Advertisement

Molecular Diversity

, Volume 14, Issue 2, pp 225–235 | Cite as

A combined LS-SVM & MLR QSAR workflow for predicting the inhibition of CXCR3 receptor by quinazolinone analogs

  • Antreas Afantitis
  • Georgia Melagraki
  • Haralambos Sarimveis
  • Panayiotis A. Koutentis
  • Olga Igglessi-Markopoulou
  • George Kollias
Full-Length Paper

Abstract

A novel QSAR workflow is constructed that combines MLR with LS-SVM classification techniques for the identification of quinazolinone analogs as “active” or “non-active” CXCR3 antagonists. The accuracy of the LS-SVM classification technique for the training set and test was 100% and 90%, respectively. For the “active” analogs a validated MLR QSAR model estimates accurately their I-IP10 IC50 inhibition values. The accuracy of the QSAR model (R 2 = 0.80) is illustrated using various evaluation techniques, such as leave-one-out procedure \({(R^{2}_{\rm LOO} =0.67)}\) and validation through an external test set \({(R^{2}_{\rm pred} =0.78)}\). The key conclusion of this study is that the selected molecular descriptors, Highest Occupied Molecular Orbital energy (HOMO), Principal Moment of Inertia along X and Y axes PMIX and PMIZ, Polar Surface Area (PSA), Presence of triple bond (PTrplBnd), and Kier shape descriptor (1 κ), demonstrate discriminatory and pharmacophore abilities.

