1.The Establishment of a Virus-related Lymphoma Risk Warning System and Health Management Model Based on Traditional Chinese Medicine Conditions
Hanjing LI ; Shunan LI ; Zewei ZHUO ; Shunyong WANG ; Qiangqiang ZHENG ; Bingyu HUANG ; Yupeng YANG ; Chenxi QIU ; Ningning CHEN ; He WANG ; Tingbo LIU ; Haiying FU
Journal of Traditional Chinese Medicine 2025;66(4):335-339
Virus-related lymphoma exhibits a dual nature as both a hematologic malignancy and a viral infectious disease, making it more resistant to treatment and associated with poorer prognosis. This paper analyzes the understanding and therapeutic advantages of traditional Chinese medicine (TCM) in virus-related lymphoma. It proposes a TCM-based approach centered around syndrome differentiation, using standardized measurements of the overall TCM condition, multi-omics research of hematologic tumors, and artificial intelligence technologies to identify the "pre-condition" of virus-related lymphoma. A risk warning model will be established to early identify high-risk populations with viral infections that may develop into malignant lymphoma, thereby establishing a risk warning system for virus-related lymphoma. At the same time, a TCM health management approach will be applied to manage and regulate virus-related lymphoma, interrupting its progression and forming a human-centered, comprehensive, continuous health service model. Based on this, a standardized, integrated clinical prevention and treatment decision-making model for virus-related lymphoma, recognized by both Chinese and western medicine, will be established to provide TCM solutions for primary prevention of major malignant tumors.
2.Study on the distribution of traditional Chinese medicine syndromes and syndrome elements in lymphoma and the correlation between syndromes and Western medicine clinical indicators
Hanjing LI ; Shunan LI ; Zewei ZHUO ; Shunyong WANG ; Qiangqiang ZHENG ; Bingyu HUANG ; Yupeng YANG ; Chenxi QIU ; Ningning CHEN ; Yanyan QIU ; He WANG ; Tingbo LIU ; Haiying FU
Journal of Beijing University of Traditional Chinese Medicine 2025;48(1):127-137
Objective:
To investigate the distribution of traditional Chinese medicine (TCM) syndromes and syndrome elements in lymphoma, as well as the correlation between TCM syndromes and Western clinical indicators, in order to analyze associations between TCM syndromes and these indicators.
Methods:
From January 2023 to May 2024, 216 patients with lymphoma who met the inclusion criteria in the Department of Hematology, Third People′s Hospital Affiliated to Fujian University of Traditional Chinese Medicine were enrolled. Four diagnostic methods were applied to perform TCM syndrome differentiation and extract syndrome elements. The correlations between various syndromes and blood test indicators of lactate dehydrogenase (LDH), β2-microglobulin (β2-MG), immunoglobulin G (IgG), immunoglobulin M (IgM), immunoglobulin A (IgA), white blood cell (WBC), hemoglobin (Hb), platelet count (PLT), neutrophil (NEUT), immunohistochemical markers of B-cell lymphoma-6 (BCL6), B-cell lymphoma-2 (BCL2), proto-oncogene MYC, and Ki67 protein expression, Ann Arbor staging, international prognostic index (IPI) score, bone marrow infiltration, concurrent infections during chemotherapy, and post-chemotherapy bone marrow suppression rate were analyzed.
