Predicting hERG channel blockers with directed message passing neural networks

Compounds with human ether-a-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present study, the directed message passing neural network (D-MPNN) was applied to construct classification models for identifying hERG blockers based on diverse datasets. Several descriptors and fingerprints were tested along with the D-MPNN model. Among all these combinations, D-MPNN with the moe206 descriptors generated from MOE (D-MPNN + moe206) showed significantly improved performances. The AUC-ROC values of the D-MPNN + moe206 model reached 0.956 +/- 0.005 under random split and 0.922 +/- 0.015 under scaffold split on Cai's hERG dataset, respectively. Moreover, the comparisons between our models and several recently reported machine learning models were made based on various datasets. Our results indicated that the D-MPNN + moe206 model is among the best classification models. Overall, the excellent performance of the DMPNN + moe206 model achieved in this study highlights its potential application in the discovery of novel and effective hERG blockers.

Automated summary

In this study, a classification model for identifying hERG blockers was developed using the D-MPNN model based on diverse datasets, and the D-MPNN + moe206 model showed significantly improved performance. Our results indicated that the D-MPNN + moe206 model is among the best classification models and has potential applications in the discovery of novel and effective hERG blockers.