Journal of Computer-Aided Molecular Design

, Volume 31, Issue 8, pp 701–714 | Cite as

Predictive cartography of metal binders using generative topographic mapping

  • Igor I. Baskin
  • Vitaly P. Solov’ev
  • Alexander A. Bagatur’yants
  • Alexandre Varnek


Generative topographic mapping (GTM) approach is used to visualize the chemical space of organic molecules (L) with respect to binding a wide range of 41 different metal cations (M) and also to build predictive models for stability constants (logK) of 1:1 (M:L) complexes using “density maps,” “activity landscapes,” and “selectivity landscapes” techniques. A two-dimensional map describing the entire set of 2962 metal binders reveals the selectivity and promiscuity zones with respect to individual metals or groups of metals with similar chemical properties (lanthanides, transition metals, etc). The GTM-based global (for entire set) and local (for selected subsets) models demonstrate a good predictive performance in the cross-validation procedure. It is also shown that the data likelihood could be used as a definition of the applicability domain of GTM-based models. Thus, the GTM approach represents an efficient tool for the predictive cartography of metal binders, which can both visualize their chemical space and predict the affinity profile of metals for new ligands.


Generative topographic mapping Metal binding Cartography of chemical space Activity landscapes 



This work was supported by the Russian Science Foundation Grant No. 14-43-00052, base organization Photochemistry Center, Russian Academy of Sciences. AAB thanks for partial support from the improving of the competitiveness program of National Research Nuclear University “MEPhI”.

Supplementary material

10822_2017_33_MOESM1_ESM.docx (4.4 mb)
Supplementary material includes: (1) activity landscapes for 41 metal ions, (2) density maps for the distribution of ligands for 41 metal ions, (3) optimal GTM parameters for global and local models, and (4) statistical characteristics of GTM-based regression models. (DOCX 4520 KB)


