This paper applies deep convolutional neural network (CNN) to identify tomato leaf disease by transfer learning. AlexNet, GoogLeNet, and ResNet were used as backbone of the CNN. The best combined model was utilized to change the structure, aiming at exploring the performance of full training and fine-tuning of CNN. The highest accuracy of 97.28% for identifying tomato leaf disease is achieved by the optimal model ResNet with stochastic gradient descent (SGD), the number of batch size of 16, the number of iterations of 4992, and the training layers from the 37 layer to the fully connected layer (denote as “fc”). The experimental results show that the proposed technique is effective in identifying tomato leaf disease and could be generalized to identify other plant diseases.
Summary Biotransformation of arsenic includes oxidation, reduction, methylation and conversion to more complex organic arsenicals. Members of the class of arsenite [As(III)] S-adenosylmethyltransferase enzymes catalyze As(III) methylation to a variety of mono-, di- and trimethylated species, some of which are less toxic than As(III) itself. However, no methyltransferase gene has been identified in plants. Here, an arsM gene from the soil bacterium Rhodopseudomonas palustris was expressed in Japonica rice (Oryza sativa L.) cultivar Nipponbare, and the transgenic rice produced methylated arsenic species, which were measured by inductively coupled plasma mass spectrometry (ICP-MS) and high performance liquid chromatography-inductively coupled plasma-mass spectrometry (HPLC-ICP-MS). Both monomethylarsenate [MAs(V)] and dimethylarsenate [DMAs(V)] were detected in the root and shoot of transgenic rice. After 12-d exposure to As(III), the transgenic rice gave off 10-fold more volatile arsenicals. The present study demonstrates that expression of an arsM gene in rice induces arsenic methylation and volatilization, providing a potential stratagem for phytoremediation theoretically.
BackgroundZFP580 is a novel C2H2 type zinc-finger transcription factor recently identified by our laboratory. We previously showed that ZFP580 may be involved in cell survival and growth. The aim of this study was to elucidate whether ZFP580 is involved in the cardioprotective effects of intermittent high-altitude (IHA) hypoxia against myocardial ischemia-reperfusion (I/R) injury.Methods and ResultsAfter rats were subjected to myocardial ischemia for 30 min followed by reperfusion, ZFP580 expression in the left ventricle was measured. ZFP580 protein expression was found to be up-regulated within 1 h and decreased at 2 h after reperfusion. Comparing normoxic and IHA hypoxia-adapted rats (5000 m, 6 h day−1, 6 weeks) following I/R injury (30 min ischemia and 2 h reperfusion), we found that adaptation to IHA hypoxia attenuated infarct size and plasma leakage of lactate dehydrogenase and creatine kinase-MB. In addition, ZFP580 expression in the myocardium was up-regulated by IHA hypoxia. Consistent with this result, ZFP580 expression was found to be significantly increased in cultured H9c2 myocardial cells in the hypoxic preconditioning group compared with those in the control group following simulated I/R injury (3 h simulated ischemic hypoxia and 2 h reoxygenation). To determine the role of ZFP580 in apoptosis, lentivirus-mediated gene transfection was performed in H9c2 cells 72 h prior to simulated I/R exposure. The results showed that ZFP580 overexpression significantly inhibited I/R-induced apoptosis and caspase-3 activation. H9c2 cells were pretreated with or without PD98059, an inhibitor of ERK1/2 phosphorylation, and Western blot results showed that PD98059 (10 µM) markedly suppressed I/R-induced up-regulation of ZFP580 expression.ConclusionsOur findings demonstrate that the cardioprotective effect of IHA hypoxia against I/R injury is mediated via ZFP580, a downstream target of ERK1/2 signaling with anti-apoptotic roles in myocardial cells.
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.