Real-time detection of 20 amino acids and discrimination of pathologically relevant peptides with functionalized nanopore.

Precise identification and quantification of amino acids is crucial for many biological applications. Here we report a copper(II)-functionalized Mycobacterium smegmatis porin A (MspA) nanopore with the N91H substitution, which enables direct identification of all 20 proteinogenic amino acids when combined with a machine-learning algorithm. The validation accuracy reaches 99.1%, with 30.9% signal recovery. The feasibility of ultrasensitive quantification of amino acids was also demonstrated at the nanomolar range. Furthermore, the capability of this system for real-time analyses of two representative post-translational modifications (PTMs), one unnatural amino acid and ten synthetic peptides using exopeptidases, including clinically relevant peptides associated with Alzheimer's disease and cancer neoantigens, was demonstrated. Notably, our strategy successfully distinguishes peptides with only one amino acid difference from the hydrolysate and provides the possibility to infer the peptide sequence.

Quantitative Pattern of hPTMs by Mass Spectrometry-Based Proteomics with Implications for Triple-Negative Breast Cancer.

Triple-negative breast cancer (TNBC) is known for its aggressive nature, and TNBC management is currently challenging due to the lack of effective targets. Despite the importance of histone post-translational modifications (hPTMs) in breast cancer, their associations with molecular subtypes of breast cancer, especially TNBC, are poorly understood. In this study, a combination of untargeted and targeted proteomics approaches, supplemented by a derivatization method, was applied to breast cancer cells and tissue samples. Untargeted proteomics of eight breast cancer cell lines belonging to different molecular subtypes revealed 36 modified peptides with 12 lysine modification sites in histone H3, and the most frequently reported top 5 histone H3 methylation and acetylation sites were covered. Then, targeted proteomics was carried out to quantify the total 20 target hPTMs at the covered modification sites (i.e., mono-, di-, trimethylation, and acetylation for each site), indicating the difficulty in distinguishing TNBC cells from normal cells. Subsequently, the analysis in TNBC patients revealed significant expression differences in 4 specific hPTMs (H3K14ac, H3K27me1, H3K36me2, and H3K36me3) between TNBC and adjacent normal tissue samples. These unique hPTM patterns allowed for the differentiation of TNBC from normal cases. This finding provides promising implications for advancing targeted treatment strategies for TNBC in the future.

Communication between alveolar macrophages and fibroblasts via the TNFSF12-TNFRSF12A pathway promotes pulmonary fibrosis in severe COVID-19 patients.

BACKGROUND: Severe COVID-19 infection has been associated with the development of pulmonary fibrosis, a condition that significantly affects patient prognosis. Understanding the underlying cellular communication mechanisms contributing to this fibrotic process is crucial. OBJECTIVE: In this study, we aimed to investigate the role of the TNFSF12-TNFRSF12A pathway in mediating communication between alveolar macrophages and fibroblasts, and its implications for the development of pulmonary fibrosis in severe COVID-19 patients. METHODS: We conducted single-cell RNA sequencing (scRNA-seq) analysis using lung tissue samples from severe COVID-19 patients and healthy controls. The data was processed, analyzed, and cell types were annotated. We focused on the communication between alveolar macrophages and fibroblasts and identified key signaling pathways. In vitro experiments were performed to validate our findings, including the impact of TNFRSF12A silencing on fibrosis reversal. RESULTS: Our analysis revealed that in severe COVID-19 patients, alveolar macrophages communicate with fibroblasts primarily through the TNFSF12-TNFRSF12A pathway. This communication pathway promotes fibroblast proliferation and expression of fibrotic factors. Importantly, silencing TNFRSF12A effectively reversed the pro-proliferative and pro-fibrotic effects of alveolar macrophages. CONCLUSION: The TNFSF12-TNFRSF12A pathway plays a central role in alveolar macrophage-fibroblast communication and contributes to pulmonary fibrosis in severe COVID-19 patients. Silencing TNFRSF12A represents a potential therapeutic strategy for mitigating fibrosis in severe COVID-19 lung disease.

Application of Optogenetics in Neurodegenerative Diseases.

