Application of Machine Learning Approaches to Identify New Anticonvulsant Compounds Active in the 6 Hz Seizure Model

  • S. Goicoechea
  • M. L. Sbaraglini
  • S. R. Chuguransky
  • J. F. Morales
  • M. E. Ruiz
  • A. Talevi
  • C. L. BelleraEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1068)


Epilepsy is the second most common chronic brain disorder, affecting 65 million people worldwide. According to the NIH’s Epilepsy Therapy Screening Program, evaluation of potential new antiepileptic drug candidates begins with assessment of their protective effects in two acute seizure models in mice, the Maximal Electroshock Seizure test and the 6 Hz test. The latter elicits partial seizures through an electrical stimulus of 44 mA, at which many clinically established anti-seizure drugs do not suppress seizures. The inclusion of this “high-hurdle” acute seizure assay at the initial stage of the drug identification phase is intended to increase the probability that agents with improved efficacy will be detected. In this work, we have used machine learning approximations to develop in silico models capable of identifying novel anticonvulsant drugs with protective effects in the 6 Hz seizure model. Linear classifiers based on Dragon conformation-independent descriptors were generated through an in-house routine in R environment and validated through standard validation procedures. They were later combined through different ensemble learning schemes. The best ensemble comprised the 29 best-performing models combined using the MIN operator. With the objective of finding new drug repurposing opportunities (i.e. identifying second or further therapeutic indications, in our case anticonvulsant activity, in existing drugs), such model ensemble was applied in a virtual screening campaign of DrugBank and Sweetlead databases. 28 approved drugs were identified as potential protective agents in the 6 Hz model. The present study constitutes an example of the use of machine learning approximations to systematically guide drug repurposing projects.


Machine learning Ensemble learning 6 Hz seizure model Anticonvulsant drugs Virtual screening Epilepsy Drug repurposing 



The authors would like to thank the following public and non-profit organisations: National University of La Plata (UNLP) and Argentinean National Council of Science and Technological Research (CONICET).


Support was received from the National University of La Plata (UNLP) [grant X729].

Supplementary material (556 kb)
Supplementary material 1 (ZIP 556 kb)