Results:
Five TCM syndromes, ranked by frequency, were syndromes of yin deficiency with phlegm accumulation(41.67%), qi depression with phlegm obstruction(30.56%), cold-phlegm congelation and stagnation(12.96%), phlegm-blood stasis toxin(12.04%), and lingering pathogen due to deficient vital qi(2.77%). Yin deficiency(50.93%) and phlegm(45.37%) were the more prevalent syndrome elements. The TCM syndromes were correlated with β2-MG, PLT, MYC, BCL2/MYC, Ki67 protein expression, and bone marrow infiltration (P<0.05). No statistically significant differences were observed in Ann Arbor staging or IPI score across the syndromes. Compared to the syndrome of cold-phlegm congelation and stagnation, the syndrome of qi depression with phlegm obstruction exhibited higher levels of NEUT, MYC, BCL2/MYC, and Ki67 protein expression, as well as a higher rate of post-chemotherapy bone marrow suppression (P<0.05); the syndrome of phlegm-blood stasis toxin showed higher MYC and BCL2/MYC protein expression and a higher rate of post-chemotherapy bone marrow suppression rate (P<0.05); the syndrome of yin deficiency with phlegm accumulation demonstrated higher MYC and BCL2/MYC protein expression and bone marrow infiltration rates, whereas PLT level was lower (P<0.05); the syndrome of lingering pathogen due to deficient vital qi had higher MYC, BCL2/MYC, and Ki67 protein expression levels, as well as a higher rate of post-chemotherapy bone marrow suppression rate (P<0.05). Compared to the syndrome of qi depression with phlegm obstruction, the syndrome of phlegm-blood stasis toxin exhibited lower Ki67 protein expression (P<0.05); the syndrome of yin deficiency with phlegm accumulation had higher β2-MG level, bone marrow infiltration rate, and rate of concurrent infections during chemotherapy, whereas PLT and NEUT levels and the rate of post-chemotherapy bone marrow suppression rate were lower (P<0.05). Compared to the syndrome of phlegm-blood stasis toxin, the syndrome of yin deficiency with phlegm accumulation had higher β2-MG level, whereas NEUT and the rate of post-chemotherapy bone marrow suppression were lower(P<0.05); the syndrome of lingering pathogen due to deficient vital qi exhibited a higher Ki67 protein expression (P<0.05). Compared to the syndrome of yin deficiency with phlegm accumulation, the syndrome of lingering pathogen due to deficient vital qi also showed a higher Ki67 protein expression(P<0.05).
Conclusion
The syndrome of yin deficiency with phlegm accumulation is relatively common in lymphoma. There is a correlation between TCM syndromes and Western medicine clinical indicators. The presence of heat signs in the syndromes may indicate active disease and poor prognosis, while the presence of strong pathogenic factors and weak vital qi in the syndromes may indicate a severer chemotherapy-related bone marrow suppression.
3.Severity Assessment Parameters and Diagnostic Technologies of Obstructive Sleep Apnea
Zhuo-Zhi FU ; Ya-Cen WU ; Mei-Xi LI ; Ping-Ping YIN ; Hai-Jun LIN ; Fu ZHANG ; Yu-Xiang YANG
Progress in Biochemistry and Biophysics 2025;52(1):147-161
Obstructive sleep apnea (OSA) is an increasingly widespread sleep-breathing disordered disease, and is an independent risk factor for many high-risk chronic diseases such as hypertension, coronary heart disease, stroke, arrhythmias and diabetes, which is potentially fatal. The key to the prevention and treatment of OSA is early diagnosis and treatment, so the assessment and diagnostic technologies of OSA have become a research hotspot. This paper reviews the research progresses of severity assessment parameters and diagnostic technologies of OSA, and discusses their future development trends. In terms of severity assessment parameters of OSA, apnea hypopnea index (AHI), as the gold standard, together with the percentage of duration of apnea hypopnea (AH%), lowest oxygen saturation (LSpO2), heart rate variability (HRV), oxygen desaturation index (ODI) and the emerging biomarkers, constitute a multi-dimensional evaluation system. Specifically, the AHI, which measures the frequency of sleep respiratory events per hour, does not fully reflect the patients’ overall sleep quality or the extent of their daytime functional impairments. To address this limitation, the AH%, which measures the proportion of the entire sleep cycle affected by apneas and hypopneas, deepens our understanding of the impact on sleep quality. The LSpO2 plays a critical role in highlighting the potential severe hypoxic episodes during sleep, while the HRV offers a different perspective by analyzing the fluctuations in heart rate thereby revealing the activity of the autonomic nervous system. The ODI provides a direct and objective measure of patients’ nocturnal oxygenation stability by calculating the number of desaturation events per hour, and the biomarkers offers novel insights into the diagnosis and management of OSA, and fosters the development of more precise and tailored OSA therapeutic strategies. In terms of diagnostic techniques of OSA, the standardized questionnaire and Epworth sleepiness scale (ESS) is a simple and effective method for preliminary screening of OSA, and the polysomnography (PSG) which is based on recording multiple physiological signals stands for gold standard, but it has limitations of complex operations, high costs and inconvenience. As a convenient alternative, the home sleep apnea testing (HSAT) allows patients to monitor their sleep with simplified equipment in the comfort of their own homes, and the cardiopulmonary coupling (CPC) offers a minimal version that simply analyzes the electrocardiogram (ECG) signals. As an emerging diagnostic technology of OSA, machine learning (ML) and artificial intelligence (AI) adeptly pinpoint respiratory incidents and expose delicate physiological changes, thus casting new light on the diagnostic approach to OSA. In addition, imaging examination utilizes detailed visual representations of the airway’s structure and assists in recognizing structural abnormalities that may result in obstructed airways, while sound monitoring technology records and analyzes snoring and breathing sounds to detect the condition subtly, and thus further expands our medical diagnostic toolkit. As for the future development directions, it can be predicted that interdisciplinary integrated researches, the construction of personalized diagnosis and treatment models, and the popularization of high-tech in clinical applications will become the development trends in the field of OSA evaluation and diagnosis.
