Search

Your search keyword '"Pan, Jialu"' showing total 22 results
Start Over Author "Pan, Jialu" Publication Year Range Last 50 years
22 results on '"Pan, Jialu"'

4. Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models

Author

Zhang, Yufeng, Pan, Jialu, Liu, Wanwei, Chen, Zhenbang, Wang, Ji, Liu, Zhiming, Li, Kenli, and Wei, Hongmei

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning
Abstract

Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data than in-distribution (ID) data. However, we cannot sample OOD data from the model. This counterintuitive phenomenon has not been satisfactorily explained and brings obstacles to OOD detection with flow-based models. In this paper, we prove theorems to investigate the Kullback-Leibler divergence in flow-based model and give two explanations for the above phenomenon. Based on our theoretical analysis, we propose a new method \PADmethod\ to leverage KL divergence and local pixel dependence of representations to perform anomaly detection. Experimental results on prevalent benchmarks demonstrate the effectiveness and robustness of our method. For group anomaly detection, our method achieves 98.1\% AUROC on average with a small batch size of 5. On the contrary, the baseline typicality test-based method only achieves 64.6\% AUROC on average due to its failure on challenging problems. Our method also outperforms the state-of-the-art method by 9.1\% AUROC. For point-wise anomaly detection, our method achieves 90.7\% AUROC on average and outperforms the baseline by 5.2\% AUROC. Besides, our method has the least notable failures and is the most robust one.

Published
2020

10. Cuproptosis-Related Biomarkers and Characterization of Immune Infiltration in Sepsis

Author

Wang,Yuanfeng, Qiu,Xu, Liu,Jiao, Liu,Xuanyi, Pan,Jialu, Cai,Jiayi, Liu,Xiaodong, Qu,Shugen, Wang,Yuanfeng, Qiu,Xu, Liu,Jiao, Liu,Xuanyi, Pan,Jialu, Cai,Jiayi, Liu,Xiaodong, and Qu,Shugen

Abstract

Yuanfeng Wang,1,* Xu Qiu,1,* Jiao Liu,1,* Xuanyi Liu,1 Jialu Pan,2 Jiayi Cai,2 Xiaodong Liu,1,3 Shugen Qu1,3 1College of Public Health and Management, Zhejiang Provincial Key Laboratory of Watershed Science and Health, Wenzhou Medical University, Wenzhou, People’s Republic of China; 2The First Clinical Medical College, Wenzhou Medical University, Wenzhou, People’s Republic of China; 3South Zhejiang Institute of Radiation Medicine and Nuclear Technology, Wenzhou, People’s Republic of China*These authors contributed equally to this work.These authors contributed equally to this workCorrespondence: Xiaodong Liu; Shugen Qu, Email forget45@wmu.edu.cn; shugenju@wmu.edu.cnIntroduction: Sepsis is a worldwide epidemic, with high morbidity and mortality. Cuproptosis is a form of cell death that is associated with a wide range of diseases. This study aimed to explore genes associated with cuproptosis in sepsis, construct predictive models and screen for potential targets.Methods: The LASSO algorithm and SVM-RFE model has been analysed the expression of cuproptosis-related genes in sepsis and immune infiltration characteristics and identified the marker genes under a diagnostic model. Gene-drug networks, mRNA-miRNA networks and PPI networks were constructed to screen for potential biological targets. The expression of marker genes was validated based on the GSE57065 dataset. Consensus clustering method was used to classify sepsis samples.Results: We found 381 genes associated with the development of sepsis and discovered significantly differentially expressed cuproptosis-related genes of 16 cell types in sepsis and immune infiltration with CD8/CD4 T cells being lower. NFE2L2, NLRP3, SLC31A1, DLD, DLAT, PDHB, MTF1, CDKN2A and DLST were identified as marker genes by the LASSO algorithm and the SVM-RFE model. AUC > 0.9 was constructed for PDHB and MTF1 alone respectively. The validation group data for PDHB (P=0.00099) and MTF1

Published
2024

13. Cuproptosis-Related Biomarkers and Characterization of Immune Infiltration in Sepsis.

Author

Wang, Yuanfeng, Qiu, Xu, Liu, Jiao, Liu, Xuanyi, Pan, Jialu, Cai, Jiayi, Liu, Xiaodong, and Qu, Shugen

Subjects
SEPSIS, GENE ontology, BIOMARKERS, DRUG target, ANIMAL experimentation, GENE expression, NEONATAL sepsis
Abstract