  1. 1.
    World Health Organization: Fact Sheet Epilepsy.
  2. 2.
    Xia, L., Ou, S., Pan, S.: Initial response to antiepileptic drugs in patients with newly diagnosed epilepsy as a predictor of long-term outcome. Front. Neurol. 8, 658 (2017). Scholar
  3. 3.
    Corsello, S.M., et al.: The Drug Repurposing Hub: a next-generation drug library and information resource. Nat. Med. 23, 405–408 (2017). Scholar
  4. 4.
    Talevi, A.: Drug repositioning: current approaches and their implications in the precision medicine era. Expert. Rev. Precis. Med. Drug Dev. 3, 49–61 (2018). Scholar
  5. 5.
    Barton, M.E., Klein, B.D., Wolf, H.H., White, H.S.: Pharmacological characterization of the 6 Hz psychomotor seizure model of partial epilepsy. Epilepsy Res. 47, 217–227 (2001). Scholar
  6. 6.
    Löscher, W.: Critical review of current animal models of seizures and epilepsy used in the discovery and development of new antiepileptic drugs. Seizure 20(5), 359–368 (2011). Scholar
  7. 7.
    Vyskovsky, R., Schwarz, D., Janousova, E., Kasparek, T.: Random subspace ensemble artificial neural networks for first-episode Schizophrenia classification. In: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems (Gdansk: FedCSIS), pp. 317–321 (2016).
  8. 8.
    Kamiński, K., Wiklik, B., Obniska, J.: Synthesis and anticonvulsant activity of new N-phenyl-2-(4-phenylpiperazin-1-yl) acetamide derivatives. Med. Chem. Res. 24(7), 3047–3061 (2015). Scholar
  9. 9.
    Dawidowski, M., Lewandowski, W., Turło, J.: Synthesis of new perhydropyrrolo [1, 2-a] pyrazine derivatives and their evaluation in animal models of epilepsy. Molecules 19(10), 15955–15981 (2014). Scholar
  10. 10.
    Coleman, N., et al.: The riluzole derivative 2-amino-6-trifluoromethylthio-benzothiazole (SKA-19), a mixed KCa2 activator and NaV blocker, is a potent novel anticonvulsant. Neurotherapeutics 12(1), 234–249 (2015). Scholar
  11. 11.
    Obniska, J., Chlebek, I., Kamiński, K., Bojarski, A.J., Satała, G.: Synthesis, anticonvulsant activity and 5-HT1A/5-HT7 receptors affinity of 1-[(4-arylpiperazin-1-yl)-propyl]-succinimides. Pharmacol. Rep. 64(2), 326–335 (2012)CrossRefGoogle Scholar
  12. 12.
    Xian-Qing, D., Ming-Xia, S., Guo-Hua, G., Shi-Ben, W., Zhe-Shan, Q.: Synthesis and anticonvulsant evaluation of some new 6-(substituted-phenyl) thiazolo [3, 2-b][1, 2, 4]triazole derivatives in mice. Iran. J. Pharm. Res. 13(2), 459–469 (2014)Google Scholar
  13. 13.
    Byrtus, H., Obniska, J., Czopek, A., Kamiński, K., Pawłowski, M.: Synthesis and anticonvulsant activity of new N-Mannich bases derived from 5-cyclopropyl-5-phenyl- and 5-cyclopropyl-5-(4-chlorophenyl)-imidazolidine-2, 4-diones. Bioorg. Med. Chem. 19(20), 6149–6156 (2011). Scholar
  14. 14.
    Florek-Luszczki, M., Wlaz, A., Luszczki, J.J.: Interactions of levetiracetam with carbamazepine, phenytoin, topiramate and vigabatrin in the mouse 6 Hz psychomotor seizure model – A type II isobolographic analysis. Eur. J. Pharmacol. 723, 410–418 (2014). Scholar
  15. 15.
    Dawidowski, M., Turło, M.: Multicomponent synthesis and anticonvulsant activity of monocyclic 2, 6-diketopiperazine derivatives. Med. Chem. Res. 23(4), 2007–2018 (2014). Scholar
  16. 16.
    Ugale, V.G., Bari, S.B.: Structural exploration of quinazolin-4 (3H)-ones as anticonvulsants: rational design, synthesis, pharmacological evaluation, and molecular docking studies. Arch. Pharm. 349(11), 864–880 (2016). Scholar
  17. 17.
    Tomaciello, F., Leclercq, K., Kaminski, R.M.: Resveratrol lacks protective activity against acute seizures in mouse models. Neurosci. Lett. 632, 199–203 (2016). Scholar
  18. 18.
    Sałat, K., et al.: Novel, highly potent and in vivo active inhibitor of GABA transporter subtype 1 with anticonvulsant, anxiolytic, antidepressant and antinociceptive properties. Neuropharmacol. 113(Pt A), 331–342 (2017). Scholar
  19. 19.
    Gunia-Krzyżak, A., et al.: Structure-anticonvulsant activity studies in the group of (E)-N-cinnamoyl aminoalkanols derivatives monosubstituted in phenyl ring with 4-Cl, 4-CH3 or 2-CH3. Bioorg. Med. Chem. 25(2), 471–482 (2017). Scholar
  20. 20.
    Zolkowska, D., Dhir, A., Krishnan, K., Covey, D.F., Rogawski, M.A.: Anticonvulsant potencies of the enantiomers of the neurosteroids androsterone and etiocholanolone exceed those of the natural forms. Psychopharmacol. (Berl). 231(17), 3325–3332 (2014). Scholar
  21. 21.