Keywords

QSAR CXCR3 Molecular modelling In silico predictions 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Neote K (2007) Chemokine biology: basic research and clinical application: vol 2: pathophysiology of chemokines (Progress in Inflammation Research). Birkhäuser, BaselGoogle Scholar
  2. 2.
    Wijtmans M, Verzijl D, Leurs R, de Esch IJ, Smit MJ (2008) Towards small-molecule CXCR3 ligands with clinical potential. ChemMedChem 3: 861–872. doi: 10.1002/cmdc.200700365 CrossRefPubMedGoogle Scholar
  3. 3.
    Cole AG, Stroke IL, Brescia MR, Simhadri S, Zhang JJ, Hussain Z et al (2006) Identification and initial evaluation of 4-N-aryl-[1,4]diazepane ureas as potent CXCR3 antagonists. Bioorg Med Chem Lett 16: 200–203. doi: 10.1016/j.bmcl.2005.09.020 CrossRefPubMedGoogle Scholar
  4. 4.
    Johnson M, Li AR, Liu J, Fu Z, Zhu L, Miao S et al (2007) Discovery and optimization of a series of quinazolinone-derived antagonists of CXCR3. Bioorg Med Chem Lett 17: 3339–3343. doi: 10.1016/j.bmcl.2007.03.106 CrossRefPubMedGoogle Scholar
  5. 5.
    Du X, Chen X, Mihalic JT, Deignan J, Duquette J, Li AR et al (2008) Design and optimization of imidazole derivatives as potent CXCR3 antagonists. Bioorg Med Chem Lett 18: 608–613. doi: 10.1016/j.bmcl.2007.11.072 CrossRefPubMedGoogle Scholar
  6. 6.
    Roy K, Mandal AS (2009) Predictive QSAR modeling of CCR5 antagonist piperidine derivatives using chemometric tools. J Enzyme Inhib Med Chem 24: 205–223. doi: 10.1080/14756360802051297 CrossRefPubMedGoogle Scholar
  7. 7.
    Aher YD, Agrawal A, Bharatam PV, Garg P (2007) 3D-QSAR studies of substituted 1-(3,3-diphenylpropyl)-piperidinyl amides and ureas as CCR5 receptor antagonists. J Mol Model 13: 519–529. doi: 10.1007/s00894-007-0173-z CrossRefPubMedGoogle Scholar
  8. 8.
    Afantitis A, Melagraki G, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2006) Investigation of substituent effect of 1-(3,3-diphenylpropyl)-piperidinyl phenylacetamides on CCR5 binding affinity using QSAR and virtual screening techniques. J Comput Aided Mol Des 20: 83–95. doi: 10.1007/s10822-006-9038-2 CrossRefPubMedGoogle Scholar
  9. 9.
    Nair PC, Srikanth K, Sobhia ME (2008) QSAR studies on CCR2 antagonists with chiral sensitive hologram descriptors. Bioorg Med Chem Lett 18: 1323–1330. doi: 10.1016/j.bmcl.2008.01.023 CrossRefPubMedGoogle Scholar
  10. 10.
    Srikanth K, Nair PC, Sobhia ME (2008) Probing the structural and topological requirements for CCR2 antagonism: holographic QSAR for indolopiperidine derivatives. Bioorg Med Chem Lett 18: 1450–1456. doi: 10.1016/j.bmcl.2007.12.072 CrossRefPubMedGoogle Scholar
  11. 11.
    Khlebnikov AI, Schepetkin IA, Quinn MT (2006) Quantitative structure-activity relationships for small non-peptide antagonists of CXCR2: indirect 3D approach using the frontal polygon method. Bioorg Med Chem 14: 352–365. doi: 10.1016/j.bmc.2005.08.026 CrossRefPubMedGoogle Scholar
  12. 12.
    Bhonsle JB, Wang Z, Tamamura H, Fujii N, Peiper SC, Trent JO (2005) A simple, automated quasi-4D-QSAR, quasi-multi way PLS approach to develop highly predictive QSAR models for highly flexible CXCR4 inhibitor cyclic pentapeptide ligands using scripted common molecular modeling tools. QSAR Comb Sci 24: 620–630. doi: 10.1002/qsar.200430912 CrossRefGoogle Scholar
  13. 13.
    Afantitis A, Melagraki G, Sarimveis H, Igglessi-Markopoulou O, Kollias G (2009) A novel QSAR model for predicting the inhibition of CXCR3 receptor by 4-N-aryl-[1,4] diazepane ureas. Eur J Med Chem 44: 877–884. doi: 10.1016/j.ejmech.2008.05.028 CrossRefPubMedGoogle Scholar
  14. 14.
    Todeschini R, Consonni V, Mannhold R (2000) In: Kubinyi H, Timmerman H (eds) Handbook of molecular descriptors. Wiley-VCH, WeinheimGoogle Scholar
  15. 15.
    Suykens JAK, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J (2002) Least squares support vector machines. World Scientific Pub Co., SingaporeGoogle Scholar
  16. 16.
