No abstract

The world currently is going through a serious pandemic due to the coronavirus disease (COVID-19). In this study, we investigate the gene structure similarity of coronavirus genomes isolated from COVID-19 patients, Severe Acute Respiratory Syndrome (SARS) patients and bats genes. We also explore the extent of similarity between their genome structures to find if the new coronavirus is similar to either of the other genome structures. Our experimental results show that there is 82.42% similarity between the CoV-2 genome structure and the bat genome structure. Moreover, we have used a bidirectional Gated Recurrent Unit (GRU) model as the deep learning technique and an improved variant of Recurrent Neural networks (i.e., Bidirectional Long Short Term Memory model) to classify the protein families of these genomes to isolate the prominent protein family accession. The accuracy of Gated Recurrent Unit (GRU) is 98% for labeled protein sequences against the protein families. By comparing the performance of the Gated Recurrent Unit (GRU) model with the Bidirectional Long Short Term Memory (Bi-LSTM) model results, we found that the GRU model is 1.6% more accurate than the Bi-LSTM model for our multiclass protein classification problem. Our experimental results would be further support medical research purposes in targeting the protein family similarity to better understand the coronavirus genomic structure.

Crowdfunding platforms, such as the Patreon platform, are a means of regular financial support to entrepreneurs and artists who create independent content in the form of images, videos, podcasts, comics, games, or any media that supporters enjoy. Entrepreneurs leverage their potential base of patrons by using various social media platforms. Even though this collaboration has proved to be a practical approach to raising funds, it is difficult to predict the success rates of new projects. In this paper, we consider Patreon as the membership-based platform and our empirical analysis shows that half of proposed projects turn out to be successful. In this research, we build a data analytics approach to predict the rate of success of Patreon projects based on a dataset containing details of various features and historical information about previous projects. We employed a family of supervised classifiers that includes Naïve Bayes, Logistic Regression, Random Forest, and Boosting algorithms to predict the success of a given project. Currently, the Gradient Boosting classifier has achieved an average accuracy of more than 74%. Such results could help creators to define a path to better promote their content and improve monthly pledges.