Zhe Wang

Zhe Wang

Auto-generated profile, based on publicly available information

Zhe Wang

Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences; School of Basic Medicine, Peking Union Medical College, Beijing, China

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
13 March 2025 in Scientific Data
Verified
Journal Article
Open access
PDF file
ZWZhe Wang
Zhe Wang
MHMeng Hao
Meng Hao
SPSuyuan Peng
Suyuan Peng
YHYuyan Huang
Yuyan Huang
YLYiwei Lu
Yiwei Lu
YZYan Zhu
Yan Zhu
This paper presents a large publicly available benchmark dataset (TCMEval-SDT) for the thought process involved in syndrome differentiation in traditional Chinese medicine (TCM). The dataset consists of 300 TCM syndrome diagnosis cases sourced from the internet, classical Chinese medical texts, and medical records from hospitals, with metadata adhering to the Findable, Accessible, Interoperable, and Reusable (FAIR) principles. Each case has been annotated and curated by TCM experts and includes medical record ID, clinical data, explanatory summary, TCM syndrome, clinical information, and TCM pathogenesis, to support algorithms or models in emulating the diagnostic process of TCM clinicians. To provide a comprehensive description of the TCM syndrome diagnosis process, we summarize the diagnosis into four steps: (1) clinical information extraction, (2) TCM pathogenesis reasoning, (3) TCM syndrome reasoning, and (4) explanatory summary. We have also established validation criteria to evaluate their ability in TCM clinical diagnosis using this dataset. To facilitate research and evaluation in syndrome diagnosis of TCM, the TCMEval-SDT dataset is made publicly available under the CC-BY 4.0 license.

23 December 2025 in Scientific Data
Verified
Journal Article
Open access
PDF file
BWBaifeng Wang
Baifeng Wang
YLYiwei Lu
Yiwei Lu
ZWZhe Wang
Zhe Wang
PGPeixin Ge
Peixin Ge
GWGuanjie Wang
Guanjie Wang
YZYan Zhu
Yan Zhu
Although large language models (LLMs) have witnessed rapid development in medical applications, their capacities to support rational medication use and guarantee prescription safety remain insufficiently investigated—especially in tasks such as prescription audit, which plays a critical role in safeguarding both. This paper presents TCMEval-PA, a benchmark dataset for assessing the capabilities of LLMs in prescription audit of Chinese herbal medicines. The dataset comprises 328 choice questions, including 297 single-choice and 31 multiple-choice. All questions were designed and compiled through rule extraction from official documents and reviewed by licensed TCM physicians. TCMEval-PA comprehensively encompasses the key dimensions of prescription safety, including normativity (e.g., dispensing, decoction requirements, and regulations for special medicines) and appropriateness (e.g., contraindicated combinations and excessive dosages). The present study employed TCMEval-PA to assess several prevalent Chinese and English LLMs. This dataset can be utilized for the evaluation of LLMs and other artificial intelligence (AI) systems in TCM prescription safety scenarios and promotes research in intelligent auditing and decision support.

20 May 2016 in Pharmacology
Verified
Journal Article
Closed access
XCXiaomin Chen
Xiaomin Chen
YDYaoyao Dong
Yaoyao Dong
SCShuyan Cao
Shuyan Cao
XLXiaoheng Li
Xiaoheng Li
ZWZhe Wang
Zhe Wang
RGRen-Shan Ge
Ren-Shan Ge
Polybrominated diphenyl ethers (PBDEs) are a class of brominated flame retardants. PBDEs have been widely used in textiles, flexible polyurethane foams, electronic components, electrical components, and plastics. 11β-Hydroxysteroid dehydrogenases, isoform 1 (HSD11B1) and isoform 2 (HSD11B2), have been demonstrated to be the regulators of local glucocorticoid levels. In this study, the potencies of 4 different PBDEs (BDE-3, BDE-47, BDE-100, and BDE-153) with 1-6 bromine atoms attached in inhibition of rat and human HSD11B1 and HSD11B2 activities were compared to 4-bromobiphenyl (BBP), a structurally similar compound. All 4 PBDEs and BBP did not inhibit rat and human HSD11B1. BDE-3 and BDE-47 potently inhibited rat HSD11B2, and BDE-47 and BDE-153 potently inhibited human HSD11B2, with the half maximal inhibitory concentration values of 12.42, 5.95, 11.97, and 4.41 µmol/l, respectively. All PBDEs noncompetitively inhibited HSD11B2 when a steroid substrate was used. However, PBDEs exerted uncompetitive inhibition when the cofactor NAD+ was used. In conclusion, some PBDEs are selective inhibitors of HSD11B2, possibly causing excessive glucocorticoid action in local tissues.