4.Effect of Wenpi tongluo kaiqiao formula against neuronal necroptosis in mice with Alzheimer’s disease and its mechanism
Xiaomin ZHU ; Wei CHEN ; Yulan FU ; Guifeng ZHUO ; Yingrui HUANG ; Ying ZHANG ; Lin WU
China Pharmacy 2025;36(9):1046-1051
OBJECTIVE To investigate the effects and mechanism of Wenpi tongluo kaiqiao formula (WPTL) against neuronal necroptosis in Alzheimer’s disease (AD) mice based on the Z-DNA binding protein 1 (ZBP1)/mixed lineage kinase domain-like protein (MLKL) signaling pathway. METHODS Forty APP/PS1 transgenic AD mice were randomly divided into model group, WPTL low-dose (WPTL-L) group (10.4 g/kg, calculated by the raw medicine), WPTL high-dose (WPTL-H) group (20.8 g/kg, calculated by the raw medicine) and donepezil hydrochloride group (3 mg/kg), with 10 mice in each group; another 10 C57BL/6J mice were selected as normal control group. Intragastric administration, once a day, for 30 consecutive days. Twenty-four hours after the last administration, Morris water maze test was performed to evaluate learning and memory abilities; the pathological morphology of hippocampal tissues was observed; the serum levels of tumor necrosis factor-α (TNF-α) and interleukin-4 (IL-4) were determined; the expressions of amyloid precursor protein (APP), Tau protein, and ZBP1/MLKL signaling pathway-related proteins in hippocampal tissues were detected; the positive expression of phosphorylated receptor-interacting protein kinase 3 (p-RIPK3) in the neurons of hippocampal tissues and mRNA expression of ZBP1 were measured in hippocampal tissues. RESULTS Compared with normal control group, the escape latency of mice in model group was prolonged significantly on day 3 to 5 (P<0.05), the times of crossing platform reduced significantly (P<0.05), and obvious pathological changes were observed in the hippocampal tissue. The level of TNF- α, the expressions of APP, p-Tau and ZBP1, the phosphorylation levels of RIPK1, RIPK3 and MLKL, the fluorescence intensity of p-RIPK3 as well as the mRNA expression of ZBP1 were significantly increased (P<0.05), while the serum level of IL-4 was decreased significantly (P<0.05). Compared with model group, above indexes were reversed significantly in administration groups (P<0.05), and pathological damage of hippocampal tissue was alleviated. CONCLUSIONS WPTL can inhibit the ZBP1/MLKL signaling pathway, reduce neuronal necroptosis in AD mice, and inhibit inflammatory responses, thereby improving learning and spatial memory abilities in AD mice.
