Siyu Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Siyu Yan has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Jianyun Lu
Department of Dermatology, Third Xiangya Hospital, Central South University
3 shared publications Boyue Jiang
Department of Dermatology The Third Xiangya Hospital Central South University Changsha China
2 shared publicationsHanyi Zhang
Department of Dermatology The Third Xiangya Hospital Central South University Changsha China
2 shared publications- Jie Li
Department of Dermatology, XiangYa Hospital, Central South University, Changsha, China
2 shared publications - Xiang Chen
Department of Dermatology, Xiangya Hospital & School of Life Sciences & Furong Laboratory, Central South University, Changsha, China
2 shared publications - Aiyuan Guo
From the Department of Dermatology, The Third Xiangya Hospital, Central South University, Changsha, P.R. China
1 shared publication
Latest Publications
- 27 November 2023
- Published by Elsevier in Journal of Investigative Dermatology
- Vol. 144 (5) , 1058-1070.e4
WTAP-Mediated N6-Methyladenosine of RNAs Facilitate the Pathophysiology of Atopic Dermatitis
- 27 November 2023
- Published by Elsevier in Journal of Investigative Dermatology
- Vol. 144 (5) , 1058-1070.e4
WTAP-Mediated N6-Methyladenosine of RNAs Facilitate the Pathophysiology of Atopic Dermatitis
- 20 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 144-149
An efficient multi-view and multi-channel disease risk prediction model
With the development of medical information, machine learning are applied on clinical aid to decision-making, for example disease prediction, mortality risk prediction, and so on. For the multi-dimensional, and multi-modality and sequential clinical data, there are being some challenges on feature fusion and representation which would impact the performance of prediction models. In addition, model interpretation attracts more attention in medical AI application field. According to the difference among the contribution from different examination indicators to predict the disease risk, we need consider the relation between indicators and disease as well as the time-dependence of indicators. In this work, we design a Multi-View and Multi-Channel (MVMC) method to construct patient record and propose an ensemble multi-view and multi-channel disease risk prediction model. In this work, we construct visit-view, feature-view and modality-view to represent the patient clinical features. Meanwhile multi-channel data processing mehod is used to extract temporal and spatial characteristics among features. We adopt GRU+CNN and Bi-GRU and transformer in our ensemble models for feature-view, visit-view and modality-view respectively. Attention mechanism is used for computation of correlation coefficient among each view to simulate physician diagnosis process. Experimental results show that our ensemble MVMC model achieves advanced performance in Precision, AUC, Recall and F1-score on the two data sets. Then we give the model interpretation by heatmap.
- 20 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 144-149
An efficient multi-view and multi-channel disease risk prediction model
With the development of medical information, machine learning are applied on clinical aid to decision-making, for example disease prediction, mortality risk prediction, and so on. For the multi-dimensional, and multi-modality and sequential clinical data, there are being some challenges on feature fusion and representation which would impact the performance of prediction models. In addition, model interpretation attracts more attention in medical AI application field. According to the difference among the contribution from different examination indicators to predict the disease risk, we need consider the relation between indicators and disease as well as the time-dependence of indicators. In this work, we design a Multi-View and Multi-Channel (MVMC) method to construct patient record and propose an ensemble multi-view and multi-channel disease risk prediction model. In this work, we construct visit-view, feature-view and modality-view to represent the patient clinical features. Meanwhile multi-channel data processing mehod is used to extract temporal and spatial characteristics among features. We adopt GRU+CNN and Bi-GRU and transformer in our ensemble models for feature-view, visit-view and modality-view respectively. Attention mechanism is used for computation of correlation coefficient among each view to simulate physician diagnosis process. Experimental results show that our ensemble MVMC model achieves advanced performance in Precision, AUC, Recall and F1-score on the two data sets. Then we give the model interpretation by heatmap.
- Open Access
- 8 May 2021
- Published by Wiley in Experimental Dermatology
- Vol. 30 (11) , 1588-1597
Current views on neuropeptides in atopic dermatitis
Atopic dermatitis (AD) is a chronic inflammatory skin disease involving skin barrier dysfunction and immune imbalance. However, the mechanism of AD is not clear completely and may be related to heredity and environment. Neuropeptides are a class of peptides secreted by nerve endings, they may play roles in promoting vasodilation, plasma extravasation, chemotaxis of inflammatory cells and mediating pruritus. Since itching and immune cell infiltration are the main manifestations of atopic dermatitis, to further investigate the impact of neuropeptides on AD, our review summarized the mechanisms of several common neuropeptides in AD and hypothesized that neuropeptides may be the novel potential targets in AD treatment.
- 8 May 2021
- Published by Wiley in Experimental Dermatology
- Vol. 30 (11) , 1588-1597
Open AccessCurrent views on neuropeptides in atopic dermatitis
Atopic dermatitis (AD) is a chronic inflammatory skin disease involving skin barrier dysfunction and immune imbalance. However, the mechanism of AD is not clear completely and may be related to heredity and environment. Neuropeptides are a class of peptides secreted by nerve endings, they may play roles in promoting vasodilation, plasma extravasation, chemotaxis of inflammatory cells and mediating pruritus. Since itching and immune cell infiltration are the main manifestations of atopic dermatitis, to further investigate the impact of neuropeptides on AD, our review summarized the mechanisms of several common neuropeptides in AD and hypothesized that neuropeptides may be the novel potential targets in AD treatment.
