{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:57:45Z","timestamp":1790607465560,"version":"4.1.0"},"reference-count":126,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018694","name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","award":["101120466"],"award-info":[{"award-number":["101120466"]}],"id":[{"id":"10.13039\/100018694","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In 2013 the Comprehensive In Vitro Proarrhythmia Assay (CiPA) initiative proposed multi-channel assessment for proarrhythmic risk evaluation, yet ligand-based predictive modeling has remained largely single-channel. To quantify and explain this mismatch, we survey 155 ligand-based modeling studies on cardiac ion channels (including conventional QSAR, machine learning, and pharmacophore- and other 3D ligand-based approaches) published between 2001 and mid-2026. Across this period, 88.4% of studies target hERG as their sole ion channel endpoint, a proportion that reflects data availability, regulatory incentives, and research inertia rather than scientific necessity. Although public data for Nav1.5 and Cav1.2 were sufficient for modeling years earlier, both channels received only isolated studies until 2022. Since then, multi-channel modeling has expanded substantially, with multiple groups now addressing the primary channels (hERG, Nav1.5, and Cav1.2) jointly. In contrast, the secondary channels (Kv7.1, Kv4.3, and Kir2.1) remain largely understudied: Kv4.3 and Kir2.1 are entirely unmodeled in the surveyed literature, and models for Kv7.1 remain scarce, likely due to the sparsity and heterogeneity of public data. A retrospective analysis of the reported model performance found no discernible improvements attributable to methodological advances. Reliability-related aspects, such as applicability domain and uncertainty quantification, were also rarely addressed. The field should treat joint modeling of the primary channels as the expected standard rather than a novel contribution. Other important aspects include the development of standardized benchmarks for multi-channel evaluation, integration with physiological models, and greater emphasis on prediction reliability. For the secondary channels, progress would additionally require coordinated data release or federated learning, methods suited to data-scarce targets, and community coordination, none of which individual research groups can establish alone.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c03072","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:02:02Z","timestamp":1789621322000},"page":"11605-11618","source":"Crossref","is-referenced-by-count":0,"title":["25 Years of Cardiac\nIon Channel QSAR: From hERG Dominance\nto Multi-Channel Modeling"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5151-4659","authenticated-orcid":true,"given":"Mateusz","family":"Iwan","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology , , P.O. Box 513 , ,","place":["Eindhoven, The Netherlands, 5600 MB"]},{"name":"Machine Learning Research, Research and Development , Bayer AG, Mu\u0308llerstr. 178 , ,","place":["Berlin, Germany, 13353"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8552-6615","authenticated-orcid":true,"given":"Francesca","family":"Grisoni","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology , , P.O. Box 513 , ,","place":["Eindhoven, The Netherlands, 5600 MB"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anastasia","family":"Pentina","sequence":"additional","affiliation":[{"name":"Machine Learning Research, Research and Development , Bayer AG, Mu\u0308llerstr. 178 , ,","place":["Berlin, Germany, 13353"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9310-7290","authenticated-orcid":true,"given":"Marina","family":"Garcia de Lomana","sequence":"additional","affiliation":[{"name":"Machine Learning Research, Research and Development , Bayer AG, Mu\u0308llerstr. 178 , ,","place":["Berlin, Germany, 13353"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandra","family":"Roncaglioni","sequence":"additional","affiliation":[{"name":"Istituto di Ricerche Farmacologiche Mario Negri IRCCS , , Via Mario Negri 2 , ,","place":["Milan, Italy, 20156"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"2026092810073188000_cit1","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s002280100290","article-title":"\u201cOrganising\nevidence on qt prolongation and occurrence of torsades de pointes\nwith non-antiarrhythmic drugs: a call for consensus\u201d","volume":"57","author":"De Ponti","year":"2001","journal-title":"Eur. J. Clin. Pharmacol."},{"key":"2026092810073188000_cit2","doi-asserted-by":"publisher","first-page":"bar017","DOI":"10.1093\/database\/bar017","article-title":"\u201chergapdbase:\na database documenting herg channel\ninhibitory potentials and apd-prolongation activities of chemical\ncompounds\u201d","volume":"2011","author":"Hishigaki","year":"2011","journal-title":"Database"},{"key":"2026092810073188000_cit3","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/nature04710","article-title":"\u201cherg\npotassium channels and cardiac arrhythmia\u201d","volume":"440","author":"Sanguinetti","year":"2006","journal-title":"Nature"},{"key":"2026092810073188000_cit4","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/S0008-6363(02)00846-5","article-title":"\u201cRelationships between preclinical cardiac electrophysiology,\nclinical QT interval prolongation and torsade de pointes for a broad\nrange of drugs: evidence for a provisional safety margin in drug development\u201d","volume":"58","author":"Redfern","year":"2003","journal-title":"Cardiovasc. Res."