  1. 1.
    Varnek A, Baskin I (2012) Machine learning methods for property prediction in chemoinformatics: quo vadis? J Chem Inf Model 52(6):1413–1437. doi: 10.1021/ci200409x CrossRefGoogle Scholar
  2. 2.
    Cherkasov A, Muratov EN, Fourches D, Varnek A, Baskin II, Cronin M, Dearden J, Gramatica P, Martin YC, Todeschini R, Consonni V, Kuz’min VE, Cramer R, Benigni R, Yang C, Rathman J, Terfloth L, Gasteiger J, Richard A, Tropsha A (2015) QSAR modeling: where have you been? Where are you going to? J Med Chem 57(12):4977–5010. doi: 10.1021/jm4004285 CrossRefGoogle Scholar
  3. 3.
    Kubinyi H, Muler G (2004) Chemogenomics in drug discovery. Wiley, WeinheimCrossRefGoogle Scholar
  4. 4.
    Varnek A, Baskin II (2011) Chemoinformatics as a theoretical chemistry discipline. Mol Inf 30(1):20–32. doi: 10.1002/minf.201000100 CrossRefGoogle Scholar
  5. 5.
    Varnek A, Solov’ev V (2009) Quantitative structure-property relationships in solvent extraction and complexation of metals. In: Sengupta AK, Moyer BA (eds) Ion exchange and solvent extraction, a series of advances, vol 19. CRC Press, Taylor and Francis Group, Boca Raton, pp 319–358CrossRefGoogle Scholar
  6. 6.
    Solov’ev V, Marcou G, Tsivadze A, Varnek A (2012) Complexation of Mn2+, Fe2+, Y3+, La3+, Pb2+, and UO2 2+ with organic ligands: QSPR ensemble modeling of stability constants. Ind Eng Chem Res 51(41):13482–13489. doi: 10.1021/ie301271s CrossRefGoogle Scholar
  7. 7.
    Solov’ev V, Sukhno I, Buzko V, Polushin A, Marcou G, Tsivadze A, Varnek A (2012) Stability constants of complexes of Zn2+, Cd2+, and Hg2+ with organic ligands: QSPR consensus modeling and design of new metal binders. J Incl Phenom Macrocycl Chem 72(3–4):309–321. doi: 10.1007/s10847-011-9978-6 CrossRefGoogle Scholar
  8. 8.
    Solov’ev VP, Tsivadze AY, Varnek AA (2012) New approach for accurate QSPR modeling of metal complexation: application to stability constants of complexes of lanthanide Ions Ln3+, Ag+, Zn2+, Cd2+ and Hg2+ with organic ligands in water. Macroheterocycles 5(4–5):404–410. doi: 10.6060/mhc2012.121104s CrossRefGoogle Scholar
  9. 9.
    Solov’ev VP, Kireeva N, Tsivadze AY, Varnek A (2013) QSPR ensemble modelling of alkaline-earth metal complexation. J Incl Phenom Macrocycl Chem 76(1–2):159–171. doi: 10.1007/s10847-012-0185-x CrossRefGoogle Scholar
  10. 10.
    Solov’ev V, Varnek A, Tsivadze A (2014) QSPR ensemble modelling of the 1:1 and 1:2 complexation of Co2+, Ni2+, and Cu2+ with organic ligands: relationships between stability constants. J Comput Aided Mol Des 28(5):549–564. doi: 10.1007/s10822-014-9741-3 CrossRefGoogle Scholar
  11. 11.
    Gaspar HA, Baskin II, Marcou G, Horvath D, Varnek A (2015) GTM-based QSAR models and their applicability domains. Mol Inf 34(6–7):348–356. doi: 10.1002/minf.201400153 CrossRefGoogle Scholar
  12. 12.
    Varnek A, Fourches D, Solov’ev V, Klimchuk O, Ouadi A, Billard I (2007) Successful “in silico” design of new efficient uranyl binders. Solvent Extr Ion Exch 25:433–462CrossRefGoogle Scholar
  13. 13.
    Varnek A, Fourches D, Sieffert N, Solov’ev VP, Hill C, Lecomte M (2007) QSPR modeling of the Am-III/Eu-III separation factor: how far can we predict. Solvent Extr Ion Exch 25(1):1–26. doi: 10.1080/07366290601067481 CrossRefGoogle Scholar
  14. 14.
    Sitnikov GV, Zhokhova NI, Ustynyuk YA, Varnek A, Baskin II (2015) Continuous indicator fields: a novel universal type of molecular fields. J Comput Aided Mol Des 29(3):233–247. doi: 10.1007/s10822-014-9818-z CrossRefGoogle Scholar
  15. 15.
    Varnek A, Fourches D, Kireeva N, Klimchuk O, Marcou G, Tsivadze A, Solov’ev V (2008) Computer-aided design of new metal binders. Radiochim Acta 96(8):505–511. doi: 10.1524/ract.2008.1518 CrossRefGoogle Scholar
  16. 16.
    Solov’ev VP, Varnek A, Wipff G (2000) Modeling of ion complexation and extraction using substructural molecular fragments. J Chem Inf Comput Sci 40(3):847–858CrossRefGoogle Scholar
  17. 17.
    Baskin I, Varnek A (2008) Fragment descriptors in SAR/QSAR/QSPR studies, molecular similarity analysis and in virtual screening. In: Varnek A, Tropsha A (eds) Chemoinformatics approaches to virtual screening RSC Publisher, Cambridge, pp 1–43Google Scholar
  18. 18.
    Varnek A, Fourches D, Horvath D, Klimchuk O, Gaudin C, Vayer P, Solov’ev V, Hoonakker F, Tetko IV, Marcou G (2008) ISIDA—Platform for virtual screening based on fragment and pharmacophoric descriptors. Curr Comput Aided Drug Des 4(3):191–198CrossRefGoogle Scholar
  19. 19.
    Varnek A, Wipff G, Solov’ev VP, Solotnov AF (2002) Assessment of the macrocyclic effect for the complexation of crown-ethers with alkali cations using the substructural molecular fragments method. J Chem Inf Comput Sci 42(4):812–829CrossRefGoogle Scholar
  20. 20.
    Tetko IV, Solov’ev VP, Antonov AV, Yao X, Doucet JP, Fan B, Hoonakker F, Fourches D, Jost P, Lachiche N, Varnek A (2006) Benchmarking of linear and nonlinear approaches for quantitative structure-property relationship studies of metal complexation with ionophores. J Chem Inf Model 46(2):808–819CrossRefGoogle Scholar
