Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), where the same item is re-consumed repeatedly over time. However, no previous studies have emphasized repeat consumption with neural networks. An effective neural approach is needed to decide when to perform repeat recommendation. In this paper, we incorporate a repeat-explore mechanism into neural networks and propose a new model, called RepeatNet, with an encoder-decoder structure. RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user's history and recommends them at the right time. We report on extensive experiments on three benchmark datasets. RepeatNet outperforms state-of-the-art baselines on all three datasets in terms of MRR and Recall. Furthermore, as the dataset size and the repeat ratio increase, the improvements of RepeatNet over the baselines also increase, which demonstrates its advantage in handling repeat recommendation scenarios.
Knowledge, attitude, and practice (KAP) are three key components for reducing the adverse health impacts of heat waves. However, research in eastern China regarding this is scarce. The present study aimed to evaluate the heat wave-related KAP of a population in Licheng in northeast China. This cross-sectional study included 2241 participants. Data regarding demographic characteristics, KAP, and heat illnesses were collected using a structured questionnaire. Univariate analysis and unconditional logistic regression models were used to analyze the data. Most residents had high KAP scores, with a mean score of 12.23 (standard deviation = 2.23) on a 17-point scale. Urban women and participants aged 35-44 years had relatively high total scores, and those with high education levels had the highest total score. There was an increased risk of heat-related illness among those with knowledge scores of 3-5 on an 8-point scale with mean score of 5.40 (standard deviation = 1.45). Having a positive attitude toward sunstroke prevention and engaging in more preventive practices to avoid heat exposure had a protective interaction effect on reducing the prevalence of heat-related illnesses. Although the KAP scores were relatively high, knowledge and practice were lacking to some extent. Therefore, governments should further develop risk-awareness strategies that increase awareness and knowledge regarding the adverse health impact of heat and help in planning response strategies to improve the ability of individuals to cope with heat waves.
Keloids are an excessive tissue response to dermal damage, characterized by uncontrolled growth and a high recurrence rate after various treatments. Abnormalities with the extracellular matrix (ECM) are one of the most important contributing factors to the formation of keloids. Although exosomes from human adipose-derived mesenchymal stem cells (adMSC-Exos) have been shown to promote repair and regeneration in wounds, they have seldom been studied for the treatment of keloids. In this study, we aimed to investigate the effects of adMSC-Exos on ECM remodeling in keloids using both in vitro and ex vivo models. The results showed that adMSC-Exos inhibited gene and protein expression of collagen I ( COL-1 ), collagen III ( COL-3 ), fibronectin ( FN ), and α-smooth muscle actin ( α-SMA ) in keloid fibroblasts (KFs). Furthermore, using an ex vivo tissue explant model, we found that adMSC-Exos significantly suppressed COL production and disrupted the microvessel stucture. We also demonstrated that adMSC-Exos inhibited the protein expression of Smad3 and Notch-1, and the expression of transforming growth factor β2 ( TGF-β2 ) in KFs, and promoted the expression of TGF-β3 . These findings largely explain the mechanisms underlying the inhibition of ECM production in keloids by adMSC-Exos. In conclusion, our results revealed that adMSC-Exos effectively inhibited the production of ECM in keloids, which provides a new potential alternative for the systemic treatment of keloids.
Background: Macrophages play important roles in renal fibrosis, partially by sensing mechanical forces, including shear stress and increased stiffness. The mechanically activated cationic channel Piezo1 drives vascular formation and blood pressure regulation to inflammatory responses, or cancer, but its role in macrophages in fibrotic kidney is elusive. Here, we hypothesized that Piezo1 in macrophages may have functions in renal fibrosis. Methods: We established a genetically engineered mouse model with Piezo1 specific knockout in myeloid cells and challenged with unilateral ureteric obstruction operation and folic acid treatment to induce the renal fibrosis, aiming to investigate the function of the mechanical-sensitive protein Piezo1 in macrophages in renal fibrosis and its underlying mechanisms. Results: Myeloid Piezo1 was indispensable for renal fibrosis generation. Piezo1 gene deletion in the myeloid lineage was protective in mice with renal fibrosis. Further analyses revealed that macrophage accumulation in the injured kidney depended on the Piezo1-regulated C-C motif chemokine ligand 2, C-C motif chemokine receptor 2 pathway, and Notch signaling cascade. Moreover, Piezo1 deletion restrained macrophage inflammation and consequently suppressed kidney fibrosis and epithelial-mesenchymal transition. In vitro assays showed that Piezo1 deficiency blocked lipopolysaccharide and Piezo1 activation-induced inflammatory responses in bone marrow–derived macrophages. Mechanistically, Piezo1 regulated inflammation through the Ca 2+ -dependent intracellular cysteine protease, as the pharmacological inhibition of calpain blocked the proinflammatory role of Piezo1. Conclusions: This study characterized the important function of Piezo1 in renal fibrosis. Targeting the Piezo1 channels by genetic or pharmacological manipulations may be a promising strategy for the treatment of renal fibrosis.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.