{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:42:56Z","timestamp":1769830976281,"version":"3.49.0"},"reference-count":57,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T00:00:00Z","timestamp":1655424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["NRF-2020R1A2C2004628"],"award-info":[{"award-number":["NRF-2020R1A2C2004628"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Unintended inhibition of the human ether-\u00e0-go-go-related gene (hERG) ion channel by small molecules leads to severe cardiotoxicity. Thus, hERG channel blockage is a significant concern in the development of new drugs. Several computational models have been developed to predict hERG channel blockage, including deep learning models; however, they lack robustness, reliability and interpretability. Here, we developed a graph-based Bayesian deep learning model for hERG channel blocker prediction, named BayeshERG, which has robust predictive power, high reliability and high resolution of interpretability. First, we applied transfer learning with 300\u00a0000 large data in initial pre-training to increase the predictive performance. Second, we implemented a Bayesian neural network with Monte Carlo dropout to calibrate the uncertainty of the prediction. Third, we utilized global multihead attentive pooling to augment the high resolution of structural interpretability for the hERG channel blockers and nonblockers. We conducted both internal and external validations for stringent evaluation; in particular, we benchmarked most of the publicly available hERG channel blocker prediction models. We showed that our proposed model outperformed predictive performance and uncertainty calibration performance. Furthermore, we found that our model learned to focus on the essential substructures of hERG channel blockers via an attention mechanism. Finally, we validated the prediction results of our model by conducting in vitro experiments and confirmed its high validity. In summary, BayeshERG could serve as a versatile tool for discovering hERG channel blockers and helping maximize the possibility of successful drug discovery. The data and source code are available at our GitHub repository (https:\/\/github.com\/GIST-CSBL\/BayeshERG).<\/jats:p>","DOI":"10.1093\/bib\/bbac211","type":"journal-article","created":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T19:13:36Z","timestamp":1651864416000},"source":"Crossref","is-referenced-by-count":27,"title":["BayeshERG: a robust, reliable and interpretable deep learning model for predicting hERG channel blockers"],"prefix":"10.1093","volume":"23","author":[{"given":"Hyunho","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST) , Buk-gu, Gwangju, 61005, Republic of Korea"}]},{"given":"Minsu","family":"Park","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST) , Buk-gu, Gwangju, 61005, Republic of Korea"}]},{"given":"Ingoo","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST) , Buk-gu, Gwangju, 61005, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5109-9114","authenticated-orcid":false,"given":"Hojung","family":"Nam","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST) , Buk-gu, Gwangju, 61005, Republic of Korea"}]}],"member":"286","published-online":{"date-parts":[[2022,6,17]]},"reference":[{"key":"2022071906090117400_ref1","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/S0008-6363(02)00846-5","article-title":"Relationships between preclinical cardiac electrophysiology, clinical QT interval prolongation and torsade de pointes for a broad range of drugs: evidence for a provisional safety margin in drug development","volume":"58","author":"Redfern","year":"2003","journal-title":"Cardiovasc Res"},{"key":"2022071906090117400_ref2","first-page":"463","article-title":"hERG potassium channels and cardiac arrhythmia","volume":"440","author":"Sanguinetti","year":"2006","journal-title":"FEBS Lett"},{"key":"2022071906090117400_ref3","first-page":"28","article-title":"A mechanism for the proarrhythmic effects of cisapride (Propulsid): high affinity blockade of the human cardiac potassium channel","volume":"417","author":"Rampe","year":"1997","journal-title":"HERG"},{"key":"2022071906090117400_ref4","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1146\/annurev.pa.36.040196.001313","article-title":"Cardiac Actions of Antihistamines","volume":"36","author":"Woosley","year":"1996","journal-title":"Annu Rev Pharmacol Toxicol"},{"key":"2022071906090117400_ref5","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1111\/j.1540-8167.1999.tb00264.x","article-title":"Block of HERG potassium channels by the antihistamine astemizole and its metabolites