},{"key":"2026092810073188000_cit7","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1002\/jcph.1880","article-title":"\u201cThe new s7b\/e14question\nand answer draft guidance\nfor industry: Contents and commentary\u201d","volume":"61","author":"Darpo","year":"2021","journal-title":"J. Clin. Pharmacol."},{"key":"2026092810073188000_cit8","doi-asserted-by":"publisher","first-page":"107562","DOI":"10.1016\/j.vascn.2024.107562","article-title":"\u201cInhibition of herg k channels by verapamil\nat physiological temperature: Implications for the cipa initiative\u201d","volume":"130","author":"Johnson","year":"2024","journal-title":"J. Pharmacol. Toxicol. Methods"},{"key":"2026092810073188000_cit9","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1093\/cvr\/cvr044","article-title":"\u201cSimulation\nof multiple ion channel block provides improved early prediction of\ncompounds\u2019 clinical torsadogenic risk\u201d","volume":"91","author":"Mirams","year":"2011","journal-title":"Cardiovasc. Res."},{"issue":"1","key":"2026092810073188000_cit10","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1038\/srep02100","article-title":"\u201cMice models: Superior to\nthe herg model in predicting torsade de pointes\u201d","volume":"3","author":"Kramer","year":"2013","journal-title":"Sci. Rep."},{"key":"2026092810073188000_cit11","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.vascn.2016.03.009","article-title":"\u201cAn evaluation\nof 30 clinical drugs against the comprehensive in vitro proarrhythmia\nassay (cipa) proposed ion channel panel\u201d","volume":"81","author":"Crumb","year":"2016","journal-title":"J. Pharmacol. Toxicol. Methods"},{"key":"2026092810073188000_cit12","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.ahj.2013.11.004","article-title":"\u201cRechanneling\nthe cardiac proarrhythmia safety paradigm: A meeting report from the\ncardiac safety research consortium\u201d","volume":"167","author":"Sager","year":"2014","journal-title":"Am. Heart J."},{"key":"2026092810073188000_cit13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.vascn.2016.06.002","article-title":"\u201cThe\ncomprehensive in vitro proarrhythmia assay (cipa) initiative \u2013\nupdate on progress\u201d","volume":"81","author":"Colatsky","year":"2016","journal-title":"J. Pharmacol. Toxicol.\nMethods"},{"key":"2026092810073188000_cit14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.vascn.2018.06.005","article-title":"\u201cCipa challenges\nand opportunities from a non-clinical, clinical and regulatory perspectives.\nan overview of the safety pharmacology scientific discussion\u201d","volume":"93","author":"Wallis","year":"2018","journal-title":"J. Pharmacol. Toxicol. Methods"},{"issue":"4","key":"2026092810073188000_cit15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s10928-025-09985-4","article-title":"FDA\u2019s insights: implementing\nnew strategies for evaluating drug-induced QTc prolongation","volume":"52","author":"Ji","year":"2025","journal-title":"J. Pharmacokinet. Pharmacodyn."},{"key":"2026092810073188000_cit16","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.vascn.2014.07.002","article-title":"\u201cPrediction of thorough qt\nstudy results using action potential simulations based on ion channel\nscreens\u201d","volume":"70","author":"Mirams","year":"2014","journal-title":"J. Pharmacol. Toxicol. Methods"},{"key":"2026092810073188000_cit17","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"\u201cScipy 1.0: fundamental algorithms for scientific\ncomputing in python\u201d","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"2026092810073188000_cit18","doi-asserted-by":"publisher","first-page":"917","DOI":"10.3389\/fphys.2017.00917","article-title":"\u201cUncertainty\nquantification reveals\nthe importance of data variability and experimental design considerations\nfor in silico proarrhythmia risk assessment\u201d","volume":"8","author":"Chang","year":"2017","journal-title":"Front. Physiol."},{"issue":"8","key":"2026092810073188000_cit19","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2025.03.1997","article-title":"\u201cThe modernized classification\nof cardiac antiarrhythmic drugs: Its application to clinical practice\u201d","volume":"22","author":"Lei","year":"2025","journal-title":"Heart Rhythm"},{"key":"2026092810073188000_cit20","doi-asserted-by":"crossref","DOI":"10.1002\/9783527621460.ch3","article-title":"Pharmacological\nand regulatory aspects of qt prolongation","volume-title":"Antitargets: Prediction and Prevention of Drug Side Effects","author":"De Ponti","year":"2008"},{"key":"2026092810073188000_cit21","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.vascn.2013.03.005","article-title":"\u201cA history of the role of\nthe herg channel in\ncardiac risk assessment\u201d","volume":"68","author":"Rampe","year":"2013","journal-title":"J. Pharmacol.\nToxicol. Methods"},{"key":"2026092810073188000_cit22","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1038\/s41580-024-00763-7","article-title":"\u201cStructural\nbiology and molecular pharmacology\nof voltage-gated ion channels\u201d","volume":"25","author":"Huang","year":"2024","journal-title":"Nat.\nRev. Mol. Cell Biol."},{"issue":"3","key":"2026092810073188000_cit23","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.cell.2017.03.048","article-title":"Cryo-EM Structure of the Open Human\nEther-a\u0300-go-go\n-Related K + Channel hERG","volume":"169","author":"Wang","year":"2017","journal-title":"Cell"},{"key":"2026092810073188000_cit24","doi-asserted-by":"publisher","first-page":"12329","DOI":"10.1073\/pnas.210244497","article-title":"\u201cA structural basis for drug-induced\nlong qt\nsyndrome\u201d","volume":"97","author":"Mitcheson","year":"2000","journal-title":"Proc. Natl. Acad. Sci. U.