In view of the harm of diabetes to the population, we have introduced an ensemble learning algorithm—EXtreme Gradient Boosting (XGBoost) to predict the risk of type 2 diabetes and compared it with Support Vector Machines (SVM), the Random Forest (RF) and K-Nearest Neighbor (K-NN) algorithm in order to improve the prediction effect of existing models. The combination of convenient sampling and snowball sampling in Xicheng District, Beijing was used to conduct a questionnaire survey on the personal data, eating habits, exercise status and family medical history of 380 middle-aged and elderly people. Then, we trained the models and obtained the disease risk index for each sample with 10-fold cross-validation. Experiments were made to compare the commonly used machine learning algorithms mentioned above and we found that XGBoost had the best prediction effect, with an average accuracy of 0.8909 and the area under the receiver’s working characteristic curve (AUC) was 0.9182. Therefore, due to the superiority of its architecture, XGBoost has more outstanding prediction accuracy and generalization ability than existing algorithms in predicting the risk of type 2 diabetes, which is conducive to the intelligent prevention and control of diabetes in the future.

(1) Background: The use of antibiotics affects the composition of gut microbiota. Studies have suggested that the colonization of gut microbiota in early life is related to later food allergies. Still, the relationship between altered intestinal microbiota in adulthood and food allergies is unclear. (2) Methods: We established three mouse models to analyze gut microbiota dysbiosis’ impact on the intestinal barrier and determine whether this effect can increase the susceptibility to and severity of food allergy in later life. (3) Results: The antibiotic-induced gut microbiota dysbiosis significantly reduced Lachnospiraceae, Muribaculaceae, and Ruminococcaceae, and increased Enterococcaceae and Clostridiales. At the same time, the metabolic abundance was changed, including decreased short-chain fatty acids and tryptophan, as well as enhanced purine. This change is related to food allergies. After gut microbiota dysbiosis, we sensitized the mice. The content of specific IgE and IgG1 in mice serum was significantly increased, and the inflammatory response was enhanced. The dysbiosis of gut microbiota caused the sensitized mice to have more severe allergic symptoms, ruptured intestinal villi, and a decrease in tight junction proteins (TJs) when re-exposed to the allergen. (4) Conclusions: Antibiotic-induced gut microbiota dysbiosis increases the susceptibility and severity of food allergies. This event may be due to the increased intestinal permeability caused by decreased intestinal tight junction proteins and the increased inflammatory response.

Glycyrrhizic acid (GA), the major bioactive triterpene glycoside of glycyrrhiza, has been shown to possess a wide range of pharmacological properties, including anti-inflammatory and anti-viral properties. However, few studies have examined the anti-allergic activity and exact mechanism of action of GA. In the present work, the anti-allergic activity and possible mechanisms of action of GA on an immunoglobulin (Ig) E-mediated allergic reaction has been studied using three models of allergic reactionin vivoandin vitro. Active systemic allergic reaction in Balb/c mice showed that GA can suppress the increased level of IL-4 to restore the immune balance of T_H1/T_H2 cells in a dose-dependent manner. Additionally, GA attenuated significantly the B cells producing allergen-specific IgE and IgG₁partly because of the low levels of T_H2 cytokines. Both passive cutaneous anaphylaxisin vivoand an RBL-2H3 cell-based immunological assayin vitroindicated that GA acted as a “mast cell stabilizer”, as it inhibited mast cell degranulation and decreased vascular permeability by inhibiting the expression of Orai1, STIM1 and TRPC1, which blocked extracellular Ca²⁺influxes. The current study suggests that GA may serve as an effective anti-allergic agent derived from food for the prevention and treatment of IgE-mediated allergic reaction.

The whey protein β-lactoglobulin (BLG) is a major milk allergen which is absent in human milk. Here, we for the first time generated DNA-freeBLGbi-allelic knockout cow by zinc-finger nuclease (ZFNs) mRNA and produced BLG-free milk. According to the allergenicity evaluation of BLG-free milk, we found it can trigger lower allergic reaction of Balb/c mice including the rectal temperature drop and the allergen-specific immunoglobulin IgE production; BLG free-milk was easily digested by pepsin at 2 min, while BLG in control milk was still not completely digested after 60 min, and the binding of IgE from cow’s milk allergy (CMA) patients to BLG free-milk was significantly lower than that to the control milk. Meanwhile, the genome sequencing revealed that our animal is free of off-target events. Importantly, editing animal genomes without introducing foreign DNA into cells may alleviate regulatory concerns related to foods produced by genome edited animals. Finally, the ZFNs-mediated targeting in cow could be transmitted through the germline by breeding. These findings will open up unlimited possibilities of modifying milk composition to make it more suitable for human health and also improve the functional properties of milk.

The clinical symptoms of prediabetes are mild and easy to overlook, but prediabetes may develop into diabetes if early intervention is not performed. In this study, a deep learning model—referred to as IGRNet—is developed to effectively detect and diagnose prediabetes in a non-invasive, real-time manner using a 12-lead electrocardiogram (ECG) lasting 5 s. After searching for an appropriate activation function, we compared two mainstream deep neural networks (AlexNet and GoogLeNet) and three traditional machine learning algorithms to verify the superiority of our method. The diagnostic accuracy of IGRNet is 0.781, and the area under the receiver operating characteristic curve (AUC) is 0.777 after testing on the independent test set including mixed group. Furthermore, the accuracy and AUC are 0.856 and 0.825, respectively, in the normal-weight-range test set. The experimental results indicate that IGRNet diagnoses prediabetes with high accuracy using ECGs, outperforming existing other machine learning methods; this suggests its potential for application in clinical practice as a non-invasive, prediabetes diagnosis technology.

Apigenin is a natural flavone with anti-inflammatory and antioxidant properties and antitumor abilities against several types of cancers. Previous studies have found that the antitumor effects of apigenin may be due to its similar chemical structure to 17β-estradiol (E2), a main kind of estrogen in women. However, the precise mechanism underlying the antitumor effects of apigenin in cervical cancer remains unknown. On the other hand, there is increasing evidence that describes a histamine role in cancer cell proliferation. In this study, we examined whether apigenin can attenuate the effects of histamine on tumors by regulating the expression level of estrogen receptors (ERs) to inhibit cervical cancer growth. Our in vitro data indicates that apigenin inhibited cell proliferation in a dose-dependent manner in human cervical cancer cells (HeLa), while histamine shows the opposite effects. After that, the xenograft model was established to explore the antitumor effects of apigenin in vivo, the results show that apigenin inhibited cervical tumor growth by reversing the abnormal ER signal in tumor tissue which was caused by histamine. We also demonstrate that apigenin inhibited cell proliferation via suppressing the PI3K/Akt/mTOR signaling pathway. Collectively, our results suggest that apigenin may inhibit tumor growth through the ER-mediated PI3K/Akt/mTOR pathway and that it can also attenuate the effects of histamine on tumors.