In silico prediction of hERG blockers using machine learning and deep learning approaches

Abstract

The human ether‐à‐go‐go‐related gene (hERG) is associated with drug cardiotoxicity. If the hERG channel is blocked, it will lead to prolonged QT interval and cause sudden death in severe cases. Therefore, it is important to evaluate the hERG‐blocking property of compounds in early drug discovery. In this study, a dataset containing 4556 compounds with IC50 values determined by patch clamp techniques on mammalian lineage cells was collected, and hERG blockers and non‐blockers were distinguished according to three single thresholds and two binary thresholds. Four machine learning (ML) algorithms combining four molecular fingerprints and molecular descriptors as well as graph convolutional neural networks (GCNs) were used to construct a series of binary classification models. The results showed that the best models varied for different thresholds. The ML models implemented by support vector machine and random forest performed well based on Morgan fingerprints and molecular descriptors, with AUCs ranging from 0.884 to 0.950. GCN showed superior prediction performance with AUCs above 0.952, which might be related to its direct extraction of molecular features from the original input. Meanwhile, the classification of binary threshold was better than that of single threshold, which could provide us with a more accurate prediction of hERG blockers. At last, the applicability domain for the model was defined, and seven structural alerts that might generate hERG blockage were identified by information gain and substructure frequency analysis. Our work would be beneficial for identifying hERG blockers in chemicals.

In Silico Prediction of Chemical Acute Dermal Toxicity Using Explainable Machine Learning Methods

“…GCN harnesses the interconnection relationships among atoms within molecular compounds to capture vital topological information on chemical substances. By aggregating information from each atom and its neighboring atoms, GCN is adept at learning enriched compound representations, including atom environments and types of chemical bonds, thereby facilitating more precise compound classification . GCN exhibits remarkable performance and promising applications in compound classification models, offering robust support for research in drug discovery, materials science, and related fields.…”

Review of machine learning and deep learning models for toxicity prediction

“…Although 1 and 10 µm have been commonly used as the activity thresholds, there is no widely accepted threshold, and multiple threshold settings are often used to change the compositions of the training datasets. Therefore, many ML and DL models, including graph convolutional neural network (GCN) by Chen et al, 52 DNN by Cai et al, 42 hERG-Att by Kim et al, 53 Deep HIT by Ryu et al 43 and BayeshERG as presented by Kim et al, 53 have been reported for the same training dataset. 47,50,51,54 This is one reason that many models (504 models) have been reported for cardiotoxicity prediction.…”

“…As shown in Table 1, by holdout validation, Liu et al 55 achieved a balanced accuracy of 0.91 using Bayesian models on a dataset containing 2389 compounds. Chen et al 52 reported a balanced accuracy of 0.863 on a dataset of 2660 compounds, and Cai et al 42 reported an average balanced accuracy of 0.873 on 7889 compounds. Using cross validations, Siramshetty et al 45 obtained an average balanced accuracy of 0.865 with RF on 3223 compounds and Shen et al 46 reached an average balanced accuracy of 0.912 on 1668 compounds.…”