\nS. A."},{"key":"2026092810073188000_cit25","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1124\/mol.105.016741","article-title":"\u201cDrug\nbinding interactions in the inner cavity of herg channels: Molecular\ninsights from structure-activity relationships of clofilium and ibutilide\nanalogs\u201d","volume":"69","author":"Perry","year":"2006","journal-title":"Mol. Pharmacol."},{"key":"2026092810073188000_cit26","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.3389\/fphar.2019.01572","article-title":"\u201cAn\nupdate on the structure of herg\u201d","volume":"10","author":"Butler","year":"2020","journal-title":"Front.\nPharmacol."},{"key":"2026092810073188000_cit27","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1085\/jgp.201010582","article-title":"\u201cherg potassium channel gating\nis mediated by\nn- and c-terminal region interactions\u201d","volume":"137","author":"Gustina","year":"2011","journal-title":"J. Gen. Physiol."},{"key":"2026092810073188000_cit28","doi-asserted-by":"publisher","first-page":"3844","DOI":"10.1021\/jm0208875","article-title":"\u201cToward\na pharmacophore for drugs inducing the long qt syndrome: Insights\nfrom a comfa study of herg k+ channel blockers\u201d","volume":"45","author":"Cavalli","year":"2002","journal-title":"J. Med. Chem."},{"key":"2026092810073188000_cit29","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1124\/jpet.301.2.427","article-title":"\u201cThree-dimensional\nquantitative structure-activity relationship for inhibition of human\nether-a-go-go-related gene potassium channel\u201d","volume":"301","author":"Ekins","year":"2002","journal-title":"J. Pharmacol. Exp. Ther."},{"key":"2026092810073188000_cit30","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/1439-7633(20020503)3:5&lt;455::AID-CBIC455&gt;3.0.CO;2-L","article-title":"\u201cA\nvirtual screening method for prediction of\nthe herg potassium channel liability of compound libraries\u201d","volume":"3","author":"Roche","year":"2002","journal-title":"ChemBioChem"},{"key":"2026092810073188000_cit31","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1016\/j.bmc.2004.02.003","article-title":"\u201cA model\nfor identifying herg k+ channel blockers\u201d","volume":"12","author":"Aronov","year":"2004","journal-title":"Bioorg. Med. Chem."},{"key":"2026092810073188000_cit32","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.pbiomolbio.2003.09.001","article-title":"\u201cHerg binding\nspecificity\nand binding site structure: evidence from a fragment-based evolutionary\ncomputing sar study\u201d","volume":"86","author":"Bains","year":"2004","journal-title":"Prog. Biophys.\nMol. Biol."},{"key":"2026092810073188000_cit33","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1021\/ci050308f","article-title":"\u201cDevelopment and evaluation of an in silico model for herg\nbinding\u201d","volume":"46","author":"Song","year":"2006","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit34","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1002\/cmdc.200500099","article-title":"\u201cIn silico classification\nof herg channel blockers: a knowledge\u2013based strategy\u201d","volume":"1","author":"Dubus","year":"2006","journal-title":"ChemMedChem"},{"key":"2026092810073188000_cit35","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1016\/j.bmcl.2005.03.080","article-title":"\u201cA discriminant model constructed\nby the support vector machine method for herg potassium channel inhibitors\u201d","volume":"15","author":"Tobita","year":"2005","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"2026092810073188000_cit36","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1002\/cmdc.200700221","article-title":"\u201cA composite\nmodel for herg blockade\u201d","volume":"3","author":"Kramer","year":"2008","journal-title":"ChemMedChem"},{"key":"2026092810073188000_cit37","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1111\/j.1747-0285.2008.00747.x","article-title":"\u201cCombining cluster analysis,\nfeature selection and multiple support vector machine models for the\nidentification of human ether\u2013a\u2013go\u2013go related\ngene channel blocking compounds\u201d","volume":"73","author":"Nisius","year":"2009","journal-title":"Chem.\nBiol. Drug Des."},{"key":"2026092810073188000_cit38","doi-asserted-by":"publisher","first-page":"1847","DOI":"10.1021\/ci7000633","article-title":"\u201cGaussian\nprocesses: A method for automatic qsar modeling of adme properties\u201d","volume":"47","author":"Obrezanova","year":"2007","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit39","doi-asserted-by":"publisher","first-page":"4107","DOI":"10.1016\/j.bmc.2008.01.017","article-title":"\u201cA binary qsar model for classification of herg\npotassium channel blockers\u201d","volume":"16","author":"Thai","year":"2008","journal-title":"Bioorg.\nMed. Chem."},{"key":"2026092810073188000_cit40","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s11030-009-9117-0","article-title":"\u201cSimilarity-based sibar descriptors for classification\nof chemically diverse herg blockers\u201d","volume":"13","author":"Thai","year":"2009","journal-title":"Mol. Diversity"},{"key":"2026092810073188000_cit41","article-title":"\u201cGeneral and independent approaches to predict herg affinity\nvalues\u201d","volume-title":"Proceedings of the Internet\nElectronic Conference of Molecular Design 2004 IECMD 2004","author":"Fioravanzo","year":"2004"},{"key":"2026092810073188000_cit42","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1016\/j.bmcl.2005.03.062","article-title":"\u201cPredictive models for herg\npotassium channel blockers\u201d","volume":"15","author":"Cianchetta","year":"2005","journal-title":"Bioorg.