A5058416645- Single-cell and spatial transcriptomics
- Gene expression and cancer classification
- Cancer-related molecular mechanisms research
- Molecular Biology Techniques and Applications
- Cell Image Analysis Techniques
- interferon and immune responses
- Ferroptosis and cancer prognosis
- Text and Document Classification Technologies
- Advanced Graph Neural Networks
- MicroRNA in disease regulation
- Circular RNAs in diseases
- Complex Network Analysis Techniques
- Extracellular vesicles in disease
- RNA modifications and cancer
- Bioinformatics and Genomic Networks
Beijing Jiaotong University
2021-2024
Tsinghua University
2017-2022
Institute of Bioinformatics
2022
Abstract Properly integrating spatially resolved transcriptomics (SRT) generated from different batches into a unified gene-spatial coordinate system could enable the construction of comprehensive spatial transcriptome atlas. Here, we propose SPIRAL, consisting two consecutive modules: SPIRAL-integration, with graph domain adaptation-based data integration, and SPIRAL-alignment, cluster-aware optimal transport-based coordination alignment. We verify SPIRAL both synthetic real SRT datasets....
Single cell RNA-seq (scRNA-seq) techniques can reveal valuable insights of cell-to-cell heterogeneities. Projection high-dimensional data into a low-dimensional subspace is powerful strategy in general for mining such big data. However, scRNA-seq suffers from higher noise and lower coverage than traditional bulk RNA-seq, hence bringing new computational difficulties. One major challenge how to deal with the frequent drop-out events. The events, usually caused by stochastic burst effect gene...
Abstract Deciphering spatial domains using spatially resolved transcriptomics (SRT) is of great value for the characterizing and understanding tissue architecture. However, inherent heterogeneity varying resolutions present challenges in joint analysis multi-modal SRT data. We introduce a geometric deep learning method, named stMMR, to effectively integrate gene expression, location histological information accurate identifying from stMMR uses graph convolutional networks (GCN)...
Understanding the molecular and cellular mechanisms of human primordial germ cells (hPGCs) is essential in studying infertility cell tumorigenesis. Many RNA-binding proteins (RBPs) non-coding RNAs are specifically expressed functional during hPGC developments. However, roles regulatory these RBPs RNAs, such as microRNAs (miRNAs), hPGCs remain elusive. In this study, we reported a new function DAZL, cell-specific RBP, miRNA biogenesis proliferation. First, DAZL co-localized with let-7a PGCs...
Recent developments of single cell RNA-sequencing technologies lead to the exponential growth sequencing datasets across different conditions. Combining these helps better understand cellular identity and function. However, it is challenging integrate from laboratories or due batch effect, which are interspersed with biological variances. To overcome this problem, we have proposed Single Cell Integration by Disentangled Representation Learning (SCIDRL), a domain adaption-based method, learn...
Abstract Background Deciphering spatial domains using spatially resolved transcriptomics (SRT) is of great value for characterizing and understanding tissue architecture. However, the inherent heterogeneity varying resolutions present challenges in joint analysis multimodal SRT data. Results We introduce a geometric deep learning method, named stMMR, to effectively integrate gene expression, location, histological information accurate identifying from stMMR uses graph convolutional networks...
Gastric cancer is a malignant tumor with high morbidity and mortality. Therefore, the accurate recognition of prognostic molecular markers key to improving treatment efficacy prognosis.In this study, we developed stable robust signature through series processes using machine-learning approaches. This PRGS was further experimentally validated in clinical samples gastric cell line.The an independent risk factor for overall survival that performs reliably has utility. Notably, proteins promote...