Advertisement

Development of classification models for identification of important structural features of isoform-selective histone deacetylase inhibitors (class I)

  • M. S. Neiband
  • A. BenvidiEmail author
  • A. Mani-Varnosfaderani
Original Article
  • 33 Downloads

Abstract

As one of the hot topics in the epigenetic studies, histone deacetylases inhibitors (HDACIs) have been introduced to treat a variety of diseases such as cancer, immune disorder and neuronal diseases. Given the high numbers of available pathways in which HDACs are involved, the HDACIs that act particularly on Class I or Class II enzymes are considered as possible candidates for anticancer drugs. Due to their effective roles in the onset of cancer and its progression, HDAC Class I isoforms (HDAC 1, 2, 3 and 8) were considered in this study. Herein, our objective is to determine the important isoform-selective and isoform-active structural features of HDACIs using the valid classification models. For this purpose, a diverse dataset comprising 8224 HDAC modulators was collected from the binding database. To identify the significant discriminative features, five classification models were generated by supervised Kohonen network and support vector machine methods. Variable importance in projection method was used as a variable selection approach. The results obtained from descriptor analysis show that physicochemical properties, such as hydrogen bonding, number of branches, size, flexibility, polarity and sphericity in the structure of molecules, were closely related to the bioactivity of HDACIs. The reliability and predictive ability of the conducted models were evaluated using the tenfold cross-validation techniques, test sets and applicability domain analysis. All of the obtained classification models represented high statistical quality and predictive ability with accuracy greater than 85% for the test sets. The proposed strategy and the selective patterns represented in this paper can be applied by researchers in the pharmaceutical sciences who aim to use the same idea for the design of drugs with improved anticancer properties.

Graphic abstract

Keywords

Isoform-selective HDAC inhibitors Supervised Kohonen network Support vector machine Classification models Anticancer agents 

Notes

Acknowledgements

We gratefully acknowledge the support of this work by Yazd University research council.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest

Supplementary material

11030_2019_10013_MOESM1_ESM.rar (15.1 mb)
Supplementary material 1 (RAR 15503 kb)

