Network Modeling and Analysis in Health Informatics and Bioinformatics最新文献

The transmittable spread of viral coronavirus (SARS-CoV-2) has resulted in a significant rise in global mortality. Due to lack of effective treatment, our aim is to generate a highly potent active molecule that can bind with the protein structure of SARS-CoV-2. Different machine learning and deep learning approaches have been proposed for molecule generation; however, most of these approaches represent the drug molecule and protein structure in 1D sequence, ignoring the fact that molecules are by nature in 3D structure, and because of this many critical properties are lost. In this work, a framework is proposed that takes account of both tertiary and sequential representations of molecules and proteins using Gated Graph Neural Network (GGNN), Knowledge graph, and Early Fusion approach. The generated molecules from GGNN are screened using Knowledge Graph to reduce the search space by discarding the non-binding molecules before being fed into the Early Fusion model. Further, the binding affinity score of the generated molecule is predicted using the early fusion approach. Experimental result shows that our framework generates valid and unique molecules with high accuracy while preserving the chemical properties. The use of a knowledge graph claims that the entire generated dataset of molecules was reduced by roughly 96% while retaining more than 85% of good binding desirable molecules and the rejection of more than 99% of fruitless molecules. Additionally, the framework was tested with two of the SARS-CoV-2 viral proteins: RNA-dependent-RNA polymerase (RdRp) and 3C-like protease (3CLpro).

In this study, the characteristics of the Covid-19 pandemic in Turkey are examined in terms of the number of cases and deaths, and a characteristic prediction is made with an approach that employs artificial intelligence. The number of cases and deaths are estimated using the number of tests, the numbers of seriously ill and recovered patients as parameters. The machine learning methods used are linear regression, polynomial regression, support vector regression with different kernel functions, decision tree and artificial neural networks. The obtained results are compared by calculating the coefficient of determination (R ²), and the mean absolute percentage error (MAPE) values. When R ² and MAPE values are compared, it is seen that the optimal results for cases in Turkey are obtained with the decision tree, for deaths with polynomial regression method. The results reached for the United States of America and Russia are similar and the optimal results are obtained by polynomial regression. However, while the optimal results are obtained by neural networks in the Indian data, linear regression for the cases in the Brazilian data, neural network for the deaths, decision tree for the cases in France, polynomial regression for the deaths, neural network for the cases in the UK data and decision tree for the deaths are the methods that produced the optimal results. These results also give an idea about the similarities and differences of country characteristics.

Spike glycoprotein of SARS-CoV-2 is mainly responsible for the recognition and membrane fusion within the host and this protein has an ability to mutate. Hence, T cell and B cell epitopes were derived from the spike glycoprotein sequence of wild SARS-CoV-2. The proposed T cell and B cell epitopes were found to be antigenic and conserved in the sequence of SARS-CoV-2 mutant (B.1.1.7). Thus, the proposed epitopes are effective against SARS-CoV-2 and its B.1.1.7 mutant. MHC-I that best interacts with the proposed T cell epitopes were found, using immune epitope database. Molecular docking and molecular dynamic simulations were done for ensuring a good binding between the proposed MHC-I and T cell epitopes. The finally proposed T cell epitope was found to be antigenic, non-allergenic, non-toxic and stable. Further, the finally proposed B cell epitopes were also found to be antigenic. The population conservation analysis has ensured the presence of MHC-I molecule (respective to the finally proposed T cell) in human population of most affected countries with SARS-CoV-2. Thus the proposed T and B cell epitope could be effective in designing an epitope-based vaccine, which is effective on SARS-CoV-2 and its B.1.1.7mutant.

Supplementary information: The online version contains supplementary material available at 10.1007/s13721-021-00348-w.

Orthohantavirus, a zoonotic virus responsible for causing human cardio-pulmonary disease, is proven to be a fatal disease. Due to the paucity of regimens to cure the disease and efficient management to eradicate this deadly virus, there is a constant need to expand in-silico approaches belonging to immunology domain to formulate best feasible peptide-based vaccine against it. In lieu of that, we have predicted and validated an epitope of nine-residue-long sequence "MIGLLSSRI". The predicted epitope has shown best interactions with HLA alleles of MHC Class II proteins, namely HLA DRB1_0101, DRB1_0401, DRB1_0405, DRB1_0701, DRB1_0901, DRB1_1302, and DRB1_1501. The structure of the epitope was modeled by deploying PEPFOLD 3.5 and verified by Ramachandran plot analysis. Molecular docking and simulation studies reveal that this epitope has satisfactory binding scores, ACE value and global energies for docked complexes along with selectable range of RMSD and RMSF values. Also, the predicted epitope "MIGLLSSRI" exhibits population coverage of more than 62% in world population and maximum of 70% in the United States of America. In this intensive study, we have used many tools like AllergenFP, NETMHCII 3.2, VaxiJen, ToxinPred, PEPFOLD 3.5, DINC, IEDB-Population coverage, MHCPred and JCat server. Most of these tools are based on modern innovative statistical algorithms like HMM, ANN, ML, etc. that help in better predictions of putative candidates for vaccine crafting. This innovative methodology is facile, cost-effective and time-efficient, which could facilitate designing of a vaccine against this virus.

Novel coronavirus is a disease that can propagate easily with very minute carelessness and with very little physical contact between people. Presently, the world's central health institution called the World Health Organization has approved and advised the Reverse Transcription-Polymerase Chain Reaction (RT-PCR) swab test as the most important and effective diagnostic method to confirm if a patient has COVID-19 symptoms or not. This test takes at least a day for revealing the results, depending on the feasible resources in the neighborhood. Moreover, the RT-PCR test gives sometimes false positive results and slow in the process. To keep the potential virus carriers and potential causes of the disease quarantined as early as possible, there is still a requirement for a much faster and more accurate diagnostic process to supplement RT-PCR test of finding the patients affected by the virus. In this regard, radiological images such as X-ray and CT (Computerized Tomography) scan are found to be useful. The X-ray and CT scan have good screening modality; they are quick at capturing and finding and widely available around the world. Therefore, a deep learning model, which makes use of CT scan and X-ray images, has been proposed to automate and analyze the diagnostic process by utilizing Convolutional Neural Network (CNN). This model makes use of InceptionV3 deep learning model, a type of CNN. It is a lightweight deep learning model that is apt for mobile, laptop, and tablet platforms. The proposed model requires low memory space and gives an accuracy of about 96%, sensitivity of 93.48% for CXRs (Chest X-rays) and accuracy of 93%, sensitivity of 89.81 % for the CT scan images respectively. The proposed model is also compared with other deep learning models like VGG 16 (Visual Geometry Group), ResNet50V2 (Residual Network) and other existing deep learning models and it is found to be better in terms of accuracy and other performance parameters. Further, a web application has been developed from the proposed model. The web application is able to detect COVID-19 cases from the CT scan and X-ray images with significant accuracy.

We investigate transmission dynamics for SARS-CoV-2 on a real network of classes at Simon Fraser University. Outbreaks are simulated over the course of one semester across numerous parameter settings, including moving classes above certain size thresholds online. Regression trees are used to analyze the effect of disease parameters on simulation outputs. We find that an aggressive class size thresholding strategy is required to mitigate the risk of a large outbreak, and that transmission by symptomatic individuals is a key driver of outbreak size. These findings provide guidance for designing control strategies at other institutions, as well as setting priorities and allocating resources for disease monitoring.

Supplementary information: The online version contains supplementary material available at 10.1007/s13721-022-00375-1.