In silico prediction of potential drug-induced nephrotoxicity with machine learning methods

In recent years, drug-induced nephrotoxicity has been one of the main reasons for the failure of drug development. Early prediction of the nephrotoxicity for drug candidates is critical to the success of clinical trials. Therefore, it is very important to construct an effective model that can predict the potential nephrotoxicity of compounds. Machine learning methods have been widely used to predict the physicochemical properties, biological activities, and safety assessment of compounds. In this study, we manually collected 777 valid drug data and constructed a total of 72 classification models using nine types of molecular fingerprints combined with different machine learning algorithms. From experimental literature and the US FDA Drugs Database, some marketed drugs were screened for external validation of the models. Finally, three models exhibited good performance in the prediction of nephrotoxicity of both chemical drugs and Chinese herbal medicines. The best model was the support vector machine algorithm combined with CDK graph only fingerprint. Furthermore, the applicability domain of the models was analyzed according to the OECD principles, and we also used the SARpy and information gain methods to find eight substructures that might cause nephrotoxicity, so as to attract attention in the future drug discovery.