References

  1. 1.
    Thangapandian S, John S, Lee KW (2012) Molecular dynamics simulation study explaining inhibitor selectivity in different class of histone deacetylases. J Biomol Struct Dyn 29(4):677–698.  https://doi.org/10.1080/07391102.2012.10507409 CrossRefPubMedGoogle Scholar
  2. 2.
    Bolden JE, Shi W, Jankowski K, Kan CY, Cluse L, Martin BP, MacKenzie KL, Smyth GK, Johnstone RW (2013) HDAC inhibitors induce tumor-cell-selective pro-apoptotic transcriptional responses. Cell Death Dis 4(2):519–534.  https://doi.org/10.1038/cddis.2013.9 CrossRefGoogle Scholar
  3. 3.
    Gao S, Zang J, Gao Q, Liang X, Ding Q, Li X, Xu W, Chou CJ, Zhang Y (2017) Design, synthesis and anti-tumor activity study of novel histone deacetylase inhibitors containing isatin-based caps and o-phenylenediamine-based zinc binding groups. Bioorg Med Chem 25(12):2981–2994.  https://doi.org/10.1016/j.bmc.2017.03.036 CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Zhang J, Zhong Q (2014) Histone deacetylase inhibitors and cell death. Cell Mol Life Sci 71:3885–3901.  https://doi.org/10.1007/s00018-014-1656-6 CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    Falkenberg KJ, Johnstone RW (2014) Histone deacetylases and their inhibitors in cancer, neurological diseases and immune disorders. Nat Rev Drug Discov 13:673–691.  https://doi.org/10.1038/nrd4360 CrossRefPubMedGoogle Scholar
  6. 6.
    Haberland M, Montgomery RL, Olson EN (2009) The many roles of histone deacetylases in development and physiology: implications for disease and therapy. Nat Rev Genet 10:32–42.  https://doi.org/10.1038/nrg2485 CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Yoon S, Eom GH (2016) HDAC and HDAC inhibitor: from cancer to cardiovascular diseases. Chonnam Med J 52(1):1–11.  https://doi.org/10.4068/cmj.2016.52.1.1 CrossRefPubMedPubMedCentralGoogle Scholar
  8. 8.
    Li Y, Seto E (2016) HDACs and HDAC inhibitors in cancer development and therapy. Cold Spring Harbor Perspect Med 6(10):26831–26872.  https://doi.org/10.1101/cshperspect.a026831 CrossRefGoogle Scholar
  9. 9.
    Barneda-Zahonero B, Parra M (2012) Histone deacetylases and cancer. Mol Oncol 6(6):579–589.  https://doi.org/10.1016/j.molonc.2012.07.003 CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    Mottamal M, Zheng S, Huang TL, Wang G (2015) Histone deacetylase inhibitors in clinical studies as templates for new anticancer agents. Molecules 20(3):3898–3941.  https://doi.org/10.3390/molecules20033898 CrossRefPubMedPubMedCentralGoogle Scholar
  11. 11.
    Mai A, Massa S, Rotili D, Cerbara I, Valente S, Pezzi R, Simeoni S, Ragno R (2005) Histone deacetylation in epigenetics: an attractive target for anticancer therapy. Med Res Rev 25(3):261–309.  https://doi.org/10.1002/med.20024 CrossRefPubMedGoogle Scholar
  12. 12.
    Goey AK, Sissung TM, Peer CJ, Figg WD (2016) Pharmacogenomics and histone deacetylase inhibitors. Pharmacogenom J 16:1807–1815.  https://doi.org/10.2217/pgs-2016-0113 CrossRefGoogle Scholar
  13. 13.
    Tang H, Wang XS, Huang XP, Roth BL, Butler KV, Kozikowski AP, Jung M, Tropsha A (2009) Novel inhibitors of human histone deacetylase (HDAC) identified by QSAR modeling of known inhibitors, virtual screening, and experimental validation. J Chem Inf Model 49:461–476.  https://doi.org/10.1021/ci800366f CrossRefPubMedGoogle Scholar
  14. 14.
    Cao GP, Thangapandian S, Son M, Kumar R, Choi YJ, Kim Y, Kwon YJ, Kim HH, Suh JK, Lee KW (2016) QSAR modeling to design selective histone deacetylase 8 (HDAC8) inhibitors. Arch Pharm Res 39(10):1356–1369.  https://doi.org/10.1007/s12272-015-0705-5 CrossRefPubMedGoogle Scholar
  15. 15.
    Pontiki E, Hadjipavlou-Litina D (2012) Histone deacetylase inhibitors (HDACIs). Structure-activity relationships: History and new QSAR perspectives. Med Res Rev 32:1–165.  https://doi.org/10.1002/med.20200 CrossRefPubMedGoogle Scholar
  16. 16.
