Skip to main content

Advertisement

An extension of the pharmacophore kernel using radial atomtype fingerprints

Article metrics

  • 1504 Accesses

The prediction of the biological activity of a chemical compound is a challenging task in Computational Chemistry and was restricted to vectorial representations of the molecular graph for decades. Kernel functions are positive semidefinite similarity measures that can be defined on arbitrary structured data. This class of similarity functions can be used in kernel-based machine learning algorithms. Interestingly, many graph kernel approaches from Computer Science share properties of traditional similarity measures for chemical compounds, like molecular fingerprints based on paths, cycles and subgraphs.

In this work, we present a hybrid technique derived from the Pharmacophore Kernel [1] and Radial Atom Environments [2]. Whereas in the original work [1] atoms were represented by their element number and partial charge, we employ a bounded depth-first-search to enumerate the complete neighbourhood of each non-carbon atom up to specified depth. Therefore, a pharmacophore can be defined by a triangle between three radial fingerprints. This opens the possibility to replace the simple Delta Kernel, which was used for the comparison of the vertices of two pharmacophores in the original work of Mahé et al. [1], by more sophisticated kernel functions defined on sets of discrete features. We tried the Tanimoto, MinMax [3] and the Spectrum Kernel [4] in our experiments. This results in valid kernel functions again, because a valid kernel function is replaced by another.

In the results section, we benchmark our approach against different state-of-the art graph kernels and the Radial Basis Function Kernel using descriptors calculated with dragonX 1.4 on various QSAR data sets taken from the literature. The models were trained using the machine learning library LIBSVM. The results show that our approach improves the predictive power significantly on many benchmark problems.

References

  1. 1.

    Mahé P, et al: J Chem Inf Mod. 2006, 46: 2003-2014. 10.1021/ci060138m.

  2. 2.

    Bender A, et al: J Chem Inf Comp Sci. 2004, 44: 170-178.

  3. 3.

    Ralaivola L, et al: Neural Networks. 2005, Elsevier Science Ltd., 18: 1093-1110. 10.1016/j.neunet.2005.07.009.

  4. 4.

    Leslie C, et al: Pacific symposium on biocomputing. 2002

Download references

Author information

Correspondence to G Hinselmann.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Hinselmann, G., Eckert, M., Holder, T. et al. An extension of the pharmacophore kernel using radial atomtype fingerprints. Chemistry Central Journal 3, P11 (2009) doi:10.1186/1752-153X-3-S1-P11

Download citation

Keywords

  • Radial Basis Function Kernel
  • Discrete Feature
  • Graph Kernel
  • Spectrum Kernel
  • Traditional Similarity