Prediction of drug-likeness using graph convolutional attention network.

MOTIVATION: The drug-likeness has been widely used as a criterion to distinguish drug-like molecules from non-drugs. Developing reliable computational methods to predict the drug-likeness of compounds is crucial to triage unpromising molecules and accelerate the drug discovery process. RESULTS: In this study, a deep learning method was developed to predict the drug-likeness based on the graph convolutional attention network (D-GCAN) directly from molecular structures. Results showed that the D-GCAN model outperformed other state-of-the-art models for drug-likeness prediction. The combination of graph convolution and attention mechanism made an important contribution to the performance of the model. Specifically, the application of the attention mechanism improved accuracy by 4.0%. The utilization of graph convolution improved the accuracy by 6.1%. Results on the dataset beyond Lipinski's rule of five space and the non-US dataset showed that the model had good versatility. Then, the billion-scale GDB-13 database was used as a case study to screen SARS-CoV-2 3C-like protease inhibitors. Sixty-five drug candidates were screened out, most substructures of which are similar to these of existing oral drugs. Candidates screened from S-GDB13 have higher similarity to existing drugs and better molecular docking performance than those from the rest of GDB-13. The screening speed on S-GDB13 is significantly faster than screening directly on GDB-13. In general, D-GCAN is a promising tool to predict the drug-likeness for selecting potential candidates and accelerating drug discovery by excluding unpromising candidates and avoiding unnecessary biological and clinical testing. AVAILABILITY AND IMPLEMENTATION: The source code, model and tutorials are available at https://github.com/JinYSun/D-GCAN. The S-GDB13 database is available at https://doi.org/10.5281/zenodo.7054367. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Convalescent plasma to treat COVID-19: clinical experience and efficacy.

The recent outbreak of COVID-19 in the world is currently a big threat to global health and economy. Convalescent plasma has been confirmed effective against the novel corona virus in preliminary studies. In this paper, we first described the therapeutic schedule, antibody detection method, indications, contraindications of the convalescent plasmas and reported the effectiveness of convalescent plasma therapy by a retrospective cohort study.

Comparative analysis of the main haematological indexes and RNA detection for the diagnosis of SARS-CoV-2 infection.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has become a public health emergency of international concern. SARS-CoV-2 RNA detection is the diagnostic criterion for coronavirus disease 2019 (COVID-19). Nevertheless, RNA detection has many limitations, such as being time-consuming and cost-prohibitive, and it must be performed in specialized laboratories. Virus antibody detection is a routine method for screening for multiple viruses, but data about SARS-CoV-2 antibody detection are limited. METHOD: Throat swabs and blood were collected from 67 suspected SARS-CoV-2 infection patients at the Affiliated Hospital of Zunyi Medical University and Zunyi Fourth People's Hospital isolated observation departments. Throat swab samples were subjected to SARS-CoV-2 RNA detection by real-time PCR. Blood was used subjected to SARS-CoV-2 IgG/IgM detection by an enzyme-linked immunosorbent assay (ELISA) and gold immunochromatography assay (GICA). Blood underwent C-reactive protein detection by immunoturbidimetry, and white blood cells, neutrophil percentages and lymphocyte percentages were counted and calculated, respectively. Clinical symptoms, age and lifestyle habits (smoking and drinking) in all patients were recorded. Data were analysed using SPSS version 19. The results were confirmed by T and χ2 tests; correlations with detection results were analysed by kappa coefficients. Odds ratio (OR) and corrected OR values were analysed by logistic regression. P < 0.05 was considered statistically significant. RESULTS: Of the 67 patients included in this study, 26 were SARS-CoV-2 RNA-positive. GICA IgM sensitivity was 50.9% (13/26), and specificity was 90.2% (37/41). ELISA IgM sensitivity was 76.9% (20/26), and specificity was 90.2% (37/41). ELISA IgG sensitivity was 76.9% (20/26), and specificity was 95.1% (39/41). The kappa coefficients between RNA detection and ELISA IgG, ELISA IgM, and GICA IgM results were 0.741 (P < 0.01), 0.681 (P < 0.01) and 0.430 (P < 0.01), respectively. CONCLUSION: Among the candidate blood indicators, serum IgG and IgM detected by ELISA had the best consistency and validity when compared with standard RNA detection; these indicators can be used as potential preliminary screening tools to identify those who should undergo nucleic acid detection in laboratories without RNA detection abilities or as a supplement to RNA detection.

Potential of coronavirus 3C-like protease inhibitors for the development of new anti-SARS-CoV-2 drugs: Insights from structures of protease and inhibitors.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), similar to SARS-CoV and Middle East respiratory syndrome coronavirus (MERS-CoV), which belong to the same Betacoronavirus genus, induces severe acute respiratory disease that is a threat to human health. Since the outbreak of infection by SARS-CoV-2 began, which causes coronavirus disease 2019 (COVID-19), the disease has rapidly spread worldwide. Thus, a search for effective drugs able to inhibit SARS-CoV-2 has become a global pursuit. The 3C-like protease (3CLpro), which hydrolyses viral polyproteins to produce functional proteins, is essential for coronavirus replication and is considered an important therapeutic target for diseases caused by coronaviruses, including COVID-19. Many 3CLpro inhibitors have been proposed and some new drug candidates have achieved success in preclinical studies. In this review, we briefly describe recent developments in determining the structure of 3CLpro and its function in coronavirus replication and summarise new insights into 3CLpro inhibitors and their mechanisms of action. The clinical application prospects and limitations of 3CLpro inhibitors for COVID-19 treatment are also discussed.