5.Summary of 16-Year Observation of Reflux Esophagitis-Like Symptoms in A Natural Village in A High-Incidence Area of Esophageal Cancer
Junqing LIU ; Lingling LEI ; Yaru FU ; Xin SONG ; Jingjing WANG ; Xueke ZHAO ; Min LIU ; Zongmin FAN ; Fangzhou DAI ; Xuena HAN ; Zhuo YANG ; Kan ZHONG ; Sai YANG ; Qiang ZHANG ; Qide BAO ; Lidong WANG
Cancer Research on Prevention and Treatment 2025;52(6):461-465
Objective To investigate the screening results and factors affecting abnormal detection rates among high-risk groups of esophageal cancer and to explore effective intervention measures. Methods We investigated and collected the information on gender, education level, age, marital status, symptoms of reflux esophagitis (heartburn, acid reflux, belching, hiccup, foreign body sensation in the pharynx, and difficulty swallowing), consumption of pickled vegetables, salt use, and esophageal cancer incidence of villagers in a natural village in Wenfeng District, Anyang City, Henan Province. Changes in reflux esophagitis symptoms in the high-incidence area of esophageal cancer before and after 16 years were observed, and the relationship of such changes with esophageal cancer was analyzed. Results In 2008, 711 cases were epidemiologically investigated, including
6.Anti-vascular dementia effect of Yifei xuanfei jiangzhuo formula by inhibiting mitochondrial fission
Yulan FU ; Wei CHEN ; Guifeng ZHUO ; Xiaomin ZHU ; Yingrui HUANG ; Jinzhi ZHANG ; Fucai YANG ; Ying ZHANG ; Lin WU
China Pharmacy 2025;36(15):1859-1865
OBJECTIVE To investigate the intervention effect and its potential mechanism of Yifei xuanfei jiangzhuo formula by inhibiting mitochondrial fission in a vascular dementia (VaD) model rats. METHODS VaD rat model was established by bilateral common carotid artery ligation. The experimental animals were randomly divided into sham operation group (SHAM), model group (MOD),Yifei xuanfei jiangzhuo formula low-dose group (YFXF-L), Yifei xuanfei jiangzhuo formula high-dose group (YFXF-H), and Donepezil hydrochloride group (positive control), with 9 animals in each group. After 30 days of intervention, the spatial learning memory ability was assessed by Morris water maze experiment; HE staining was used to observe histopathological changes in CA1 area of hippocampus; ELISA was used to detect the levels of serum inflammatory factors [interleukin-1β (IL-1β) and IL-4]; Western blot was used to detect the expressions of heat shock protein 90 (HSP90)/mixed lineage kinase domain-like protein (MLKL)/dynamin-related protein 1 (Drp1) pathway-related proteins, mitochondrial fusion proteins (MFN1, MFN2), and adenosine triphosphate synthase 5A (ATP5A) in hippocampal tissues. The immunohistochemistry was used to detect the level of phosphorylated MLKL (p-MLKL); real-time fluorescence quantitative PCR was adopted to detect mRNA expressions ofHSP90, MFN1, MFN2 and ATP5A. RESULTS Compared with SHAM group, the escape latency of rats in the MOD group was significantly prolonged, the number of crossing the platform was significantly reduced, and the hippocampal tissues showed typical neuronal damage characteristics, the positive expression level of p-MLKL and the serum level of IL-1β significantly increased, while the serum level of IL-4 significantly decreased, the protein and mRNA expression of HSP90, as well as the protein expressions of p-MLKL/MLKL and p-Drp1(Ser616)/Drp1 were all significantly increased in hippocampal tissue, the protein and mRNA expressions of MFN1, MFN2 and ATP5A, and protein expression of p-Drp1(Ser637)/Drp1 were all significantly decreased (P<0.05). After the intervention of Yifei xuanfei jiangzhuo formula, above indicators in each treatment group were all significantly reversed (P<0.05). CONCLUSIONS Yifei xuanfei jiangzhuo formula may alleviate neuronal damage and neuroinflammatory responses in VaD rats by regulating the HSP90/MLKL/Drp1 signaling pathway, inhibiting mitochondrial fission, thereby maintaining mitochondrial dynamic balance and improving mitochondrial function.
7.Quality evaluation of Commelina communis medicinal materials from different origins based on content of four alkaloid components combined with chemometrics.
Bi-Ru FU ; Wei-Jie ZHUO ; Xuan-Xiu HUANG ; Peng-Cong LU ; Xin HE ; Rui-Feng JI
China Journal of Chinese Materia Medica 2025;50(9):2422-2431
This study employs ultra-performance liquid chromatography(UPLC) to analyze the differences in alkaloid content of Commelina communis from various geographical origins, exploring its feasibility as a quality evaluation indicator. A total of 57 batches of C. communis samples from 23 provinces, autonomous regions, and municipalities in China were selected. The MicroPulite HSS T3(2.1 mm×50 mm, 1.8 μm)column was used with a mobile phase of acetonitrile-0.2% phosphoric acid aqueous solution(20∶80), detection wavelength at 254 nm, and a flow rate of 0.3 mL·min~(-1) to measure the content of 1-deoxynojirimycin(DNJ) and deoxymannojirimycin(DMJ). The MicroPulite XP tC_(18)(2.1 mm×100 mm, 1.7 μm)column was employed with a mobile phase of acetonitrile-0.2% phosphoric acid aqueous solution(4∶96), detection wavelength at 254 nm, and a flow rate of 0.4 mL·min~(-1) to measure the content of norharmine(NHM) and harmanme(HM). Chemometric methods were applied to study the relationships and differences among the 57 batches of C. communis. Significant differences in alkaloid content were observed among C. communis from different regions, with the average total content decreasing in the order of North China, Northeast China, Northwest China, East China, Southwest China, Central China, and South China. Cluster analysis(CA) and principal component analysis(PCA) further revealed the quality differences of C. communis from various origins, and partial least squares discriminant analysis(PLS-DA) identified DNJ as a marker compound to distinguish the quality differences between different geographical sources of C. communis. It is recommended that the content limit of DNJ be set at no less than 0.055 9%, providing a reference for the quality evaluation and clinical application of C. communis medicinal materials.