Optogenetics, a revolutionary technique integrating optical and genetic methodologies, offers unparalleled precision in spatial targeting and temporal resolution for cellular control. This approach enables the selective manipulation of specific neuronal populations, inducing subtle electrical changes that significantly impact complex neural circuitry. As optogenetics precisely targets and modulates neuronal activity, it holds the potential for significant breakthroughs in understanding and potentially altering the course of neurodegenerative diseases, characterized by selective neuronal loss leading to functional deficits within the nervous system. The integration of optogenetics into neurodegenerative disease research has significantly advanced in the field, offering new insights and paving the way for innovative treatment strategies. Its application in clinical settings, although still in the nascent stages, suggests a promising future for addressing some of the most challenging aspects of neurodegenerative disorders. In this review, we provide a comprehensive overview of these research undertakings.

SCAPE: a mixture model revealing single-cell polyadenylation diversity and cellular dynamics during cell differentiation and reprogramming.

Alternative polyadenylation increases transcript diversities at the 3' end, regulating biological processes including cell differentiation, embryonic development and cancer progression. Here, we present a Bayesian method SCAPE, which enables de novo identification and quantification of polyadenylation (pA) sites at single-cell level by utilizing insert size information. We demonstrated its accuracy and robustness and identified 31 558 sites from 36 mouse organs, 43.8% (13 807) of which were novel. We illustrated that APA isoforms were associated with miRNAs binding and regulated in tissue-, cell type-and tumor-specific manners where no difference was found at gene expression level, providing an extra layer of information for cell clustering. Furthermore, we found genome-wide dynamic changes of APA usage during erythropoiesis and induced pluripotent stem cell (iPSC) differentiation, suggesting APA contributes to the functional flexibility and diversity of single cells. We expect SCAPE to aid the analyses of cellular dynamics and diversities in health and disease.

Versatile iodine-doped BiOCl with abundant oxygen vacancies and (110) crystal planes for enhanced pollutant photodegradation.

Crystal plane regulation, defect engineering, and element doping can effectively solve the problems of large band gaps, poor light absorption, and fast recombination of BiOCl. In this work, iodine-doped BiOCl (I/BiOCl) nanowafers with abundant (110) crystal planes and oxygen vacancies (OV) were prepared by a simple hydrothermal method and assessed for pollutant photodegradation. I/BiOCl with a molar ratio of I to Cl of 0.6 (I0.6/BiOCl) degraded under visible light 95.8% of the toxic dye rhodamine B and 85.1% of the persistent antibiotic tetracycline in 5 and 10 min, respectively. In comparison, unmodified BiOCl photodegraded only between 42.0% and 48.2% of these critical water pollutants. Furthermore, I0.6/BiOCl was highly stable with most of its photocatalytic activity remaining after 4 cycles. Three reasons explain the excellent photodegradation properties of I0.6/BiOCl. First, the doped photocatalyst grew abundant (110) crystal planes, which inhibits the recombination of photogenerated electron-hole pairs. Second, the large quantity of OV present in I0.6/BiOCl increased active sites for reactive oxygen species generation, improved photogenerated charge separation, and pollutants adsorption. Lastly, I0.6/BiOCl had a modified electronic band structure enhancing light absorption. Overall, these results describe a promising photocatalyst capable of degrading efficiently major pollutants with different structures.

Application of preoperative CT texture analysis in papillary gastric adenocarcinoma.

BACKGROUND: This study aimed to analyze the ability of computed tomography (CT) texture analysis to discriminate papillary gastric adenocarcinoma (PGC) and to explore the diagnostic efficacy of multivariate models integrating clinical information and CT texture parameters for discriminating PGCs. METHODS: This retrospective study included 20 patients with PGC and 80 patients with tubular adenocarcinoma (TAC). The clinical data and CT texture parameters based on the arterial phase (AP) and venous phase (VP) of all patients were collected and analyzed. Two CT signatures based on the AP and VP were built with the optimum features selected by the least absolute shrinkage and selection operator method. The performance of CT signatures was tested by regression analysis. Multivariate models based on regression analysis and the support vector machine (SVM) algorithm were established. The diagnostic performance of the established nomogram based on regression analysis was evaluated by receiver operating characteristic curve analysis. RESULTS: Thirty-two and fifteen CT texture parameters extracted from AP and VP CT images, respectively, differed significantly between PGCs and TACs (all p < 0.05). The diagnostic performance of CT signatures based on the AP and VP achieved AUCs of 0.873 and 0.859 in distinguishing PGCs. Multivariate models that integrated two CT signatures and age based on regression analysis and the SVM algorithm showed favorable performance in preoperatively predicting PGCs (AUC = 0.922 and 0.914, respectively). CONCLUSION: CT texture analysis based multivariate models could preoperatively predict PGCs with satisfactory diagnostic efficacy.