    Stewart JJP (2007) Optimization of parameters for semiempirical methods V: modification of NDDO approximations and application to 70 elements. J Mol Model 13: 1173–1213. doi: 10.1007/s00894-007-0233-4 CrossRefPubMedGoogle Scholar
  17. 17.
    Stewart JJP (2008) Application of the PM6 method to modeling the solid state. J Mol Model 14: 499–535. doi: 10.1007/s00894-008-0299-7 CrossRefPubMedGoogle Scholar
  18. 18.
    Puzyn T, Suzuki N, Haranczyk M, Rak J (2008) Calculation of quantum-mechanical descriptors for QSPR at the dft level: is it necessary. J Chem Inf Model 48: 1174–1180. doi: 10.1021/ci800021p CrossRefPubMedGoogle Scholar
  19. 19.
    Chem 3D. CambridgeSoft Corporation, 100 CambridgePark Drive Cambridge, MA 02140, USA. http://www.cambridgesoft.com
  20. 20.
    Topix. Epina GmbH, Am Wienerwald 15, 3013 Pressbaum, Austria. http://www.lohninger.com/topix.html
  21. 21.
    MOPAC2007. Stewart Computational Chemisitry (SCC), 15210 Paddington Circle Colorado Springs, CO80921, USA, http://openmopac.net/home.html
  22. 22.
    ROCS & EON. OpenEye Scientific Software Inc, 9 Bisbee Court, Suite D Santa Fe, NM 87508, USA. http://www.eyesopen.com
  23. 23.
    Kennard RW, Stone LA (1969) Computer aided design of experiments. Technometrics 11: 137–148. doi: 10.2307/1266770 CrossRefGoogle Scholar
  24. 24.
    Ghosh P, Thanadath M, Bagchi MC (2006) On an aspect of calculated molecular descriptors in QSAR studies of quinolone antibacterials. Mol Divers 10: 415–427. doi: 10.1007/s11030-006-9018-4 CrossRefPubMedGoogle Scholar
  25. 25.
    Melagraki G, Afantitis A, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2007) Optimization of biaryl piperidine and 4-amino-2-biarylurea MCH1 receptor antagonists using QSAR modeling, classification techniques and virtual screening. J Comput Aided Mol Des 21: 251–267. doi: 10.1007/s10822-007-9112-4 CrossRefPubMedGoogle Scholar
  26. 26.
    Afantitis A, Melagraki G, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2006) A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis. Mol Divers 10: 405–414. doi: 10.1007/s11030-005-9012-2 CrossRefPubMedGoogle Scholar
  27. 27.
    Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3: 1157–1182. doi: 10.1162/153244303322753616 CrossRefGoogle Scholar
  28. 28.
    Hung YH, Liao YS (2008) Applying PCA and fixed size LS-SVM method for large scale classification problems. Inf Technol J 7: 890–896. doi: 10.3923/itj.2008.890.896 CrossRefGoogle Scholar
  29. 29.
    Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27: 861–874. doi: 10.1016/j.patrec.2005.10.010 CrossRefGoogle Scholar
  30. 30.
    Tropsha A, Golbraikh A (2007) Predictive QSAR modeling workflow, model applicability domains, and virtual screening. Curr Pharm Des 13: 3494–3504. doi: 10.2174/138161207782794257 CrossRefPubMedGoogle Scholar
  31. 31.
    Melagraki G, Afantitis A, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2007) A novel QSPR model for predicting θ (lower critical solution temperature) in polymer solutions using molecular descriptors. J Mol Model 13: 55–64. doi: 10.1007/s00894-006-0125-z CrossRefGoogle Scholar
  32. 32.
    Golbraikh A, Tropsha A (2002) Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection. Mol Divers 5: 231–243. doi: 10.1023/A:1021372108686 CrossRefPubMedGoogle Scholar
  33. 33.
    Melagraki G, Afantitis A, Sarimveis H, Igglessi-Markopoulou O, Alexandridis A (2006) A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri. Mol Divers 10: 213–221. doi: 10.1007/s11030-005-9008-y CrossRefPubMedGoogle Scholar
  34. 34.
    Melagraki G, Afantitis A, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2007) Identification of a series of novel derivatives as potent HCV inhibitors by a ligand-based virtual screening optimized procedure. Bioorg Med Chem 15: 7237–7247. doi: 10.1016/j.bmc.2007.08.036 CrossRefPubMedGoogle Scholar
  35. 35.