- 1 October 2020
- Published by Elsevier in International Immunopharmacology
- Vol. 87, 106755
A promising therapeutic target for psoriasis: Neuropeptides in human skin
- 1 October 2020
- Published by Elsevier in International Immunopharmacology
- Vol. 87, 106755
A promising therapeutic target for psoriasis: Neuropeptides in human skin
- 1 July 2019
- Published by Elsevier in Life Sciences
- Vol. 228, 152-157
Calcium release-activated calcium modulator 1 as a therapeutic target in allergic skin diseases
- 1 July 2019
- Published by Elsevier in Life Sciences
- Vol. 228, 152-157
Calcium release-activated calcium modulator 1 as a therapeutic target in allergic skin diseases
- 11 January 2019
- Published by Wiley in Experimental Dermatology
- Vol. 28 (3) , 240-246
C‐reactive protein (CRP) rs3093059C predicts poor mizolastine response in chronic spontaneous urticaria patients with elevated serum CRP level
Chronic spontaneous urticaria (CSU) is a frequent disorder with recurrent itchy wheals and/or angioedema, and nearly 35% patients respond poorly to non‐sedating H1 antihistamine treatment. CRP gene encodes the C‐reactive protein, which is involved in the pathogenesis of CSU. To investigate the impacts of CRP polymorphisms on the susceptibility and therapeutic efficacy in the South Han CSU patients, we enrolled 145 CSU patients in our study. After 4‐week non‐sedating H1 antihistamine monotherapy treatment, more than 50% reduction of the severity score is considered as effective, or else non‐effective. The CRP rs3093059T/C and rs2794521G/A genotypes of patients were determined by Sequenom MassARRAY. Functional studies including relative luciferase assay and β‐hexosaminidase assay were conducted in HEK293T cells or RBL‐2H3 cells to explore the function of variants. Forty (62.50%) CSU patients were effective when treated with mizolastine, and 55 (72.4%) patients were effective in the desloratadine group. We found that the patients carried with rs3093059TT genotype were significantly associated with good response (OR = 4.20, P = 0.015), had lower serum CRP, IL‐6 and TNF‐α levels than the CT/CC genotypes. In vitro, the rs3093059C allele exhibited significantly higher luciferase activity than wild allele (P < 0.001). From the β‐hexosaminidase assay, we observed the inhibiting degranulation effects by mizolastine and this effect is weakened when with a higher dose CRP in RBL‐2H3 cells. Our findings suggested that CSU patients carrying the rs3093059C allele may respond poorly to mizolastine with elevated serum CRP level.
- 11 January 2019
- Published by Wiley in Experimental Dermatology
- Vol. 28 (3) , 240-246
C‐reactive protein (CRP) rs3093059C predicts poor mizolastine response in chronic spontaneous urticaria patients with elevated serum CRP level
Chronic spontaneous urticaria (CSU) is a frequent disorder with recurrent itchy wheals and/or angioedema, and nearly 35% patients respond poorly to non‐sedating H1 antihistamine treatment. CRP gene encodes the C‐reactive protein, which is involved in the pathogenesis of CSU. To investigate the impacts of CRP polymorphisms on the susceptibility and therapeutic efficacy in the South Han CSU patients, we enrolled 145 CSU patients in our study. After 4‐week non‐sedating H1 antihistamine monotherapy treatment, more than 50% reduction of the severity score is considered as effective, or else non‐effective. The CRP rs3093059T/C and rs2794521G/A genotypes of patients were determined by Sequenom MassARRAY. Functional studies including relative luciferase assay and β‐hexosaminidase assay were conducted in HEK293T cells or RBL‐2H3 cells to explore the function of variants. Forty (62.50%) CSU patients were effective when treated with mizolastine, and 55 (72.4%) patients were effective in the desloratadine group. We found that the patients carried with rs3093059TT genotype were significantly associated with good response (OR = 4.20, P = 0.015), had lower serum CRP, IL‐6 and TNF‐α levels than the CT/CC genotypes. In vitro, the rs3093059C allele exhibited significantly higher luciferase activity than wild allele (P < 0.001). From the β‐hexosaminidase assay, we observed the inhibiting degranulation effects by mizolastine and this effect is weakened when with a higher dose CRP in RBL‐2H3 cells. Our findings suggested that CSU patients carrying the rs3093059C allele may respond poorly to mizolastine with elevated serum CRP level.
- 1 February 2015
- Published by Elsevier in Neurobiology of Aging
- Vol. 36 (2) , 1037-1044
Discovering novel microRNAs and age-related nonlinear changes in rat brains using deep sequencing
- 1 February 2015
- Published by Elsevier in Neurobiology of Aging
- Vol. 36 (2) , 1037-1044
Discovering novel microRNAs and age-related nonlinear changes in rat brains using deep sequencing