Recent research on vision-based tasks has achieved great improvement due to the development of deep learning solutions. However, deep models have been found vulnerable to adversarial attacks where the original inputs are maliciously manipulated and cause dramatic shifts to the outputs. In this paper, we focus on adversarial attacks in image classifiers built with deep neural networks and propose a model-agnostic approach to detect adversarial inputs. We argue that the logit semantics of adversarial inputs follow a different evolution with respect to original inputs, and construct a logits-based embedding of features for effective representation learning. We train an LSTM network to further analyze the sequence of logitsbased features to detect adversarial examples. Experimental results on the MNIST, CIFAR-10, and CIFAR-100 datasets show that our method achieves state-of-the-art accuracy for detecting adversarial examples and has strong generalizability.
Background Sufficient reference standards of drug metabolites are required in the drug discovery and development process. However, such drug standards are often expensive or not commercially available. Chemical synthesis of drug metabolite is often difficulty due to the highly regio- and stereo-chemically demanding. The present work aims to construct stable and efficient biocatalysts for the generation of drug metabolites in vitro. Result In this work, using benzydamine as a model drug, two easy-to-perform approaches (whole cell catalysis and enzyme immobilization) were investigated for the synthesis of FMO3-generated drug metabolites. The whole cell catalysis was carried out by using cell suspensions of E. coli JM109 harboring FMO3 and E. coli BL21 harboring GDH (glucose dehydrogenase), giving 1.2 g/L benzydamine N -oxide within 9 h under the optimized conditions. While for another approach, two HisTrap HP columns respectively carrying His 6 -GDH and His 6 -FMO3 were connected in series used for the biocatalysis. In this case, 0.47 g/L benzydamine N -oxide was generated within 2.5 h under the optimized conditions. In addition, FMO3 immobilization at the C-terminal (membrane anchor region) significantly improved its enzymatic thermostability by more than 10 times. Moreover, the high efficiency of these two biocatalytic approaches was also confirmed by the N -oxidation of tamoxifen. Conclusions The results presented in this work provides new possibilities for the drug-metabolizing enzymes-mediated biocatalysis. Electronic supplementary material The online version of this article (10.1186/s12934-019-1189-7) contains supplementary material, which is available to authorized users.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.