these issues, high-performance accurate workflow called...
Abstract Spatially resolved omics technologies generating multimodal and high-throughput data lead to the urgent need for advanced analysis allow biological discoveries by comprehensively utilizing information from multi-omics data. The H&E image spatial transcriptomic indicate abundant features which are different complementary each other. AI algorithms can perform nonlinear on these aligned or unaligned complex datasets decode tumoral heterogeneity detecting functional domain....
<title>Abstract</title> Spatially resolved omics technologies generating multimodal and high-throughput data necessitate the development of advanced analysis methods, facilitate biological discoveries by comprehensively utilizing information from multi-omics data. Spatial transcriptomic hematoxylin eosin (H&E) images reveal abundant features which are different complementary to each other. We presented a machine learning based toolchain called StereoMM, graph fusion model that can...
ABSTRACT In recent years, cell segmentation techniques have played a critical role in the analysis of biological images, especially for quantitative studies. Deep learning-based models demonstrated remarkable performance segmenting and nucleus boundaries, however, they are typically tailored to specific modalities or require manual tuning hyperparameters, limiting their generalizability unseen data. Comprehensive datasets that support both training universal evaluation various essential...
ABSTRACT Understanding transcription profiles of living tissues is critical for biology and medicine. However, measurement the transcript levels typically done in homogenized post-mortem. Here, we present a new platform that enables non-invasive monitoring specific mRNA vivo , without tissue destruction. We achieved this by combining two cutting-edge tools - synthetic serum markers, called Released Markers Activity ( RMAs ), RNA-based sensors transcription. call IN-vivo Tracking ACtive...
Large language models (LLMs) have seen rapid improvement in the recent years, and been used a wider range of applications. After being trained on large text corpus, LLMs obtain capability extracting rich features from textual data. Such is potentially useful for web service recommendation task, where users services intrinsic attributes that can be described using natural sentences are recommendation. In this paper, we explore possibility practicality We propose model aided QoS prediction...