    Norinder U, Naveja JJ, López-López E, Mucs D, Medina-Franco JL (2019) Conformal prediction of HDAC inhibitors. SAR QSAR Environ Res 30(4):265–277CrossRefGoogle Scholar
  17. 17.
    Nair SB, Teli MK, Pradeep H, Rajanikant GK (2012) Computational identification of novel histone deacetylase inhibitors by docking based QSAR. Comput Biol Med 42(6):697–705.  https://doi.org/10.1016/j.compbiomed.2012.04.001 CrossRefPubMedGoogle Scholar
  18. 18.
    Katritzky AR, Slavov SH, Dobchev DA, Karelson M (2007) Comparison between 2D and 3D-QSAR approaches to correlate inhibitor activity for a series of indole amide hydroxamic acids. QSAR Comb Sci 26:333–345.  https://doi.org/10.1002/qsar.200630021 CrossRefGoogle Scholar
  19. 19.
    Guo Y, Xiao J, Guo Z, Chu F, Cheng Y, Wu S (2005) Exploration of a binding mode of indole amide analogues as potent histone deacetylase inhibitors and 3D-QSAR analyses. Bioorg Med Chem 13(18):5424–5434.  https://doi.org/10.1016/j.bmc.2005.05.016 CrossRefPubMedGoogle Scholar
  20. 20.
    Xiang Y, Hou Z, Zhang Z (2012) Pharmacophore and QSAR studies to design novel histone deacetylase 2 inhibitors. Chem Biol Drug Des 79:760–770.  https://doi.org/10.1111/j.1747-0285.2012.01341.x CrossRefPubMedGoogle Scholar
  21. 21.
    Abdel-Atty MM, Farag NA, Kassab SE, Serya RA, Abouzid KA (2014) Design, synthesis, 3D pharmacophore, QSAR, and docking studies of carboxylic acid derivatives as Histone Deacetylase inhibitors and cytotoxic agents. Bioorg Chem 57:65–82.  https://doi.org/10.1016/j.bioorg.2014.08.006 CrossRefPubMedGoogle Scholar
  22. 22.
    Noor Z, Afzal N, Rashid S (2015) Exploration of novel inhibitors for class I histone deacetylase isoforms by QSAR modeling and molecular dynamics simulation assays. PLoS ONE 10(10):e0139588.  https://doi.org/10.1371/journal.pone.0139588 CrossRefPubMedPubMedCentralGoogle Scholar
  23. 23.
    Uba AI, Yelekçi K (2017) Identification of potential isoform-selective histone deacetylase inhibitors for cancer therapy: a combined approach of structure-based virtual screening, ADMET prediction and molecular dynamics simulation assay. J Biomol Struct Dyn 21:1–5.  https://doi.org/10.1080/07391102.2017.1384402 CrossRefGoogle Scholar
  24. 24.
    Dessalew N (2007) QSAR study on amino phenyl benzamides and acrylamides as histone deacetylase inhibitors: an insight into the structural basis of ant proliferative activity. Med Chem Res 16(7–9):449–460.  https://doi.org/10.1007/s00044-007-9085-9 CrossRefGoogle Scholar
  25. 25.
    Yang JS, Chun TG, Nam KY, Kim HM, Han G (2012) Structure-activity relationship of novel lactam based histone deacetylase inhibitors as potential anticancer drugs. Bull Korean Chem Soc 33:2063–2066.  https://doi.org/10.5012/bkcs.2012.33.6.2063 CrossRefGoogle Scholar
  26. 26.
    Zhao L, Xiang Y, Song J, Zhang ZA (2013) Novel two-step QSAR modeling work flow to predict selectivity and activity of HDAC inhibitors. Bioorg Med Chem Lett 23(4):929–933.  https://doi.org/10.1016/j.bmcl.2012.12.067 CrossRefPubMedGoogle Scholar
  27. 27.
    Cao GP, Arooj M, Thangapandian S, Park C, Arulalapperumal V, Kim Y, Kwon YJ, Kim HH, Suh JK, Lee KW (2015) A lazy learning-based QSAR classification study for screening potential histone deacetylase 8 (HDAC8) inhibitors. SAR QSAR Environ Res 26:397–420.  https://doi.org/10.1080/1062936X.2015.1040453 CrossRefPubMedGoogle Scholar
  28. 28.
    Liu XH, Song HY, Zhang JX, Han BC, Wei XN, Ma XH, Cui WK, Chen YZ (2010) Identifying novel type ZBGs and nonhydroxamate HDAC inhibitors through a SVM based virtual screening approach. Mol Inf 29:407–420.  https://doi.org/10.1002/minf.200900014 CrossRefGoogle Scholar
  29. 29.
    Gilson MK, Liu T, Baitaluk M, Nicola G, Hwang L, Chong J (2016) Binding DB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res 44:D1045–D1053.  https://doi.org/10.1093/nar/gkv1072 CrossRefPubMedGoogle Scholar
  30. 30.
