Prediction of hERG potassium channel blockage using ensemble learning methods and molecular fingerprints. (10th October 2020)

• Record Type: Journal Article
• Authors: Liu, Miao; Zhang, Li; Li, Shimeng; Yang, Tianzhou; Liu, Lili; Zhao, Jian; Liu, Hongsheng
• Is Part Of: Toxicology letters. Volume 332(2020)
• Page Start: 88
• Page End: 96
• Publication Date: 2020-10-10
• Subjects: hERG -- Molecular fingerprint -- Molecular descriptor -- Machine learning -- Ensemble model; Toxicology -- Periodicals; 363.179
• DOI: 10.1016/j.toxlet.2020.07.003
• Languages: English
• ISSNs: 0378-4274

Abstract

Highlights: A new cardiotoxicity classification model with better predictive performance was developed using ensemble learning methods. The best model achieved an accuracy of 84.9 % and AUC of 0.887 in the 5-fold cross-validation. Some substructures related to the cardiotoxicity were achieved. Abstract: The human ether-a-go-go-related gene (hERG) encodes a tetrameric potassium channel called Kv11.1. This channel can be blocked by certain drugs, which leads to long QT syndrome, causing cardiotoxicity. This is a significant problem during drug development. Using computer models to predict compound cardiotoxicity during the early stages of drug design will help to solve this problem. In this study, we used a dataset of 1865 compounds exhibiting known hERG inhibitory activities as a training set. Thirty cardiotoxicity classification models were established using three machine learning algorithms based on molecular fingerprints and molecular descriptors. Through using these models as the base classifier, a new cardiotoxicity classification model with better predictive performance was developed using ensemble learning method. The accuracy of the best base classifier, which was generated using the XGBoost method with molecular descriptors, was 84.8 %, and the area under the receiver-operating characteristic curve (AUC) was 0.876 in the five fold cross-validation. However, all of the ensemble models that we developed had higher predictive performance than the base classifiers in the five fold cross-validation. The best predictive performance was achieved by the Ensemble-Top7 model, with accuracy of 84.9 % and AUC of 0.887. We also tested the ensemble model using external validation data and achieved accuracy of 85.0 % and AUC of 0.786. Furthermore, we identified several hERG-related substructures, which provide valuable information for designing drug candidates.