Alkaloids/analysis*
;
Drugs, Chinese Herbal/chemistry*
;
China
;
Chromatography, High Pressure Liquid
;
Chemometrics/methods*
;
Quality Control
8.Clinical efficacy of autologous apheresis platelet-rich plasma combined with adjustable titanium plate fixation in the treatment of Rockwood type Ⅲ acromioclavicular joint dislocation.
Wei CAI ; An-Ping WU ; Hai-Tao TAN ; Gao-Bing XU ; Zhuo-Yi FU ; Yong PENG ; Di-Shi GUI ; Qiao-Mei PU
China Journal of Orthopaedics and Traumatology 2025;38(6):587-593
OBJECTIVE:
To explore clinical efficacy of autologous platelet-rich plasma(PRP) in treating Rockwood type Ⅲ acromioclavicular dislocation.
METHODS:
From January 2019 to July 2021, 32 patients with Rockwood type Ⅲ acromioclavicular dislocation were treated with minimally invasive adjustable titanium plate internal fixation, and were divided into PRP group and control group according to whether PRP treatment was performed, with 16 patients in each group. In PRP group, there were 10 males and 6 females, aged from 28 to 47 years old with an average of (36.75±7.14) years old;the time from injury to surgery ranged from 1 to 31 h with an average of (26.13±3.98) h;5 patients on the left side and 11 patients on the right side;PRP was injected once during operation and the 4th and 8th weeks after operation respectively. In control group, there were 8 males and 8 females, aged from 30 to 52 years old with an average of (38.50±5.48) years old; the time from injury to surgery ranged from 1 to 29 h with an average of (25.48±3.11) h;7 patients on the left side and 9 patients on the right side; minimally invasive surgical treatment was performed. Visual analogue scale(VAS) was used to evaluate pain and Constant-Murley score for shoulder joint function was used to evaluate the recovery of shoulder joint movement function before operation and 1, 3, 6, and 12 months after operation respectively.
RESULTS:
All patients were followed up for 12 to 28 months with an average of (18.3±5.2) months. All incisions patients healed well without adverse events such as infection. Postoperative VAS of PRP group at 1, 3, and 6 months were (5.5±1.2), (3.7±1.6), and (2.4±1.2), respectively, while were lower than those of control group (6.6±1.4), (4.9±1.1), and (3.7±1.3), respectively;and had statistical differences between two groups (P<0.05). There was no statistically significant difference in VAS between two groups before operation and 12 months after operation (P>0.05). Postoperative Constant-Murley scores of PRP group at 1, 3, and 6 months were (64.09±11.61), (73.19±12.89), and (82.61±14.81) points, respectively, which were higher than those of control group were (52.32±17.42), (61.65±14.43), and (72.52±11.04) respectively;and the differences were statistically significant (P<0.05). There was no statistically significant difference in Constant-Murley scores at 12 months after operation between two groups (P>0.05). In PRP group, there was no statistically significant difference at 6 months and 12 months after operation (P>0.05), while there were statistically significant differences at the other time points (1 month after operation compared with before operation, 3 months after operation compared with 6 months after operation, and 3 months after operation compared with 1 month after operation) (P<0.05). In control group, there was no statistically significant difference when comparing 1 month and 3 months after operation (P>0.05), while at the other time points (1 month after operation with before operation, 3 months after operation with 6 months after operation, and 6 months after operation with 12 months after operation), the differences were all statistically significant (P<0.05).
