Point-of-interest (POI) recommendation is an important application in location-based social networks (LBSNs), which learns the user preference and mobility pattern from check-in sequences to recommend POIs. However, previous POI recommendation systems model check-in sequences based on either tensor factorization or Markov chain model, which cannot capture contextual check-in information in sequences.The contextual check-in information implies the complementary functions among POIs that compose an individual's daily checkin sequence. In this paper, we exploit the embedding learning technique to capture the contextual check-in information and further propose the SEquential Embedding Rank (SEER) model for POI recommendation. In particular, the SEER model learns user preferences via a pairwise ranking model under the sequential constraint modeled by the POI embedding learning method. Furthermore, we incorporate two important factors, i.e., temporal influence and geographical influence, into the SEER model to enhance the POI recommendation system. Due to the temporal variance of sequences on different days, we propose a temporal POI embedding model and incorporate the temporal POI representations into a temporal preference ranking model to establish the Temporal SEER (T-SEER) model. In addition, We incorporate the geographical influence into the T-SEER model and develop the Geo-Temporal SEER (GT-SEER) model. To verify the effectiveness of our proposed methods, we conduct elaborated experiments on two real life datasets. Experimental results show that our proposed methods outperform state-of-the-art models. Compared with the best baseline competitor, the GT-SEER model improves at least 28% on both datasets for all metrics.

We investigated the role of nuclear factor erythroid 2-related factor 2 (Nrf2) in renin-angiotensin system (RAS) gene expression in renal proximal tubule cells (RPTCs) and in the development of systemic hypertension and kidney injury in diabetic Akita mice. We used adult male Akita Nrf2 knockout mice and Akita mice treated with trigonelline (an Nrf2 inhibitor) or oltipraz (an Nrf2 activator). We also examined rat immortalized RPTCs (IRPTCs) stably transfected with control plasmids or plasmids containing rat angiotensinogen (Agt), angiotensin-converting enzyme (ACE), angiotensin-converting enzyme-2 (Ace2), or angiotensin 1-7 (Ang 1-7) receptor (MasR) gene promoters. Genetic deletion of Nrf2 or pharmacological inhibition of Nrf2 in Akita mice attenuated hypertension, renal injury, tubulointerstitial fibrosis, and the urinary albumin/creatinine ratio. Furthermore, loss of Nrf2 upregulated RPTC Ace2 and MasR expression, increased urinary Ang 1-7 levels, and downregulated expression of Agt, ACE, and profibrotic genes in Akita mice. In cultured IRPTCs, Nrf2 small interfering RNA transfection or trigonelline treatment prevented high glucose stimulation of Nrf2 nuclear translocation, Agt, and ACE transcription with augmentation of Ace2 and MasR transcription, which was reversed by oltipraz. These data identify a mechanism, Nrf2-mediated stimulation of intrarenal RAS gene expression, by which chronic hyperglycemia induces hypertension and renal injury in diabetes.

No abstract

We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the final prediction performance. Unlike the graph convolutional matrix completion model with one-hot encoding node inputs, our STAR-GCN learns lowdimensional user and item latent factors as the input to restrain the model space complexity. Moreover, our STAR-GCN can produce node embeddings for new nodes by reconstructing masked input node embeddings, which essentially tackles the cold start problem. Furthermore, we discover a label leakage issue when training GCN-based models for link prediction tasks and propose a training strategy to avoid the issue. Empirical results on multiple rating prediction benchmarks demonstrate our model achieves state-of-the-art performance in four out of five real-world datasets and significant improvements in predicting ratings in the cold start scenario. The code implementation is available in https://github.com/jennyzhang0215/STAR-GCN.

No abstract