A discriminative approach to structured biological data

Stefan Mutter, Bernhard Pfahringer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)


This paper introduces the first author's PhD project which has just got out of its initial stage. Biological sequence data is, on the one hand, highly structured. On the other hand there are large amounts of unlabelled data. Thus we combine probabilistic graphical models and semi-supervised learning. The former to handle structured data and the latter to deal with unlabelled data. We apply our models to genotype-phenotype modelling problems. In particular we predict the set of Single Nucleotide Polymorphisms which underlie a specific phenotypical trait.

Original languageEnglish
Title of host publicationProceedings of NZCSRSC 2007, the 5th New Zealand Computer Science Research Student Conference
Publication statusPublished - 2007
Externally publishedYes
Event5th New Zealand Computer Science Research Student Conference, NZCSRSC 2007 - Hamilton, New Zealand
Duration: 10 Apr 200713 Apr 2007


Other5th New Zealand Computer Science Research Student Conference, NZCSRSC 2007
CountryNew Zealand


  • Bioinformatics
  • Probabilistic graphical models
  • Semi-supervised learning
  • Single nucleotide polymorphism

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Education

Cite this