Integrative Predictive Models of Computed Tomography Texture Parameters and Hematological Parameters for Lymph Node Metastasis in Lung Adenocarcinomas.

OBJECTIVES: The aims of the study were to integrate characteristics of computed tomography (CT), texture, and hematological parameters and to establish predictive models for lymph node (LN) metastasis in lung adenocarcinoma. METHODS: A total of 207 lung adenocarcinoma cases with confirmed postoperative pathology and preoperative CT scans between February 2017 and April 2019 were included in this retrospective study. All patients were divided into training and 2 validation cohorts chronologically in the ratio of 3:1:1. The χ2 test or Fisher exact test were used for categorical variables. The Shapiro-Wilk test and Mann-Whitney U test were used for continuous variables. Logistic regression and machine learning algorithm models based on CT characteristics, texture, and hematological parameters were used to predict LN metastasis. The performance of the multivariate models was evaluated using a receiver operating characteristic curve; prediction performance was evaluated in the validation cohorts. Decision curve analysis confirmed its clinical utility. RESULTS: Logistic regression analysis demonstrated that pleural thickening (P = 0.013), percentile 25th (P = 0.033), entropy gray-level co-occurrence matrix 10 (P = 0.019), red blood cell distribution width (P = 0.012), and lymphocyte-to-monocyte ratio (P = 0.049) were independent risk factors associated with LN metastasis. The area under the curve of the predictive model established using the previously mentioned 5 independent risk factors was 0.929 in the receiver operating characteristic analysis. The highest area under the curve was obtained in the training cohort (0.777 using Naive Bayes algorithm). CONCLUSIONS: Integrative predictive models of CT characteristics, texture, and hematological parameters could predict LN metastasis in lung adenocarcinomas. These findings may provide a reference for clinical decision making.

Efficiency evaluation of surgical nursing wards based on data envelopment analysis.

AIMS: This study aimed to evaluate the efficiency and influencing factors of surgical ward nursing. BACKGROUND: High-quality development of public hospitals and implementation of nursing fine management require improvements to promote nursing efficiency. METHOD: This study examined input data, such as number of beds, nurses, and nursing hours, and output data on discharged person-times, surgical output, and case mix index of released patients, in 40 surgical wards in China between September 2020 and August 2021. Nursing efficiency was assessed and analysed using data envelopment analysis, and changes in efficiency were dynamically evaluated using the Malmquist index analysis. RESULTS: The average total technical efficiency, pure technical efficiency, and scale efficiency were 78%, 94%, and 82%, respectively. In addition, 81% and 67% of surgical wards had input redundancy and output insufficiency, respectively. The monthly average total factor productivity was 118%, and the overall efficiency increased month after month. CONCLUSION: Overall, nursing service efficiency was low, which was limited by scale efficiency, pure technical efficiency, or both. IMPLICATIONS FOR NURSING MANAGEMENT: Data envelopment analysis could help nursing managers optimize nursing human resource allocation and nursing performance allocation.

Simultaneous Detection of Six Isoforms of Tau Protein in Human Cerebrospinal Fluid by Multidimensional Mass Spectrometry-Based Targeted Proteomics.

Abnormal expression of Tau protein can cause the development of Alzheimer's disease (AD). So far, much evidence has demonstrated that Tau has multiple isoforms. These isoforms are suggested to have distinct physiological roles and contribute unequally to the progress of AD. Thus, detection of individual Tau isoforms may be helpful to better understand the link between clinical outcome and Tau status and to further improve AD diagnosis and treatment. However, few studies have been conducted on absolute quantification of Tau isoforms, probably due to high sequence homology and also low abundance of these isoforms in biofluids such as cerebrospinal fluid (CSF). Therefore, mass spectrometry-based targeted proteomics was attempted here. This targeted proteomics approach can principally measure a protein of interest at the surrogate peptide level, yet little has been done to detect protein isoforms, probably due to lack of isoform-specific surrogate peptides in mass spectrometry. In this study, separations in more dimensions were added, including immunoprecipitation (IP) and sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE) for sample pretreatment and systems of linear equations for post-lab data extraction. Moreover, the reliability of the approach including IP enrichment, gel separation, and linear algebra algorithms was discussed. As a result, each isoform of Tau protein can be individually detected and quantified. Using IP enrichment, ∼250-fold enhancement of sensitivity was achieved. The ultimate LOQ was 0.50 nM. Finally, this multidimensional mass spectrometry-based targeted proteomics assay was validated and applied to simultaneous quantitative analysis of six Tau isoforms in CSF of AD patients.

