Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks

Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen; Wilkes, Jon

doi:10.1186/s12859-017-1895-2

Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks

Journal Article · Fri Dec 01 00:00:00 EST 2017 · BMC Bioinformatics

DOI:https://doi.org/10.1186/s12859-017-1895-2· OSTI ID:1626766

Sharifi, Mohsen ^[1]; Buzatu, Dan ^[2]; Harris, Stephen ^[2]; Wilkes, Jon ^[2]

U.S. Food and Drug Administration (FDA), Jefferson, AR (United States). National Center for Toxicology Research. Division of Systems Biology; DOE/OSTI
U.S. Food and Drug Administration (FDA), Jefferson, AR (United States). National Center for Toxicology Research. Division of Systems Biology

Background: Blockage of some ion channels and in particular, the hERG (human Ether-a’-go-go-Related Gene) cardiac potassium channel delays cardiac repolarization and can induce arrhythmia. In some cases it leads to a potentially life-threatening arrhythmia known as Torsade de Pointes (TdP). Therefore recognizing drugs with TdP risk is essential. Candidate drugs that are determined not to cause cardiac ion channel blockage are more likely to pass successfully through clinical phases II and III trials (and preclinical work) and not be withdrawn even later from the marketplace due to cardiotoxic effects. The objective of the present study is to develop an SAR (Structure-Activity Relationship) model that can be used as an early screen for torsadogenic (causing TdP arrhythmias) potential in drug candidates. The method is performed using descriptors comprised of atomic NMR chemical shifts (13C and 15N NMR) and corresponding interatomic distances which are combined into a 3D abstract space matrix. The method is called 3D-SDAR (3-dimensional spectral data-activity relationship) and can be interrogated to identify molecular features responsible for the activity, which can in turn yield simplified hERG toxicophores. A dataset of 55 hERG potassium channel inhibitors collected from Kramer et al. consisting of 32 drugs with TdP risk and 23 with no TdP risk was used for training the 3D-SDAR model. Results: An artificial neural network (ANN) with multilayer perceptron was used to define collinearities among the independent 3D-SDAR features. A composite model from 200 random iterations with 25% of the molecules in each case yielded the following figures of merit: training, 99.2%; internal test sets, 66.7%; external (blind validation) test set, 68. 4%. In the external test set, 70.3% of positive TdP drugs were correctly predicted. Moreover, toxicophores were generated from TdP drugs. Conclusion: A 3D-SDAR was successfully used to build a predictive model for drug-induced torsadogenic and non-torsadogenic drugs based on 55 compounds. The model was tested in 38 external drugs.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge Institute for Science and Education (ORISE), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: SC0014664

OSTI ID:: 1626766

Journal Information:: BMC Bioinformatics, Journal Name: BMC Bioinformatics Journal Issue: S14 Vol. 18; ISSN 1471-2105

Publisher:: BioMed CentralCopyright Statement

Country of Publication:: United States

Language:: English

References (37)

