Predicting lipophilicity of drug-discovery molecules using Gaussian process models

Timon S. Schroeter, Anton Schwaighofer, Sebastian Mika, Antonius Ter Laak, Detlev Suelzle, Ursula Ganzer, Nikolaus Heinrich, Klaus Robert Müller

Research output: Contribution to journalArticlepeer-review

29 Citations (Scopus)


(Figure Presented) The lipophilicity of 14556 library compounds at Bayer Schering was modeled using Gaussian process methodology. In a blind test with 7013 new drug-discovery molecules from the last few months, 81% were predicted correctly within one log unit,compared with only 44% achieved by commercial software. Predicted error bars exhibit close to ideal statistical properties, thereby allowing assessment of the model's domain of applicability.

Original languageEnglish
Pages (from-to)1265-1267
Number of pages3
Issue number9
Publication statusPublished - 2007 Sept 10


  • Domain of applicability
  • Drug design
  • Gaussian process
  • Lipophilicity
  • Machine learning

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Medicine
  • Pharmacology
  • Drug Discovery
  • Pharmacology, Toxicology and Pharmaceutics(all)
  • Organic Chemistry


Dive into the research topics of 'Predicting lipophilicity of drug-discovery molecules using Gaussian process models'. Together they form a unique fingerprint.

Cite this