Prediction of serosal invasion in gastric cancer: development and validation of multivariate models integrating preoperative clinicopathological features and radiographic findings based on late arterial phase CT images.

BACKGROUND: To develop and validate multivariate models integrating endoscopic biopsy, tumor markers, and CT findings based on late arterial phase (LAP) to predict serosal invasion in gastric cancer (GC). METHODS: The preoperative differentiation degree, tumor markers, CT morphological characteristics, and CT value-related and texture parameters of 154 patients with GC were analyzed retrospectively. Multivariate models based on regression analysis and machine learning algorithms were performed to improve the diagnostic efficacy. RESULTS: The differentiation degree, carbohydrate antigen (CA) 199, CA724, CA242, and multiple CT findings based on LAP differed significantly between T1-3 and T4 GCs in the primary cohort (all P < 0.05). Multivariate models based on regression analysis and random forest achieved AUCs of 0.849 and 0.865 in the primary cohort, respectively. CONCLUSION: We developed and validated multivariate models integrating endoscopic biopsy, tumor markers, CT morphological characteristics, and CT value-related and texture parameters to predict serosal invasion in GCs and achieved favorable performance.

Simultaneous and quantitative monitoring transcription factors in human embryonic stem cell differentiation using mass spectrometry-based targeted proteomics.

Human embryonic stem cells (hESCs) can be self-propagated indefinitely in culture while holding the capacity to generate almost all cell types. Although this powerful differentiation ability of hESCs has become a potential source of cell replacement therapies, application of stem cells in clinical practice relies heavily on the exquisite control of their developmental fate. In general, an essential first step in differentiation is to exit the pluripotent state, which is precariously balanced and depends on a variety of factors, mainly centering on the core transcriptional mechanism. To date, much evidence has indicated that transcription factors such as Sox2, Oct4, and Nanog control the self-renewal and pluripotency of hESCs. Their expression displays a restricted spatial-temporal pattern and their small changes in level can significantly affect directed differentiation and the cell type derived. So far, few assays have been developed to monitor this process. Herein, we provided a mass spectrometry (MS)-based approach for simultaneous and quantitative monitoring of these transcription factors, in an attempt to provide insight into their contributions in hESC differentiation.

Increased ratio of sST2/LVMI predicted cardiovascular mortality and heart failure rehospitalization in heart failure with reduced ejection fraction patients: a prospective cohort study.

BACKGROUND: Inflammation is one of the principal triggering mechanisms for left ventricular fibrosis and remodeling in heart failure, leading to adverse clinical outcomes. Soluble suppression of tumorigenicity 2 (sST2), a member of the interleukin-1 receptor family, is assumed to play a significant role in the fibrotic response to inflammation. Left ventricular mass index (LVMI) is a parameter of the prefibrotic inflammatory phase of heart failure preceding remodeling. The present study aimed to investigate the prognostic value of the sST2/LVMI ratio in heart failure with reduced ejection fraction. METHODS: This was a prospective cohort study. A total of 45 consecutive patients with heart failure with reduced ejection fraction, treated between September 2015 and December 2016, were enrolled. The sST2/LVMI ratio was measured at baseline. The primary endpoint was a composite of cardiovascular mortality and readmission for heart failure. The prognostic impact of the sST2/LVMI ratio was evaluated using a multivariable Cox proportional hazards regression model. RESULTS: Forty-five patients were enrolled in this study. Their average age was 48 ± 14 years, and approximately 20% of them were men. Patients were followed for 9 months, during which the primary outcome occurred in 15 patients. Kaplan-Meier analysis showed that patients with a high sST2/LVMI ratio (≥ 0.39) had shorter event-free survival than those with intermediate (between 0.39 and 0.24) and low ratios (< 0.24) (log-rank, P = 0.022). The fully adjusted multivariable Cox regression analysis showed that the sST2/LVMI ratio was positively associated with the composite outcome in patients with heart failure with reduced ejection fraction after adjusting for confounders (hazard ratio 1.64, 95% confidence interval 1.06 to 2.54). By subgroup analysis, a stronger association was found with age between 40 and 55 years, systolic blood pressure < 115 or ≥ 129 mmHg, diastolic blood pressure < 74 mmHg, hematocrit < 44.5%, and interventricular septum thickness ≥ 8.5 mm. CONCLUSION: In patients with heart failure with reduced ejection fraction, the relationship between the sST2/LVMI ratio and the composite outcome was linear. A higher baseline ratio of sST2/LVMI was associated with an increased risk of cardiovascular mortality and heart failure rehospitalization in the short-term follow-up.