Torsades de Pointes Occurring in Association With Terfenadine Use Monahan, Brian P. JAMA: The Journal of the American Medical Association, Vol. 264, Issue 21 https://doi.org/10.1001/jama.1990.03450210088038	journal	December 1990
QT prolongation and torsades de pointes among methadone users: reports to the FDA spontaneous reporting system Pearson, Ellen C.; Woosley, Raymond L. Pharmacoepidemiology and Drug Safety, Vol. 14, Issue 11 https://doi.org/10.1002/pds.1112	journal	November 2005
Alignment-independent technique for 3D QSAR analysis Wilkes, Jon G.; Stoyanova-Slavova, Iva B.; Buzatu, Dan A. Journal of Computer-Aided Molecular Design, Vol. 30, Issue 4 https://doi.org/10.1007/s10822-016-9909-0	journal	March 2016
Dealing with Global Safety Issues: Was the Response to QT-Liability of Non-Cardiac Drugs Well Coordinated? Stockbridge, Norman; Morganroth, Joel; Shah, Rashmi R. Drug Safety, Vol. 36, Issue 3 https://doi.org/10.1007/s40264-013-0016-z	journal	February 2013
Computational investigations of hERG channel blockers: New insights and current predictive models Villoutreix, Bruno O.; Taboureau, Olivier Advanced Drug Delivery Reviews, Vol. 86 https://doi.org/10.1016/j.addr.2015.03.003	journal	June 2015
Contribution of voltage-gated potassium channels to the regulation of apoptosis Szabò, Ildikò; Zoratti, Mario; Gulbins, Erich FEBS Letters, Vol. 584, Issue 10 https://doi.org/10.1016/j.febslet.2010.01.038	journal	January 2010
Computational approaches to understand the adverse drug effect on potassium, sodium and calcium channels for predicting TdP cardiac arrhythmias Sharifi, Mohsen Journal of Molecular Graphics and Modelling, Vol. 76 https://doi.org/10.1016/j.jmgm.2017.06.012	journal	September 2017
Structure and function of two-pore-domain K channels: contributions from genetic model organisms Buckingham, S.; Kidd, J.; Law, R. Trends in Pharmacological Sciences, Vol. 26, Issue 7 https://doi.org/10.1016/j.tips.2005.05.003	journal	July 2005
Hose — a novel substructure code Bremser, W. Analytica Chimica Acta, Vol. 103, Issue 4 https://doi.org/10.1016/s0003-2670(01)83100-7	journal	December 1978
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 Redfern, W.; Carlsson, L.; Davis, A. Cardiovascular Research, Vol. 58, Issue 1 https://doi.org/10.1016/s0008-6363(02)00846-5	journal	April 2003
Characterization of HERG potassium channel inhibition using CoMSiA 3D QSAR and homology modeling approaches Pearlstein, Robert A.; Vaz, Roy J.; Kang, Jiesheng Bioorganic & Medicinal Chemistry Letters, Vol. 13, Issue 10 https://doi.org/10.1016/s0960-894x(03)00196-3	journal	May 2003
Experimentally Validated hERG Pharmacophore Models as Cardiotoxicity Prediction Tools Kratz, Jadel M.; Schuster, Daniela; Edtbauer, Michael Journal of Chemical Information and Modeling, Vol. 54, Issue 10 https://doi.org/10.1021/ci5001955	journal	September 2014
Voltage-gated potassium channels as therapeutic targets Wulff, Heike; Castle, Neil A.; Pardo, Luis A. Nature Reviews Drug Discovery, Vol. 8, Issue 12 https://doi.org/10.1038/nrd2983	journal	December 2009
Cisapride and Fatal Arrhythmia Wysowski, Diane K.; Bacsanyi, Janos New England Journal of Medicine, Vol. 335, Issue 4 https://doi.org/10.1056/nejm199607253350416	journal	July 1996
Simulation of multiple ion channel block provides improved early prediction of compounds’ clinical torsadogenic risk Mirams, Gary R.; Cui, Yi; Sher, Anna Cardiovascular Research, Vol. 91, Issue 1 https://doi.org/10.1093/cvr/cvr044	journal	February 2011
The Utility of hERG and Repolarization Assays in Evaluating Delayed Cardiac Repolarization: Influence of Multi-Channel Block Martin, Ruth L.; McDermott, Jeff S.; Salmen, Heinz J. Journal of Cardiovascular Pharmacology, Vol. 43, Issue 3 https://doi.org/10.1097/00005344-200403000-00007	journal	January 2004
Three-Dimensional Quantitative Structure-Activity Relationship for Inhibition of Human Ether-a-Go-Go -Related Gene Potassium Channel Ekins, Sean; Crumb, William J.; Sarazan, R. Dustan Journal of Pharmacology and Experimental Therapeutics, Vol. 301, Issue 2 https://doi.org/10.1124/jpet.301.2.427	journal	May 2002
Drug induced QT prolongation and torsades de pointes Yap, Y. G. Heart, Vol. 89, Issue 11 https://doi.org/10.1136/heart.89.11.1363	journal	November 2003
