Cardiotoxicity is a critical issue in drug development that poses serious health risks, including potentially fatal arrhythmias. The human ether-à-go-go related gene (hERG) potassium channel, as one of the primary targets of cardiotoxicity, has garnered widespread attention. Traditional cardiotoxicity testing methods are expensive and time-consuming, making computational virtual screening a suitable alternative. In this study, we employed machine learning techniques utilizing molecular fingerprints and descriptors to predict the cardiotoxicity of compounds, with the aim of improving prediction accuracy and efficiency. We used four types of molecular fingerprints and descriptors combined with machine learning and deep learning algorithms, including Gaussian naive Bayes (NB), random forest (RF), support vector machine (SVM), K-nearest neighbors (KNN), eXtreme gradient boosting (XGBoost), and Transformer models, to build predictive models. Our models demonstrated advanced predictive performance. The best machine learning model, XGBoost Morgan, achieved an accuracy (ACC) value of 0.84, and the deep learning model, Transformer_Morgan, achieved the best ACC value of 0.85, showing a high ability to distinguish between toxic and non-toxic compounds. On an external independent validation set, it achieved the best area under the curve (AUC) value of 0.93, surpassing ADMETlab3.0, Cardpred, and CardioDPi. In addition, we explored the integration of molecular descriptors and fingerprints to enhance model performance and found that ensemble methods, such as voting and stacking, provided slight improvements in model stability. Furthermore, the SHapley Additive exPlanations (SHAP) explanations revealed the relationship between benzene rings, fluorine-containing groups, NH groups, oxygen in ether groups, and cardiotoxicity, highlighting the importance of these features. This study not only improved the predictive accuracy of cardiotoxicity models but also promoted a more reliable and scientifically interpretable method for drug safety assessment. Using computational methods, this study facilitates a more efficient drug development process, reduces costs, and improves the safety of new drug candidates, ultimately benefiting medical and public health.

OBJECTIVE To investigate t he attitude of endocrinology physicians to clinical conversion and substitution of insulin drugs ，and to provide basis for improving the centralized procurement program of insulin. METHODS The proportion of convertible and substitutable insulin recognized by endocrinology physicians was investigated by questionnaire from 4 dimensions： intergenerational level ，bargaining group level ，common name level and brand/specification level. The subjects were endocrinology physicians in the third grade class A general hospitals in Nanchang. RESULTS A total of 89 questionnaires were successfully distributed，accounting for 80.2％ of the on-the-job endocrinology physicians （111 in total ）in the third grade class A general hospitals in Nanchang. Eighty-nine questionnaires were collected ，one of which was invalid ，and the effective rate was 98.9％. At the intergenerational level ，93.2％ of endocrinology physicians preferred insulin analogues. At the bargaining group level ，the weighted average of the convertible ratio between group 3 and group 4 approved by physicians was 63.9％. At the levels of common name and brand/specification ，the weighted averages of convertible proportion of each group were more than 70％. CONCLUSIONS The method of insulin grouping in Wuhan is reasonable which can complete clinical conversion and substitution of insulin in the group safely. It is suggested to cancel long-acting human insulin group. The weighted average of the proportion of convertible and substitutable drugs in the group is high. It is suggested to increase the agreed purchase volume of insulin and conduct“volume price linked ”negotiations. When the surveyed physicians choose the initial treatment scheme of insulin ，they pay more attention to the factors such as efficacy and safety ，so the replacement of insulin should be based on the clinical efficacy and drug safety.