\nMed. Chem. Lett."},{"key":"2026092810073188000_cit43","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.1016\/j.ejmech.2008.11.009","article-title":"\u201cGrind-based\n3d-qsar and comfa\nto investigate topics dominated by hydrophobic interactions: The case\nof herg k+ channel blockers\u201d","volume":"44","author":"Ermondi","year":"2009","journal-title":"Eur. J.\nMed. Chem."},{"key":"2026092810073188000_cit44","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1016\/S0960-894X(03)00492-X","article-title":"\u201cPrediction\nof herg potassium channel affinity by traditional and hologram qsar\nmethods\u201d","volume":"13","author":"Keseru\u0308","year":"2003","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"2026092810073188000_cit45","doi-asserted-by":"publisher","first-page":"3153","DOI":"10.1016\/j.bmc.2005.12.030","article-title":"\u201cPrediction of herg potassium channel affinity\nby the codessa approach\u201d","volume":"14","author":"Coi","year":"2006","journal-title":"Bioorg. Med.\nChem."},{"key":"2026092810073188000_cit46","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1111\/j.1747-0285.2006.00379.x","article-title":"\u201cA qsar model of herg binding using a large,\ndiverse, and internally consistent training set\u201d","volume":"67","author":"Seierstad","year":"2006","journal-title":"Chem. Biol. Drug Des."},{"key":"2026092810073188000_cit47","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1042\/bst0310611","article-title":"\u201cIn\nsilico approaches to predicting drug metabolism, toxicology and beyond\u201d","volume":"31","author":"Ekins","year":"2003","journal-title":"Biochem. Soc. Trans."},{"key":"2026092810073188000_cit48","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1016\/S0960-894X(03)00196-3","article-title":"\u201cCharacterization\nof herg potassium channel inhibition using comsia 3d qsar and homology\nmodeling approaches\u201d","volume":"13","author":"Pearlstein","year":"2003","journal-title":"Bioorg. Med. Chem.\nLett."},{"key":"2026092810073188000_cit49","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1021\/tx060230c","article-title":"\u201cA\nnovel approach using pharmacophore ensemble\/support vector machine\n(phe\/svm) for prediction of herg liability\u201d","volume":"20","author":"Leong","year":"2007","journal-title":"Chem. Res. Toxicol."},{"key":"2026092810073188000_cit50","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1021\/ci9000794","article-title":"\u201cBias-correction of regression\nmodels: A case study on herg inhibition\u201d","volume":"49","author":"Hansen","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit51","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1080\/10629360412331297353","article-title":"\u201cPrediction of herg k+ blocking potency: Application\nof structural knowledge\u201d","volume":"15","author":"Aptula","year":"2004","journal-title":"SAR QSAR Environ.\nRes."},{"key":"2026092810073188000_cit52","doi-asserted-by":"publisher","first-page":"5325","DOI":"10.1016\/j.bmc.2006.03.043","article-title":"\u201cDetermination of herg channel blockers using\na decision tree\u201d","volume":"14","author":"Gepp","year":"2006","journal-title":"Bioorg. Med. Chem."},{"key":"2026092810073188000_cit53","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1002\/qsar.200810015","article-title":"\u201cIdentifying\nherg potassium\nchannel inhibitors by machine learning methods\u201d","volume":"27","author":"Wang","year":"2008","journal-title":"QSAR Comb. Sci."},{"key":"2026092810073188000_cit54","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1111\/j.1747-0285.2009.00873.x","article-title":"\u201cQuantitative structure\u2013activity\nrelationship models for predicting biological properties, developed\nby combining structure and ligand based approaches: An application\nto the human ether-a-go-go related gene potassium channel inhibition\u201d","volume":"74","author":"Coi","year":"2009","journal-title":"Chem. Biol. Drug Des."},{"key":"2026092810073188000_cit55","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1021\/ci800304t","article-title":"\u201cSimilarity-based\nclassifier using topomers\nto provide a knowledge base for herg channel inhibition\u201d","volume":"49","author":"Nisius","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit56","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1002\/cmdc.200500047","article-title":"\u201cAn\naccurate and interpretable bayesian classification model for prediction\nof herg liability\u201d","volume":"1","author":"Sun","year":"2006","journal-title":"ChemMedChem"},{"issue":"11","key":"2026092810073188000_cit57","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"\u201cThe ChEMBL Database in 2023:\na drug discovery platform spanning multiple bioactivity data types\nand time periods\u201d","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"2026092810073188000_cit58","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"\u201cPubchem 2025 update\u201d","volume":"53","author":"Kim","year":"2025","journal-title":"Nucleic Acids Res."