Incorporating Molecule’s Stereisomerism within the Machine Learning Framework

  • Pierre-Anthony Grenier
  • Luc Brun
  • Didier Villemin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8621)


An important field of chemoinformatics consists in the prediction of molecule’s properties, and within this field, graph kernels constitute a powerful framework thanks to their ability to combine a natural encoding of molecules by graphs, with classical statistical tools. Unfortunately some molecules encoded by a same graph and differing only by the three dimensional orientation of their atoms in space have different properties. Such molecules are called stereoisomers. These latter properties can not be predicted by usual graph methods which do not encode stereoisomerism. In this paper we propose to encode the stereoisomerism property of each atom of a molecule by a local subgraph. A kernel between bags of such subgraphs provides a similarity measure incorporating stereoisomerism properties. We then propose two extensions of this kernel incorporating in each sub graph information about its surroundings.


Asymmetric Carbon Support Vector Regression Machine Graph Kernel Adjacency Relationship Dimensional Orientation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bonnici, V., Giugno, R., Pulvirenti, A., Shasha, D., Ferro, A.: A subgraph isomorphism algorithm and its application to biochemical data. BMC Bioinformatics 14(suppl. 7), S13 (2013)CrossRefGoogle Scholar
  2. 2.
    Brown, J.B., Urata, T., Tamura, T., Arai, M.A., Kawabata, T., Akutsu, T.: Compound analysis via graph kernels incorporating chirality. Journal of Bioinformatics and Computational Biology 8(1), 63–81 (2010)CrossRefGoogle Scholar
  3. 3.
    Castillo-Garit, J.A., Marrero-Ponce, Y., Torrens, F., Rotondo, R.: Atom-based stochastic and non-stochastic 3d-chiral bilinear indices and their applications to central chirality codification. Journal of Molecular Graphics and Modelling 26(1), 32–47 (2007)CrossRefGoogle Scholar
  4. 4.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  5. 5.
    Drucker, H., Burges, C.J.C., Kaufman, L., Smola, A.J., Vapnik, V.: Support vector regression machines. In: NIPS, pp. 155–161 (1996)Google Scholar
  6. 6.
    Gaüzère, B., Brun, L., Villemin, D.: Two New Graphs Kernels in Chemoinformatics. Pattern Recognition Letters 33(15), 2038–2047 (2012)CrossRefGoogle Scholar
  7. 7.
    Grenier, P.-A., Brun, L., Villemin, D.: Incorporating stereo information within the graph kernel framework. Technical report, CNRS UMR 6072 GREYC (2013),
  8. 8.
    Grenier, P.-A., Brun, L., Villemin, D.: Treelet kernel incorporating chiral information. In: Kropatsch, W.G., Artner, N.M., Haxhimusa, Y., Jiang, X. (eds.) GbRPR 2013. LNCS, vol. 7877, pp. 132–141. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  9. 9.
    Jacques, J., Collet, A., Wilen, S.: Enantiomers, racemates, and resolutions. Krieger Pub. Co. (1991)Google Scholar
  10. 10.
    Mahé, P., Vert, J.-P.: Graph kernels based on tree patterns for molecules. Machine Learning 75(1), 3–35 (2008)CrossRefGoogle Scholar
  11. 11.
    Petitjean, M.: Chirality in metric spaces. Symmetry, Culture and Science 21, 27–36 (2010)zbMATHGoogle Scholar
  12. 12.
    Vismara, P.: Union of all the minimum cycle bases of a graph. The Electronic Journal of Combinatorics 4(1), 73–87 (1997)MathSciNetGoogle Scholar
  13. 13.
    Wipke, W.T., Dyott, T.M.: Stereochemically unique naming algorithm. Journal of the American Chemical Society 96(15), 4834–4842 (1974)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Pierre-Anthony Grenier
    • 1
  • Luc Brun
    • 1
  • Didier Villemin
    • 2
  1. 1.GREYC UMR CNRS 6072CaenFrance
  2. 2.LCMT UMR CNRS 6507CaenFrance

Personalised recommendations