Molecular Diversity

, Volume 13, Issue 3, pp 321–336 | Cite as

Similarity-based SIBAR descriptors for classification of chemically diverse hERG blockers

  • Khac-Minh Thai
  • Gerhard F. EckerEmail author
Full Length Paper


There is an increasing interest in computational models for the classification and prediction of the human ether-a-go-go-related-gene (hERG) potassium channel affinity in the early phase of drug discovery and development. In this study, similarity-based SIBAR descriptors were applied in order to develop and validate in silico binary QSAR and counter-propagation neural network models for the classification of hERG activity. The SIBAR descriptors were calculated based on four reference datasets using four sets of 2D- and 3D-descriptors including 3D-grid-based VolSurf, 3D ‘inductive’ QSAR, Van der Waals surface area (P_VSA) and a set of 11 hERG relevant 2D descriptors devised from feature selection methods. The results indicate that the reference data set tailored to the specific problem, together with a set of hERG relevant descriptors, provides highly predictive models.


hERG SIBAR Classification Counter-propagation neural networks Antitarget Similarity-based descriptor 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

11030_2009_9117_MOESM1_ESM.pdf (659 kb)
ESM 1 (PDF 660kb)
11030_2009_9117_MOESM2_ESM.docx (10 kb)
ESM 2 (DOCX 11kb)