CONCLUSION
Adjustable titanium plate fixation combined with postoperative injection of PRP for the treatment of Rockwood type III acromioclavicular joint dislocation has effect of promoting the recovery of shoulder joint function and reducing pain.
Humans
;
Male
;
Female
;
Adult
;
Middle Aged
;
Platelet-Rich Plasma
;
Acromioclavicular Joint/surgery*
;
Bone Plates
;
Titanium
;
Joint Dislocations/therapy*
;
Fracture Fixation, Internal/methods*
9.Zedoarondiol Inhibits Neovascularization in Atherosclerotic Plaques of ApoE-/- Mice by Reducing Platelet Exosomes-Derived MiR-let-7a.
Bei-Li XIE ; Bo-Ce SONG ; Ming-Wang LIU ; Wei WEN ; Yu-Xin YAN ; Meng-Jie GAO ; Lu-Lian JIANG ; Zhi-Die JIN ; Lin YANG ; Jian-Gang LIU ; Da-Zhuo SHI ; Fu-Hai ZHAO
Chinese journal of integrative medicine 2025;31(3):228-239
OBJECTIVE:
To investigate the effect of zedoarondiol on neovascularization of atherosclerotic (AS) plaque by exosomes experiment.
METHODS:
ApoE-/- mice were fed with high-fat diet to establish AS model and treated with high- and low-dose (10, 5 mg/kg daily) of zedoarondiol, respectively. After 14 weeks, the expressions of anti-angiogenic protein thrombospondin 1 (THBS-1) and its receptor CD36 in plaques, as well as platelet activation rate and exosome-derived miR-let-7a were detected. Then, zedoarondiol was used to intervene in platelets in vitro, and miR-let-7a was detected in platelet-derived exosomes (Pexo). Finally, human umbilical vein endothelial cells (HUVECs) were transfected with miR-let-7a mimics and treated with Pexo to observe the effect of miR-let-7a in Pexo on tube formation.
RESULTS:
Animal experiments showed that after treating with zedoarondiol, the neovascularization density in plaques of AS mice was significantly reduced, THBS-1 and CD36 increased, the platelet activation rate was markedly reduced, and the miR-let-7a level in Pexo was reduced (P<0.01). In vitro experiments, the platelet activation rate and miR-let-7a levels in Pexo were significantly reduced after zedoarondiol's intervention. Cell experiments showed that after Pexo's intervention, the tube length increased, and the transfection of miR-let-7a minics further increased the tube length of cells, while reducing the expressions of THBS-1 and CD36.
CONCLUSION
Zedoarondiol has the effect of inhibiting neovascularization within plaque in AS mice, and its mechanism may be potentially related to inhibiting platelet activation and reducing the Pexo-derived miRNA-let-7a level.
Animals
;
MicroRNAs/genetics*
;
Exosomes/drug effects*
;
Plaque, Atherosclerotic/genetics*
;
Neovascularization, Pathologic/genetics*
;
Human Umbilical Vein Endothelial Cells/metabolism*
;
Humans
;
Blood Platelets/drug effects*
;
Apolipoproteins E/deficiency*
;
Thrombospondin 1/metabolism*
;
CD36 Antigens/metabolism*
;
Platelet Activation/drug effects*
;
Male
;
Mice
;
Mice, Inbred C57BL
10.Multi-scale information fusion and decoupled representation learning for robust microbe-disease interaction prediction.
Wentao WANG ; Qiaoying YAN ; Qingquan LIAO ; Xinyuan JIN ; Yinyin GONG ; Linlin ZHUO ; Xiangzheng FU ; Dongsheng CAO
Journal of Pharmaceutical Analysis 2025;15(8):101134-101134
Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases. Accurately predicting microbe-disease interactions (MDIs) offers critical insights for disease intervention and pharmaceutical research. Current advanced AI-based technologies automatically generate robust representations of microbes and diseases, enabling effective MDI predictions. However, these models continue to face significant challenges. A major issue is their reliance on complex feature extractors and classifiers, which substantially diminishes the models' generalizability. To address this, we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs. Initially, we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation. Secondly, we employ decoupled representation learning technology, compelling the graph neural network (GNN) to independently learn the weights for each feature subspace, thus enhancing its expressive power. Finally, we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN, reducing information loss due to occlusion. Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models. This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research. Code and data are accessible at: https://github.com/shmildsj/MDI-IFDRL.


Result Analysis
Print
Save
E-mail