Prediction of antimicrobial activity of imidazole derivatives by artificial neural networks

Małgorzata Wnuk 1 , Michał Marszałł 2 , Anna Zapęcka 1 , Alicja Nowaczyk 3 , Jerzy Krysiński 4 , Jerzy Romaszko 5 , Piotr Kawczak 6 , Tomasz Bączek 6 , and Adam Buciński 1
  • 1 Department of Biopharmacy, Faculty of Pharmacy, Collegium Medicum, Nicolaus Copernicus University, Jurasza 2, 85-094, Bydgoszcz, Poland
  • 2 Department of Medicinal Chemistry, Faculty of Pharmacy, Collegium Medicum, Nicolaus Copernicus University, Jurasza 2, 85-094, Bydgoszcz, Poland
  • 3 Department of Organic Chemistry, Faculty of Pharmacy, Collegium Medicum, Nicolaus Copernicus University, Jurasza 2, 85-094, Bydgoszcz, Poland
  • 4 Department of Pharmaceutical Technology, Faculty of Pharmacy, Collegium Medicum, Nicolaus Copernicus University, Jurasza 2, 85-094, Bydgoszcz, Poland
  • 5 NZOZ Pantamed Sp z o.o. in Olsztyn, 10-461, Olsztyn, Poland
  • 6 Department of Pharmaceutical Chemistry, Faculty of Pharmacy, Medical University of Gdańsk, Hallera 107, 80-416, Gdańsk, Poland


The main goal of our study is the analysis of data obtained from molecular modeling for a series of imidazole derivatives that possess strong antifungal activity. The research was designed to use artificial neural network (ANN) analysis to determine quantitative relationships between the structural parameters and anti-Streptococcus pyogenes activity of a series of imidazole derivatives. ANN in association with quantitative structure-activity relationships (QSAR) represents a promising tool in the search for drug candidates among the practically unlimited number of possible derivatives. In this work, a series of 286 imidazole derivatives presented as cationic three-dimensional structures was used. The activity was expressed as a logarithm of the reciprocal of the minimal inhibitory concentrations, log 1/MIC. Multilayer perceptron ANN was used for predictions of antimicrobial potency of new imidazole derivatives on the basis of their structural descriptors. The obtained correlation coefficient equaled 0.9461 for the learning set, 0.9060 for the validation set and 0.8824 for the testing set of imidazole derivatives. Hence, satisfactory and practically useful predictions of anti-Streptococcus pyogenes activity for a series of imidazole derivatives was obtained, supporting the future successful interpretation of QSAR analysis for those compounds.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] Weglewski J, Pernak J, Krysiński J, Synthesis and bactericidalproperties of pyridiniumchlorides with alkylthiomethyl and alkoxymethylhydrophobicgroups, J. Pharm.Sci., 1991, 80, 91–95

  • [2] Pernak J, Krysiński J, Skrzypczak A, Activity of New Quaternary Iminium Compounds: [Bakterizide Wirkung von Iminiumverbindungen],Tenside Surfactants Detergents,1987, 24, 276–279

  • [3] Wiktorowicz W, Markuszewski M, Krysiński J, Kaliszan R, Quantitative structure-activity relationships study of a series of imidazole derivatives as potential new antifungal drugs,Acta Pol.Pharm., 2002, 59, 295–306

  • [4] Ranke J, Möltera K, Stocka F, Bottin-Webera U, Poczobutta J, Hoffmannb J, Ondruschkab B, Filsera J, Jastorffa B, Biological effects of imidazolium ionic liquids with varying chain lengths in acute Vibrio fischeri and WST-1 cell viability assays,Ecotox. Env.Safety,2004,58, 396–404

  • [5] Hadj-esfandiari N, Navidpour L, Shadnia H, Amini M, Samadi N, Faramarzi MA, Shafiee A, Synthesis, antibacterial activity, and quantitative structure-activity relationships of new (Z)-2-(nitroimidazolylmethylene)-3-benzofuranone derivatives,Bioorg.Med. Chem.Lett.,2007,17, 6354–6363

  • [6] Ghasemi A, Namaki S, Mirshafiey A, Streptococcus pyogenes. J. Chin. Clin.Medicine,2009,4, 9–18

  • [7] Guilherme L, Postol E, Freschi de Barros S, Higa F, Alencar R, Lastre M, Zayas C, Puschel CR, Silva WR, Sa-Rocha LC, Sa-Rocha VM, Pérez O, Kalil J, A vaccine against S. pyogenes: Design and experimental immune response, Methods,2009, 49, 316–321