  1. 1.
    Ekins S (2004) Predicting undesirable drug interactions with promiscuous proteins in silico. Drug Discov Today 9: 276–285. doi: 10.1016/S1359-6446(03)03008-3 PubMedCrossRefGoogle Scholar
  2. 2.
    Ecker GF, Stockner T, Chiba P (2008) Computational models for prediction of interactions with ABC-transporters. Drug Discov Today 13: 311–317. doi: 10.1016/j.drudis.2007.12.012 PubMedCrossRefGoogle Scholar
  3. 3.
    Thai K-M, Ecker GF (2007) Predictive models for hERG channel blockers: ligand-based and structure-based approaches. Curr Med Chem 14: 3003–3026. doi: 10.2174/092986707782794087 PubMedCrossRefGoogle Scholar
  4. 4.
    Aronov AM (2005) Predictive in silico modeling for hERG channel blockers. Drug Discov Today 10: 149–155. doi: 10.1016/S1359-6446(04)03278-7 PubMedCrossRefGoogle Scholar
  5. 5.
    Witchel HJ (2007) The hERG potassium channel as a therapeutic target. Expert Opin Ther Targets 11: 321–336. doi: 10.1517/14728222.11.3.321 PubMedCrossRefGoogle Scholar
  6. 6.
    Recanatini M, Poluzzi E, Masetti M, Cavalli A, De Ponti F (2005) QT prolongation through hERG K(+) channel blockade: current knowledge and strategies for the early prediction during drug development. Med Res Rev 25: 133–166. doi: 10.1002/med.20019 PubMedCrossRefGoogle Scholar
  7. 7.
    Fermini B, Fossa AA (2003) The impact of drug-induced QT interval prolongation on drug discovery and development. Nat Rev Drug Discov 2: 439–447. doi: 10.1038/nrd1108 PubMedCrossRefGoogle Scholar
  8. 8.
    Sanguinetti MC, Tristani-Firouzi M (2006) hERG potassium channels and cardiac arrhythmia. Nature 440: 463–469. doi: 10.1038/nature04710 PubMedCrossRefGoogle Scholar
  9. 9.
    Aronov AM (2008) Tuning out of hERG. Curr Opin Drug Discov Devel 11: 128–135PubMedGoogle Scholar
  10. 10.
    Kaiser D, Zdrazil B, Ecker GF (2005) Similarity-based descriptors (SIBAR)—a tool for safe exchange of chemical information. J Comput Aided Mol Des 19: 687–692. doi: 10.1007/s10822-005-9000-8 PubMedCrossRefGoogle Scholar
  11. 11.
    Klein C, Kaiser D, Kopp S, Chiba P, Ecker GF (2002) Similarity based SAR (SIBAR) as tool for early ADME profiling. J Comput Aided Mol Des 16: 785–793. doi: 10.1023/A:1023828527638 PubMedCrossRefGoogle Scholar
  12. 12.
    Zdrazil B, Kaiser D, Kopp S, Chiba P, Ecker Gerhard F (2007) Similarity-based descriptors (SIBAR) as tool for QSAR studies on p-glycoprotein inhibitors: influence of the reference set. QSAR Comb Sci 26: 669–678. doi: 10.1002/qsar.200610149 CrossRefGoogle Scholar
  13. 13.
    MOE 2007.02 Chemical Computing Group Inc., Montreal, H3A 2R7 Canada,
  14. 14.
    Crivori P, Cruciani G, Carrupt PA, Testa B (2000) Predicting blood-brain barrier permeation from three-dimensional molecular structure. J Med Chem 43: 2204–2216. doi: 10.1021/jm990968+ PubMedCrossRefGoogle Scholar
  15. 15.
    Cherkasov A, Shi Z, Fallahi M, Hammond GL (2005) Successful in silico discovery of novel nonsteroidal ligands for human sex hormone binding globulin. J Med Chem 48: 3203–3213. doi: 10.1021/jm049087f PubMedCrossRefGoogle Scholar
  16. 16.
    Cherkasov A (2005) ‘Inductive’ descriptors: 10 successful years in QSAR. Curr Comput Aided Drug Des 1: 21–42. doi: 10.2174/1573409052952288 CrossRefGoogle Scholar
  17. 17.
    Thai K-M, Ecker GF (2008) A binary QSAR model for classification of hERG potassium channel blockers. Bioorg Med Chem 16: 4107–4119. doi: 10.1016/j.bmc.2008.01.017 PubMedCrossRefGoogle Scholar
  18. 18.
    PubChem, National Center for Biotechnology Information NCBI,
  19. 19.
    Labute P (2000) A widely applicable set of descriptors. J Mol Graph Model 18: 464–477. doi: 10.1016/S1093-3263(00)00068-1 PubMedCrossRefGoogle Scholar
  20. 20.
    Hogg RV, Tanis EA (1993) Probability and statistical inference. Macmillan Publishing, New YorkGoogle Scholar
  21. 21.
    Thai K-M, Ecker GF (2008) Classification models for hERG inhibitors by counter-propagation neural networks. Chem Biol Drug Des 72: 279–289. doi: 10.1111/j.1747-0285.2008.00705.x PubMedCrossRefGoogle Scholar
  22. 22.
    Schwaha R, Ecker GF (2008) The similarity principle—new trends and applications in ligand-based drug discovery and ADMET profiling. Sci Pharm 76: 5–18. doi: 10.3797/scipharm.0802-05 CrossRefGoogle Scholar
  23. 23.
    Sköld C, Winiwarter S, Wernevik J, Bergstrom F, Engstrom L, Allen R, Box K, Comer J, Mole J, Hallberg A, Lennernas H, Lundstedt T, Ungell AL, Karlen A (2006) Presentation of a structurally diverse and commercially available drug data set for correlation and benchmarking studies. J Med Chem 49: 6660–6671. doi: 10.1021/jm0506219 PubMedCrossRefGoogle Scholar
  24. 24.
    Labute P (1999) Binary QSAR: a new method for the determination of quantitative structure activity relationships. In: Proceedings of the Pacific Symposium on Biocomputing, pp 444–455Google Scholar
  25. 25.
    Roncaglioni A, Novic M, Vracko M, Benfenati E (2004) Classification of potential endocrine disrupters on the basis of molecular structure using a nonlinear modeling method. J Chem Inf Comput Sci 44: 300–309. doi: 10.1021/ci030421a PubMedGoogle Scholar
  26. 26.
    Burkard U (2003) Methods for data analysis. In: Gasteiger J, Engel T. Chemoinformatics: a textbook. Wiley-VCH, Weinheim, pp 439–486Google Scholar
  27. 27.
    Zupan J, Gasteiger J (1999) Neural networks in chemistry and drug design, 2nd edn. Wiley-VCH, WeinheimGoogle Scholar
