Fast metabolite identification with Input Output Kernel Regression.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: An important problematic of metabolomics is to identify metabolites using tandem mass spectrometry data. Machine learning methods have been proposed recently to solve this problem by predicting molecular fingerprint vectors and matching these fingerprints against existing molecular structure databases. In this work we propose to address the metabolite identification problem using a structured output prediction approach. This type of approach is not limited to vector output space and can handle structured output space such as the molecule space.

Authors

  • Céline Brouard
    Helsinki Institute for Information Technology HIIT, Department of Computer Science, Aalto University, Espoo, Finland.
  • Huibin Shen
    Helsinki Institute for Information Technology, Department of Computer Science, Aalto University, 02150 Espoo, Finland.
  • Kai Dührkop
    Chair for Bioinformatics, Friedrich Schiller University, 07743 Jena, Germany;
  • Florence d'Alché-Buc
    LTCI, CNRS, Télécom ParisTech, Université Paris-Saclay, Paris, France.
  • Sebastian Böcker
    Chair for Bioinformatics, Friedrich Schiller University, 07743 Jena, Germany; sebastian.boecker@uni-jena.de.
  • Juho Rousu
    Department of Computer Science, Aalto University, 00076, Aalto, Finland. juho.rousu@aalto.fi.