A5034008160- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Cancer-related molecular mechanisms research
- Machine Learning in Bioinformatics
- COVID-19 diagnosis using AI
- AI in cancer detection
- RNA modifications and cancer
- Epigenetics and DNA Methylation
- SARS-CoV-2 and COVID-19 Research
- Computational Drug Discovery Methods
- Cancer Genomics and Diagnostics
- Molecular Biology Techniques and Applications
- Functional Brain Connectivity Studies
- COVID-19 Clinical Research Studies
- Advanced Neuroimaging Techniques and Applications
- RNA Research and Splicing
- Gene Regulatory Network Analysis
- Advanced Neural Network Applications
- EEG and Brain-Computer Interfaces
- RNA and protein synthesis mechanisms
- Ferroptosis and cancer prognosis
- Cutaneous Melanoma Detection and Management
- Generative Adversarial Networks and Image Synthesis
- Genetic factors in colorectal cancer
- ECG Monitoring and Analysis
Dalian Maritime University
2024-2025
Yunnan Agricultural University
2025
Jilin University
2019-2024
Jilin Province Science and Technology Department
2021-2023
Guiyang Medical University
2023
Xidian University
2020
Jilin Medical University
2020
PRG S&Tech (South Korea)
2019
The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to human society in China and across world. COVID-19 induced pneumonia hosts carried a highly inter-person contagiousness. patients may carry severe symptoms, some them even die major organ failures. This study utilized machine learning algorithms build severeness detection model. Support vector (SVM) demonstrated promising accuracy after 32 features were detected be significantly associated with...
Abstract Motivation Deep neural network (DNN) algorithms were utilized in predicting various biomedical phenotypes recently, and demonstrated very good prediction performances without selecting features. This study proposed a hypothesis that the DNN models may be further improved by feature selection algorithms. Results A comprehensive comparative was carried out evaluating 11 on three conventional algorithms, i.e. convolution (CNN), deep belief (DBN) recurrent (RNN), recent DNNs,...
Abstract Small average differences in the left-right asymmetry of cerebral cortical thickness have been reported individuals with autism spectrum disorder (ASD) compared to typically developing controls, affecting widespread regions. The possible impacts these regional alterations terms structural network effects not previously characterized. Inter-regional morphological covariance analysis can capture connectivity between different areas at macroscale level. Here, we used data from 1455 ASD...
Drug repositioning, which identifies new therapeutic potential of approved drugs, is instrumental in accelerating drug discovery. Recently, to alleviate the effect data sparsity on predicting possible drug-disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm for discriminative representations drugs and diseases through distilling informative self-supervised signals. However, existing GCLbased methods devised DDA prediction still encounter two...
The novel coronavirus severe acute respiratory syndrome 2 (SARS-CoV-2) has caused a major pandemic outbreak recently. Various diagnostic technologies have been under active development. disease (COVID-19) may induce pulmonary failures, and chest X-ray imaging becomes one of the confirmed technologies. very limited number publicly available samples rendered training deep neural networks unstable inaccurate. This study proposed two-step transfer learning pipeline residual network framework...
Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces most human cells and exerts an essential role in immune system responding to invasive items. The T cell antigen receptors may recognize HLA-peptide complexes cancer destroy these through toxic lymphocytes. computational determination HLA-binding peptides will facilitate rapid development immunotherapies. This study hypothesized that natural language processing-encoded peptide features be further enriched by another...
Drug repositioning, which identifies new therapeutic potential of approved drugs, is pivotal in accelerating drug discovery. Recently, growing efforts are devoted to applying graph neural networks (GNNs) for effectively modeling drug-disease associations (DDAs). However, current GNN-based methods generally designed unsigned graphs and fail gain complementary insights provided by negative links. Despite the proposal sign-aware GNNs general fields, there exist two intractable challenges when...
OMIC datasets have high dimensions, and the connection among features is very complicated. It difficult to establish linkages these certain biological traits of significance. The proposed ensemble swarm intelligence-based approaches can identify key biomarkers reduce feature dimension efficiently. an end-to-end method that only relies on rules algorithm itself, without presets such as number filtering features. Additionally, this achieves good classification accuracy excessive consumption...
Abstract Background Acne is one of the most common skin lesions in adolescents. Some severe or inflammatory acne leads to scars, which may have major impacts on patients’ quality life even job prospects. Grading plays an important role diagnosis, and diagnosis made by counting number acne. It a labor‐intensive it easy for dermatologists make mistakes, so very develop automatic methods. Ensemble learning improve prediction results base models, but its time complexity relatively high. The...
Enhancers are short genomic regions exerting tissue-specific regulatory roles, usually for remote coding regions. observed in both prokaryotic and eukaryotic genomes, their detections facilitate a better understanding of the transcriptional regulation mechanism. The accurate detection strength evaluation enhancers remain major bioinformatics challenge. Most current studies utilized statistical features fixed-length nucleotide sequences. This study introduces location information each k-mer...
Aging was a biological process under regulations from both inherited genetic factors and various molecular modifications within cells during the lifespan. Multiple studies demonstrated that chronological age may be accurately predicted using methylomic data. This study proposed three-step feature selection algorithm AgeGuess for regression problem. selected 107 features as gender-independent biomarkers Support Vector Regressor (SVR) model these achieved 2.0267 in mean absolute deviation...
ABSTRACT The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to human society in China and across world. COVID-19 induced pneumonia hosts carried a highly inter-person contagiousness. patients may carry severe symptoms, some them even die major organ failures. This study utilized machine learning algorithms build severeness detection model. Support vector (SVM) demonstrated promising accuracy after 32 features were detected be significantly associated...
Abstract Drug repositioning, which involves identifying new therapeutic indications for approved drugs, is pivotal in accelerating drug discovery. Recently, to mitigate the effect of label sparsity on inferring potential drug–disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm supplement high-quality self-supervised signals through designing auxiliary tasks, then transfer shareable knowledge main task, i.e. DDA prediction. However, existing...
Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in dimension of genic features, but number clinical samples cohorts relatively small due various reasons, including difficulties participant recruitment and high data-generation costs. Transcriptome one most abundantly available OMIC (referring high-throughput data, genomic, transcriptomic, proteomic epigenomic) data types. This study introduced a multitask graph attention...
LIDAR (light detection and ranging) based real‐time 3D perception is crucial for applications such as autonomous driving. However, most of the convolutional neural network (CNN) methods are time‐consuming computation‐intensive. These drawbacks mainly attributed to highly variable density point cloud complexity their pipelines. To find a balance between speed accuracy object from LIDAR, authors propose RTL3D, computationally efficient Real‐time LIDAR‐based detector. In an effective voxel‐wise...
Aim: Breast cancer histologic grade (HG) is a well-established prognostic factor. This study aimed to select methylomic biomarkers predict breast HGs. Materials & methods: The proposed algorithm BioDog firstly used correlation bias reduction strategy eliminate redundant features. Then incremental feature selection was applied find the features with high HG prediction accuracy. sequential backward elimination employed further refine biomarkers. A comparison existing algorithms were conducted....