},{"issue":"5","key":"2026092810073188000_cit59","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1002\/cmdc.201000024","article-title":"\u201cProspective\nvalidation of a comprehensive in silico herg model and its applications\nto commercial compound and drug databases\u201d","volume":"5","author":"Doddareddy","year":"2010","journal-title":"ChemMedChem"},{"key":"2026092810073188000_cit60","doi-asserted-by":"publisher","first-page":"2240","DOI":"10.1021\/ci400308z","article-title":"\u201cherg\nme out\u201d","volume":"53","author":"Czodrowski","year":"2013","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit61","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1007\/s10822-016-9986-0","article-title":"\u201cCompilation\nand physicochemical classification\nanalysis of a diverse herg inhibition database\u201d","volume":"30","author":"Didziapetris","year":"2016","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"2026092810073188000_cit62","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1002\/minf.201000159","article-title":"\u201cDevelopment\nand comparison of herg blocker classifiers: Assessment on different\ndatasets yields markedly different results\u201d","volume":"30","author":"Marchese Robinson","year":"2011","journal-title":"Mol. Inf."},{"key":"2026092810073188000_cit63","doi-asserted-by":"publisher","first-page":"2290","DOI":"10.1021\/mp300156r","article-title":"\u201cQsar\nmodeling and data mining link torsades de pointes risk to the interplay\nof extent of metabolism, active transport, and herg liability\u201d","volume":"9","author":"Broccatelli","year":"2012","journal-title":"Mol. Pharm."},{"key":"2026092810073188000_cit64","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.2174\/1568026614666140506124442","article-title":"\u201cTuning herg out: Antitarget\nqsar models for drug development\u201d","volume":"14","author":"Braga","year":"2014","journal-title":"Curr.\nTop. Med. Chem."},{"issue":"4","key":"2026092810073188000_cit65","doi-asserted-by":"publisher","first-page":"1600126","DOI":"10.1002\/minf.201600126","article-title":"Prediction of hERG\nLiability \u2013 Using SVM Classification, Bootstrapping\nand Jackknifing","volume":"36","author":"Sun","year":"2017","journal-title":"Mol. Inf."},{"key":"2026092810073188000_cit66","first-page":"211","article-title":"Randomforest based assessment of the\nherg channel inhibition potential for the early drug cardiotoxicity\ntesting","volume-title":"Bio-Algorithms And Med-Systems","author":"Wis\u0301niowska","year":"2010"},{"key":"2026092810073188000_cit67","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1021\/acs.jcim.8b00150","article-title":"\u201cThe\ncatch-22 of predicting herg blockade using publicly accessible bioactivity\ndata\u201d","volume":"58","author":"Siramshetty","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit68","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.1021\/ci200271d","article-title":"\u201cA\ncritical assessment of\ncombined ligand- and structure-based approaches to herg channel blocker\nmodeling\u201d","volume":"51","author":"Du-Cuny","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit69","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s10822-016-9898-z","article-title":"\u201cA k-nearest\nneighbor classification of herg k+ channel blockers\u201d","volume":"30","author":"Chavan","year":"2016","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"2026092810073188000_cit70","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1021\/acs.jcim.8b00124","article-title":"\u201cMulti-descriptor\nread across (mudra): A simple\nand transparent approach for developing accurate quantitative structure\u2013activity\nrelationship models\u201d","volume":"58","author":"Alves","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit71","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/ci500747n","article-title":"\u201cDeep\nneural nets as a method for quantitative structure-activity relationships\u201d","volume":"55","author":"Ma","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit72","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.comtox.2017.05.001","article-title":"\u201cPerformance of machine learning algorithms\nfor qualitative and quantitative prediction drug blockade of herg1\nchannel\u201d","volume":"6","author":"Wacker","year":"2018","journal-title":"Comput. Toxicol."},{"issue":"2","key":"2026092810073188000_cit73","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1039\/C5TX00294J","article-title":"\u201cIn silico prediction of herg\npotassium channel blockage by\nchemical category approaches\u201d","volume":"5","author":"Zhang","year":"2016","journal-title":"Toxicol.\nRes."},{"key":"2026092810073188000_cit74","doi-asserted-by":"publisher","first-page":"1700074","DOI":"10.1002\/minf.201700074","article-title":"\u201cModeling of\nthe herg k+ channel blockage using online chemical database and modeling\nenvironment (ochem)\u201d","volume":"36","author":"Li","year":"2017","journal-title":"Mol. Inf."},{"issue":"4","key":"2026092810073188000_cit75","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.5012\/bkcs.2011.32.4.1237","article-title":"\u201cThe predictive qsar model\nfor herg inhibitors using bayesian and random forest classification\nmethod\u201d","volume":"32","author":"Kim","year":"2011","journal-title":"Bull. Korean Chem. Soc."},{"key":"2026092810073188000_cit76","doi-asserted-by":"publisher","first-page":"996","DOI":"10.1021\/mp300023x","article-title":"\u201cAdmet evaluation in drug discovery. 12. development of binary\nclassification models for prediction of herg potassium channel blockage\u201d","volume":"9","author":"Wang","year":"2012","journal-title":"Mol. Pharm."},{"key":"2026092810073188000_cit77","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1038\/aps.2014.35","article-title":"\u201cNovel bayesian classification\nmodels for predicting compounds blocking herg potassium channels\u201d","volume":"35","author":"Liu","year":"2014","journal-title":"Acta Pharmacol. Sin."},{"key":"2026092810073188000_cit78","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1002\/jat.2719","article-title":"\u201cSlow\ndelayed rectifying potassium current (iks) \u2013 analysis of the\nin vitro inhibition data and predictive model development\u201d","volume":"33","author":"Polak","year":"2013","journal-title":"J. Appl. Toxicol."