Uncovering the statistical patterns that characterize the trajectories humans follow during their daily activity is not only a major intellectual challenge, but also of importance for public health 1-5 , city planning 6-8 , traffic engineering 9, 10 and economic forecasting 11 . For example, quantifiable models of human mobility are indispensable for predicting the spread of biological pathogens 1-5 or mobile phone viruses 12 .In the past few years the availability of mobile phone records, GPS data, and other datasets capturing aspects of human mobility have given a new empirically driven momentum to the subject. While the available datasets significantly differ in their reach and resolution, the results appear to agree on a number of quantitative characteristics of human mobility. For example, both dollar bill tracking 13 and mobile phone data 14 indicate that the

Heterozygous mutations in the gene encoding isocitrate dehydrogenase-1 (IDH1) occur in certain human brain tumors, but their mechanistic role in tumor development is unknown. We have shown that tumor-derived IDH1 mutations impair the enzyme’s affinity for its substrate and dominantly inhibit wild-type IDH1 activity through the formation of catalytically inactive heterodimers. Forced expression of mutant IDH1 in cultured cells reduces formation of the enzyme product,α-ketoglutarate (α-KG), and increases the levels of hypoxia-inducible factor subunit HIF-1α, a transcription factor that facilitates tumor growth when oxygen is low and whose stability is regulated by α-KG. The rise in HIF-1α levels was reversible by an α-KG derivative. HIF-1α levels were higher in human gliomas harboring an IDH1 mutation than in tumors without a mutation. Thus, IDH1 appears to function as a tumor suppressor that, when mutationally inactivated, contributes to tumorigenesis in part through induction of the HIF-1 pathway.

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.