A5081282913- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Biomedical Text Mining and Ontologies
- Advanced Graph Neural Networks
- Human Mobility and Location-Based Analysis
- Full-Duplex Wireless Communications
- Digital Marketing and Social Media
- Statistical Methods and Inference
- Recommender Systems and Techniques
- Wireless Networks and Protocols
- Fuzzy Systems and Optimization
- Graph Theory and Algorithms
- Complex Network Analysis Techniques
- Advanced Statistical Methods and Models
- Genetic Mapping and Diversity in Plants and Animals
- Topic Modeling
- Semantic Web and Ontologies
- Genetic Associations and Epidemiology
- Cooperative Communication and Network Coding
Hefei University of Technology
2025
Huazhong Agricultural University
2022-2024
Shanghai Institute of Nutrition and Health
2021
University of Chinese Academy of Sciences
2021
Chongqing University of Posts and Telecommunications
2020
Beijing University of Posts and Telecommunications
2010
Abstract Despite the abundance of genotype-phenotype association studies, resulting outcomes often lack robustness and interpretations. To address these challenges, we introduce PheSeq, a Bayesian deep learning model that enhances interprets studies through integration perception phenotype descriptions. By implementing PheSeq in three case on Alzheimer’s disease, breast cancer, lung identify 1024 priority genes for disease 818 566 cancer respectively. Benefiting from data fusion, findings...
In a downlink wireless network, the XOR network coding method was used to combine with Hybrid-ARQ (HARQ) scheme, which can improve retransmission efficiency of network. The average number transmissions and packet delay metrics were evaluate performance based HARQ (NC-HARQ). theoretical analysis given compare NC-HARQ scheme traditional both in broadcast unicast scenarios. simulation results show that reduce trans-missions benefit some expense.
Abstract Summary Here we describe fastQTLmapping, a C++ package that is computationally efficient not only for mQTL-like analysis but as generic solver also conducting exhaustive linear regressions involving extraordinarily large numbers of dependent and explanatory variables allowing covariates. Compared to the state-of-the-art MatrixEQTL, fastQTLmapping was an order magnitude faster with much lower peak memory usage. In dataset consisting 3,500 individuals, 8 million SNPs, 0.8 CpGs 20...
With the improvement of people's living standards, spiritual needs continue to increase, which makes personalized travel recommendation more and popular. However, complicated overloaded information in internet have caused troubles for people choose scenic spots. Although collaborative filtering is widely used algorithms, neither user-based nor item-based take users' characteristics into account. In order recommend better spots users, we propose a fusion algorithm combining original matrix...
The identification of cancer driver genes is important for better understanding the hallmarks and developing precision therapies. Though integration multiomics protein-protein interaction (PPI) data into graph convolutional networks (GCN) has been emerging as a promising strategy, these GCN-based methods rely heavily on reliability completeness PPI network data, thereby hampering pan-cancer key oncogenic interactions. Furthermore, few models today enables detection function modules in...