We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, modelfree deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.
Background: Thioredoxin-interacting protein (TxNIP) is up-regulated by high glucose (HG), inhibits the antioxidant, thioredoxin, and thereby is implicated in oxidative stress. Results: TxNIP deficiency protects mesangial cells from HG-induced oxidative stress and increased collagen by blocking mitochondrial glucose metabolism, NADPH oxidase, and Nox4. Conclusion: TxNIP controls ROS generation by regulating the TCA cycle versus glycolytic glucose flux. Significance: Inhibition of TxNIP is a promising approach to treat glucose toxicity.
Chronic exposure to high glucose leads to diabetic nephropathy characterized by increased mesangial matrix protein (e.g., collagen) accumulation. Altered cell signaling and gene expression accompanied by oxidative stress have been documented. The contribution of the tyrosine kinase, c-Src (Src), which is sensitive to oxidative stress, was examined. Cultured rat mesangial cells were exposed to high glucose (25 mmol/L) in the presence and absence of Src inhibitors (PP2, SU6656), Src small interfering RNA (siRNA), and the tumor necrosis factor-α–converting enzyme (TACE) inhibitor, TAPI-2. Src was investigated in vivo by administration of PP2 to streptozotocin (STZ)-induced diabetic DBA2/J mice. High glucose stimulated Src, TACE, epidermal growth factor receptor (EGFR), mitogen-activated protein kinases (MAPKs), extracellular signal–regulated kinase (ERK1/2, p38), and collagen IV accumulation in mesangial cells. PP2 and SU6656 blocked high glucose–stimulated phosphorylation of Src Tyr-416, EGFR, and MAPKs. These inhibitors and Src knockdown by siRNA, as well as TAPI-2, also abrogated high glucose–induced phosphorylation of these targets and collagen IV accumulation. In STZ-diabetic mice, albuminuria, increased Src pTyr-416, TACE activation, ERK and EGFR phosphorylation, glomerular collagen accumulation, and podocyte loss were inhibited by PP2. These data indicate a role for Src in a high glucose-Src-TACE-heparin-binding epidermal growth factor-EGFR-MAPK–signaling pathway to collagen accumulation. Thus, Src may provide a novel therapeutic target for diabetic nephropathy.
Many people share their activities with others through online communities. These shared activities have an impact on other users' activities. For example, users are likely to become interested in items that are adopted (e.g. liked, bought and shared) by their friends. In this paper, we propose a probabilistic model for discovering latent influence from sequences of item adoption events. An inhomogeneous Poisson process is used for modeling a sequence, in which adoption by a user triggers the subsequent adoption of the same item by other users. For modeling adoption of multiple items, we employ multiple inhomogeneous Poisson processes, which share parameters, such as influence for each user and relations between users. The proposed model can be used for finding influential users, discovering relations between users and predicting item popularity in the future. We present an efficient Bayesian inference procedure of the proposed model based on the stochastic EM algorithm. The effectiveness of the proposed model is demonstrated by using real data sets in a social bookmark sharing service.
Expression of thioredoxin-interacting protein (TxNIP), an endogenous inhibitor of the thiol oxidoreductase thioredoxin, is augmented by high glucose (HG) and promotes oxidative stress. We previously reported that TxNIP-deficient mesangial cells showed protection from HG-induced reactive oxygen species, mitogenactivated protein kinase phosphorylation, and collagen expression. Here, we investigated the potential role of TxNIP in the pathogenesis of diabetic nephropathy (DN) in vivo. Wild-type (WT) control, TxNIP 2/2 , and TxNIP +/2 mice were rendered equally diabetic with low-dose streptozotocin. In contrast to effects in WT mice, diabetes did not increase albuminuria, proteinuria, serum cystatin C, or serum creatinine levels in TxNIP 2/2 mice. Whereas morphometric studies of kidneys revealed a thickened glomerular basement membrane and effaced podocytes in the diabetic WT mice, these changes were absent in the diabetic TxNIP 2/2 mice. Immunohistochemical analysis revealed significant increases in the levels of glomerular TGF-b1, collagen IV, and fibrosis only in WT diabetic mice. Additionally, only WT diabetic mice showed significant increases in oxidative stress (nitrotyrosine, urinary 8-hydroxy-2-deoxy-guanosine) and inflammation (IL-1b mRNA, F4/80 immunohistochemistry). Expression levels of Nox4-encoded mRNA and protein increased only in the diabetic WT animals. A significant loss of podocytes, assessed by Wilms' tumor 1 and nephrin staining and urinary nephrin concentration, was found in diabetic WT but not TxNIP 2/2 mice. Furthermore, in cultured human podocytes exposed to HG, TxNIP knockdown with siRNA abolished the increased mitochondrial O 2 2 generation and apoptosis. These data indicate that TxNIP has a critical role in the progression of DN and may be a promising therapeutic target.
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.