    Shekh-Ahmad, T., et al.: Enantioselective pharmacodynamic and pharmacokinetic analysis of two chiral CNS-active carbamate derivatives of valproic acid. Epilepsia 55(12), 1944–1952 (2014). Scholar
  22. 22.
    Kamiński, K., Wiklik, B., Obniska, J.: Synthesis, anticonvulsant properties, and SAR analysis of differently substituted pyrrolidine-2, 5-diones and piperidine-2, 6-diones. Arch. Pharm. (Weinheim) 347(11), 840–852 (2014). Scholar
  23. 23.
    Orellana-Paucar, A.M., et al.: Insights from zebrafish and mouse models on the activity and safety of ar-turmerone as a potential drug candidate for the treatment of epilepsy. PLoS ONE 8(12), e81634 (2013). Scholar
  24. 24.
    Nieoczym, D., Socała, K., Jedziniak, P., Olejnik, M., Wlaź, P.: Effect of sildenafil, a selective phosphodiesterase 5 inhibitor, on the anticonvulsant action of some antiepileptic drugs in the mouse 6-Hz psychomotor seizure model. Prog. Neuropsychopharmacol. Biol. Psychiatry 47, 104–110 (2012). Scholar
  25. 25.
    Dawidowski, M., Wilczek, M., Kubica, K., Skolmowski, M., Turło, J.: Structure-activity relationships of the aromatic site in novel anticonvulsant pyrrolo [1, 2-a]pyrazine derivatives. Bioorg. Med. Chem. Lett. 23(22), 6106–6110 (2013). Scholar
  26. 26.
    Shaikh, M.F., Tan, K.N., Borges, K.: Anticonvulsant screening of luteolin in four mouse seizure models. Neurosci. Lett. 550, 195–199 (2013). Scholar
  27. 27.
    Buenafe, O.E., et al.: Tanshinone IIA exhibits anticonvulsant activity in zebrafish and mouse seizure models. ACS. Chem. Neurosci. 4(11), 1479–1487 (2013). Scholar
  28. 28.
    Kumar, D., Kumar Sharma, V., Kumar, R., Singh, T., Singh, H., Singh, A.D., Roy, R.K.: Design, synthesis and anticonvulsant activity of some new 5, 7-dibromoisatin semicarbazone derivatives. EXCLI J. 12, 628–640 (2013)Google Scholar
  29. 29.
    Wlaz, A., Kondrat-Wrobel, M.W., Zaluska, K., Kochman, E., Rekas, A.R., Luszczki, J.J.: Synergistic interaction of levetiracetam with gabapentin in the mouse 6 Hz psychomotor seizure model – A type II isobolographic analysis. Curr. Issues Pharm. Med. Sci. 28(3), 204–207 (2015). Scholar
  30. 30.
    Shandra, A., Shandra, P., Kaschenko, O., Matagne, A., Stöhr, T.: Synergism of lacosamide with established antiepileptic drugs in the 6-Hz seizure model in mice. Epilepsia 54(7), 1167–1175 (2013). Scholar
  31. 31.
    Ahsan, M.J., Khalilullah, H., Yasmin, S., Singh Jadav, S., Stables, J.P.: Synthesis and anticonvulsant evaluation of 2-(substituted benzylidene/ethylidene)-N-(substituted phenyl) hydrazinecarboxamide analogues. Med. Chem. Res. 22(6), 2746–2754 (2013). Scholar
  32. 32.
    Tripathi, L., Kumar, P.: Augmentation of GABAergic neurotransmission by novel N-(substituted)-2-[4-(substituted) benzylidene] hydrazinecarbothioamides—a potential anticonvulsant approach. Eur. J. Med. Chem. 64, 477–487 (2013). Scholar
  33. 33.
    Ulloora, S., Shabaraya, R., Ranganathan, R., Adhikari, A.V.: Synthesis, anticonvulsant and anti-inflammatory studies of new 1, 4-dihydropyridin-4-yl-phenoxyacetohydrazones. Eur. J. Med. Chem. 70, 341–349 (2013). Scholar
  34. 34.
    Zuliani, V., Rivara, M.: In vivo screening of diarylimidazoles as anticonvulsant agents. Med. Chem. Res. 21(11), 3428–3434 (2011). Scholar
  35. 35.
    Kumar, P., Shrivastava, B., Pandeya, S.M., Tripathi, L., Stables, J.P.: Design, synthesis, and anticonvulsant evaluation of some novel 1, 3 benzothiazol-2-yl hydrazones/acetohydrazones. Med. Chem. Res. 21(9), 2428–2442 (2012). Scholar
  36. 36.
    Hebeisen, S., et al.: Eslicarbazepine and the enhancement of slow inactivation of voltage-gated sodium channels: a comparison with carbamazepine, oxcarbazepine and lacosamide. Neuropharmacology 89, 122–1235 (2015). Scholar
  37. 37.
    Ahsan, M.J., Khalilullah, H., Stables, J.P., Govindasamy, J.: Synthesis and anticonvulsant activity of 3a, 4-dihydro-3H-indeno [1, 2-c] pyrazole-2-carboxamide/carbothioamide analogues. J. Enzyme Inhib. Med. Chem. 28(3), 644–650 (2013). Scholar
  38. 38.
    Tosh, D.K., et al.: Structural sweet spot for A1 adenosine receptor activation by truncated (N)-methanocarba nucleosides: receptor docking and potent anticonvulsant activity. J. Med. Chem. 55(18), 8075–8090 (2012)CrossRefGoogle Scholar
  39. 39.
    Mishra, R.K., Baker, M.T.: Ortho Substituent effects on the anticonvulsant properties of 4-hydroxy-trifluoroethyl phenols. Bioorg. Med. Chem. Lett. 22(17), 5608–5611 (2012). Scholar
  40. 40.