[A Light Adaptive Heart Rate Detection Method Based on Webcam].

In order to extract the pulse wave signal of blood volume effectively in the case of uneven light, a light-adaptive heart rate detection method based on webcam was proposed. In this method, adaptive gamma transform is applied to face image sequence to eliminate the influence of illumination. The pulse wave source signal was extracted from the forehead area and the blood volume pulse wave was obtained by wavelet filtering. The heart rate is estimated by Fourier transform analysis. The Bland-Altman analysis indicates that the method used in this paper is in good agreement with the measurement results of the electronic sphygmomanometer, and the adaptive gamma transformation used in this paper eliminates the influence of light interference, and the measurement error of heart rate is significantly reduced, which is completely able to meet the requirements of daily heart rate monitoring.

Endothelial Cdc42 deficiency impairs endothelial regeneration and vascular repair after inflammatory vascular injury.

BACKGROUND: Endothelial cell (EC) regeneration is essential for inflammation resolution and vascular integrity recovery after inflammatory vascular injury. Cdc42 is a central regulator of cell survival and vessel formation in EC development. However, it is unknown that whether Cdc42 could be a regulating role of EC repair following the inflammatory injury in the lung. The study sought to test the hypothesis that Cdc42 is required for endothelial regeneration and vascular integrity recovery after LPS-induced inflammatory injury. METHODS AND RESULTS: The role of Cdc42 for the regulation of pulmonary vascular endothelial repair was tested in vitro and in vivo. In LPS-induced acute lung injury (ALI) mouse models, knockout of the Cdc42 gene in ECs increased inflammatory cell infiltration and pulmonary vascular leakage and inhibited vascular EC proliferation, which eventually resulted in more severe inflammatory lung injury. In addition, siRNA-mediated knockdown of Cdc42 protein on ECs disrupted cell proliferation and migration and tube formation, which are necessary processes for recovery after inflammatory vascular injury, resulting in inflammatory vascular injury recovery defects. CONCLUSION: We found that Cdc42 deficiency impairs EC function and regeneration, which are crucial in the post-inflammatory vascular injury repair process. These findings indicate that Cdc42 is a potential target for novel treatments designed to facilitate endothelial regeneration and vascular repair in inflammatory pulmonary vascular diseases, such as ALI/ARDS.

[Chemical study on Cassiae Semen processing procedure].

References and our previous experiment showed that the contents of glycosides were significantly decreased，while the contents of aglycones were significantly increased after processing of Cassiae Semen.It may be related to its glycosidases or the heating process. In order to investigate the reasons, high performance liquid chromatographic (HPLC) was used to study the effects of these two factors on contents of Cassiae Semen's main chemical components in processing. The results showed that glycoside hydrolases was present in Cassiae Semen and could rapidly hydrolyze glycosides from Cassiae Semen into aglycones in suitable temperature with sufficient water.However，it didn't show effect on contents change of main constituents in the procedure of Cassiae Semen processing.The reason for content decrease of glycosides and content increase of aglycones in processed Cassiae Semen was glycoside bond cracking to produce corresponding aglycone at high temperature.This study further provides basis for further revealing of the processing mechanism of Cassiae Semen.

[Chemical constituents from seeds of Astragali complanati].

A new flavonoid glycoside, named complanatoside C (1), and 19 known compounds (2-20) were isolated from an 95% ethanol extract of Astragali Semen by various chromatographic methods. Their structures were identified on the basis of UV, IR, NMR, MS spectroscopic data analysis, and comparison with those in literature, including fifteen flavonoid glycoside (1-15), and six other constituents (16-20), among which compounds 16-19 were isolated from this plant for the first time.