desmethylastemizole and norastemizole","volume":"10","author":"Zhou","year":"1999","journal-title":"J Cardiovasc Electrophysiol"},{"key":"2022071906090117400_ref6","first-page":"498","volume-title":"Clinical evaluation of QT\/QTc prolongation and proarrhythmic potential for nonantiarrhythmic drugs: the international conference on harmonization of technical requirements for registration of pharmaceuticals for human use E14 guideline","author":"Darpo","year":"2006"},{"key":"2022071906090117400_ref7","doi-asserted-by":"crossref","first-page":"87","DOI":"10.4161\/chan.2.2.6004","article-title":"Role of hERG potassium channel assays in drug development","volume":"2","author":"Priest","year":"2008","journal-title":"Channels"},{"key":"2022071906090117400_ref8","doi-asserted-by":"crossref","first-page":"3049","DOI":"10.1093\/bioinformatics\/btaa075","article-title":"DeepHIT: a deep learning framework for prediction of hERG-induced cardiotoxicity","volume":"36","author":"Ryu","year":"2020","journal-title":"Bioinformatics"},{"key":"2022071906090117400_ref9","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1021\/tx060230c","article-title":"A novel approach using pharmacophore ensemble\/support vector machine (PhE\/SVM) for prediction of hERG liability","volume":"20","author":"Leong","year":"2007","journal-title":"Chem Res Toxicol"},{"key":"2022071906090117400_ref10","doi-asserted-by":"crossref","first-page":"2855","DOI":"10.1021\/acs.molpharmaceut.6b00471","article-title":"ADMET evaluation in drug discovery. 16. Predicting hERG blockers by combining multiple pharmacophores and machine learning approaches","volume":"13","author":"Wang","year":"2016","journal-title":"Mol Pharm"},{"key":"2022071906090117400_ref11","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1002\/minf.201500040","article-title":"Pred-hERG: a novel web-accessible computational tool for predicting cardiac toxicity","volume":"34","author":"Braga","year":"2015","journal-title":"Mol Inform"},{"key":"2022071906090117400_ref12","doi-asserted-by":"crossref","first-page":"100089","DOI":"10.1016\/j.comtox.2019.100089","article-title":"hERG liability classification models using machine learning techniques","volume":"12","author":"Konda","year":"2019","journal-title":"Comput Toxicol"},{"key":"2022071906090117400_ref13","doi-asserted-by":"crossref","first-page":"1700074","DOI":"10.1002\/minf.201700074","article-title":"Modeling of the hERG K+ channel blockage using online chemical database and modeling environment (OCHEM)","volume":"36","author":"Li","year":"2017","journal-title":"Mol inform"},{"key":"2022071906090117400_ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-47536-3","article-title":"Support Vector Machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-II","volume":"9","author":"Ogura","year":"2019","journal-title":"Sci Rep"},{"key":"2022071906090117400_ref15","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1021\/acs.jcim.8b00769","article-title":"Deep Learning-based prediction of drug-induced cardiotoxicity","volume":"59","author":"Cai","year":"2019","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref16","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s12859-019-2814-5","article-title":"Computational determination of hERG-related cardiotoxicity of drug candidates","volume":"20","author":"Lee","year":"2019","journal-title":"BMC Bioinform"},{"key":"2022071906090117400_ref17","doi-asserted-by":"crossref","first-page":"6007","DOI":"10.1021\/acs.jcim.0c00884","article-title":"Critical assessment of artificial intelligence methods for prediction of hERG channel inhibition in the \u201cBig Data\u201d Era","volume":"60","author":"Siramshetty","year":"2020","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref18","first-page":"1","article-title":"CardioTox net: a robust predictor for hERG channel blockade based on deep learning meta-feature ensembles","volume":"13","author":"Karim","year":"2021","journal-title":"J Chem"},{"key":"2022071906090117400_ref19","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume":"30","author":"Kendall","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2022071906090117400_ref20","doi-asserted-by":"crossref","first-page":"2697","DOI":"10.1021\/acs.jcim.9b00975","article-title":"Evaluating scalable uncertainty estimation methods for deep learning-based molecular property prediction","volume":"60","author":"Scalia","year":"2020","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref21","doi-asserted-by":"crossref","first-page":"8154","DOI":"10.1039\/C9SC00616H","article-title":"Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning","volume":"10","author":"Zhang","year":"2019","journal-title":"Chem