Search

The neural network method is a type of machine learning that has made significant advances over the past few years in a variety of fields, particularly text, speech, images, videos, etc. In areas where data is unstructured, traditional machine learning has not been able to surpass the 'glass ceiling'; therefore, researchers have turned to neural networks as auxiliary tools to achieve significant breakthroughs or develop new research methods. An array of computational chemistry challenges can be addressed using neural networks, including virtual screening, quantitative structure-activity relationships, protein structure prediction, materials design, quantum chemistry, and property prediction, among others. This paper proposes a strategy for predicting the chemical properties of fruits by using graph neural networks, and it aims to provide some guidance to researchers and streamline the identification process., (© 2024. The Author(s).)

Background: Obesity often co-exists with metabolic abnormalities, but the results of studies on the relationship between obesity, metabolic abnormalities and the risk of gout are inconsistent., Objectives: We aimed to study whether there was a mutual regulation between obesity, metabolic abnormalities and the risk of gout., Methods: We conducted a cross-sectional study to expound the association between obesity based on different metabolic statuses and the risk of gout. Patients were derived from Nationwide Readmission Database (2018 sample)., Results: A total of 9,668,330 records were recruited for analysis from January to December. The risk of gout in the obesity group, metabolic abnormalities group and obesity combined with metabolic abnormalities group was 1.67 times (OR = 1.67, 95%CI 1.64-1.70), 3.12 times (OR = 3.12, 95%CI 3.09-3.15) and 4.27 times (OR = 4.27, 95%CI 4.22-4.32) higher than that in the normal control group. For different metabolic components, OR value was highest in hypertension group (OR = 2.65, 95%CI 2.60-2.70 and OR = 4.85, 95%CI 4.73-4.97), followed by dyslipidemia group (OR = 2.23, 95%CI 2.16-2.30 and OR = 3.74, 95%CI 3.55-3.95) and in hyperglycemia group (OR = 1.73, 95%CI 1.66-1.80 and OR = 2.94, 95%CI 2.78-3.11). Fewer components of metabolic syndrome were associated with a lower risk of gout in both nonobese and obese patients., Conclusion: When metabolic abnormalities were present, obesity induced a higher risk of gout. Different components of metabolic abnormalities had different effects on the risk of gout occurrence, and the number of metabolic abnormalities was closely related to the risk of gout occurrence. Follow-up and intervention methods targeting obesity and metabolic abnormalities should be considered for patients with gout., (Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.)

Background/aims: To evaluate the causal correlation between complement components and non-viral liver diseases and their potential use as druggable targets., Methods: We conducted Mendelian randomization (MR) to assess the causal role of circulating complements in the risk of non-viral liver diseases. A complement-centric protein interaction network was constructed to explore biological functions and identify potential therapeutic options., Results: In the MR analysis, genetically predicted levels of complement C1q C chain (C1QC) were positively associated with the risk of autoimmune hepatitis (odds ratio 1.125, 95% confidence interval 1.018-1.244), while complement factor H-related protein 5 (CFHR5) was positively associated with the risk of primary sclerosing cholangitis (PSC;1.193, 1.048- 1.357). On the other hand, CFHR1 (0.621, 0.497-0.776) and CFHR2 (0.824, 0.703-0.965) were inversely associated with the risk of alcohol-related cirrhosis. There were also significant inverse associations between C8 gamma chain (C8G) and PSC (0.832, 0.707-0.979), as well as the risk of metabolic dysfunction-associated steatotic liver disease (1.167, 1.036-1.314). Additionally, C1S (0.111, 0.018-0.672), C7 (1.631, 1.190-2.236), and CFHR2 (1.279, 1.059-1.546) were significantly associated with the risk of hepatocellular carcinoma. Proteins from the complement regulatory networks and various liver diseaserelated proteins share common biological processes. Furthermore, potential therapeutic drugs for various liver diseases were identified through drug repurposing based on the complement regulatory network., Conclusion: Our study suggests that certain complement components, including C1S, C1QC, CFHR1, CFHR2, CFHR5, C7, and C8G, might play a role in non-viral liver diseases and could be potential targets for drug development.