19 April 2013 in Tumor Biology
Verified
Journal Article
Closed access
PDF file
ZWZhe Wang
Zhe Wang
WMWenhui Ma
Wenhui Ma
JWJing Wang
Jing Wang
JDJinglan Deng
Jinglan Deng
MYMenghui Yuan
Menghui Yuan
GLGuoquan Li
Guoquan Li

2 September 2021 in Gut
Verified
Conference Paper
Open access
PDF file
XWXueliang Wang
Xueliang Wang
ZWZhe Wang
Zhe Wang
DLDi Liu
Di Liu
HJHao Jiang
Hao Jiang
CCChao Cai
Chao Cai
Guangli YuGuangli Yu
Guangli Yu
Background T2DM is associated with CVD. SGLT2i represent the most effective class of oral medications for the treatment of T2DM, and have been shown to improve generalized vascular dysfunction. Methods T2DM was induced by HFD to male C57BL/6J mice for 24 weeks. After that, HFD-fed mice were treated with Cana (50 mg/kg/d) by oral gavage for 6 weeks. Myocardial mitochondrial morphology and cardiovascular abnormalities were assessed by TEM, immunofluorescence staining and Masson’s staining; lipids profile and oxidative stress state were assessed by corresponding biochemical assay kits and immunohistochemical staining; the myocardial injury was characterized by H&E staining, TUNEL, and ELISA assays; colonic gut microbiota was assessed by 16S rDNA sequencing. Results Cana reduced the lipid (such as TG, TC, and LDL-C) accumulation in serum, thus decreased atherogenic index of plasma and arteriosclerosis index values. More importantly, Cana decreased the thickness of the vascular basement membrane, improved cardiac mitochondrial homeostasis, and relieved oxidative stress (e.g. regulation of ROS, SOD, GSH, and MDA levels). And, Cana reduced the circulating markers of inflammation (such as TNFα, MCP-1, and IL-6). Myocardial injury was alleviated after Cana treatment with decreasing levels of serous cTn I (from 95 pg/mL to 75 pg/mL) and sCD40L (from 120 pg/mL to 90 pg/mL). Thus, the cardiovascular abnormality was relieved by elevating the CD31 expression level and suppressing fibrosis and basement membrane thickening (from 0.6 μm to 0.2 μm) in T2DM mice. Interestingly, Cana administration increased the ratio of Firmicutes/Bacteroidetes (from 230% to 98%) and the relative abundance of Olsenella, Alistipes, and Alloprevotella, while decreasing the abundance of Helicobacter and Mucispirillum in mice with diabetic CVD. Conclusions Cana treatment improved CVD by decreasing the risk of atherosclerosis and reducing the thickness of the vascular basement membrane. Importantly, Cana treatment significantly elevated myocardial mitochondria homeostasis, thus ameliorated the oxidative stress and inflammatory states. Moreover, Cana subtly altered microbiota composition in T2DM mice with CVD, which contributed to the improvement of CVD. Collectively, the improvements of myocardial mitochondrial and gut microbiota homeostasis, may represent an important mechanism underlying the cardiovascular benefits of Cana treatment.

24 July 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
ZWZhe Wang
Zhe Wang
KLKeqian Li
Keqian Li
SPSuyuan Peng
Suyuan Peng
LLLihong Liu
Lihong Liu
XYXiaolin Yang
Xiaolin Yang
YZYan Zhu
Yan Zhu
Background: Several clinical cases and experiments have demonstrated the effectiveness of traditional Chinese medicine (TCM) formulas in treating and preventing diseases. These formulas contain critical information about their ingredients, efficacy, and indications. Classifying TCM formulas based on this information can effectively standardize TCM formulas management, support clinical and research applications, and promote the modernization and scientific use of TCM. To further advance this task, TCM formulas can be classified using various approaches, including manual classification, machine learning, and deep learning. Additionally, large language models (LLMs) are gaining prominence in the biomedical field. Integrating LLMs into TCM research could significantly enhance and accelerate the discovery of TCM knowledge by leveraging their advanced linguistic understanding and contextual reasoning capabilities. Objective: The objective of this study is to evaluate the performance of different LLMs in the TCM formula classification task. Additionally, by employing ensemble learning with multiple fine-tuned LLMs, this study aims to enhance classification accuracy. Methods: The data for the TCM formula were manually refined and cleaned. We selected 10 LLMs that support Chinese for fine-tuning. We then employed an ensemble learning approach that combined the predictions of multiple models using both hard and weighted voting, with weights determined by the average accuracy of each model. Finally, we selected the top 5 most effective models from each series of LLMs for weighted voting (top 5) and the top 3 most accurate models of 10 for weighted voting (top 3). Results: A total of 2441 TCM formulas were curated manually from multiple sources, including the Coding Rules for Chinese Medicinal Formulas and Their Codes, the Chinese National Medical Insurance Catalog for proprietary Chinese medicines, textbooks of TCM formulas, and TCM literature. The dataset was divided into a training set of 1999 TCM formulas and test set of 442 TCM formulas. The testing results showed that Qwen-14B achieved the highest accuracy of 75.32% among the single models. The accuracy rates for hard voting, weighted voting, weighted voting (top 5), and weighted voting (top 3) were 75.79%, 76.47%, 75.57%, and 77.15%, respectively. Conclusions: This study aims to explore the effectiveness of LLMs in the TCM formula classification task. To this end, we propose an ensemble learning method that integrates multiple fine-tuned LLMs through a voting mechanism. This method not only improves classification accuracy but also enhances the existing classification system for classifying the efficacy of TCM formula.