},{"key":"2026092810073188000_cit79","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1002\/jat.2784","article-title":"\u201cPredictive\nmodel for l-type channel inhibition: multichannel block in qt prolongation\nrisk assessment\u201d","volume":"32","author":"Wis\u0301niowska","year":"2012","journal-title":"J. Appl. Toxicol."},{"key":"2026092810073188000_cit80","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1021\/ci100423z","article-title":"\u201cA\nmultiscale simulation system for the prediction of drug-induced cardiotoxicity\u201d","volume":"51","author":"Obiol-Pardo","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit81","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1021\/acs.jcim.6b00591","article-title":"\u201cExtreme\ngradient boosting as a method for quantitative structure-activity\nrelationships\u201d","volume":"56","author":"Sheridan","year":"2016","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit82","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1109\/BIBM47256.2019.8983163","article-title":"\u201cCardiotoxicity prediction\nbased on integreted herg database with molecular convolution model\u201d","volume-title":"2019 IEEE International Conference on Bioinformatics\nand Biomedicine (BIBM)","author":"Hu","year":"2019"},{"key":"2026092810073188000_cit83","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1093\/bioinformatics\/btaa075","article-title":"\u201cDeephit:\na deep learning framework for prediction of herg-induced cardiotoxicity\u201d","volume":"36","author":"Ryu","year":"2020","journal-title":"Bioinformatics"},{"issue":"1","key":"2026092810073188000_cit84","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s13321-021-00541-z","article-title":"\u201cCardiotox net: a robust predictor\nfor herg channel blockade based on deep learning meta-feature ensembles\u201d","volume":"13","author":"Karim","year":"2021","journal-title":"J. Cheminf."},{"key":"2026092810073188000_cit85","doi-asserted-by":"publisher","first-page":"6924","DOI":"10.1021\/acs.jmedchem.1c00421","article-title":"\u201cMining toxicity\ninformation from large amounts of toxicity\ndata\u201d","volume":"64","author":"Wu","year":"2021","journal-title":"J. Med. Chem."},{"key":"2026092810073188000_cit86","doi-asserted-by":"publisher","first-page":"W5","DOI":"10.1093\/nar\/gkab255","article-title":"\u201cAdmetlab\n2.0: an integrated online platform\nfor accurate and comprehensive predictions of admet properties\u201d","volume":"49","author":"Xiong","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2026092810073188000_cit87","doi-asserted-by":"publisher","first-page":"bbac211","DOI":"10.1093\/bib\/bbac211","article-title":"\u201cBayesherg:\na robust, reliable and interpretable deep learning model for predicting\nherg channel blockers\u201d","volume":"23","author":"Kim","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026092810073188000_cit88","doi-asserted-by":"publisher","first-page":"100121","DOI":"10.1016\/j.crtox.2023.100121","article-title":"\u201cherg-toxicity prediction\nusing traditional machine learning and advanced deep learning techniques\u201d","volume":"5","author":"Ylipa\u0308a\u0308","year":"2023","journal-title":"Curr. Res. Toxicol."},{"key":"2026092810073188000_cit89","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.3389\/fphar.2019.01631","article-title":"\u201cCapsule networks showed excellent performance\nin the classification of herg blockers\/nonblockers\u201d","volume":"10","author":"Wang","year":"2020","journal-title":"Front. Pharmacol."},{"key":"2026092810073188000_cit90","doi-asserted-by":"publisher","first-page":"109088","DOI":"10.1016\/j.cmpb.2025.109088","article-title":"\u201cMemol:\nMixture of experts\nfor multimodal learning through multi-head attention to predict drug\ntoxicity\u201d","volume":"273","author":"Chu","year":"2026","journal-title":"Comput. Methods Programs Biomed"},{"key":"2026092810073188000_cit91","doi-asserted-by":"publisher","first-page":"6007","DOI":"10.1021\/acs.jcim.0c00884","article-title":"\u201cCritical\nassessment of artificial intelligence\nmethods for prediction of herg channel inhibition in the \u201cbig\ndata\u201d era\u201d","volume":"60","author":"Siramshetty","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit92","doi-asserted-by":"publisher","first-page":"106464","DOI":"10.1016\/j.compbiomed.2022.106464","article-title":"\u201cInvestigating\ncardiotoxicity related with herg\nchannel blockers using molecular fingerprints and graph attention\nmechanism\u201d","volume":"153","author":"Wang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"2026092810073188000_cit93","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1021\/acs.jcim.3c01301","article-title":"\u201cBenchmarking\nof small molecule feature representations\nfor herg, nav1.5, and cav1.2 cardiotoxicity prediction\u201d","volume":"64","author":"Arab","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit94","doi-asserted-by":"publisher","first-page":"133825","DOI":"10.1016\/j.ijbiomac.2024.133825","article-title":"\u201cMulticblo:\nEnhancing predictions of compound-induced inhibition of cardiac ion\nchannels with advanced multimodal learning\u201d","volume":"276","author":"Wang","year":"2024","journal-title":"Int. J. Biol. Macromol."