  • [8] Moura H, Woolfitt AR, Carvalho MG, Pavlopoulos A, Teixeira LM, Satten GA, Barr JR, MALDI-TOF mass spectrometryas a tool for differentiation of invasive and noninvasive Streptococcus pyogenes isolates, FEMS Immunol.Med.Microbiol.,2008,53, 333–342

  • [9] JR, MALDI-TOF mass spectrometryas a tool for differentiation of invasive and noninvasive Streptococcus pyogenes isolates, FEMS Immunol. Med.Microbiol.,2008,53, 333–342

  • [10] Miller AK, Antibacterial activity of ronidazole,Appl. Microbiol., 1971, 22, 480–481

  • [11] Berkelhammer G, Asato G, 2-Amino-5-(1-methyl-5-nitro-2-imidazolyl)-1,3, 4-thiadiazole: a new antimicrobial agent,Science,1986, 162, 1146

  • [12] Buciński A, Markuszewski MJ, Wiktorowicz W, Krysinski J, Kaliszan R, Artificial neural networks for prediction of antibacterial activity in series of imidazole derivatives, Comb. Chem. High ThroughputScreen,2004,7, 327–336

  • [13] Buciński A, Nasal A, Kaliszan R, Pharmacological classification of drugs based on neural network processing of molecular modeling data, Comb. Chem. High ThroughputScreen, 2000,3, 525–533

  • [14] Nasal A, Buciński A, Bączek T, Wojdełko A, Prediction of the affinity of the newly synthesisedazapirone derivatives for 5-HT1A receptors based on artificial neural network analysis of chromatographic retention data and calculation chemistry parameters, Comb.Chem. High ThroughputScreen,2004, 7, 313–325.

  • [15] So SS, Richards WG, Application of neural networks: quantitative structure-activity relationships of the derivatives of 2,4-diamino-5-(substitutedbenzyl) pyrimidines as DHFR inhibitors,J.Med. Chem.,1992,35, 3201–3207

  • [16] Jaen-Oltra J, Salabert-Salvador MT, Garcia-March FJ, Perez-Gimenez F, Tomas-Vert F, Artificial neural network applied to prediction of fluorquinolone antibacterial activity by topological methods, J.Med.Chem.,2000,43, 1143–1148

  • [17] Buciński A, Socha A, Wnuk M, Bączek T, Nowaczyk A, Krysiński J, Goryński K, Koba M, Artificial neural networks in prediction of antifungal activity of series of pyridine derivatives against Candida albicans, J. Microbiol. Methods,2009,79, 25–29

  • [18] Kövesdi I, Dominguez-Rodriguez MF, Ôrfi L, Náray-Szabó G, Varró A, Papp JG, Mátyus P, Application of neural networks in structure — activity relationships,Med. Res.Rev.,1999,19, 249–269<249::AID-MED4>3.0.CO;2-0

  • [19] Pernak J, Jędraszczyk J, Skrzypczak A, Krysiński J, Węcłaś H,Antimikrobiellewirkungvon iminiumverbindungen,MittTenside Surf. Det., 1992, 29, 280–284

  • [20] Kier LB, Hall LH, Molecular Connectivity in Structure-Activity Analysis, John Wiley and Sons, New York, 1986

  • [21] Hall LH, Kier LB, Reviews in Computational Chemistry, Ch. 9, ed. KB, Lipkowitz and DB, Boyd, 1992

  • [22] Todeschini R, Lasagni M, Marengo E, New Molecular Descriptors for 2D- and 3D-Structures, Theoretical J.Chemometr.,1984, 8, 263–273

  • [23] Moriguchi I, Hirono S, Liu Q, Nakagome Y, Matsushita Y, Simple method of calculating octanol/water partition coefficient, Chem. Pharm. Bull.,1992,40, 127–130

  • [24] Ghose AK, Pritchett A, Crippen GM, Atomic physicochemical parameters for three dimensional structure directed quantitative structure-activity relationships III: Modeling hydrophobic interactions,J. Comp. Chem., 1988, 9, 80–90

  • [25] Todeschini R, Consonni V, Handbook of molecular descriptors, Wiley-VHC, Weinheim (Germany), 2000

  • [26] Bączek T, Buciński A, Ivanow AR, Kaliszan R, Artificial Neural Network analysis for evaluation of peptide MS/MS spectra in proteomics, Anal. Chem.,2004,76, 1726–173


Journal + Issues