    Todeschini R, Consonni V, Mauri A, Pavan M (2007) DRAGONs software for the calculation of molecular descriptors, version 5.5 for Windows. Milan, Italy. http://www.talete.mi.it/products/dragon_description.htm
  31. 31.
    O’Boyle NM, Banck M, James CA, Morley C, Vandermeersch T, Hutchison GR (2011) Open Babel: an open chemical toolbox. J Chem Inf 3:1–14.  https://doi.org/10.1186/1758-2946-3-33 CrossRefGoogle Scholar
  32. 32.
    Mani-Varnosfaderani A, Neiband MS, Benvidi A (2018) Identification of molecular features necessary for selective inhibition of B cell lymphoma proteins using machine learning techniques. Mol divers 12:1–9.  https://doi.org/10.1007/s11030-018-9856-x CrossRefGoogle Scholar
  33. 33.
    Farrés M, Platikanov S, Tsakovski S, Tauler R (2015) Comparison of the variable importance in projection (VIP) and of the selectivity ratio (SR) methods for variable selection and interpretation. J Chemom 29(10):528–536.  https://doi.org/10.1002/cem.2736 CrossRefGoogle Scholar
  34. 34.
    Reis A, Rudnitskaya A, Chariyavilaskul P, Dhaun N, Melville V, Goddard J, Webb DJ, Pitt AR, Spickett CM (2015) Top-down lipidomics of low density lipoprotein reveal altered lipid profiles in advanced chronic kidney disease. J Lipid Res 56:413–422.  https://doi.org/10.1194/jlr.M055624 CrossRefPubMedPubMedCentralGoogle Scholar
  35. 35.
    Wang J, Su M, Li T, Gao A, Yang W, Sheng L, Zang Y, Li J, Liu H (2017) Design, synthesis and biological evaluation of thienopyrimidine hydroxamic acid based derivatives as structurally novel histone deacetylase (HDAC) inhibitors. Eur J Med Chem 128:293–309.  https://doi.org/10.1016/j.ejmech.2017.01.035 CrossRefPubMedGoogle Scholar
  36. 36.
    Hu E, Dul E, Sung CM, Chen Z, Kirkpatrick R, Zhang GF, Johanson K, Liu R, Lago A, Hofmann G, Macarron R (2003) Identification of novel isoform-selective inhibitors within class I histone deacetylases. J Pharmacol Exp Ther 307(2):720–728.  https://doi.org/10.1124/jpet.103.055541 CrossRefPubMedGoogle Scholar
  37. 37.
    Melssen W, Wehrens R, Buydens L (2006) Supervised Kohonen networks for classification problems. Chemom Intell Lab Syst 83(2):99–113.  https://doi.org/10.1016/j.chemolab.2006.02.003 CrossRefGoogle Scholar
  38. 38.
    Vasighi M, Kompany-Zareh M (2013) Classification ability of self organizing maps in comparison with other classification methods. MATCH Commun Math Comput Chem 70:29–44Google Scholar
  39. 39.
    Omara H, Lazaar M, Tabii Y (2018) Self-organizing maps and principal component analysis to improve classification accuracy. Res J Appl Sci Eng Technol 15(5):190–196.  https://doi.org/10.19026/rjaset.15.5851 CrossRefGoogle Scholar
  40. 40.
    Ballabio D, Vasighi M (2012) A MATLAB Toolbox for Self Organizing Maps and supervised neural network learning strategies. Chemom Intell Lab 118:24–32CrossRefGoogle Scholar
  41. 41.
    Vapnik VN (1998) Statistical learning theory, 1st edn. Wiley-Interscience, New York. ISBN 978-0-471-03003-4Google Scholar
  42. 42.
    Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27.  https://doi.org/10.1145/1961189.1961199 CrossRefGoogle Scholar
  43. 43.
    Gramatica P (2007) Principles of QSAR models validation: Internal and external. QSAR Comb Sci 26:694–701.  https://doi.org/10.1002/qsar.200610151 CrossRefGoogle Scholar
  44. 44.
    Eriksson L, Jaworska J, Worth AP, Cronin MTD, McDowell RM (2003) Methods for reliability and uncertainty assessment and for applicability evaluations of classification- and regression-based QSARs. Environ Health Perspect 111:1361–1375.  https://doi.org/10.1289/ehp.5758 CrossRefPubMedPubMedCentralGoogle Scholar
  45. 45.
    Balaban AT (1983) Topological indices based on topological distances in molecular graphs. Pure Appl Chem 5(2):199–206.  https://doi.org/10.1351/pac198855020199 CrossRefGoogle Scholar
  46. 46.
    Todeschini R, Consonni V, Mannhold R, Kubinyi H, Folkers G (2009) Molecular descriptors for chemoinformatics. Wiley, Weinheim. ISBN 978-3-527-31852-0CrossRefGoogle Scholar
