Detecting SARS-CoV-2 From Chest X-Ray Using Artificial Intelligence.

Chest radiographs (X-rays) combined with Deep Convolutional Neural Network (CNN) methods have been demonstrated to detect and diagnose the onset of COVID-19, the disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). However, questions remain regarding the accuracy of those methods as they are often challenged by limited datasets, performance legitimacy on imbalanced data, and have their results typically reported without proper confidence intervals. Considering the opportunity to address these issues, in this study, we propose and test six modified deep learning models, including VGG16, InceptionResNetV2, ResNet50, MobileNetV2, ResNet101, and VGG19 to detect SARS-CoV-2 infection from chest X-ray images. Results are evaluated in terms of accuracy, precision, recall, and f- score using a small and balanced dataset (Study One), and a larger and imbalanced dataset (Study Two). With 95% confidence interval, VGG16 and MobileNetV2 show that, on both datasets, the model could identify patients with COVID-19 symptoms with an accuracy of up to 100%. We also present a pilot test of VGG16 models on a multi-class dataset, showing promising results by achieving 91% accuracy in detecting COVID-19, normal, and Pneumonia patients. Furthermore, we demonstrated that poorly performing models in Study One (ResNet50 and ResNet101) had their accuracy rise from 70% to 93% once trained with the comparatively larger dataset of Study Two. Still, models like InceptionResNetV2 and VGG19's demonstrated an accuracy of 97% on both datasets, which posits the effectiveness of our proposed methods, ultimately presenting a reasonable and accessible alternative to identify patients with COVID-19.

Mapping the Mitochondrial Regulation of Epigenetic Modifications in Association With Carcinogenic and Noncarcinogenic Polycyclic Aromatic Hydrocarbon Exposure.

Polycyclic aromatic hydrocarbons (PAHs) refer to a ubiquitous group of anthropogenic air pollutants that are generated through incomplete carbon combustion. Although the immunotoxic nature of PAHs has been previously reported, the underlying molecular mechanisms of this effect are not fully understood. In the present study, we investigated the mitochondrial-mediated epigenetic regulation of 2 PAHs, carcinogenic (benzo[a]pyrene; BaP) and noncarcinogenic (anthracene [ANT]), in peripheral lymphocytes. While ANT exposure triggered mitochondrial oxidative damage, no appreciable epigenetic modifications were observed. On the other hand, exposure to BaP perturbed the mitochondrial redox machinery and initiated cascade of epigenetic modifications. Cells exposed to BaP showed prominent changes in the expression of mitochondrial microRNAs (miR-24, miR-34a, miR-150, and miR-155) and their respective gene targets (NF-κß, MYC, and p53). The exposure of BaP also caused significant alterations in the expression of epigenetic modifiers (DNMT1, HDAC1, HDAC7, KDM3a, EZH2, and P300) and hypomethylation within nuclear and mitochondrial DNA. This further induced methylation of histone tails, which play a crucial role in the regulation of chromatin structure. Overall, our study provides novel mechanistic insights into the mitochondrial regulation of epigenetic modifications in association with PAH-induced immunotoxicity.

Exposure to ultrafine particulate matter induces NF-κß mediated epigenetic modifications.

Exposure to ultrafine particulate matter (PM0.1) is positively associated with the etiology of different acute and chronic disorders; however, the in-depth biological imprints that link these submicron particles with the disturbances in the epigenomic machinery are not well defined. Earlier, we showed that exposure to these particles causes significant disturbances in the mitochondrial machinery and triggers PI-3-kinase mediated DNA damage responses. In the present study, we aimed to further understand the epigenomic insights of the ultrafine PM exposure. The higher levels of intracellular reactive oxygen species and depleted Nrf-2 in ultrafine PM exposed cells reconfirmed its potential to induce oxidative stress. Importantly, the observed increase in the levels of NF-κß and associated cytokines among exposed cells suggested the activation of NF-κß mediated inflammatory loop which potentially serves as a platform for initiating epigenetic insinuations. This fact was strongly supported by the altered miRNA expression profile of the ultrafine PM exposed cells. These NF-κß induced miRNA alterations were also found to be associated with other epigenetic targets as the exposed cells showed higher expression levels of DNA methyltransferases which positively corresponded with the global changes in DNA methylation levels. Upon further analysis, significant alterations in histone code were also reported in ultrafine PM exposed cells. Conclusively our results suggested that NF-κß acts as an inflammatory switch that possesses the potential to induce genome-wide epigenetic modification upon ultrafine PM exposure.

Evaluation of promising algal strains for sustainable exploitation coupled with CO2 fixation.

The photosynthetic activity of three microalgae, Chlamydomonas reinhardtii, Chlorella AU1, Scenedesmus AU1, and six cyanobacteria, Spirulina platensis, Anabaena cylindrica, Oscillatoria AU1, Nostoc muscurum, Synechococcus AU1, Synechocystis sp. PCC6803, was investigated. Strains S. platensis, Scenedesmus AU1 sp. and Chlorella AU1 sp. showed the highest fluorescence quenching than other strains tested. Thus, these were selected for CO2 mitigation analysis in a designed tubular photobioreactor system at 0.06%, 6%, 12%, 18% and 24% CO2 concentrations. Spirulina showed maximum biomass productivity of 1.03 g L(-1) d(-1) with the highest CO2 fixation rate of 0.678 g [Formula: see text] L(-1) d(-1) at 6% CO2 concentration. The maximum protein content (66.63%) was also achieved in Spirulina sp. at 6% CO2 concentration. Thus, Spirulina could be utilized as a source of protein supplement coupled with CO2 fixation. Maximum carbohydrate proportion (51.71%) was noted with Scenedesmus AU1 sp. at 12% CO2. Scenedesmus AU1 sp. also accumulated the maximum lipid content (25.07%) at 6% CO2 concentration, which was further analysed for biodiesel production. The extracted Scenedesmus oil was mainly rich in short chain fatty acids (C-16 : 0, C-18:1, C-18:2, C-18:3) which is an ideal combination for efficient biodiesel. Thus, this is vital in helping to choose Scenedesmus as a biodiesel feedstock, coupled with CO2 fixation.