Communication

From Machine Learning to Natural Product Derivatives that Selectively Activate Transcription Factor PPARγ

  1. Matthias Rupp1,
  2. Timon Schroeter Dr.2,
  3. Ramona Steri3,
  4. Heiko Zettl Dr.3,
  5. Ewgenij Proschak Dr.1,
  6. Katja Hansen2,
  7. Oliver Rau Dr.3,
  8. Oliver Schwarz Dr.4,
  9. Lutz Müller-Kuhrt Dr.4,
  10. Manfred Schubert-Zsilavecz Prof. Dr.3,
  11. Klaus-Robert Müller Prof. Dr.2,
  12. Gisbert Schneider Prof. Dr.1,5

Article first published online: 30 DEC 2009

DOI: 10.1002/cmdc.200900469

Issue

ChemMedChem

ChemMedChem

Volume 5, Issue 2, pages 191–194, February 1, 2010

Additional Information

How to Cite

Rupp, M., Schroeter, T., Steri, R., Zettl, H., Proschak, E., Hansen, K., Rau, O., Schwarz, O., Müller-Kuhrt, L., Schubert-Zsilavecz, M., Müller, K.-R. and Schneider, G. (2010), From Machine Learning to Natural Product Derivatives that Selectively Activate Transcription Factor PPARγ. ChemMedChem, 5: 191–194. doi: 10.1002/cmdc.200900469

Author Information

  1. 1

    Goethe University, Chair for Chem- and Bioinformatics, LIFF, ZAFES, Siesmayerstr. 70, 60323 Frankfurt a.M. (Germany)

  2. 2

    Technical University of Berlin, Chair for Machine Learning, Franklinstr. 28/29, 10587 Berlin (Germany)

  3. 3

    Goethe University, Chair for Pharmaceutical Chemistry, LIFF, ZAFES, Max-von-Laue-Str. 9, 60438 Frankfurt a.M. (Germany)

  4. 4

    AnalytiCon Discovery GmbH, Hermannswerder Haus 17, 14473 Potsdam (Germany)

  5. 5

    Present address: ETH Zürich, Institute of Pharmaceutical Sciences, Wolfgang-Pauli-Str. 10, 8093 Zürich (Switzerland)

Publication History

  1. Issue published online: 26 JAN 2010
  2. Article first published online: 30 DEC 2009
  3. Manuscript Revised: 10 DEC 2009
  4. Manuscript Received: 15 NOV 2009

Funded by

  • DFG. Grant Number: MU 987/4-1

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article with Supporting Information (HTML) Get PDF (212K)

Keywords:

  • drug design;
  • machine learning;
  • natural products;
  • NMR;
  • virtual screening

Graphical Abstract

Thumbnail image of graphical abstract

Advanced kernel-based machine learning methods enable the identification of innovative bioactive compounds with minimal experimental effort. Comparative virtual screening revealed that nonlinear models of the underlying structure–activity relationship are necessary for successful compound picking. In a proof-of-concept study a novel truxillic acid derivative was found to selectively activate transcription factor PPARγ.

View Full Article with Supporting Information (HTML) Get PDF (212K)