},{"key":"2026092810073188000_cit95","doi-asserted-by":"publisher","first-page":"3517","DOI":"10.1021\/acs.jcim.5c00022","article-title":"\u201cMultictox: Empowering accurate cardiotoxicity\nprediction through adaptive multimodal learning\u201d","volume":"65","author":"Feng","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"2026092810073188000_cit96","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s13321-025-00976-8","article-title":"\u201cCardiogenai:\na machine learning-based framework for re-engineering drugs for reduced\nherg liability\u201d","volume":"17","author":"Kyro","year":"2025","journal-title":"J. Cheminf."},{"issue":"1","key":"2026092810073188000_cit97","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13321-025-00957-x","article-title":"\u201chergat: predicting herg blockers using graph\nattention mechanism\nthrough atom- and molecule-level interaction analyses\u201d","volume":"17","author":"Lee","year":"2025","journal-title":"J. Cheminf."},{"key":"2026092810073188000_cit98","doi-asserted-by":"publisher","first-page":"81018","DOI":"10.1109\/ACCESS.2025.3566440","article-title":"\u201cLeveraging\nmachine and deep learning algorithms for herg blocker prediction\u201d","volume":"13","author":"Mohammad","year":"2025","journal-title":"IEEE Access"},{"key":"2026092810073188000_cit99","doi-asserted-by":"publisher","first-page":"103","DOI":"10.47852\/bonviewMEDIN42022049","article-title":"\u201cClop-herg:\nThe contrastive learning optimized\npre-trained model for representation learning in predicting drug-induced\nherg channel blockers\u201d","volume":"1","author":"He","year":"2024","journal-title":"Medinformatics"},{"key":"2026092810073188000_cit100","doi-asserted-by":"publisher","DOI":"10.1101\/2025.02.17.638731","article-title":"herg-ltn: A new\nparadigm in herg cardiotoxicity assessment using neuro-symbolic and\ngenerative ai embedding (megamolbart, llama3.2, gemini, deepseek)\napproach","author":"Hossain","year":"2025","journal-title":"bioRxiv"},{"issue":"20","key":"2026092810073188000_cit101","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.4155\/fmc-2020-0156","article-title":"Machine learning-based\nQSAR Models to Predict Sodium Ion Channel (Na v 1.5) Blockers","volume":"12","author":"Khalifa","year":"2020","journal-title":"Future Med. Chem."},{"key":"2026092810073188000_cit102","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1111\/jcmm.17652","article-title":"\u201cMultiple machine\nlearning methods aided virtual screening of nav1.5 inhibitors\u201d","volume":"27","author":"Kong","year":"2023","journal-title":"J. Cell. Mol. Med."},{"key":"2026092810073188000_cit103","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.13467","article-title":"Toxtree: descriptor-based\nmachine learning models for both herg and nav1.5 cardiotoxicity liability\npredictions","author":"Arab","year":"2021","journal-title":"arXiv"},{"key":"2026092810073188000_cit104","doi-asserted-by":"publisher","first-page":"6410","DOI":"10.1021\/acs.jcim.4c01102","article-title":"\u201cSemisupervised\nlearning to boost herg, nav1.5, and cav1.2 cardiac ion channel toxicity\nprediction by mining a large unlabeled small molecule data set\u201d","volume":"64","author":"Arab","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit105","doi-asserted-by":"publisher","first-page":"134724","DOI":"10.1016\/j.jhazmat.2024.134724","article-title":"\u201cCardiodpi: An explainable deep-learning model for identifying\ncardiotoxic chemicals targeting herg, cav1.2, and nav1.5 channels\u201d","volume":"474","author":"Chen","year":"2024","journal-title":"J. Hazard. Mater."},{"key":"2026092810073188000_cit106","doi-asserted-by":"publisher","first-page":"117575","DOI":"10.1016\/j.ejmech.2025.117575","article-title":"\u201cCupid: A free drug discovery\nplatform for the explainable multi-ion channel assessment of cardiotoxicity\u201d","volume":"290","author":"Gambacorta","year":"2025","journal-title":"Eur. J. Med. Chem."},{"key":"2026092810073188000_cit107","doi-asserted-by":"publisher","DOI":"10.64898\/2026.05.06.723181","article-title":"Cardiosafe: Multi-task\nprediction of cardiac ion channel activity with reverse-leak audited\nbenchmarking","author":"Jovanovic\u0301","year":"2026","journal-title":"bioRxiv"},{"key":"2026092810073188000_cit108","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1021\/acs.jcim.8b00769","article-title":"\u201cDeep\nlearning-based\nprediction of drug-induced cardiotoxicity\u201d","volume":"59","author":"Cai","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit109","doi-asserted-by":"publisher","first-page":"100089","DOI":"10.1016\/j.comtox.2019.100089","article-title":"\u201cherg liability\nclassification models using machine learning techniques\u201d","volume":"12","author":"Konda","year":"2019","journal-title":"Comput. Toxicol."},{"key":"2026092810073188000_cit110","doi-asserted-by":"publisher","first-page":"4758","DOI":"10.1021\/acs.jcim.1c00744","article-title":"\u201cStructure-based prediction\nof herg-related cardiotoxicity: A benchmark study\u201d","volume":"61","author":"Creanza","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"2026092810073188000_cit111","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1021\/acs.chemrestox.5c00369","article-title":"\u201cGraph-based\nclassification with gnn-explainer for predicting cardiac toxicity\nassociated with multi-ion channel blockers\u201d","volume":"39","author":"Agarwal","year":"2026","journal-title":"Chem. Res. Toxicol."},{"key":"2026092810073188000_cit112","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","article-title":"\u201cOn a test\nof whether one\nof two random variables is stochastically larger than the other\u201d","volume":"18","author":"Mann","year":"1947","journal-title":"Ann. Math. Stat."},{"key":"2026092810073188000_cit113","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1002\/ejsp.2420020412","article-title":"\u201cDealing with a common problem in social science:\nA simplified rank-biserial coefficient of correlation based on the\nu statistic\u201d","volume":"2","author":"Wendt","year":"1972","journal-title":"Eur. J. Soc. Psychol."