VEntNet: Hybrid deep convolutional neural network model for automated multi-class categorization of chest X-rays

Visual interpretation of chest X-rays (CXRs) is tedious and prone to error. Significant amount of time is spent by the radiologist in differentiating normal from abnormal CXRs and in identifying the location and type of abnormalities. An assistance tool for automatically classifying normal and different types of abnormal CXRs can facilitate the diagnosis and potentially save time costs. In this paper, a novel hybrid model having concatenation of Visual Geometry Group (VGG19) network and Entropy features as a modified deep convolutional neural network (DCNN) architecture, called VEntNet, is proposed for the automated multi-class categorization of CXR images into normal, coronavirus disease (COVID), tuberculosis (TB), viral pneumonia, and bacterial pneumonia. The VEntNet model implemented consists of deep features extraction from convolutional layers of VGG19 network which are then concatenated with hand-crafted entropy features extracted from CXRs. The concatenated features are then fed to the fully connected (FC) layers for performing multi-class categorization using Softmax activation function. The performance of proposed VEntNet model is compared with other DCNNs with and without the hybrid approach for categorization of closely related lung pathologies and normal CXR images. Our proposed VEntNet achieved accuracies of 98.78% and 90.96%, respectively, for four and five-class classification of CXRs. Thus, it is demonstrated that among the different DCNNs, our VEntNet outperformed in four-class CXR categorization tasks. The proposed model can potentially save time by facilitating the screening of CXRs to identify those with abnormalities present as well as to categorize the abnormalities. © 2022 Wiley Periodicals LLC.

Targeting Natural Products for the Treatment of COVID-19 - An Updated Review.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is an ongoing, rapidly spreading pandemic caused by Severe Acute Respiratory Syndrome Coronavirus2 (SARS-CoV2). Among all the infected countries around the globe as of now (June 15, 2020), the total confirmed positive cases reported are 7,805,148, with the death of 431,192. At present, no specialized treatments evolved to cure COVID-19. Its treatment is symptomatic. Though huge efforts are being made to produce potential therapies to scuffle COVID-19, no drug has been discovered so far. OBJECTIVE: Natural products have been playing a significant role in disease control since ancient days. These products serve as templates for designing new anti-microbial agents with a different mechanism of action and also open a door for investigation of effective anti-viral drugs to combat COVID-19. By focusing on this, the authors have narrated the basic structure, infection, and pathogenesis of SARS-CoV2 virus in humans and also reported various natural products or plant-based extracts/bioactive compounds tested against coronaviruses like SARS and MERS, as these viruses are structurally similar to SARS-CoV2 and can be used in designing novel drug against this virus. CONCLUSION: The natural products having the potential to combat SARS, MERS, and other viruses reviewed in this review article might have anti-viral activities against the SARS-CoV2 virus and can be used directly for further preclinical studies. Therefore, all efforts should be focused on overcoming this serious problem to save many people's lives all over the world.

Molecular screening of antimalarial, antiviral, anti-inflammatory and HIV protease inhibitors against spike glycoprotein of coronavirus.

Coronavirus outbreak in December 2019 (COVID-19) is an emerging viral disease that poses major menace to Humans and it's a crucial need to find the possible treatment strategies. Spike protein (S2), a envelop glycoprotein aids viral entry into the host cells that corresponds to immunogenic ACE2 receptor binding and represents a potential antiviral drug target. Several drugs such as antimalarial, antibiotic, anti-inflammatory and HIV-protease inhibitors are currently undergoing treatment as clinical studies to test the efficacy and safety of COVID-19. Some promising results have been observed with the patients and also with high mortality rate. Hence, there is a need to screen the best CoV inhibitors using insilico analysis. The Molecular methodologies applied in the present study are, Molecular docking, virtual screening, drug-like and ADMET prediction helps to target CoV inhibitors. The results were screened based on docking score, H-bonds, and amino acid interactions. The results shows HIV-protease inhibitors such as cobicistat (-8.3kcal/mol), Darunavir (-7.4kcal/mol), Lopinavir (-9.1kcal/mol) and Ritonavir (-8.0 kcal/mol), anti-inflammatory drugs such as Baricitinib (-5.8kcal/mol), Ruxolitinib (-6.5kcal/mol), Thalidomide (-6.5kcal/mol), antibiotic drugs such as Erythromycin(-9.0kcal/mol) and Spiramycin (-8.5kcal/mol) molecules have good affinity towards spike protein compared to antimalarial drugs Chloroquine (-6.2kcal/mol), Hydroxychloroquine (-5.2kcal/mol) and Artemisinin (-6.8kcal/mol) have poor affinity to spike protein. The insilico pharmacological evaluation shows that these molecules exhibit good affinity of drug-like and ADMET properties. Hence, we propose that HIVprotease, anti-inflammatory and antibiotic inhibitors are the potential lead drug molecules for spike protein and preclinical studies needed to confirm the promising therapeutic ability against COVID-19.