Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction
<p dir="ltr">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 expect...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1864513534115708928 |
|---|---|
| author | Syed Mohammad (21075689) |
| author2 | Vaisali Chandrasekar (16904526) Omar Aboumarzouk (18427923) Ajay Vikram Singh (22501868) Sarada Prasad Dakua (22501871) |
| author2_role | author author author author |
| author_facet | Syed Mohammad (21075689) Vaisali Chandrasekar (16904526) Omar Aboumarzouk (18427923) Ajay Vikram Singh (22501868) Sarada Prasad Dakua (22501871) |
| author_role | author |
| dc.creator.none.fl_str_mv | Syed Mohammad (21075689) Vaisali Chandrasekar (16904526) Omar Aboumarzouk (18427923) Ajay Vikram Singh (22501868) Sarada Prasad Dakua (22501871) |
| dc.date.none.fl_str_mv | 2025-05-14T12:00:00Z |
| dc.identifier.none.fl_str_mv | 10.1109/access.2025.3566440 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/journal_contribution/Leveraging_Machine_and_Deep_Learning_Algorithms_for_hERG_Blocker_Prediction/30454286 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biomedical and clinical sciences Cardiovascular medicine and haematology Pharmacology and pharmaceutical sciences Health sciences Health services and systems Information and computing sciences Machine learning hERG machine learning cardiotoxicity prediction Fingerprint recognition Feature extraction Compounds Classification algorithms Chemicals Training Principal component analysis Drugs |
| dc.title.none.fl_str_mv | Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction |
| dc.type.none.fl_str_mv | Text Journal contribution info:eu-repo/semantics/publishedVersion text contribution to journal |
| description | <p dir="ltr">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 ≤10 μ M and for non-blockers, it is >10 μ M, our analysis indicates that a threshold of 60- 80 μ 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.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3566440" target="_blank">https://dx.doi.org/10.1109/access.2025.3566440</a></p> |
| eu_rights_str_mv | openAccess |
| id | Manara2_39883fb91e6ca3841c6f9e70780e1fcb |
| identifier_str_mv | 10.1109/access.2025.3566440 |
| network_acronym_str | Manara2 |
| network_name_str | Manara2 |
| oai_identifier_str | oai:figshare.com:article/30454286 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Leveraging Machine and Deep Learning Algorithms for hERG Blocker PredictionSyed Mohammad (21075689)Vaisali Chandrasekar (16904526)Omar Aboumarzouk (18427923)Ajay Vikram Singh (22501868)Sarada Prasad Dakua (22501871)Biomedical and clinical sciencesCardiovascular medicine and haematologyPharmacology and pharmaceutical sciencesHealth sciencesHealth services and systemsInformation and computing sciencesMachine learninghERGmachine learningcardiotoxicitypredictionFingerprint recognitionFeature extractionCompoundsClassification algorithmsChemicalsTrainingPrincipal component analysisDrugs<p dir="ltr">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 ≤10 μ M and for non-blockers, it is >10 μ M, our analysis indicates that a threshold of 60- 80 μ 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.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3566440" target="_blank">https://dx.doi.org/10.1109/access.2025.3566440</a></p>2025-05-14T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3566440https://figshare.com/articles/journal_contribution/Leveraging_Machine_and_Deep_Learning_Algorithms_for_hERG_Blocker_Prediction/30454286CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/304542862025-05-14T12:00:00Z |
| spellingShingle | Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction Syed Mohammad (21075689) Biomedical and clinical sciences Cardiovascular medicine and haematology Pharmacology and pharmaceutical sciences Health sciences Health services and systems Information and computing sciences Machine learning hERG machine learning cardiotoxicity prediction Fingerprint recognition Feature extraction Compounds Classification algorithms Chemicals Training Principal component analysis Drugs |
| status_str | publishedVersion |
| 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 | Biomedical and clinical sciences Cardiovascular medicine and haematology Pharmacology and pharmaceutical sciences Health sciences Health services and systems Information and computing sciences Machine learning hERG machine learning cardiotoxicity prediction Fingerprint recognition Feature extraction Compounds Classification algorithms Chemicals Training Principal component analysis Drugs |