Cardiac Ion Channels Grant, Augustus O. Circulation: Arrhythmia and Electrophysiology, Vol. 2, Issue 2 https://doi.org/10.1161/circep.108.789081	journal	April 2009
Antipsychotic Drugs: Prolonged QTc Interval, Torsade de Pointes, and Sudden Death Glassman, Alexander H.; Bigger, J. Thomas American Journal of Psychiatry, Vol. 158, Issue 11 https://doi.org/10.1176/appi.ajp.158.11.1774	journal	November 2001
In Silico Predictions of hERG Channel Blockers in Drug Discovery: From Ligand-Based and Target-Based Approaches to Systems Chemical Biology Taboureau, Olivier; Steen Jorgensen, Flemming Combinatorial Chemistry & High Throughput Screening, Vol. 14, Issue 5 https://doi.org/10.2174/138620711795508322	journal	June 2011
Torsades de pointes occurring in association with terfenadine use Monahan, B. P. JAMA: The Journal of the American Medical Association, Vol. 264, Issue 21 https://doi.org/10.1001/jama.264.21.2788	journal	December 1990
Torsades de pointes occurring in association with terfenadine use Mathews, D. R. JAMA: The Journal of the American Medical Association, Vol. 266, Issue 17 https://doi.org/10.1001/jama.266.17.2375	journal	November 1991
A Composite Model for hERG Blockade Kramer, Christian; Beck, Bernd; Kriegl, Jan M. ChemMedChem, Vol. 3, Issue 2 https://doi.org/10.1002/cmdc.200700221	journal	February 2008
Using Neural Networks for 13C NMR Chemical Shift Prediction–Comparison with Traditional Methods Meiler, Jens; Maier, Walter; Will, Martin Journal of Magnetic Resonance, Vol. 157, Issue 2 https://doi.org/10.1006/jmre.2002.2599	journal	August 2002
Clinical guidance for navigating the QTc-prolonging and arrhythmogenic potential of pharmacotherapy during the COVID-19 pandemic Carron, Jennifer; Sharif, Zain; Hussein, Hafiz Irish Journal of Medical Science (1971 -), Vol. 190, Issue 1 https://doi.org/10.1007/s11845-020-02291-7	journal	July 2020
Hose — a novel substructure code Bremser, W. Analytica Chimica Acta, Vol. 103, Issue 4 https://doi.org/10.1016/S0003-2670(01)83100-7	journal	December 1978
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 Redfern, W.; Carlsson, L.; Davis, A. Cardiovascular Research, Vol. 58, Issue 1 https://doi.org/10.1016/S0008-6363(02)00846-5	journal	April 2003
Characterization of HERG potassium channel inhibition using CoMSiA 3D QSAR and homology modeling approaches Pearlstein, Robert A.; Vaz, Roy J.; Kang, Jiesheng Bioorganic & Medicinal Chemistry Letters, Vol. 13, Issue 10 https://doi.org/10.1016/S0960-894X(03)00196-3	journal	May 2003
3D-SDAR modeling of hERG potassium channel affinity: A case study in model design and toxicophore identification Stoyanova-Slavova, Iva B.; Slavov, Svetoslav H.; Buzatu, Dan A. Journal of Molecular Graphics and Modelling, Vol. 72 https://doi.org/10.1016/j.jmgm.2017.01.012	journal	March 2017
Methadone—metabolism, pharmacokinetics and interactions Ferrari, A.; Coccia, C.; Bertolini, A. Pharmacological Research, Vol. 50, Issue 6 https://doi.org/10.1016/j.phrs.2004.05.002	journal	December 2004
Predicting drug–hERG channel interactions that cause acquired long QT syndrome Sanguinetti, Michael C.; Mitcheson, John S. Trends in Pharmacological Sciences, Vol. 26, Issue 3 https://doi.org/10.1016/j.tips.2005.01.003	journal	March 2005
MICE Models: Superior to the HERG Model in Predicting Torsade de Pointes Kramer, James; Obejero-Paz, Carlos A.; Myatt, Glenn Scientific Reports, Vol. 3, Issue 1 https://doi.org/10.1038/srep02100	journal	July 2013
Cisapride and Fatal Arrhythmia Wysowski, Diane K.; Bacsanyi, Janos New England Journal of Medicine, Vol. 335, Issue 4 https://doi.org/10.1056/NEJM199607253350416	journal	July 1996
Cardiac Ion Channels Epstein, Franklin H.; Katz, Arnold M. New England Journal of Medicine, Vol. 328, Issue 17 https://doi.org/10.1056/nejm199304293281707	journal	April 1993
Cardiac ion channels Priest, Birgit T.; McDermott, Jeff S. Channels, Vol. 9, Issue 6 https://doi.org/10.1080/19336950.2015.1076597	journal	July 2015
Cardiac Ion Channels Grant, Augustus O. Circulation: Arrhythmia and Electrophysiology, Vol. 2, Issue 2 https://doi.org/10.1161/CIRCEP.108.789081	journal	April 2009