Introduction: Sepsis is a worldwide epidemic, with high morbidity and mortality. Cuproptosis is a form of cell death that is associated with a wide range of diseases. This study aimed to explore genes associated with cuproptosis in sepsis, construct predictive models and screen for potential targets. Methods: The LASSO algorithm and SVM-RFE model has been analysed the expression of cuproptosis-related genes in sepsis and immune infiltration characteristics and identified the marker genes under a diagnostic model. Gene-drug networks, mRNA-miRNA networks and PPI networks were constructed to screen for potential biological targets. The expression of marker genes was validated based on the GSE57065 dataset. Consensus clustering method was used to classify sepsis samples. Results: We found 381 genes associated with the development of sepsis and discovered significantly differentially expressed cuproptosis-related genes of 16 cell types in sepsis and immune infiltration with CD8/CD4 T cells being lower. NFE2L2, NLRP3, SLC31A1, DLD, DLAT, PDHB, MTF1, CDKN2A and DLST were identified as marker genes by the LASSO algorithm and the SVM-RFE model. AUC > 0.9 was constructed for PDHB and MTF1 alone respectively. The validation group data for PDHB (P=0.00099) and MTF1 (P=7.2e-14) were statistically significant. Consistent clustering analysis confirmed two subtypes. The C1 subtype may be more relevant to cellular metabolism and the C2 subtype has some relevance to immune molecules.The results of animal experiments showed that the gene expression was consistent with the bioinformatics analysis. Discussion: Our study systematically explored the relationship between sepsis and cuproptosis and constructed a diagnostic model. And, several cuproptosis-related genes may interfere with the progression of sepsis through immune cell infiltration. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

20. Kullback-Leibler Divergence-Based Out-of-Distribution Detection With Flow-Based Generative Models

Author

Zhang, Yufeng, Pan, Jialu, Liu, Wanwei, Chen, Zhenbang, Li, Kenli, Wang, Ji, Liu, Zhiming, and Wei, Hongmei

Abstract

Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data than in-distribution (ID) data. However, we cannot sample OOD data from the model. This counterintuitive phenomenon has not been satisfactorily explained and brings obstacles to OOD detection with flow-based models. In this article, we prove theorems to investigate the Kullback-Leibler divergence in flow-based model and give two explanations for the above phenomenon. Based on our theoretical analysis, we propose a new method KLODS to leverage KL divergence and local pixel dependence of representations to perform anomaly detection. Experimental results on prevalent benchmarks demonstrate the effectiveness and robustness of our method. For group anomaly detection, our method achieves 98.1% AUROC on average with a small batch size of 5. On the contrary, the baseline typicality test-based method only achieves 64.6% AUROC on average due to its failure on challenging problems. Our method also outperforms the state-of-the-art method by 9.1% AUROC. For point-wise anomaly detection, our method achieves 90.7% AUROC on average and outperforms the baseline by 5.2% AUROC. Besides, our method has the least notable failures and is the most robust one.

Published
2024
Full Text
View/download PDF

22. Host-derived lactic acid bacteria alleviate short beak and dwarf syndrome by preventing bone loss, intestinal barrier disruption, and inflammation.

Author

Liu, Mandi, Xiang, Fengjun, Pan, Jialu, Xue, Yongzhi, Sun, Maoyuan, Zhao, Kuan, Zhang, Wuchao, Lei, Baishi, Gao, Peipei, Li, Limin, and Yuan, Wanzhe

Abstract

Short-beak and dwarf syndrome (SBDS) is caused by novel goose parvovirus (NGPV) infection, which leads to farm economic losses. Our research aimed to investigate the potential of administering isolated lactic acid bacteria (LAB) in alleviating SBDS in ducks. Eight wild LAB strains were isolated from duck feces and their biosecurity was investigated in both duck embryo fibroblast (DEF) and live ducks. Moreover, the LAB strains exhibited no detrimental effects on bone metabolism levels and facilitated the tight junction proteins (TJPs) mRNA expression, and contributing to the mitigation of inflammation in healthy ducks. Subsequently, we conducted in vitrol and in vivo experiments to assess the impact of LAB on NGPV infection. The LAB strains significantly reduced the viral load of NGPV and downregulated the mRNA levels of pro-inflammatory factors in DEF. Additionally, LAB treatment alleviated SBDS in NGPV-infected ducks. Furthermore, LAB treatment alleviated intestinal damage, and reduced the inflammatory response, while also mitigating bone resorption in NGPV-infected ducks. In conclusion, the LAB strains isolated from duck feces have favorable biosecurity and alleviate SBDS in ducks, and the mechanism related to LAB improves intestinal barrier integrity, alleviates inflammation, and reduces bone resorption. Our study presents a novel concept for the prevention and treatment of NGPV, thereby establishing a theoretical foundation for the future development of probiotics in the prevention and treatment of NGPV. • Eight Lactobacillus strains isolated from duck feces have favorable biosecurity. • The strains inhibited NGPV infection in duck embryo fibroblasts. • The strains alleviates SBDS in NGPV infected ducks. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results