},{"key":"2026092810073188000_cit114","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"\u201cControlling\nthe false discovery\nrate: A practical and powerful approach to multiple testing\u201d","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. Royal Stat. Society: Ser. B"},{"key":"2026092810073188000_cit115","doi-asserted-by":"publisher","first-page":"3385","DOI":"10.3390\/ijms20143385","article-title":"\u201cMolecular docking\nguided grid-independent descriptor analysis to probe the impact of\nwater molecules on conformational changes of herg inhibitors in drug\ntrapping phenomenon\u201d","volume":"20","author":"Munawar","year":"2019","journal-title":"Int. J. Mol. Sci."},{"issue":"1","key":"2026092810073188000_cit116","doi-asserted-by":"publisher","first-page":"16586","DOI":"10.1038\/s41598-019-53120-6","article-title":"\u201cCalculation\nof absolute binding free energies between the herg channel and structurally\ndiverse drugs\u201d","volume":"9","author":"Negami","year":"2019","journal-title":"Sci. Rep."},{"key":"2026092810073188000_cit117","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1021\/acs.jcim.7b00403","article-title":"\u201cMost ligand-based classification\nbenchmarks reward memorization rather than generalization\u201d","volume":"58","author":"Wallach","year":"2018","journal-title":"J. Chem. Inf. Model."},{"issue":"2","key":"2026092810073188000_cit118","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"\u201cMoleculenet:\na benchmark for molecular machine learning\u201d","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"2026092810073188000_cit119","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1002\/prot.25823","article-title":"\u201cCritical\nassessment of methods of protein structure prediction\n(casp)-round xiii\u201d","volume":"87","author":"Kryshtafovych","year":"2019","journal-title":"Proteins: Struct.,\nFunct., Bioinf."},{"key":"2026092810073188000_cit120","unstructured":"McManus, O. B.; Garcia, M. L.; Weaver, D.; Bryant, M.; Titus, S.; Herrington, J. B.,  \u201cIon channel screening,\u201d\nin Assay Guidance Manual, Bethesda, MD: Eli Lilly & Company and\nthe National Center for Advancing Translational Sciences; 2012. https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK100915\/."},{"key":"2026092810073188000_cit121","doi-asserted-by":"publisher","first-page":"107803","DOI":"10.1016\/j.vascn.2025.107803","article-title":"\u201cTemperature effect on herg channel pharmacology\nmeasured using the qube automated patch clamp system\u201d","volume":"135","author":"Nagy","year":"2025","journal-title":"J. Pharmacol. Toxicol. Methods"},{"key":"2026092810073188000_cit122","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s13321-026-01165-x","article-title":"\u201cIntegrating artificial intelligence and manual\ncuration to enhance bioassay annotations in chembl\u201d","volume":"18","author":"Smit","year":"2026","journal-title":"J. Cheminf."},{"key":"2026092810073188000_cit124","doi-asserted-by":"publisher","first-page":"3862","DOI":"10.1016\/j.bpj.2009.02.017","article-title":"\u201cMechanisms\nof \u03b2-adrenergic modulation\nof iks in the guinea-pig ventricle: Insights from experimental and\nmodel-based analysis\u201d","volume":"96","author":"Severi","year":"2009","journal-title":"Biophys. J."},{"key":"2026092810073188000_cit125","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002061","article-title":"\u201cSimulation of the undiseased\nhuman cardiac ventricular action\npotential: Model formulation and experimental validation\u201d","volume":"7","author":"O\u2019hara","year":"2011","journal-title":"PLoS Comput. Biol."},{"key":"2026092810073188000_cit126","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.125.328073","article-title":"\u201cT-world virtual\nhuman cardiomyocyte. i. development, validation, and cell arrhythmogenesis\u201d","volume":"138","author":"Tomek","year":"2026","journal-title":"Circ. Res."},{"key":"2026092810073188000_cit127","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1038\/s42256-025-00991-2","article-title":"\u201cData-driven\nfederated learning in drug discovery with knowledge distillation\u201d","volume":"7","author":"Hanser","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026092810073188000_cit128","article-title":"\u201cFS-Mol:\nA few-shot learning dataset of molecules\u201d","volume-title":"Thirty-fifth Conference on Neural Information Processing\nSystems (NeurIPS) Datasets and Benchmarks Track","author":"Stanley","year":"2021"},{"key":"2026092810073188000_cit129","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1021\/acscentsci.6b00367","article-title":"\u201cLow\ndata drug discovery with one-shot learning\u201d","volume":"3","author":"Altae-Tran","year":"2017","journal-title":"ACS Cent. Sci."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c03072","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11605\/68539405\/acs.jcim.6c03072.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11605\/68539405\/acs.jcim.6c03072.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:16:44Z","timestamp":1790605004000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/18\/11605\/5431755\/25-Years-of-Cardiac-Ion-Channel-QSAR-From-hERG"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":126,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,17]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c03072","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.15004509\/v1","asserted-by":"object"}]},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}