A5010917006- Radiomics and Machine Learning in Medical Imaging
- Cancer Immunotherapy and Biomarkers
- Cancer Genomics and Diagnostics
- Single-cell and spatial transcriptomics
- Immune cells in cancer
- Bioinformatics and Genomic Networks
- AI in cancer detection
- Pharmacogenetics and Drug Metabolism
- Computational Drug Discovery Methods
- Chemokine receptors and signaling
- MicroRNA in disease regulation
- Advanced biosensing and bioanalysis techniques
- Immunotherapy and Immune Responses
- Biomedical Text Mining and Ontologies
- Antimicrobial Peptides and Activities
- Gene expression and cancer classification
- Machine Learning in Bioinformatics
- T-cell and B-cell Immunology
- Gene Regulatory Network Analysis
- Immune Cell Function and Interaction
- vaccines and immunoinformatics approaches
- Cell Image Analysis Techniques
- Cancer Cells and Metastasis
- Extracellular vesicles in disease
- RNA modifications and cancer
Harbin Institute of Technology
2021-2024
Central South University
2019-2020
Recent advances in spatial transcriptomics (ST) have brought unprecedented opportunities to understand tissue organization and function context. However, it is still challenging precisely dissect domains with similar gene expression histology situ. Here, we present DeepST, an accurate universal deep learning framework identify domains, which performs better than the existing state-of-the-art methods on benchmarking datasets of human dorsolateral prefrontal cortex. Further testing a breast...
Abstract Accurate prediction of immunogenic peptide recognized by T cell receptor (TCR) can greatly benefit vaccine development and cancer immunotherapy. However, identifying peptides accurately is still a huge challenge. Most the antigen predicted in silico fail to elicit immune responses vivo without considering TCR as key factor. This inevitably causes costly time-consuming experimental validation test for antigens. Therefore, it necessary develop novel computational methods precisely...
The assignment of function to proteins at a large scale is essential for understanding the molecular mechanism life. However, only very small percentage more than 179 million in UniProtKB have Gene Ontology (GO) annotations supported by experimental evidence. In this paper, we proposed an integrated deep-learning-based classification model, named SDN2GO, predict protein functions. SDN2GO applies convolutional neural networks learn and extract features from sequences, domains, known PPI...
Abstract The inference of cell–cell communication (CCC) is crucial for a better understanding complex cellular dynamics and regulatory mechanisms in biological systems. However, accurately inferring spatial CCCs at single-cell resolution remains significant challenge. To address this issue, we present versatile method, called DeepTalk, to infer CCC by integrating RNA sequencing (scRNA-seq) data transcriptomics (ST) data. DeepTalk utilizes graph attention network (GAT) integrate scRNA-seq ST...
To efficiently save cost and reduce risk in drug research development, there is a pressing demand to develop silico methods predict sensitivity cancer cells. With the exponentially increasing number of multi-omics data derived from high-throughput techniques, machine learning-based have been applied prediction sensitivities. However, these drawbacks either interpretability mechanism action or limited performance modeling sensitivity. In this paper, we presented pathway-guided deep neural...
Cell-cell interactions (CCIs) play critical roles in many biological processes such as cellular differentiation, tissue homeostasis, and immune response. With the rapid development of high throughput single-cell RNA sequencing (scRNA-seq) technologies, it is importance to identify CCIs from ever-increasing scRNA-seq data. However, limited by algorithmic constraints, current computational methods based on statistical strategies ignore some key latent information contained data with sparsity...
Advances in single-cell transcriptomics provide an unprecedented opportunity to explore complex biological processes. However, computational methods for analyzing still have room improvement especially dimension reduction, cell clustering, and cell-cell communication inference. Herein, we propose a versatile method, named DcjComm, comprehensive analysis of transcriptomics. DcjComm detects functional modules expression patterns performs reduction clustering discover cellular identities by the...
Abstract T cells recognize tumor antigens and initiate an anticancer immune response in the very early stages of development, antigen specificity is determined by T-cell receptor (TCR). Therefore, monitoring changes TCR repertoire peripheral blood may offer a strategy to detect various cancers at relatively stage. Here, we developed deep learning framework iCanTCR identify patients with cancer based on repertoire. The uses TCRβ sequences from individual as input outputs predicted...
Tumor-infiltrating T cells are essential players in tumor immunotherapy. Great progress has been achieved the investigation of cell heterogeneity. However, little is well known about shared characteristics tumor-infiltrating across cancers. In this study, we conduct a pan-cancer analysis 349,799 15 The results show that same types had similar expression patterns regulated by specific transcription factor (TF) regulons Multiple type transition paths were consistent We found TF associated with...
MicroRNAs (miRNAs) are a highly abundant collection of functional non-coding RNAs involved in cellular regulation and various complex human diseases. Although large number miRNAs have been identified, most their physiological functions remain unknown. Computational methods play vital role exploring the potential miRNAs. Here, we present DeepMiR2GO, tool for integrating miRNAs, proteins diseases, to predict gene ontology (GO) based on multiple deep neuro-symbolic models. DeepMiR2GO starts by...
Circulating tumor cells (CTCs) that undergo epithelial-to-mesenchymal transition (EMT) can provide valuable information regarding metastasis and potential therapies. However, current studies on the EMT overlook alternative splicing. Here, we used single-cell full-length transcriptome data mRNA sequencing of CTCs to identify stage-specific splicing partial mesenchymal states during pancreatic cancer metastasis. We classified definitive normal epithelial via genetic aberrations demonstrated...
The rapid development of single-cel+l RNA sequencing (scRNA-seq) technology provides unprecedented opportunities for exploring biological phenomena at the single-cell level. discovery cell types is one major applications researchers to explore heterogeneity cells. Some computational methods have been proposed solve problem scRNA-seq data clustering. However, unavoidable technical noise and notorious dropouts also reduce accuracy clustering methods. Here, we propose cauchy-based bounded...
<div>Abstract<p>T cells recognize tumor antigens and initiate an anticancer immune response in the very early stages of development, antigen specificity T is determined by T-cell receptor (TCR). Therefore, monitoring changes TCR repertoire peripheral blood may offer a strategy to detect various cancers at relatively stage. Here, we developed deep learning framework iCanTCR identify patients with cancer based on repertoire. The uses TCRβ sequences from individual as input outputs...