A5048890418- Epigenetics and DNA Methylation
- Protein Degradation and Inhibitors
- Cancer, Hypoxia, and Metabolism
- Cancer, Lipids, and Metabolism
- RNA modifications and cancer
- Microplastics and Plastic Pollution
- biodegradable polymer synthesis and properties
- Digital and Cyber Forensics
- Ubiquitin and proteasome pathways
- Polymer Nanocomposites and Properties
- Advanced Malware Detection Techniques
- Melanoma and MAPK Pathways
- Multiple Myeloma Research and Treatments
- Histone Deacetylase Inhibitors Research
- Digital Media Forensic Detection
- Click Chemistry and Applications
- Ferroptosis and cancer prognosis
- Traffic Prediction and Management Techniques
- Gene expression and cancer classification
- Transportation Planning and Optimization
- Photopolymerization techniques and applications
- Simulation and Modeling Applications
- Single-cell and spatial transcriptomics
- Anomaly Detection Techniques and Applications
- Advanced biosensing and bioanalysis techniques
Beihang University
2025
Hangzhou Medical College
2022-2024
Zhejiang Provincial People's Hospital
2022-2024
Tang Hospital
2024
Northwest A&F University
2021-2024
Sam Houston State University
2021-2024
State Forestry and Grassland Administration
2022-2024
Shandong University
2024
Nanjing Forestry University
2022-2024
Chinese Academy of Sciences
2019-2023
Abstract Motivation Three-dimensional (3D) genome organization is of vital importance in gene regulation and disease mechanisms. Previous studies have shown that CTCF-mediated chromatin loops are crucial to studying the 3D structure cells. Although various experimental techniques been developed detect loops, they found be time-consuming costly. Nowadays, sequence-based computational methods can capture significant features help predict loops. However, these low performance poor...
Single-cell Hi-C data are a common source for studying the differences in three-dimensional structure of cell chromosomes. The development single-cell technology makes it possible to obtain batches data. How quickly and effectively discriminate types has become one hot research field. However, existing computational methods predict based on found be low accuracy. Therefore, we propose high accuracy classification algorithm, called scHiCStackL, In our work, first improve preprocessing method...
Accurately predicting traffic flow on roads is crucial to address urban congestion and save travel time. However, this a challenging task due the strong spatial temporal correlations of data. Existing prediction methods based graph neural networks recurrent often overlook dynamic spatiotemporal dependencies between road nodes excessively focus local flow, thereby failing effectively model global dependencies. To overcome these challenges, article proposes new Spatio-temporal Causal Graph...
Purpose The purpose of this paper is to develop a real-time trajectory planner with optimal maneuver for autonomous vehicles deal dynamic obstacles during parallel parking. Design/methodology/approach To parking, long- and short-term mixed planning algorithm proposed in paper. In long term, considering obstacle behavior, A-star was improved by RS curve potential function via spatio-temporal map obtain safe efficient initial trajectory. short proposes nonlinear model predictive control...
The proliferation of software tools and automated techniques in digital forensics has brought about some controversies regarding bias fairness. Different biases exist have been proven civil criminal cases. In our research, we analyze discuss these present automation systems used by law enforcement organizations court proceedings. Furthermore, real-life cases scenarios where determined or influenced We were also able to provide recommendations for reducing tools, which hope will be the...
Abstract Single-cell clustering is the most significant part of single-cell RNA sequencing (scRNA-seq) data analysis. One main issue facing scRNA-seq noise and sparsity, which poses a great challenge for advance high-precision algorithms. This study adopts cellular markers to identify differences between cells, contributes feature extraction single cells. In this work, we propose algorithm-SCMcluster (single-cell cluster using marker genes). algorithm integrates two cell databases(CellMarker...
Utilizing smart mobile devices for entertainment, education, and social networking has grown recently. Even though applications are getting more sophisticated resource-intensive, the computing power of is still constrained. Mobile phone can perform better by shifting parts their functions to cloud servers. However, because frequently positioned far from users, there may be a significant unpredictable delay in data transfer between users cloud. It crucial since customers value rapid responses...
The chromatin loops in the three-dimensional (3D) structure of chromosomes are essential for regulation gene expression. Despite fact that high-throughput capture techniques can identify 3D chromosomes, loop detection utilizing biological experiments is arduous and time-consuming. Therefore, a computational method required to detect loops. Deep neural networks form complex representations Hi-C data provide possibility processing datasets. we propose bagging ensemble one-dimensional...
Cell type prediction is crucial to cell identification of genomics, cancer diagnosis and drug development, it can solve the time-consuming difficult problem classification in biological experiments. Therefore, a computational method urgently needed classify predict types using single-cell Hi-C data. In previous studies, there lack convenient accurate based on Deep neural networks form complex representations data make possible handle multidimensional sparse datasets.
Facial expression recognition plays an increasingly important role in many fields. The richness of facial expressions and the ambiguity increase difficulty recognition. rate existing algorithms is either high or complex. Either complexity low also low. Can a compromise be made between rate? So, we designed basic effective convolutional neural networks (BASE) algorithm. In order to further improve performance BASE algorithm, propose algorithm based on efficient channel attention for deep...
Abstract The degradation and stability of biodegradable films determine the service length mulch in actual use. Most polymers degrade too fast to meet required durability films. objective this work is investigate behaviors poly(butylene adipate-co-terephthalate) (PBAT) /polyhydroxyalkanoate (PHA) blend Several different types stabilizers were incorporated blends provide protection for PHA/PBAT during thermal processing aging on agricultural fields. process was systematically studied under an...
Air pollution and carbon emissions caused by modern transportation are closely related to global climate change. With the help of next-generation information technology such as Internet Things (IoT) Artificial Intelligence (AI), accurate traffic flow prediction can effectively solve problems congestion mitigate environmental It further promotes development Intelligent Transportation Systems (ITS) smart cities. However, strong spatial temporal correlation data makes task forecasting a...