    Afantitis A, Melagraki G, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2008) Development and evaluation of a QSPR model for the prediction of diamagnetic susceptibility. QSAR Comb Sci 27: 432–436. doi: 10.1002/qsar.200730083 CrossRefGoogle Scholar
  36. 36.
    Toropov AA, Benfenati E (2008) Additive SMILES-based optimal descriptors in QSAR modelling bee toxicity: using rare SMILES attributes to define the applicability domain. Bioorg Med Chem 16: 4801–4809. doi: 10.1016/j.bmc.2008.03.048 CrossRefPubMedGoogle Scholar
  37. 37.
    Todeschini R, Consonni V, Mauri A, Pavan M (2004) Detecting “bad” regression models: multicriteria fitness functions in regression analysis. Anal Chim Acta 515: 199–208. doi: 10.1016/j.aca.2003.12.010 CrossRefGoogle Scholar
  38. 38.
    Afantitis A, Melagraki G, Sarimveis H, Koutentis PA, Markopoulos J, Igglessi-Markopoulou O (2006) A novel QSAR model for evaluating and predicting the inhibition activity of dipeptidyl aspartyl fluoromethylketones. QSAR Comb Sci 25: 928–935. doi: 10.1002/qsar.200530208 CrossRefGoogle Scholar
  39. 39.
    Jalali-Heravi M, Asadollahi-Baboli M, Shahbazikhah P (2008) QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg–Marquardt algorithm. Eur J Med Chem 43: 548–556. doi: 10.1016/j.ejmech.2007.04.014 CrossRefPubMedGoogle Scholar
  40. 40.
    Ertl P, Rohde B, Selzer P (2000) Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties. J Med Chem 43: 3714–3717. doi: 10.1021/jm000942e CrossRefPubMedGoogle Scholar
  41. 41.
    Patai S (1992) Patai’s 1992 guide to the chemistry of functional groups. Wiley, ChichesterGoogle Scholar
  42. 42.
    McQuarrie DA, Simon JD (1997) Physical chemistry: a molecular approach. University Science Books, CAGoogle Scholar
  43. 43.
    Kier LB (1986) Molecular connectivity in structure–activity analysis (chemometrics series). Wiley, New YorkGoogle Scholar
  44. 44.
    Devillers J, Balaban AT (1999) Topological indices and related descriptors in QSAR and QSPAR. Taylor & Francis Inc, New YorkGoogle Scholar
  45. 45.
    Colombo A, Benfenati E, Karelson M, Maran U (2008) The proposal of architecture for chemical splitting to optimize QSAR models for aquatic toxicity. Chemosphere 72: 772–780. doi: 10.1016/j.chemosphere.2008.03.016 CrossRefPubMedGoogle Scholar
  46. 46.
    Baumann K (2003) Cross-validation as the objective function for variable-selection techniques. Trends Analyt Chem 22: 395–406. doi: 10.1016/S0165-9936(03)00607-1 CrossRefGoogle Scholar
  47. 47.
    Agrafiotis DK, Bandyopadhyay D, Wegner JK, Vlijmen H (2007) Recent advances in chemoinformatics. J Chem Inf Model 47: 1279–1293. doi: 10.1021/ci700059g CrossRefPubMedGoogle Scholar
  48. 48.
    Muegge I, Oloff S (2006) Advances in virtual screening. Drug Discov Today Technol 3: 405–411. doi: 10.1016/j.ddtec.2006.12.002 CrossRefGoogle Scholar
  49. 49.
    Melagraki G, Afantitis A, Sarimveis H, Koutentis PA, Kollias G, Igglessi-Markopoulou O (2009) Predictive QSAR workflow for the in silico identification and screening of novel HDAC inhibitors. Mol Divers. doi: 10.1007/s11030-009-9115-2 Google Scholar
  50. 50.
    Salum LB, Andricopulo AD (2009) Fragment-based QSAR: perspectives in drug design. Mol Divers 2009. doi: 10.1007/s11030-009-9112-5 Google Scholar
  51. 51.
    Guido RV, Oliva G, Andricopulo AD (2008) Virtual screening and its integration with modern drug design technologies. Curr Med Chem 15: 37–46. doi: 10.2174/092986708783330683 CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  • Antreas Afantitis
    • 1
    • 2
  • Georgia Melagraki
    • 3
  • Haralambos Sarimveis
    • 3
  • Panayiotis A. Koutentis
    • 4
  • Olga Igglessi-Markopoulou
    • 3
  • George Kollias
    • 1
  1. 1.Biomedical Sciences Research Center “Alexander Fleming”AthensGreece
  2. 2.Department of ChemInformaticsNovaMechanics LtdNicosiaCyprus
  3. 3.School of Chemical EngineeringNational Technical University of AthensAthensGreece
  4. 4.Department of ChemistryUniversity of CyprusNicosiaCyprus

Personalised recommendations