Compound analysis via graph kernels incorporating chirality

J. B. Brown, Takashi Urata, Takeyuki Tamura, Midori A. Arai, Takeo Kawabata, Tatsuya Akutsu

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)


High accuracy is paramount when predicting biochemical characteristics using Quantitative Structural-Property Relationships (QSPRs). Although existing graph-theoretic kernel methods combined with machine learning techniques are efficient for QSPR model construction, they cannot distinguish topologically identical chiral compounds which often exhibit different biological characteristics. In this paper, we propose a new method that extends the recently developed tree pattern graph kernel to accommodate stereoisomers. We show that Support Vector Regression (SVR) with a chiral graph kernel is useful for target property prediction by demonstrating its application to a set of human vitamin D receptor ligands currently under consideration for their potential anti-cancer effects.

Original languageEnglish
Pages (from-to)63-81
Number of pages19
JournalJournal of Bioinformatics and Computational Biology
Issue numberSUPPL. 1
Publication statusPublished - 2010 Dec
Externally publishedYes


  • Kernel method
  • QSAR
  • QSPR
  • graph kernel
  • support vector machine

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications


Dive into the research topics of 'Compound analysis via graph kernels incorporating chirality'. Together they form a unique fingerprint.

Cite this