A5114859464- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Single-cell and spatial transcriptomics
- Computational Drug Discovery Methods
- Cancer-related molecular mechanisms research
- Domain Adaptation and Few-Shot Learning
- Extracellular vesicles in disease
- Molecular Biology Techniques and Applications
- MicroRNA in disease regulation
- Pharmacogenetics and Drug Metabolism
- Protein Structure and Dynamics
Hunan University
2023-2025
Central South University
2020
Recent advances in spatial transcriptomics technologies have enabled gene expression profiles while preserving context. Accurately identifying domains is crucial for downstream analysis and it requires the effective integration of information. While increasingly computational methods been developed domain detection, most them cannot adaptively learn complex relationship between information, leading to sub-optimal performance.To overcome these challenges, we propose a novel deep learning...
Abstract Motivation Single-cell RNA-sequencing (scRNA-seq) is widely used to reveal cellular heterogeneity, complex disease mechanisms and cell differentiation processes. Due high sparsity gene expression patterns, scRNA-seq data present a large number of dropout events, affecting downstream tasks such as clustering pseudo-time analysis. Restoring the levels genes essential for reducing technical noise facilitating However, existing imputation methods ignore topological structure information...
Recent advances in spatial transcriptomics technologies have provided multi-modality data integrating gene expression, context, and histological images. Accurately identifying domains spatially variable genes is crucial for understanding tissue structures biological functions. However, effectively combining to identify determining SVGs closely related these remains a challenge.
Single-cell RNA sequencing (scRNA-seq) technology is utilized to analyze cellular heterogeneity, perform cellular-level biological research and derive novel insights from complex systems. However, the raw scRNA-seq data not directly suitable for downstream task analysis due its high variability, sparsity dimensionality. Therefore, in this study, we propose a new self-supervised framework based on siamese representation learning, named scSRL which can fully explore intrinsic properties of...