With air pollution having become a global concern, scientists are committed to working on its amelioration. In the field of air pollution prediction, there have been good results in experimental research so far, but few studies have integrated weather forecast information and the properties of air pollution drift. In this work, we propose a novel wind‐sensitive attention mechanism with a long short‐term memory (LSTM) neural network model to predict the air pollution ‐ PM2.5 concentrations by considering the influence of wind direction and speed on the changes of spatial–temporal PM2.5 concentrations in neighbouring areas. Preliminary predictions for PM2.5 are then made by an LSTM neural network regarding neighbouring pollution; these predictions are “paid attention to” and we finally apply an ensemble learning method based on eXtreme Gradient Boosting (XGBoost) to combine the preliminary predictions with weather forecasting to make second phase predictions of PM2.5. The experiment is conducted using PM2.5 data and weather forecast data. Our results illustrate that the proposed method is superior to other methods in predicting PM2.5 concentrations, including multi‐layer perceptron, support vector regression, LSTM neural network, and extreme gradient boosting algorithm.
BackgroundMycoplasma gallisepticum is a major poultry pathogen and causes severe economic loss to the poultry industry. In mycoplasmas lipoproteins are abundant on the membrane surface and play a critical role in interactions with the host, but tools for exploring their molecular biology are limited.ResultsIn this study we examined whether the alkaline phosphatase gene (phoA ) from Escherichia coli could be used as a reporter in mycoplasmas. The promoter region from the gene for elongation factor Tu (ltuf) and the signal and acylation sequences from the vlhA 1.1 gene, both from Mycoplasma gallisepticum , together with the coding region of phoA , were assembled in the transposon-containing plasmid pISM2062.2 (pTAP) to enable expression of alkaline phosphatase (AP) as a recombinant lipoprotein. The transposon was used to transform M. gallisepticum strain S6. As a control, a plasmid containing a similar construct, but lacking the signal and acylation sequences, was also produced (pTP) and also introduced into M. gallisepticum . Using a colorimetric substrate for detection of alkaline phosphatase activity, it was possible to detect transformed M. gallisepticum . The level of transcription of phoA in organisms transformed with pTP was lower than in those transformed with pTAP, and alkaline phosphatase was not detected by immunoblotting or enzymatic assays in pTP transformants, eventhough alkaline phosphatase expression could be readily detected by both assays in pTAP transformants. Alkaline phosphatase was shown to be located in the hydrophobic fraction of transformed mycoplasmas following Triton X-114 partitioning and in the membrane fraction after differential fractionation. Trypsin proteolysis confirmed its surface exposure. The inclusion of the VlhA lipoprotein signal sequence in pTAP enabled translocation of PhoA and acylation of the amino terminal cysteine moiety, as confirmed by the effect of treatment with globomycin and radiolabelling studies with [14 C]palmitate. PhoA could be identified by mass-spectrometry after separation by two-dimensional electrophoresis.ConclusionThis is the first study to express PhoA as a lipoprotein in mycoplasmas. The pTAP plasmid will facilitate investigations of lipoproteins and protein translocation across the cell membrane in mycoplasmas, and the ease of detection of these transformants makes this vector system suitable for the simultaneous screening and detection of cloned genes expressed as membrane proteins in mycoplasmas.
Relatively few virulence genes have been identified in pathogenic mycoplasmas, so we used signature-tagged mutagenesis to identify mutants of the avian pathogen Mycoplasma gallisepticum with a reduced capacity to persist in vivo and compared the levels of virulence of selected mutants in experimentally infected chickens. Four mutants had insertions in one of the two incomplete oppABCDF operons, and a further three had insertions in distinct hypothetical genes, two containing peptidase motifs and one containing a member of a gene family. The three hypothetical gene mutants and the two with insertions in oppD 1 were used to infect chickens, and all five were shown to have a reduced capacity to induce respiratory tract lesions. One oppD 1 mutant and the MGA_1102 and MGA_1079 mutants had a greatly reduced capacity to persist in the respiratory tract and to induce systemic antibody responses against M. gallisepticum. The other oppD 1 mutant and the MGA_0588 mutant had less capacity than the wild type to persist in the respiratory tract but did elicit systemic antibody responses. Although M. gallisepticum carries two incomplete opp operons, one of which has been acquired by horizontal gene transfer, our results suggest that one of the copies of oppD may be required for full expression of virulence. We have also shown that three hypothetical genes, two of which encode putative peptidases, may be required for full expression of virulence in M. gallisepticum. None of these genes has previously been shown to influence virulence in pathogenic mycoplasmas. KEYWORDS Mycoplasma gallisepticum, oppD, virulence Mycoplasma gallisepticum is the most important mycoplasmal pathogen in poultry (1, 2) and a particularly useful model of mycoplasmal pathogenesis, in part as a typical representative of the Pneumoniae phylogenic group, which includes the important human pathogen M. pneumoniae. There have been relatively few studies attempting to identify virulence genes in mycoplasmas, in part because of the limited availability of tools for such studies. Signature-tagged mutagenesis (STM) is a useful technique for identifying genes likely to be involved in virulence, as it enables the rapid comparison of populations of mutants used to inoculate animals with those recovered from these animals during the course of infection, allowing identification of mutants with a reduced capacity to persist in experimentally infected animals (3, 4). However, the examination of only pools of mutants may result in a failure to distinguish between a mutation in a gene that is essential in vivo and a mutation in a gene that reduces the capacity of the mutant to compete with other mutants in vivo. In addition, it is not possible to fully assess the virulence of individual mutants within populations. Therefore, STM needs to be complemented with direct comparisons of isolated mutants for their capacity to infect, persist, and cause disease.
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.