Sci"},{"key":"2022071906090117400_ref22","doi-asserted-by":"crossref","first-page":"3770","DOI":"10.1021\/acs.jcim.0c00502","article-title":"Uncertainty quantification using neural networks for molecular property prediction","volume":"60","author":"Hirschfeld","year":"2020","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref23","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1021\/acscentsci.1c00546","article-title":"Evidential deep learning for guided molecular property prediction and discovery","volume":"7","author":"Soleimany","year":"2021","journal-title":"ACS Cent Sci"},{"key":"2022071906090117400_ref24","doi-asserted-by":"crossref","first-page":"8438","DOI":"10.1039\/C9SC01992H","article-title":"A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification","volume":"10","author":"Ryu","year":"2019","journal-title":"Chem Sci"},{"key":"2022071906090117400_ref25","doi-asserted-by":"crossref","first-page":"6924","DOI":"10.1021\/acs.jmedchem.1c00421","article-title":"Mining toxicity information from large amounts of toxicity data","volume":"64","author":"Wu","year":"2021","journal-title":"J Med Chem"},{"key":"2022071906090117400_ref26","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1021\/acs.jcim.0c01224","article-title":"Transferable multilevel attention neural network for accurate prediction of quantum chemistry properties via multitask learning","volume":"61","author":"Liu","year":"2021","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref27","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1021\/acs.jcim.8b00672","article-title":"Deepchemstable: chemical stability prediction with an attention-based graph convolution network","volume":"59","author":"Li","year":"2019","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref28","doi-asserted-by":"crossref","first-page":"107286","DOI":"10.1016\/j.compbiolchem.2020.107286","article-title":"hERG-Att: Self-attention-based deep neural network for predicting hERG blockers","volume":"87","author":"Kim","year":"2020","journal-title":"Comput Bio Chem"},{"key":"2022071906090117400_ref29","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2019","journal-title":"J Med Chem"},{"key":"2022071906090117400_ref30","first-page":"1","article-title":"A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility","volume":"12","author":"Tang","year":"2020","journal-title":"J Chem"},{"key":"2022071906090117400_ref31","doi-asserted-by":"crossref","first-page":"4528","DOI":"10.1021\/acs.jcim.9b00626","article-title":"Deep transferable compound representation across domains and tasks for low data drug discovery","volume":"59","author":"Abbasi","year":"2019","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref32","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s13321-020-00430-x","article-title":"Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT","volume":"12","author":"Li","year":"2020","journal-title":"J Chem"},{"key":"2022071906090117400_ref33","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1021\/acs.molpharmaceut.8b00816","article-title":"An Integrated transfer learning and multitask learning approach for pharmacokinetic parameter prediction","volume":"16","author":"Ye","year":"2019","journal-title":"Mol Pharm"},{"key":"2022071906090117400_ref34","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1021\/acscentsci.6b00367","article-title":"Low data drug discovery with one-shot learning","volume":"3","author":"Altae-Tran","year":"2017","journal-title":"ACS Cent Sci"},{"key":"2022071906090117400_ref35","doi-asserted-by":"crossref","first-page":"13041","DOI":"10.1039\/D0CP02319A","article-title":"Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks","volume":"22","author":"Fare","year":"2020","journal-title":"J Phys Chem Chem Phys"},{"key":"2022071906090117400_ref36","volume-title":"Strategies for Pre-Training Graph Neural Networks","author":"Hu","year":"2019"},{"key":"2022071906090117400_ref37","doi-asserted-by":"crossref","first-page":"e0118324","DOI":"10.1371\/journal.pone.0118324","article-title":"Global analysis reveals families of chemical motifs enriched for HERG inhibitors","volume":"10","author":"Du","year":"2015","journal-title":"PloS one"},{"key":"2022071906090117400_ref38","doi-asserted-by":"crossref","first-page":"D930","DOI":"10.1093\/nar\/gky1075","article-title":"ChEMBL: towards direct deposition of bioassay data","volume":"47","author":"Mendez","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2022071906090117400_ref39","doi-asserted-by":"crossref","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","article-title":"PubChem in 2021: new data