  47. 47.
    Kier LB, Hall LH (1986) Molecular connectivity in structure-activity analysis. Res Stud 33:2096.  https://doi.org/10.1002/aic.690331230 CrossRefGoogle Scholar
  48. 48.
    Randic M, Kleiner AF, De Alba LM (1994) Distance/distance matrixes. J Chem Inf Comput Sci 34(2):277–286CrossRefGoogle Scholar
  49. 49.
    Bath PA, Poirrette AR, Willett P, Allen FH (1995) The extent of the relationship between the graph–theoretical and the geometrical shape coefficients of chemical compounds. J Chem Inf Comput Sci 35:714–716.  https://doi.org/10.1021/ci00026a007 CrossRefGoogle Scholar
  50. 50.
    Puzyn T, Leszczynski J, Cronin MT (2010) Recent advances in QSAR studies: methods and applications. Chall Adv Comput Chem Phys 8:1–415.  https://doi.org/10.1007/978-1-4020-9783-6 CrossRefGoogle Scholar
  51. 51.
    Hall LH, Kier LB, Brown BB (1995) Molecular similarity based on novel atom-type electrotopological state indices. J Chem Inf Comput Sci 35(6):1074–1080CrossRefGoogle Scholar
  52. 52.
    Copeland JC, Zehr LJ, Cerny RL, Powers R (2012) The applicability of molecular descriptors for designing an electrospray ionization mass spectrometry compatible library for drug discovery. Comb Chem high T Scr 15(10):806–815.  https://doi.org/10.2174/138620712803901180 CrossRefGoogle Scholar
  53. 53.
    Todeschini R, Consoni V (2008) Handbook of molecular descriptors. Methods and principles in medicinal chemistry. Wiley, New York.  https://doi.org/10.1002/9783527613106 CrossRefGoogle Scholar
  54. 54.
    Fatemi MH, Chahi ZG (2012) QSPR-based estimation of the half-lives for polychlorinated biphenyl congeners. SAR QSAR Environ Res 23(1–2):155–168.  https://doi.org/10.1080/1062936X.2011.645876 CrossRefPubMedGoogle Scholar
  55. 55.
    Suzuki T, Kasuya Y, Itoh Y, Ota Y, Zhan P, Asamitsu K, Nakagawa H, Okamoto T, Miyata N (2013) Identification of highly selective and potent histone deacetylase 3 inhibitors using click chemistry-based combinatorial fragment assembly. PLoS ONE 8(7):68669–68681.  https://doi.org/10.1371/journal.pone.0068669 CrossRefGoogle Scholar
  56. 56.
    Zhang L, Zhang J, Jiang Q, Zhang L, Song W (2018) Zinc binding groups for histone deacetylase inhibitors. J Enzym Inhib Med Chem 33(1):714–721.  https://doi.org/10.1080/14756366.2017.1417274 CrossRefGoogle Scholar
  57. 57.
    Jalali-Heravi M, Mani-Varnosfaderani A (2012) Navigating drug-like chemical space of anticancer molecules using genetic algorithms and counter propagation artificial neural networks. Mol Inf 31(1):63–74.  https://doi.org/10.1002/minf.201100098 CrossRefGoogle Scholar
  58. 58.
    Bertrand P (2010) Inside HDAC with HDAC inhibitors. Eur J Med Chem 45(6):2095–2116.  https://doi.org/10.1016/j.ejmech.2010.02.030 CrossRefPubMedGoogle Scholar
  59. 59.
    Rajak H, Singh A, Raghuwanshi K, Kumar R, Dewangan PK, Veerasamy R, Sharma PC, Dixit A, Mishra P (2014) A structural insight into hydroxamic acid based histone deacetylase inhibitors for the presence of anticancer activity. Curr Med Chem 21(23):2642–2664.  https://doi.org/10.2174/09298673113209990191 CrossRefPubMedGoogle Scholar
  60. 60.
    Bolden JE, Peart MJ, Johnstone RW (2006) Anticancer activities of histone deacetylase inhibitors. Nat Rev Drug Discov 5(9):769–784.  https://doi.org/10.1038/nrd2133 CrossRefPubMedGoogle Scholar
  61. 61.
    Neiband MS, Mani-Varnosfaderani A, Benvidi A (2017) Classification of sphingosine kinase inhibitors using counter propagation artificial neural networks: a systematic route for designing selective SphK inhibitors. SAR QSAR Environ Res 28(2):91–109.  https://doi.org/10.1080/1062936X.2017.1280535 CrossRefPubMedGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of ChemistryYazd UniversityYazdIran
  2. 2.Department of ChemistryPayame Noor University (PNU)TehranIran
  3. 3.Chemometrics and Chemoinformatics LaboratoryTarbiat Modares UniversityTehranIran

Personalised recommendations