Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence. To capture the spatial and temporal dependence simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is in combination with the graph convolutional network (GCN) and gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures to capture spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data to capture temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://github.com/lehaifeng/T-GCN.

Large-scale IoT services such as healthcare, smart cities and marine monitoring are pervasive in Cyber-physical environments strongly supported by Internet technologies and Fog computing. Complex IoT services are increasingly composed of sensors, devices, and compute resources within Fog computing infrastructures. The orchestration of such applications can be leveraged to alleviate the difficulties of maintenance and enhance data security and system reliability. However, how to efficiently deal with dynamic variations and transient operational behavior is a crucial challenge within the context of choreographing complex services. Furthermore, with the rapid increase of the scale of IoT deployments, the heterogeneity, dynamicity, and uncertainty within Fog environments and increased computational complexity further dramatically aggravate this challenge. This article provides an overview of the core issues, challenges and future research directions in Fog-enabled orchestration for IoT services. Additionally, we present early experiences of an orchestration scenario, demonstrating the feasibility and initial results of using a distributed genetic algorithm in this context.

Purpose: The progression of disease within 24 months (POD24) has been considered to be a strong prognostic indicator for various types of malignant lymphoma. However, the value of POD24 in Diffuse Large B-Cell Lymphoma (DLBCL) is unclear. We evaluated the value of POD24 in patients with DLBCL. Methods: A total of 476 newly diagnosed DLBCL patients were analyzed in this study. Overall Survival (OS) was evaluated by Kaplan Meier method. We performed univariate and multivariate analyses to evaluate the potential prognostic value of POD24. Results: A total of 476 newly diagnosed patients with DLBCL were analyzed in our study. The 5-year OS rates of patients in the POD24 group and non-POD24 group were 22.6% and 82.5%, respectively (HR 7.397; 95% CI 5.403-10.125; p < 0.001). The 5-year OS rates of patients in the POD24 group and non-POD24 group in Complete Release (CR) were 26.5% and 73.7%, respectively (HR 4.374; 95% CI 2.521-7.590; p<0.001). These results were similar in patients with non-CR: the 5-year OS rates were 20.5% and 83.7% (HR 8.697; 95% CI 5.934-12.746; p<0.001). The 5-year OS rates of the POD24 group and the non-POD24 group in the low stage (stage I and II) were 48% and 85.6%, respectively (HR 5.122; 95% CI 2.803-9.363; p<0.001). The results were the same in the high stage (stage III and IV): 10.2% and 79.4% (HR 5.122; 95% CI 2.803-9.363; p<0.001). Only stage was an independent prognostic factor for OS in the POD24 group in the multivariate analysis (P=0.001). Conclusion: The association between POD24 and OS was confirmed, and POD24 can predict poor OS in patients with DLBCL. These marked differences in outcome suggest that POD24 is useful for patient counseling, study design, and risk stratification in DLBCL.

Abstractp53, encoded by the tumor suppressor gene TP53, is one of the most important tumor suppressor factors in vivo and can be negatively regulated by MDM2 through p53–MDM2 negative feedback loop. Abnormal p53 can be observed in almost all tumors, mainly including p53 mutation and functional inactivation. Blocking MDM2 to restore p53 function is a hotspot in the development of anticancer candidates. Till now, nine MDM2 inhibitors with different structural types have entered clinical trials. However, no MDM2 inhibitor has been approved for clinical application. This review focused on the discovery, structural modification, preclinical and clinical research of the above compounds from the perspective of medicinal chemistry. Based on this, the possible defects in MDM2 inhibitors in clinical development were analyzed to suggest that the multitarget strategy or targeted degradation strategy based on MDM2 has the potential to reduce the dose-dependent hematological toxicity of MDM2 inhibitors and improve their anti-tumor activity, providing certain guidance for the development of agents targeting the p53–MDM2 interaction.

The renewable energy-powered electrolytic reduction of carbon dioxide (CO2) to methane (CH4) using water as a reaction medium is one of the most promising paths to store intermittent renewable energy and address global energy and sustainability problems. However, the role of water in the electrolyte is often overlooked. In particular, the slow water dissociation kinetics limits the proton-feeding rate, which severely damages the selectivity and activity of the methanation process involving multiple electrons and protons transfer. Here, we present a novel tandem catalyst comprising Ir single-atom (Ir1)-doped hybrid Cu3N/Cu2O multisite that operates efficiently in converting CO2 to CH4. Experimental and theoretical calculation results reveal that the Ir1 facilitates water dissociation into proton and feeds to the hybrid Cu3N/Cu2O sites for the *CO protonation pathway toward *CHO. The catalyst displays a high Faradaic efficiency of 75% for CH4 with a current density of 320 mA cm–2 in the flow cell. This work provides a promising strategy for the rational design of high-efficiency multisite catalytic systems.