content and improved web interfaces","volume":"49","author":"Kim","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2022071906090117400_ref40","doi-asserted-by":"crossref","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","article-title":"BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology","volume":"44","author":"Gilson","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2022071906090117400_ref41","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3389\/fchem.2017.00007","article-title":"Computational tool for fast in silico evaluation of hERG K+ channel affinity","volume":"5","author":"Chemi","year":"2017","journal-title":"Front Chem"},{"key":"2022071906090117400_ref42","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1002\/cmdc.201000024","article-title":"Prospective validation of a comprehensive in silico hERG model and its applications to commercial compound and drug databases","volume":"5","author":"Doddareddy","year":"2010","journal-title":"Chem Med Chem"},{"key":"2022071906090117400_ref43","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1007\/s10822-016-9986-0","article-title":"Compilation and physicochemical classification analysis of a diverse hERG inhibition database","volume":"30","author":"Didziapetris","year":"2016","journal-title":"J Comput Aided Mol Des"},{"key":"2022071906090117400_ref44","volume-title":"RDKit: RDKit: Open-source cheminformatics","author":"Landrum","year":"2022"},{"key":"2022071906090117400_ref45","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref46","article-title":"Chemberta: large-scale self-supervised pretraining for molecular property prediction","author":"Chithrananda","year":"2020","journal-title":"arXiv preprint arXiv:201009885"},{"key":"2022071906090117400_ref47","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2022071906090117400_ref48","first-page":"1050","volume-title":"International Conference on Machine Learning","author":"Gal","year":"2016"},{"key":"2022071906090117400_ref49","article-title":"Concrete dropout","author":"Gal","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022071906090117400_ref50","doi-asserted-by":"crossref","first-page":"106816","DOI":"10.1016\/j.csda.2019.106816","article-title":"Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation","volume":"142","author":"Kwon","year":"2020","journal-title":"Comput Stat Data Anal"},{"key":"2022071906090117400_ref51","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem Sci"},{"key":"2022071906090117400_ref52","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1093\/bioinformatics\/bty707","article-title":"admetSAR 2.0: web-service for prediction and optimization of chemical ADMET properties","volume":"35","author":"Yang","year":"2019","journal-title":"Bioinformatics"},{"key":"2022071906090117400_ref53","doi-asserted-by":"crossref","first-page":"W5","DOI":"10.1093\/nar\/gkab255","article-title":"ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties","volume":"49","author":"Xiong","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2022071906090117400_ref54","first-page":"3319","volume-title":"International Conference on Machine Learning","author":"Sundararajan","year":"2017"},{"key":"2022071906090117400_ref55","doi-asserted-by":"crossref","first-page":"3428","DOI":"10.1093\/bioinformatics\/btab346","article-title":"Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction","volume":"37","author":"Kim","year":"2021","journal-title":"Bioinformatics"},{"key":"2022071906090117400_ref56","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1021\/acs.jcim.0c01344","article-title":"Coloring molecules with explainable artificial intelligence for preclinical relevance assessment","volume":"61","author":"Jim\u00e9nez-Luna","year":"2021","journal-title":"J Chem Inform Model"},{"key":"2022071906090117400_ref57","doi-asserted-by":"crossref","first-page":"4348","DOI":"10.1039\/C6GC01492E","article-title":"Alarms about structural alerts","volume":"18","author":"Alves","year":"2016","journal-title":"Green Chem"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/4\/bbac211\/45017317\/bbac211.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/4\/bbac211\/45017317\/bbac211.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T06:13:19Z","timestamp":1658211199000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac211\/6609519"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,17]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7,18]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac211","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,18]]},"published":{"date-parts":[[2022,6,17]]},"article-number":"bbac211"}}