Hirsch Whitehead (colonyatom5)

CRISPR/Cas9 is a preferred genome editing tool and has been widely adapted to ranges of disciplines, from molecular biology to gene therapy. A key prerequisite for the success of CRISPR/Cas9 is its capacity to distinguish between single guide RNAs (sgRNAs) on target and homologous off-target sites. Thus, optimized design of sgRNAs by maximizing their on-target activity and minimizing their potential off-target mutations are crucial concerns for this system. Zasocitinib Several deep learning models have been developed for comprehensive understanding of sgRNA cleavage efficacy and specificity. Although the proposed methods yield the performance results by automatically learning a suitable representation from the input data, there is still room for the improvement of accuracy and interpretability. Here, we propose novel interpretable attention-based convolutional neural networks, namely CRISPR-ONT and CRISPR-OFFT, for the prediction of CRISPR/Cas9 sgRNA on- and off-target activities, respectively. Experimental tests on public datasets demonstrate that our models significantly yield satisfactory results in terms of accuracy and interpretability. Our findings contribute to the understanding of how RNA-guide Cas9 nucleases scan the mammalian genome. Data and source codes are available at https//github.com/Peppags/CRISPRont-CRISPRofft.Infectious disease is a great enemy of humankind. The ravages of COVID-19 are leading to profound crises across the world. There is an urgent requirement for analyzing the current pandemic situation, predicting trends over time, and assessing the effectiveness of containment measures. Thus, numerous statistical models, primarily based on the susceptible-exposed-infected-recovered or removed (SEIR) model, have been established. However, these models are highly technical, which are difficult for the public and governing bodies to understand and use. To address this issue, we developed a simple operating software based on our improved K-SEIR model termed as the kernelkernel SEIR simulator (K-SEIR-Sim). This software includes natural propagation parameters, containment measure parameters, and certain characteristic parameters that can deduce the effects of natural propagation and containment measures. Further, the applicability of the proposed software was demonstrated using the example of the COVID-19 outbreak in the United States and the city of Wuhan, China. Operating results verified the potency of the proposed software in evaluating the epidemic situation and human intervention during COVID-19. Importantly, the software can perform real-time, backward-looking, and forward-looking analysis by functioning in data-driven and model-driven ways. All of them have considerable practical values in their applications according to the actual needs of personal use. Conclusively, K-SEIR-Sim is the first simple customized operating software that is highly valuable for the global fight against COVID-19 and other infectious diseases.The SARS-CoV2 is a highly contagious pathogen that causes COVID-19 disease. It has affected millions of people globally with an average lethality of ~3%. There is an urgent need of drugs for the treatment of COVID-19. In the current studies, we have used bioinformatics techniques to screen the FDA approved drugs against nine SARS-CoV2 proteins to identify drugs for repurposing. Additionally, we analyzed if the identified molecules can also affect the human proteins whose expression in lung changed during SARS-CoV2 infection. Targeting such genes may also be a beneficial strategy to curb disease manifestation. We have identified 74 molecules that can bind to various SARS-CoV2 and human host proteins. We experimentally validated our in-silico predictions using vero E6 cells infected with SARS-CoV2 virus. Interestingly, many of our predicted molecules viz. capreomycin, celecoxib, mefloquine, montelukast, and nebivolol showed good activity (IC50) against SARS-CoV2. We hope that these stud