    Wang, D.D., Englot, D.J., Garcia, P.A., Lawton, M.T., Young, W.L.: Minocycline and tetracycline-class antibiotics are protective against partial seizures in vivo. Epilepsy Behav. 24(3), 314–318 (2012). Scholar
  41. 41.
    Dawidowski, M., Herold, F., Chodkowski, A., Kleps, J.: Synthesis and anticonvulsant activity of novel 2, 6-diketopiperazine derivatives. Part 2: Perhydropyrido [1, 2-a] pyrazines. Eur. J. Med. Chem. 48, 347–353 (2012). Scholar
  42. 42.
    Gasior, M., Socała, K., Nieoczym, D., Wlaź, P.: Clavulanic acid does not affect convulsions in acute seizure tests in mice. J. Neural. Transm. 119(1), 1–6 (2012). Scholar
  43. 43.
    Perez-Llamas, C., Lopez-Bigas, N.: Gitools: analysis and visualisation of genomic data using interactive heat-maps. PLoS ONE 6, e19541 (2011). Scholar
  44. 44.
    Golbraikh, A., Shen, M., Xiao, Z., Xiao, Y.D., Lee, K.H., Tropsha, A.: Rational selection of training and test sets for the development of validated QSAR models. J. Comput. Aided Mol. Des. 17, 241–253 (2003). Scholar
  45. 45.
    Martin, T.M., et al.: Does rational selection of training and test sets improve the outcome of QSAR modeling? J. Chem. Inf. Model. 52, 2570–2578 (2012). Scholar
  46. 46.
    Everitt, B.S., Landau, S., Leese, M., Stahl, D.: Cluster Analysis, 5th edn. Wiley, West Sussex (2011)CrossRefGoogle Scholar
  47. 47.
    El Habib Daho, M., Chikh, M.A.: Combining bootstrapping samples, random subspaces and random forests to build classifiers. J. Med. Imaging Health Inf. 5, 539–544 (2015). Scholar
  48. 48.
    Yu, G., Zhang, G., Domeniconi, C., Yu, Z., You, J.: Semi-supervised classification based on random subspace dimensionality reduction. Pattern Recogn. 45, 1119–1135 (2012). Scholar
  49. 49.
    Toropova, A.P., Toropov, A.A.: CORAL: binary classifications (active/inactive) for drug-induced liver injury. Toxicol. Lett. 268, 51–57 (2017). Scholar
  50. 50.
    Gramatica, P.: On the development and validation of QSAR models. Methods Mol. Biol. 930, 499–526 (2013). Scholar
  51. 51.
    Roy, K., Mitra, I.: On various metrics used for validation of predictive QSAR models with applications in virtual screening and focused library design. Comb. Chem. High Throughput Screen. 14(6), 450–474 (2011). Scholar
  52. 52.
    Dietterich, T.G.: Ensemble methods in machine learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000). CrossRefGoogle Scholar
  53. 53.
    Robin, X., et al.: pROC: an open-source package for R and S + to analyze and compare ROC curves. BMC Bioinf. 12, 77 (2011). Scholar
  54. 54.
    Truchon, J.F., Bayly, C.L.: Evaluating virtual screening methods: good and bad metrics for the “early recognition” problem. J. Chem. Inf. Model. 47, 488–508 (2007). Scholar
  55. 55.
    Yabuuchi, H., et al.: Analysis of multiple compound–protein interactions reveals novel bioactive molecules. Mol. Syst. Biol. 7, 472, 1–12 (2011). Scholar
  56. 56.
    Lätti, S., Niinivehmas, S., Pentikäinen, O.T.: Rocker: open source, easy-to-use tool for AUC and enrichment calculations and ROC visualization. J. Cheminformatics 8(1), 45 (2016). Scholar
  57. 57.
    Mysinger, M.M., Carchia, M., Irwin, J.J., Shoichet, B.K.: Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. J. Med. Chem. 55(14), 6582–6594 (2012). Scholar
  58. 58.
    Alberca, L.N., et al.: Cascade ligand-and structure-based virtual screening to identify new trypanocidal compounds inhibiting putrescine uptake. Front. Cell. Infect. Microbiol. 8, 173 (2018). Scholar
  59. 59.
    Law, V., et al.: DrugBank 4.0: shedding new light on drug metabolism. Nucleic Acids Res. 42, D1091–D1097 (2014). Scholar
  60. 60.
    Novick, P.A., Ortiz, O.F., Poelman, J., Abdulhay, A.Y., Pande, V.S.: SWEETLEAD: an in silico database of approved drugs, regulated chemicals, and herbal isolates for computer-aided drug discovery. PLoS ONE 8(11), e79568 (2013). Scholar
  61. 61.
    Talevi, A., Carrillo, C., Comini, M.: The thiol-polyamine metabolism of Trypanosoma cruzi: molecular targets and drug repurposing strategies. Curr. Med. Chem. 26 (2019).
  62. 62.
    Oprea, T.I., Overington, J.P.: Computational and practical aspects of drug repositioning. Assay Drug Dev. Technol. 13, 299–306 (2015). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Laboratory of Bioactive Research and Development (LIDeB), Department of Biological Sciences, Faculty of Exact SciencesUniversity of La Plata (UNLP)La Plata, Buenos AiresArgentina
  2. 2.CCT La Plata, Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET)Buenos AiresArgentina

Personalised recommendations