HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors

Abstract The human Ether-à-go-go-Related Gene (hERG) potassium channel is crucial for repolarizing the cardiac action potential and regulating the heartbeat. Molecules that inhibit this protein can cause acquired long QT syndrome, increasing the risk of arrhythmias and sudden fatal cardiac arrests....

Full description

Saved in:
Bibliographic Details
Main Authors: Viet-Khoa Tran-Nguyen, Ulrick Fineddie Randriharimanamizara, Olivier Taboureau
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Journal of Cheminformatics
Subjects:
Online Access:https://doi.org/10.1186/s13321-025-01063-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331979418337280
author Viet-Khoa Tran-Nguyen
Ulrick Fineddie Randriharimanamizara
Olivier Taboureau
author_facet Viet-Khoa Tran-Nguyen
Ulrick Fineddie Randriharimanamizara
Olivier Taboureau
author_sort Viet-Khoa Tran-Nguyen
collection DOAJ
description Abstract The human Ether-à-go-go-Related Gene (hERG) potassium channel is crucial for repolarizing the cardiac action potential and regulating the heartbeat. Molecules that inhibit this protein can cause acquired long QT syndrome, increasing the risk of arrhythmias and sudden fatal cardiac arrests. Detecting compounds with potential hERG inhibitory activity is therefore essential to mitigate cardiotoxicity risks. In this article, we present a new hERG data set of unprecedented size, comprising nearly 300,000 molecules reported in PubChem and ChEMBL, approximately 2000 of which were confirmed hERG blockers identified through in vitro assays. Multiple structure-based artificial intelligence (AI) binary classifiers for predicting hERG inhibitors were developed, employing, as descriptors, protein–ligand extended connectivity (PLEC) fingerprints fed into random forest, extreme gradient boosting, and deep neural network (DNN) algorithms. Our best-performing model, a stacking ensemble classifier with a DNN meta-learner, achieved state-of-the-art classification performance, accurately identifying 86% of molecules having half-maximal inhibitory concentrations (IC50s) not exceeding 20 µM in our challenging test set, including 94% of hERG blockers whose IC50s were not greater than 1 µM. It also demonstrated superior screening power compared to virtual screening schemes that used existing scoring functions. This model, named “HERGAI,” along with relevant input/output data and user-friendly source code, is available in our GitHub repository ( https://github.com/vktrannguyen/HERGAI ) and can be used to predict drug-induced hERG blockade, even on large data sets.
format Article
id doaj-art-6893bb353528417c8d7373cf8902afb8
institution Kabale University
issn 1758-2946
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Journal of Cheminformatics
spelling doaj-art-6893bb353528417c8d7373cf8902afb82025-08-20T03:46:21ZengBMCJournal of Cheminformatics1758-29462025-07-0117111510.1186/s13321-025-01063-8HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitorsViet-Khoa Tran-Nguyen0Ulrick Fineddie Randriharimanamizara1Olivier Taboureau2Université Paris Cité, CNRS UMR 8251Université Paris Cité, CNRS UMR 8251Université Paris Cité, CNRS UMR 8251Abstract The human Ether-à-go-go-Related Gene (hERG) potassium channel is crucial for repolarizing the cardiac action potential and regulating the heartbeat. Molecules that inhibit this protein can cause acquired long QT syndrome, increasing the risk of arrhythmias and sudden fatal cardiac arrests. Detecting compounds with potential hERG inhibitory activity is therefore essential to mitigate cardiotoxicity risks. In this article, we present a new hERG data set of unprecedented size, comprising nearly 300,000 molecules reported in PubChem and ChEMBL, approximately 2000 of which were confirmed hERG blockers identified through in vitro assays. Multiple structure-based artificial intelligence (AI) binary classifiers for predicting hERG inhibitors were developed, employing, as descriptors, protein–ligand extended connectivity (PLEC) fingerprints fed into random forest, extreme gradient boosting, and deep neural network (DNN) algorithms. Our best-performing model, a stacking ensemble classifier with a DNN meta-learner, achieved state-of-the-art classification performance, accurately identifying 86% of molecules having half-maximal inhibitory concentrations (IC50s) not exceeding 20 µM in our challenging test set, including 94% of hERG blockers whose IC50s were not greater than 1 µM. It also demonstrated superior screening power compared to virtual screening schemes that used existing scoring functions. This model, named “HERGAI,” along with relevant input/output data and user-friendly source code, is available in our GitHub repository ( https://github.com/vktrannguyen/HERGAI ) and can be used to predict drug-induced hERG blockade, even on large data sets.https://doi.org/10.1186/s13321-025-01063-8hERGInhibitorBinary classification modelMachine learningDeep learningDeep neural network
spellingShingle Viet-Khoa Tran-Nguyen
Ulrick Fineddie Randriharimanamizara
Olivier Taboureau
HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
Journal of Cheminformatics
hERG
Inhibitor
Binary classification model
Machine learning
Deep learning
Deep neural network
title HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
title_full HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
title_fullStr HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
title_full_unstemmed HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
title_short HERGAI: an artificial intelligence tool for structure-based prediction of hERG inhibitors
title_sort hergai an artificial intelligence tool for structure based prediction of herg inhibitors
topic hERG
Inhibitor
Binary classification model
Machine learning
Deep learning
Deep neural network
url https://doi.org/10.1186/s13321-025-01063-8
work_keys_str_mv AT vietkhoatrannguyen hergaianartificialintelligencetoolforstructurebasedpredictionofherginhibitors
AT ulrickfineddierandriharimanamizara hergaianartificialintelligencetoolforstructurebasedpredictionofherginhibitors
AT oliviertaboureau hergaianartificialintelligencetoolforstructurebasedpredictionofherginhibitors