Zhiyong Luo

Zhiyong Luo

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2024 in Frontiers in Nutrition
Verified
Journal Article
Open access
ZLZining Luo
Zining Luo
LXLijun Xiong
Lijun Xiong
XXXinyu Xu
Xinyu Xu
MSMeng Sun
Meng Sun
YMYingfei Mu
Yingfei Mu
YLYing Liu
Ying Liu
Objective: Existing studies have reported sustained changes in the cortical structure of rats due to coffee-related factors, which are speculated to occur in the human body. However, there is a lack of research on this topic. Additionally, previous observational studies have found the impact of diseases on cortical structure and the potential therapeutic effects of coffee on these diseases. Our aim was to study the causal effects of coffee-related factors on the human brain using SNPs (single nucleotide polymorphisms). We will connect these discovered causal effects to the impact of diseases on the brain. Through triangulating evidence, we will reveal the potential active areas of coffee in preventing diseases.Methods: We utilized GWAS data from multiple cohorts and their databases, selecting instrumental variables for genetic prediction of coffee intake and plasma levels of caffeine and its direct metabolites. We applied these instrumental variables to individual data on cortical thickness and surface area, as well as hippocampal volume, from the ENIGMA and CHARGE consortium for Mendelian randomization analysis (MR). Triangular evidence was obtained by integrating existing evidence through a specified retrieval strategy, calculating the overlap between coffee's effects on brain regions and disease-related brain regions to identify potential regions of action.Results: The MR analysis yielded 93 positive results for 9 exposures, among which theobromine, a metabolite in the caffeine pathway, was found to be associated with increased hippocampal volume. For cortical structure, theobromine in the caffeine pathway was associated with a decrease in total surface area, while theobromine and caffeine in the pathway were associated with an increase in total thickness. The overlap rate of triangular evidence showed no difference in both overall and subgroup analyses, indicating a high overlap between the effects of coffee on brain regions and disease.Conclusions: From predicted outcomes from causal effects, coffee intake-related factors may have lasting effects on cortical structure. Additionally, theobromine and theophylline have the greatest impact on certain brain gyri, rather than caffeine. Triangulation evidence indicates that disease and coffee intake-related factors act on the same cortical regions, suggesting the presence of potential shared or antagonistic pathways.

Verified
Journal Article
Open access
PDF file
XWXin Wang
Xin Wang
GLGang LIU
Gang LIU
JHJing He
Jing He
XZXiangbing Zhou
Xiangbing Zhou
ZLZhiyong Luo
Zhiyong Luo
With the rapid development of Intelligent Transportation Systems (ITSs), traffic prediction, a crucial component of ITSs, has garnered growing scholarly attention. The appli-cation of deep learning into traffic prediction has emerged as a prominent research direction, especially amid the rapid advancement of pretrained large language models (LLMs), which offer substantial benefits in time-series analysis through cross-modal knowledge transfer. In response to this advancement, this study introduces an innovative model for traffic flow prediction, designated as WGLLM. To capture spatiotemporal characteristics inherent in traffic flow data, this model incorporates a sequence embedding layer constructed on the stationary wavelet transform (SWT) and long short-term memory (LSTM), in conjunction with a spatial embedding layer founded on graph convolutional networks (GCNs). Additionally, a fully connected layer is utilized to integrate embeddings into the LLMs for comprehensive global dependency analysis. To verify the effectiveness of the proposed approach, experiments were carried out on two real traffic flow datasets. The experimental results demonstrate that WGLLM achieves superior predictive performance compared to multiple mainstream baseline models, accompanied by a significant enhancement in prediction accuracy.