Classifying 'drug-likeness' with kernel-based learning methods

Klaus Muller, Gunnar Rätsch, Sören Sonnenburg, Sebastian Mika, Michael Grimm, Nikolaus Heinrich

Research output: Contribution to journalArticle

72 Citations (Scopus)


In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

Original languageEnglish
Pages (from-to)249-253
Number of pages5
JournalJournal of Chemical Information and Modeling
Issue number2
Publication statusPublished - 2005 Mar 1
Externally publishedYes

ASJC Scopus subject areas

  • Chemistry(all)
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Classifying 'drug-likeness' with kernel-based learning methods'. Together they form a unique fingerprint.

  • Cite this

    Muller, K., Rätsch, G., Sonnenburg, S., Mika, S., Grimm, M., & Heinrich, N. (2005). Classifying 'drug-likeness' with kernel-based learning methods. Journal of Chemical Information and Modeling, 45(2), 249-253.