Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and different definitions of imperceptible perturbations bring unique challenges and opportunities for the adversarial attacks and defenses for graph data. In this paper, we propose both attack and defense techniques. For attack, we show that the discreteness problem could easily be resolved by introducing integrated gradients which could accurately reflect the effect of perturbing certain features or edges while still benefiting from the parallel computations. For defense, we observe that the adversarially manipulated graph for the targeted attack differs from normal graphs statistically. Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbation. Our experiments on a number of datasets show the effectiveness of the proposed methods.
Nutrients are absorbed solely by the intestinal villi. Aging of this organ causes malabsorption and associated illnesses, yet its aging mechanisms remain unclear. Here, we show that aging-caused intestinal villus structural and functional decline is regulated by mTORC1, a sensor of nutrients and growth factors, which is highly activated in intestinal stem and progenitor cells in geriatric mice. These aging phenotypes are recapitulated in intestinal stem cell-specific Tsc1 knockout mice. Mechanistically, mTORC1 activation increases protein synthesis of MKK6 and augments activation of the p38 MAPK-p53 pathway, leading to decreases in the number and activity of intestinal stem cells as well as villus size and density. Targeting p38 MAPK or p53 prevents or rescues ISC and villus aging and nutrient absorption defects. These findings reveal that mTORC1 drives aging by augmenting a prominent stress response pathway in gut stem cells and identify p38 MAPK as an anti-aging target downstream of mTORC1.
Cytokine expression pattern in the aqueous humor, in contrast to that in serum, may reflect intraocular immune reactions during active inflammation in patients with AAU. Both Th1 and Th17 are involved in immunopathogenesis of HLA-B27 associated and idiopathic AAU, but a different cytokine pattern was identified in these two clinical entities. A predominant Th17-driven immune response may play an important role in the immunopathogenesis of idiopathic AAU, while Th1 dominant immune response may be responsible for the inflammation in HLA-B27 associated AAU.
The objective of this study was to investigate the method of the combination of radiological and textural features for the differentiation of malignant from benign solitary pulmonary nodules by computed tomography. Features including 13 gray level co-occurrence matrix textural features and 12 radiological features were extracted from 2,117 CT slices, which came from 202 (116 malignant and 86 benign) patients. Lasso-type regularization to a nonlinear regression model was applied to select predictive features and a BP artificial neural network was used to build the diagnostic model. Eight radiological and two textural features were obtained after the Lasso-type regularization procedure. Twelve radiological features alone could reach an area under the ROC curve (AUC) of 0.84 in differentiating between malignant and benign lesions. The 10 selected characters improved the AUC to 0.91. The evaluation results showed that the method of selecting radiological and textural features appears to yield more effective in the distinction of malignant from benign solitary pulmonary nodules by computed tomography.
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.