ChemSpaceShuttle: A tool for data mining in drug discovery by classification, projection, and 3D visualization

Authors

  • Alireza Givehchi,

    1. CallistoGen AG, Neuendorfstr. 24b, D-16761 Hennigsdorf, Germany
    2. Johann Wolfgang Goethe-Universität, Institut für Organische Chemie und Chemische Biologie, Marie-Curie-Str. 11, D-60439 Frankfurt, Germany, Tel: +49 – (0)69 798 29824, Fax: +49 – (0)69 798 29826
    Search for more papers by this author
  • Axel Dietrich,

    1. CallistoGen AG, Neuendorfstr. 24b, D-16761 Hennigsdorf, Germany
    2. Present address: The Genetics Company, Wagistraße 27, CH-8952 Schlieren, Switzerland
    Search for more papers by this author
  • Paul Wrede,

    1. CallistoGen AG, Neuendorfstr. 24b, D-16761 Hennigsdorf, Germany
    2. Present address: Freie Universität Berlin, Institut für Molekularbiologie und Bioinformatik, Arnimallee 22, D-14195 Berlin, Germany
    Search for more papers by this author
  • Gisbert Schneider

    1. Johann Wolfgang Goethe-Universität, Institut für Organische Chemie und Chemische Biologie, Marie-Curie-Str. 11, D-60439 Frankfurt, Germany
    Search for more papers by this author

Abstract

The ChemSpaceShuttle toolbox provides a graphical interface allowing for ligand-based design of focused compound libraries by means of linear and non-linear projection techniques and clustering algorithms. The software implements a non-linear encoder network and non-linear partial least squares for the projection of high-dimensional descriptor vectors into a three dimensional space for visualisation. Compound clustering by a self-organising map (SOM) is incorporated. Visualization can facilitate the selection of compounds with desired properties from large compound libraries. Two sample applications are presented: similarity-based compound selection for focused library design, and classification of drugs and nondrugs. A version of ChemSpaceShuttle is freely available at URL: http://gecco.org.chemie.uni-frankfurt.de/gecco.html.

Ancillary