Search

[Display omitted] • The QSAR model for the inhibitors of SARS-CoV-2 Nsp14 was built for the first time. • Mechanistic analysis identified the main influencing factors for Nsp14 inhibition. • The best model was used for virtual screening of 262 untested compounds. • Docking and ADMET predictions identified two hit candidates as Nsp14 inhibitors. • The developed QSAR model can avoid unnecessary chemical synthesis and test. Corona Virus Disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), poses a serious threat to human health and life safety. How to effectively prevent and treat COVID-19 is crucial. In this study, we used the inhibitors of nonstructural protein Nsp14 of SARS-CoV-2 to perform the quantitative structure activity relationship (QSAR) modelling for the first time. Based on different dataset division strategies, we selected partial least square (PLS) and multiple linear regression (MLR) methods to develop easily interpretable and reproducible QSAR models with 2D molecular descriptors. All models complied with the strict QSAR validation principles of OECD and internationally recognized validation metrics. The best model contained two molecular descriptors with the following statistical parameters: R 2 = 0.7796, Q LOO 2 = 0.7373, R test 2 = 0.8539 and CCC test = 0.9073. Obviously, the model exhibited good prediction performance and can be used for quickly predicting the inhibitory activity of unknown compounds against Nsp14. Mechanistic interpretation identified the detailed relationship between molecular structure information and inhibitory activity. The best QSAR model was used to predict the inhibitory activity of 263 true external compounds without experimental values against Nsp14, and the prediction reliability was analyzed and discussed. Molecular docking and ADMET analyses were conducted for compounds with higher similarity to the modelling compounds. Finally, two compounds were identified as potential candidate drugs of targeting Nsp14. The current work lays a solid theoretical foundation for the discovery of inhibitors targeting Nsp14, and has an important reference significance for the development of anti-COVID-19 drugs. [ABSTRACT FROM AUTHOR]

Nitroaromatic compounds (NACs) are an important type of environmental organic pollutants. However, it is lack of sufficient information relating to their potential adverse effects on human health and the environment due to the limited resources. Thus, using in silico technologies to assess their potential hazardous effects is urgent and promising. In this study, quantitative structure activity relationship (QSAR) and classification models were constructed using a set of NACs based on their mutagenicity against Salmonella typhimurium TA100 strain. For QSAR studies, DRAGON descriptors together with quantum chemistry descriptors were calculated for characterizing the detailed molecular information. Based on genetic algorithm (GA) and multiple linear regression (MLR) analyses, we screened descriptors and developed QSAR models. For classification studies, seven machine learning methods along with six molecular fingerprints were applied to develop qualitative classification models. The goodness of fitting, reliability, robustness and predictive performance of all developed models were measured by rigorous statistical validation criteria, then the best QSAR and classification models were chosen. Moreover, the QSAR models with quantum chemistry descriptors were compared to that without quantum chemistry descriptors and previously reported models. Notably, we also obtained some specific molecular properties or privileged substructures responsible for the high mutagenicity of NACs. Overall, the developed QSAR and classification models can be utilized as potential tools for rapidly predicting the mutagenicity of new or untested NACs for environmental hazard assessment and regulatory purposes, and may provide insights into the in vivo toxicity mechanisms of NACs and related compounds. Image 1 • An excellent QSAR model was developed for the mutagenicity of nitroaromatics. • Classification models were built to classify the high mutagenic nitroaromatics. • Specific molecular properties related to the high mutagenicity were obtained. • Privileged substructures provide better explanations for the high mutagenicity. • Our models can be used to rapidly predict the mutagenicity for hazard assessment. [ABSTRACT FROM AUTHOR]