Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction

The human ether-a-go-go-related (hERG) gene is crucial in enabling the regulation of repolarisation process in the heart. Some chemicals act as hERG blockers, resulting in prolonged QT intervals. Predicting the binding capability of molecules with hERG channels is expected to reduce the burden of ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Syed Mohammad, Vaisali Chandrasekar, Omar Aboumarzouk, Ajay Vikram Singh, Sarada Prasad Dakua
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10982226/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031675753365504
author Syed Mohammad
Vaisali Chandrasekar
Omar Aboumarzouk
Ajay Vikram Singh
Sarada Prasad Dakua
author_facet Syed Mohammad
Vaisali Chandrasekar
Omar Aboumarzouk
Ajay Vikram Singh
Sarada Prasad Dakua
author_sort Syed Mohammad
collection DOAJ
description The human ether-a-go-go-related (hERG) gene is crucial in enabling the regulation of repolarisation process in the heart. Some chemicals act as hERG blockers, resulting in prolonged QT intervals. Predicting the binding capability of molecules with hERG channels is expected to reduce the burden of cardiotoxicity testing in drug evaluation. The application of machine learning (ML) and deep learning (DL) models in the field of toxicity has gained burgeoning interest. The current study utilises state-of-the-art ML and DL models for predicting the hERG-blocking ability of chemical compounds using a dataset of 8337 molecules. It is noted that spatial relationships within molecules are crucial in predicting hERG blockers. While the threshold for blockers is defined as <inline-formula> <tex-math notation="LaTeX">$\leq 10~\mu $ </tex-math></inline-formula>M and for non-blockers, it is <inline-formula> <tex-math notation="LaTeX">$\gt 10~\mu $ </tex-math></inline-formula>M, our analysis indicates that a threshold of 60-<inline-formula> <tex-math notation="LaTeX">$80~\mu $ </tex-math></inline-formula>M provides a more accurate cut-off for non-blockers. This adjustment highlights the importance of concentration levels in reflecting the variability specific to individual interaction sites. The algorithm results show that the internal validation performance of RF, XGBoost, and MLP is strong, with AUC scores of 0.90, 0.90, and 0.87, respectively. In summary, the current study provides a machine learning framework for computation cardiotoxicity assessment by analysis of the hERG blocker concentration cut-offs using different fingerprints at multiple thresholds.
format Article
id doaj-art-699d1228c84345aa8299cd4e3c7104b5
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-699d1228c84345aa8299cd4e3c7104b52025-08-20T02:58:54ZengIEEEIEEE Access2169-35362025-01-0113810188102810.1109/ACCESS.2025.356644010982226Leveraging Machine and Deep Learning Algorithms for hERG Blocker PredictionSyed Mohammad0https://orcid.org/0009-0008-1915-9640Vaisali Chandrasekar1https://orcid.org/0000-0001-7149-5459Omar Aboumarzouk2https://orcid.org/0000-0002-7961-7614Ajay Vikram Singh3https://orcid.org/0000-0002-9875-7727Sarada Prasad Dakua4https://orcid.org/0000-0003-2979-0272Department of Surgery, Hamad Medical Corporation, Doha, QatarDepartment of Surgery, Hamad Medical Corporation, Doha, QatarDepartment of Surgery, Hamad Medical Corporation, Doha, QatarGerman Federal Institute for Risk Assessment (BfR), Berlin, GermanyDepartment of Surgery, Hamad Medical Corporation, Doha, QatarThe human ether-a-go-go-related (hERG) gene is crucial in enabling the regulation of repolarisation process in the heart. Some chemicals act as hERG blockers, resulting in prolonged QT intervals. Predicting the binding capability of molecules with hERG channels is expected to reduce the burden of cardiotoxicity testing in drug evaluation. The application of machine learning (ML) and deep learning (DL) models in the field of toxicity has gained burgeoning interest. The current study utilises state-of-the-art ML and DL models for predicting the hERG-blocking ability of chemical compounds using a dataset of 8337 molecules. It is noted that spatial relationships within molecules are crucial in predicting hERG blockers. While the threshold for blockers is defined as <inline-formula> <tex-math notation="LaTeX">$\leq 10~\mu $ </tex-math></inline-formula>M and for non-blockers, it is <inline-formula> <tex-math notation="LaTeX">$\gt 10~\mu $ </tex-math></inline-formula>M, our analysis indicates that a threshold of 60-<inline-formula> <tex-math notation="LaTeX">$80~\mu $ </tex-math></inline-formula>M provides a more accurate cut-off for non-blockers. This adjustment highlights the importance of concentration levels in reflecting the variability specific to individual interaction sites. The algorithm results show that the internal validation performance of RF, XGBoost, and MLP is strong, with AUC scores of 0.90, 0.90, and 0.87, respectively. In summary, the current study provides a machine learning framework for computation cardiotoxicity assessment by analysis of the hERG blocker concentration cut-offs using different fingerprints at multiple thresholds.https://ieeexplore.ieee.org/document/10982226/hERGmachine learningcardiotoxicityprediction
spellingShingle Syed Mohammad
Vaisali Chandrasekar
Omar Aboumarzouk
Ajay Vikram Singh
Sarada Prasad Dakua
Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
IEEE Access
hERG
machine learning
cardiotoxicity
prediction
title Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
title_full Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
title_fullStr Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
title_full_unstemmed Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
title_short Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
title_sort leveraging machine and deep learning algorithms for herg blocker prediction
topic hERG
machine learning
cardiotoxicity
prediction
url https://ieeexplore.ieee.org/document/10982226/
work_keys_str_mv AT syedmohammad leveragingmachineanddeeplearningalgorithmsforhergblockerprediction
AT vaisalichandrasekar leveragingmachineanddeeplearningalgorithmsforhergblockerprediction
AT omaraboumarzouk leveragingmachineanddeeplearningalgorithmsforhergblockerprediction
AT ajayvikramsingh leveragingmachineanddeeplearningalgorithmsforhergblockerprediction
AT saradaprasaddakua leveragingmachineanddeeplearningalgorithmsforhergblockerprediction