FB2001 for COVID-19

This article systematically presents the current clinically significant therapeutic developments for the treatment of COVID-19 by providing an in-depth review of molecular mechanisms of action for SARS-CoV-2 antivirals and critically analyzing the potential targets that may allow the selection of resistant viral variants. Two main categories of agents can display antiviral activity: direct-acting antivirals, which act by inhibiting viral enzymes, and host-directed antivirals, which target host cell factors that are involved in steps of the viral life cycle. We discuss both these types of antivirals, highlighting the agents that have already been approved for treatment of COVID-19, and providing an overview of the main molecules that are currently in drug development. Direct-acting antivirals target viral enzymes that are essential in the viral life cycle. Three direct-acting antivirals are currently in use: two are nucleoside analogs that inhibit the RNA-dependent RNA polymerase of SARS-CoV-2, i.e., remdesivir and molnupiravir, and the third one, nirmatrelvir/ritonavir, is an inhibitor of SARS-CoV-2 main protease. The potential for induction of viral resistance is discussed for each of these antivirals, along with their clinical activity on each of the SARS-CoV-2 variants and sublineages that have been dominant over the course of the pandemic, i.e., Alpha, Delta, as well as Omicron and its sublineages BA.1, BA.2, BA.5, BQ.1 and XBB. Host-directed antivirals are currently in preclinical or clinical development; these agents target host cell enzymes that are involved in facilitating viral entry, replication, or virion release. By blocking these enzymes, viral replication can theoretically be effectively stopped. As no SARS-CoV-2 host-directed antiviral has been approved so far, further research is still needed and we present the host-directed antivirals that are currently in the pipeline. Another specific type of agents that have been used in the treatment of COVID-19 are neutralizing antibodies (NAbs). Their main binding site is the spike protein, and therefore their neutralization activity is influenced by mutations occurring in this region. We discuss the main changes in neutralization activity of NAbs for the most important dominant SARS-CoV-2 variants. Close monitoring of emerging variants and sublineages is still warranted, to better understand the impact of viral mutations on the clinical efficiency of antivirals and neutralizing antibodies developed for the treatment of COVID-19.

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.