Cobicistat for COVID-19

According to the World Health Organization (WHO), in the second half of 2022, there are about 606 million confirmed cases of COVID-19 and almost 6,500,000 deaths around the world. A pandemic was declared by the WHO in March 2020 when the new coronavirus spread around the world. The short time between the first cases in Wuhan and the declaration of a pandemic initiated the search for ways to stop the spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) or to attempt to cure the disease COVID-19. More than ever, research groups are developing vaccines, drugs, and immunobiological compounds, and they are even trying to repurpose drugs in an increasing number of clinical trials. There are great expectations regarding the vaccine’s effectiveness for the prevention of COVID-19. However, producing sufficient doses of vaccines for the entire population and SARS-CoV-2 variants are challenges for pharmaceutical industries. On the contrary, efforts have been made to create different vaccines with different approaches so that they can be used by the entire population. Here, we summarize about 8162 clinical trials, showing a greater number of drug clinical trials in Europe and the United States and less clinical trials in low-income countries. Promising results about the use of new drugs and drug repositioning, monoclonal antibodies, convalescent plasma, and mesenchymal stem cells to control viral infection/replication or the hyper-inflammatory response to the new coronavirus bring hope to treat the disease.

Abstract Due to the lack of a method to efficiently represent the multimodal information of a protein, including its structure and sequence information, predicting compound-protein binding affinity (CPA) still suffers from low accuracy when applying machine-learning methods. To overcome this limitation, in a novel end-to-end architecture (named FeatNN), we develop a coevolutionary strategy to jointly represent the structure and sequence features of proteins and ultimately optimize the mathematical models for predicting CPA. Furthermore, from the perspective of data-driven approach, we proposed a rational method that can utilize both high- and low-quality databases to optimize the accuracy and generalization ability of FeatNN in CPA prediction tasks. Notably, we visually interpret the feature interaction process between sequence and structure in the rationally designed architecture. As a result, FeatNN considerably outperforms the state-of-the-art (SOTA) baseline in virtual drug evaluation tasks, indicating the feasibility of this approach for practical use. FeatNN provides an outstanding method for higher CPA prediction accuracy and better generalization ability by efficiently representing multimodal information of proteins via a coevolutionary strategy.