An imbalanced learning method based on graph tran-smote for fraud detection.

Fraud seriously threatens individual interests and social stability, so fraud detection has attracted much attention in recent years. In scenarios such as social media, fraudsters typically hide among numerous benign users, constituting only a small minority and often forming "small gangs". Due to the scarcity of fraudsters, the conventional graph neural network might overlook or obscure critical fraud information, leading to insufficient representation of fraud characteristics. To address these issues, the tran-smote on graphs (GTS) method for fraud detection is proposed by this study. Structural features of each type of node are deeply mined using a subgraph neural network extractor, these features are integrated with attribute features using transformer technology, and the node's information representation is enriched, thereby addressing the issue of inadequate feature representation. Additionally, this approach involves setting a feature embedding space to generate new nodes representing minority classes, and an edge generator is used to provide relevant connection information for these new nodes, alleviating the class imbalance problem. The results from experiments on two real datasets demonstrate that the proposed GTS, performs better than the current state-of-the-art baseline.

Diagnosis of Inverted Meckel's diverticulum by double-balloon enteroscopy: a case report.

Background: Meckel's diverticulum (MD) is the most common congenital defect of the gastrointestinal tract, occurring in about 1% to 2% of population. Most MD are rarely symptomatic, with presenting symptoms including diverticulitis, digestive tract hemorrhage and intestinal obstruction. The semblance of symptoms to enteritis and appendicitis makes preoperative diagnosis challenging. Current diagnosis of MD includes technetium-99m pertechnate scan, laparoscopic or intraoperative findings and examining surgical specimens. Here, we report that a double-balloon enteroscopy (DBE) improves the diagnosis accuracy of MD and presents high clinical application value. Case Description: A 12-year-old male patient was admitted to our hospital due to recurrent abdominal pain and black stools for more than half a year, recurrence for 2 days, accompanied by vomiting. The boy had anemic appearance, with periumbilical tenderness, and no mass was detected upon palpations. Past medical records revealed recurrent abdominal pain episodes thrice. Pre-surgery 99TcmO4-single-photon emission computed tomography/computed tomography (SPECT/CT) imaging was performed but did not reach the condition for diagnosis of MD. DBE was then performed and identified an upper ileum mass. After surgery, it was confirmed that the patient was an inverted MD, and the pathology showed gastric mucosa and pancreatic tissue. The patient recovered well after surgery and was discharged. Conclusions: DBE is not widely used in the diagnosis of MD, but its accuracy is higher than that of radionuclide scanning imaging. In addition, several advantages such as hemostasis treatment, direct detection and observation of the diverticulum, and demarcation of the site and scope of the lesion prior to surgery brings high clinical application value.

Biocontrol and Growth Promotion Potential of Bacillus subtilis CTXW 7-6-2 against Rhizoctonia solani that Causes Tobacco Target Spot Disease.

Fungal diseases form perforated disease spots in tobacco plants, resulting in a decline in tobacco yield and quality. The present study investigated the antagonistic effect of Bacillus subtilis CTXW 7-6-2 against Rhizoctonia solani, its ability to promote the growth of tobacco seedlings, and the expression of disease resistance-related genes for efficient and eco-friendly plant disease control. Our results showed that CTXW 7-6-2 had the most vigorous growth after being cultured for 96 h, and its rate of inhibition of R. solani growth in vitro was 94.02%. The volatile compounds produced by CTXW 7-6-2 inhibited the growth of R. solani significantly (by 96.62%). The fungal growthinhibition rate of the B. subtilis CTXW 7-6-2 broth obtained after high-temperature and no-high-temperature sterile fermentation was low, at 50.88% and 54.63%, respectively. The lipopeptides extracted from the B. subtilis CTXW 7-6-2 fermentation broth showed a 74.88% fungal growth inhibition rate at a concentration of 100 mg/l. Scanning and transmission electron microscopy showed some organelle structural abnormalities, collapse, shrinkage, blurring, and dissolution in the R. solani mycelia. In addition, CTXW 7-6-2 increased tobacco seedling growth and improved leaf and root weight compared to the control. After CTXW 7-6-2 inoculation, tobacco leaves showed the upregulation of the PDF1.2, PPO, and PAL genes, which are closely related to target spot disease resistance. In conclusion, B. subtilis CTXW 7-6-2 may be an efficient biological control agent in tobacco agriculture and enhance plant growth potential.

Bioinformatics and experimental findings reveal the therapeutic actions and targets of pachymic acid against cystitis glandularis.

Pachymic acid (PA), a bioactive ingredient isolated from Poria cocos Wolf, is reported with potential benefits of anti-inflammatory, anti-oxidative actions. It is reasoned that PA may play the potential benefits against cystitis glandularis (CG), an inflammation of the bladder tissue. In this study, we aimed to apply the network pharmacology and molecular docking analyses to reveal concrete anti-CG targets and mechanisms of PA, and then the bioinformatic findings were verified by using clinical and animal samples. The methodological data from network pharmacology approach showed that 303 and 243 reporting targets of CG and PA, and other 31 shared targets of CG and PA were identified. Subsequently, all top targets of PA against CG were screened out, including cyclooxygenase-2, epidermal growth factor receptor, tumor antigen p53 (TP53), tumor necrosis factor-alpha (TNF), interleukin-1 (IL-1) beta, proto-oncogene c-jun. Molecular docking data demonstrated that PA exerted potent bonding capacities with TNF, TP53 proteins in CG. In human study, the findings suggested that overactivated TNF-α expression and suppressed TP53 activation were detected in CG samples. In animal study, PA-treated mice showed reduced intravesical IL-1, IL-6 levels, and lactate dehydrogenase content, downregulated TNF-α and upregulated TP53 proteins in bladder samples. Taken together, our bioinformatics and experimental findings identify the key anti-CG biotargets and mechanisms of PA. More markedly, these pivotal pharmacological targets of PA against CG have been screened out and verified by using computational and experimental analyses.