Bee pollen possesses potential hypoglycemic effects but its inhibitory mechanisms on glucose absorption and transportation in intestinal cells still need to be clarified. Here, we determined the inhibitory effects of bee pollen extract originating from Camellia sinensis L. (BP-Cs) as well as its representative phenolic compounds on glucose uptake and transport through a human intestinal Caco-2 cell monolayer model. It showed that three representative phenolic compounds, including gallic acid (GA), ), with contents of 27.7 ± 0.86, 9.88 ± 0.54, and 7.83 ± 0.46 μg/mg in BP-Cs extract, respectively, exerted mutual antagonistic actions interacting with glucose transporters to inhibit glucose uptake and transport based on their combination index (CI) and molecular docking analysis. K1, K2, and GA might compete with D-glucose to form hydrogen bonds with the same active residues including GLU-412, GLY-416, GLN-314, and TRP-420 in GLUT2. These findings provide us a deep understanding of the mechanisms underlying the anti-hyperglycemia by bee pollen, which provide a new sight on dietary intervention strategies against diabetes.
Deep learning has made breakthroughs in recent decades and has been widely used in many domains. However, most of those methods heavily rely on large labeled datasets, which results in poor performance when provided with limited labeled data. Few-shot learning (FSL), which aims at learning a novel task with limited samples, has attracted a lot of research recently. The previous metric-based methods ignore the internal bias between the training and testing datasets since the categories of the testing dataset are completely different from the training set. Transfer learning methods also suffer from few labeled data and tends to be overfitting in this situation. This paper proposes Transductive Mutual Information Encoder Network (TMIN) for few-shot learning problems. TMIN typically trains a convolutional neural network with a mutual information maximization module in an unsupervised manner. The trained network maps images to a high dimensional embedding space. Then the embeddings are exploited to measure the similarity between samples by a distance metric. Experiments indicate that the proposed model achieves competitive performance compared with the counterparts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.