  28. 28.
    Vracko M (2005) Kohonen artificial neural network and counter propagation neural network in molecular structure-toxicity studies. Curr Comp Aided Drug Des 1: 73–78. doi: 10.2174/1573409052952224 CrossRefGoogle Scholar
  29. 29.
    SONNIA, Molecular Networks GmbH: Naegelsbachstr. 25, 91052, Erlangen, Germany (
  30. 30.
    Kubinyi H, Hamprecht FA, Mietzner T (1998) Three-dimensional quantitative similarity-activity relationships (3D QSiAR) from SEAL similarity matrices. J Med Chem 41: 2553–2564. doi: 10.1021/jm970732a PubMedCrossRefGoogle Scholar
  31. 31.
    Oprea TI, Gottfries J (2001) Chemography: the art of navigating in chemical space. J Comb Chem 3: 157–166. doi: 10.1021/cc0000388 PubMedCrossRefGoogle Scholar
  32. 32.
    Oprea TI, Zamora I, Ungell AL (2002) Pharmacokinetically based mapping device for chemical space navigation. J Comb Chem 4: 258–266. doi: 10.1021/cc010093w PubMedCrossRefGoogle Scholar
  33. 33.
    Seri-Levy A, West S, Richards WG (1994) Molecular similarity, quantitative chirality, and QSAR for chiral drugs. J Med Chem 37: 1727–1732. doi: 10.1021/jm00037a025 PubMedCrossRefGoogle Scholar
  34. 34.
    Johnson MA, Maggiora GM (1990) Concepts and applications of molecular similarity. Wiley, New YorkGoogle Scholar
  35. 35.
    Ekins S, Balakin KV, Savchuk N, Ivanenkov Y (2006) Insights for human ether-a-go-go-related gene potassium channel inhibition using recursive partitioning and Kohonen and Sammon mapping techniques. J Med Chem 49: 5059–5071. doi: 10.1021/jm060076r PubMedCrossRefGoogle Scholar
  36. 36.
    Chekmarev DS, Kholodovych V, Balakin KV, Ivanenkov Y, Ekins S, Welsh WJ (2008) Shape signatures: new descriptors for predicting cardiotoxicity in silico. Chem Res Toxicol 21: 1304–1314. doi: 10.1021/tx800063r PubMedCrossRefGoogle Scholar
  37. 37.
    Dubus E, Ijjaali I, Petitet F, Michel A (2006) In silico classification of hERG channel blockers: a knowledge-based strategy. ChemMedChem 1: 622–630. doi: 10.1002/cmdc.200500099 PubMedCrossRefGoogle Scholar
  38. 38.
    Wang M, Yang X-G, Xue Y (2008) Identifying hERG potassium channel inhibitors by machine learning methods. QSAR Comb Sci 27: 1028–1035. doi: 10.1002/qsar.200810015 CrossRefGoogle Scholar
  39. 39.
    Demel MA, Janecek AGK, Thai K-M, Ecker GF, Gansterer WN (2008) Predictive QSAR models for polyspecific drug targets: the importance of feature selection. Curr Comp Aided Drug Des 4: 91–110. doi: 10.2174/157340908784533256 CrossRefGoogle Scholar
  40. 40.
    Roche O, Trube G, Zuegge J, Pflimlin P, Alanine A, Schneider G (2002) A virtual screening method for prediction of the HERG potassium channel liability of compound libraries. ChemBioChem 3: 455–459. doi: 10.1002/1439-7633(20020503)3:5<455::AID-CBIC455>3.0.CO;2-L PubMedCrossRefGoogle Scholar
  41. 41.
    Keserü GM (2003) Prediction of hERG potassium channel affinity by traditional and hologram QSAR methods. Bioorg Med Chem Lett 13: 2773–2775. doi: 10.1016/S0960-894X(03)00492-X PubMedCrossRefGoogle Scholar
  42. 42.
    Bains W, Basman A, White C (2004) HERG binding specificity and binding site structure: evidence from a fragment-based evolutionary computing SAR study. Prog Biophys Mol Biol 86: 205–233. doi: 10.1016/j.pbiomolbio.2003.09.001 PubMedCrossRefGoogle Scholar
  43. 43.
    Aronov AM, Goldman BB (2004) A model for identifying HERG K+ channel blockers. Bioorg Med Chem 12: 2307–2315. doi: 10.1016/j.bmc.2004.02.003 PubMedCrossRefGoogle Scholar
  44. 44.
    Dubus E, Ijjaali I, Petitet F, Michel A (2006) In silico classification of hERG channel blockers: a knowledge-based strategy. ChemMedChem 1: 662. doi: 10.1002/cmdc.200500099 CrossRefGoogle Scholar
  45. 45.
    Fioravanzo E, Cazzolla N, Durando L, Ferrari C, Mabilia M, Ombrato R, Parenti MD (2005) General and independent approaches to predict HERG affinity values. Internet Electron J Mol Des 4: 625–646Google Scholar
  46. 46.
    Tobita M, Nishikawa T, Nagashima R (2005) A discriminant model constructed by the support vector machine method for HERG potassium channel inhibitors. Bioorg Med Chem Lett 15: 2886–2890. doi: 10.1016/j.bmcl.2005.03.080 PubMedCrossRefGoogle Scholar
  47. 47.
    O’Brien SE, de Groot MJ (2005) Greater than the sum of its parts: combining models for useful ADMET prediction. J Med Chem 48: 1287–1291. doi: 10.1021/jm049254b PubMedCrossRefGoogle Scholar
  48. 48.
    Sun H (2006) An accurate and interpretable bayesian classification model for prediction of hERG liability. ChemMedChem 1: 315–322. doi: 10.1002/cmdc.200500047 PubMedCrossRefGoogle Scholar
  49. 49.
    Li Q, Jørgensen FS, Oprea T, Brunak S, Taboureau O (2008) hERG Classification model based on a combination of support vector machine method and GRIND descriptors. Mol Pharm 5: 117–127. doi: 10.1021/mp700124e PubMedCrossRefGoogle Scholar
  50. 50.
    Jia L, Sun H (2008) Support vector machines classification of hERG liabilities based on atom types. Bioorg Med Chem 16: 6252–6260. doi: 10.1016/j.bmc.2008.04.028 PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  1. 1.Emerging Field Pharmacoinformatics, Department of Medicinal ChemistryUniversity of ViennaViennaAustria
  2. 2.Department of Pharmaceutical Chemistry, School of PharmacyUniversity of Medicine and Pharmacy at Ho Chi Minh CityHo Chi Minh CityVietnam

Personalised recommendations