Cited By (2)

Synthesis and Biological Evaluation of Five‐Atom‐Linker‐Based Arylpiperazine Derivatives with an Atypical Antipsychotic Profile Wu, Chunhui; Wang, Yu; Yang, Feipu ChemMedChem, Vol. 14, Issue 24 https://doi.org/10.1002/cmdc.201900439	journal	November 2019
Comparison of Machine Learning Techniques for Prediction of Hospitalization in Heart Failure Patients Lorenzoni, Giulia; Sabato, Stefano Santo; Lanera, Corrado Journal of Clinical Medicine, Vol. 8, Issue 9 https://doi.org/10.3390/jcm8091298	journal	August 2019

Similar Records

The continuing evolution of torsades de pointes liability testing methods: Is there an end in sight?

Journal Article · Sun Feb 28 23:00:00 EST 2010 · Toxicology and Applied Pharmacology · OSTI ID:21344875

Use of in vitro methods to predict QT prolongation

Journal Article · Thu Sep 01 00:00:00 EDT 2005 · Toxicology and Applied Pharmacology · OSTI ID:20721943

Mechanisms of QT prolongation by buprenorphine cannot be explained by direct hERG channel block

Journal Article · Thu Nov 05 19:00:00 EST 2020 · PLoS ONE · OSTI ID:1904961

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
Artificial Neural Network
Biochemistry & Molecular Biology
Biotechnology & Applied Microbiology
Cardiac arrhythmia
Cardiotoxicity
Ion channels
Mathematical & Computational Biology
Multilayer Perceptron
Quantitative structure-activity relationship
Spectral data-activity relationship
TdP
Torsade de Pointes
hERG

Additional file 4: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/M9.FIGSHARE.5742276 The current record is supplemented by this dataset	dataset	January 2017
Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/M9.FIGSHARE.C.3964365 The current record is supplemented by this collection	collection	January 2017
Additional file 1: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742210 The current record is supplemented by this dataset	dataset	January 2017
Additional file 1: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742210.v1 The current record is supplemented by this dataset	dataset	January 2017
Additional file 2: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742237 The current record is supplemented by this text	text	January 2017
Additional file 2: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742237.v1 The current record is supplemented by this text	text	January 2017
Additional file 3: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742258 The current record is supplemented by this text	text	January 2017
Additional file 3: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742258.v1 The current record is supplemented by this text	text	January 2017
Additional file 4: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742276.v1 The current record is supplemented by this dataset	dataset	January 2017
Additional file 5: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742297 The current record is supplemented by this text	text	January 2017
Additional file 5: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742297.v1 The current record is supplemented by this text	text	January 2017
Additional file 6: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742306 The current record is supplemented by this text	text	January 2017
Additional file 6: of Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.5742306.v1 The current record is supplemented by this text	text	January 2017
Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks Sharifi, Mohsen; Buzatu, Dan; Harris, Stephen https://doi.org/10.6084/m9.figshare.c.3964365.v1 The current record is supplemented by this collection	collection	January 2017

Development of models for predicting Torsade de Pointes cardiac arrhythmias using perceptron neural networks

Citation Formats

References (37)

Cited By (2)

Linked Research (14)

Similar Records

Related Subjects