Simultaneous Determination of Seven Anthraquinone Aglycones of Crude and Processed Semen Cassiae Extracts in Rat Plasma by UPLC-MS/MS and Its Application to a Comparative Pharmacokinetic Study.

Semen cassiae is the ripe seed of Cassia obtusifolia L. or Cassia tora L. of the family Leguminosae. In traditional Chinese medicine, the two forms of Semen cassiae are raw Semen cassiae (R-SC) and parched Semen cassiae (P-SC). To clarify the processing mechanism of Semen cassiae, the pharmacokinetics of R-SC and P-SC extracts were examined. A simple, rapid, sensitive ultra-high-performance liquid chromatography-tandem mass spectroscopy (UPLC-MS/MS) method was developed and validated for the simultaneous determination of seven anthraquinone aglycones of Semen cassiae (aurantio-obtusin, obtusifolin, questin, 2-hydroxyemodin-1-methyl-ether, rhein, emodin, 1,2,7-trimethoxyl-6,8-dihydroxy-3-methylanthraquinone) to compare the pharmacokinetics of raw and parched Semen cassiae in rat plasma. Compared with the R-SC group, Cmax and AUC0-12 tended to be higher in the P-SC group. In particular, Cmax values for aurantio-obtusin, obtusifolin, questin, 2-hydroxyemodin-1-methyl-ether and rhein were significantly higher in the P-SC group (p < 0.05). Meanwhile, Tmax and MRT0-12 tended to be lower in the P-SC group. Specifically, Tmax for aurantio-obtusin and 2-hydroxyemodin-1-methyl-ether and MRT0-12 for obtusifolin and rhein were significantly higher in the P-SC group (p < 0.05).

Synthesis of Controllable Superparamagnetic Nano Fe3O4 Based on Reduction Method for Colloidal Clusters of Magnetically Responsive Photonic Crystals.

In this paper, we designed and investigated a reduction-based method to synthesize controllably monodisperse superparamagnetic nano Fe3O4 colloidal clusters for magnetically responsive photonic crystals. It was shown that the addition of ascorbic acid (VC) to the system could synthesize monodisperse superparamagnetic nano Fe3O4 and avoided the generation of γ-Fe2O3 impurities, while the particle size and saturation magnetization intensity of nano Fe3O4 gradually decreased with the increase of VC dosage. Nano Fe3O4 could be rapidly assembled into photonic crystal dot matrix structures under a magnetic field, demonstrating tunability to various diffraction wavelengths. The nano Fe3O4 modified by polyvinylpyrrolidone (PVP) and silicon coated could be stably dispersed in a variety of organic solvents and thus diffracted different wavelengths under a magnetic field. This is expected to be applied in various scenarios in the field of optical color development.

Epstein-Barr virus positive gastric cancer: the pathological basis of CT findings and radiomics models prediction.

PURPOSE: To analyze the clinicopathologic information and CT imaging features of Epstein-Barr virus (EBV)-positive gastric cancer (GC) and establish CT-based radiomics models to predict the EBV status of GC. METHODS: This retrospective study included 144 GC cases, including 48 EBV-positive cases. Pathological and immunohistochemical information was collected. CT enlarged LN and morphological characteristics were also assessed. Radiomics models were constructed to predict the EBV status, including decision tree (DT), logistic regression (LR), random forest (RF), and support vector machine (SVM). RESULTS: T stage, Lauren classification, histological differentiation, nerve invasion, VEGFR2, E-cadherin, PD-L1, and Ki67 differed significantly between the EBV-positive and -negative groups (p = 0.015, 0.030, 0.006, 0.022, 0.028, 0.030, < 0.001, and < 0.001, respectively). CT enlarged LN and large ulceration differed significantly between the two groups (p = 0.019 and 0.043, respectively). The number of patients in the training and validation cohorts was 100 (with 33 EBV-positive cases) and 44 (with 15 EBV-positive cases). In the training cohort, the radiomics models using DT, LR, RF, and SVM yielded areas under the curve (AUCs) of 0.905, 0.771, 0.836, and 0.886, respectively. In the validation cohort, the diagnostic efficacy of radiomics models using the four classifiers were 0.737, 0.722, 0.751, and 0.713, respectively. CONCLUSION: A significantly higher proportion of CT enlarged LN and a significantly lower proportion of large ulceration were found in EBV-positive GC. The prediction efficiency of radiomics models with different classifiers to predict EBV status in GC was good.