Get access

Multiple Kernel Learning for Drug Discovery

Authors

  • Nicholas C. V. Pilkington,

    1. University of Cambridge Computer Laboratory, 15 JJ Thomson Avenue, Cambridge, CB3 0FD, UK phone: +44 (0)1223 763725
    Search for more papers by this author
  • Matthew W. B. Trotter,

    1. Anne McLaren Laboratory for Regenerative Medicine & Department of Surgery, University of Cambridge, UK
    2. Celgene Institute for Translational Research Europe (CITRE), Sevilla, Spain
    Search for more papers by this author
  • Sean B. Holden

    Corresponding author
    1. University of Cambridge Computer Laboratory, 15 JJ Thomson Avenue, Cambridge, CB3 0FD, UK phone: +44 (0)1223 763725
    • University of Cambridge Computer Laboratory, 15 JJ Thomson Avenue, Cambridge, CB3 0FD, UK phone: +44 (0)1223 763725
    Search for more papers by this author

Abstract

The support vector machine (SVM) methodology has become a popular and well-used component of present chemometric analysis. We assess a relatively recent development of the algorithm, multiple kernel learning (MKL), on published structure-property relationship (SPR) data. The MKL algorithm learns a weighting across multiple kernel-based representations of the data during supervised classifier creation and, thereby, may be used to describe the influence of distinct groups of structural descriptors upon a single structure–property classifier without explicitly omitting any of them. We observe a statistically significant performance improvement over a conventional, single kernel SVM on all three SPR data sets analysed. Furthermore, MKL output is observed to provide useful information regarding the relative influence of five distinct descriptor subsets present in each data set.

Get access to the full text of this article

Ancillary