  21. 21.
    Baskin II, Kireeva N, Varnek A (2010) The one-class classification approach to data description and to models applicability domain. Mol Inf 29(8–9):581–587. doi: 10.1002/minf.201000063 CrossRefGoogle Scholar
  22. 22.
    Oprea TI, Gottfries J (2001) Chemography: the art of navigating in chemical space. J Comb Chem 3(2):157–166CrossRefGoogle Scholar
  23. 23.
    Isayev O, Fourches D, Muratov EN, Oses C, Rasch K, Tropsha A, Curtarolo S (2015) Materials cartography: Representing and mining materials space using structural and electronic fingerprints. Chem Mat 27(3):735–743CrossRefGoogle Scholar
  24. 24.
    Pletnev IV, Zernov VV (2002) Classification of metal ions according to their complexing properties: a data-driven approach. Anal Chim Acta 455(1):131–142. doi: 10.1016/S0003-2670(01)01571-9 CrossRefGoogle Scholar
  25. 25.
    Bishop CM, Svensén M, Williams CKI (1998) GTM: the generative topographic mapping. Neural Comput 10(1):215–234CrossRefGoogle Scholar
  26. 26.
    Bishop CM, Svensén M, Williams CKI (1998) Developments of the generative topographic mapping. Neurocomputing 21(1–3):203–224CrossRefGoogle Scholar
  27. 27.
    Maniyar DM, Nabney IT, Williams BS, Sewing A (2006) Data visualization during the early stages of drug discovery. J Chem Inf Model 46(4):1806–1818. doi: 10.1021/ci050471a CrossRefGoogle Scholar
  28. 28.
    Owen JR, Nabney IT, Medina-Franco JL, López-Vallejo F (2011) Visualization of molecular fingerprints. J Chem Inf Model 51(7):1552–1563. doi: 10.1021/ci1004042 CrossRefGoogle Scholar
  29. 29.
    Kireeva N, Baskin II, Gaspar HA, Horvath D, Marcou G, Varnek A (2012) Generative topographic mapping (GTM): universal tool for data visualization, structure-activity modeling and dataset comparison. Mol Inf 31(3–4):301–312. doi: 10.1002/minf.201100163 CrossRefGoogle Scholar
  30. 30.
    Gaspar HA, Baskin II, Marcou G, Horvath D, Varnek A (2015) Chemical data visualization and analysis with incremental generative topographic mapping: big data challenge. J Chem Inf Model 55(1):84–94. doi: 10.1021/ci500575y CrossRefGoogle Scholar
  31. 31.
    Gaspar HA, Marcou G, Horvath D, Arault A, Lozano S, Vayer P, Varnek A (2013) Generative topographic mapping-based classification models and their applicability domain: application to the biopharmaceutics drug disposition classification system (BDDCS). J Chem Inf Model 53(12):3318–3325. doi: 10.1021/ci400423c CrossRefGoogle Scholar
  32. 32.
    Gaspar HA, Sidorov P, Horvath D, Baskin II, Marcou G, Varnek A (2016) Generative topographic mapping approach to chemical space analysis. In: Frontiers in molecular design and chemical information science—Herman Skolnik Award Symposium 2015: Jürgen Bajorath, vol 1222. ACS symposium series, vol 1222. American Chemical Society, Washington, DC, pp 211–241. doi: 10.1021/bk-2016-1222.ch011 Google Scholar
  33. 33.
    The IUPAC Stability Constants Database, SC-Database. Accessed 24 June 2017
  34. 34.
    Gaspar HA, Baskin II, Marcou G, Horvath D, Varnek A (2015) Stargate GTM: bridging descriptor and activity spaces. J Chem Inf Model 55(11):2403–2410. doi: 10.1021/acs.jcim.5b00398 CrossRefGoogle Scholar
  35. 35.
    Varnek A, Fourches D, Hoonakker F, Solov’ev V (2005) Substructural fragments: an universal language to encode reactions, molecular and supramolecular structures. J Comput Aided Mol Des 19(9):693–703. doi: 10.1007/s10822-005-9008-0 CrossRefGoogle Scholar
  36. 36.
    Horvath D, Brown JB, Marcou G, Varnek A (2014) An evolutionary optimizer of libsvm models. Challenges 5(2):450–472CrossRefGoogle Scholar
  37. 37.
    Sidorov P, Gaspar H, Marcou G, Varnek A, Horvath D (2015) Mappability of drug-like space: towards a polypharmacologically competent map of drug-relevant compounds. J Comput Aided Mol Des 29(12):1087–1108. doi: 10.1007/s10822-015-9882-z CrossRefGoogle Scholar
  38. 38.
    Monev V (2004) Introduction to similarity searching in chemistry. MATCH Commun Math Comput Chem 51:7–38Google Scholar
  39. 39.
    Csardi G, Nepusz T (2006) The igraph software package for complex network research. Int J Complex Syst 1695(5):1–9Google Scholar
  40. 40.
    Kamada T, Kawai S (1989) An algorithm for drawing general undirected graphs. Inf Process Lett 31(1):7–15CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Faculty of PhysicsM.V. Lomonosov Moscow State UniversityMoscowRussian Federation
  2. 2.Laboratory of Chemoinformatics, Butlerov Institute of ChemistryKazan Federal UniversityKazanRussian Federation
  3. 3.Institute of Physical Chemistry and ElectrochemistryRussian Academy of SciencesMoscowRussian Federation
  4. 4.Federal Research Center Crystallography and Photonics RASMoscowRussian Federation
  5. 5.National Research Nuclear University MEPhI (Moscow Engineering Physics Institute)MoscowRussian Federation
  6. 6.Laboratoire de Chemoinformatique, UMR 7140Université de StrasbourgStrasbourgFrance

Personalised recommendations