Summarizing gene-expression-based classifiers by meta-mining comprehensible relational patterns

Filip Železný, Olga Štěpánková, Jakub Tolar, Nada Lavrač

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a methodology for predictive classification from gene expression data, able to combine the robustness of high-dimensional statistical classification methods with the comprehensibility and interpretability of simple logic-based models. We first construct a robust classifier combining contributions of a large number of gene expression values, and then (meta)-mine the classifier for compact summarizations of subgroups among genes associated with a given class therein. The subgroups are described by means of relational logic features extracted from publicly available gene ontology information. The curse of dimensionality pertaining to the gene expression based classification problem due to the large number of attributes (genes) is turned into an advantage in the secondary, meta-mining task as here the original attributes become learning examples. We cross-validate the proposed method on two classification problems: (i) acute lymphoblastic leukemia (ALL) vs. acute myeloid leukemia (AML), (ii) seven subclasses of ALL.

Original languageEnglish (US)
Title of host publicationProceedings of the Fourth IASTED International Conference on Biomedical Engineering
Pages19-24
Number of pages6
StatePublished - Dec 1 2006
Event4th IASTED International Conference on Biomedical Engineering - Innsbruck, Austria
Duration: Feb 15 2006Feb 17 2006

Publication series

NameProceedings of the Fourth IASTED International Conference on Biomedical Engineering
Volume2006

Other

Other4th IASTED International Conference on Biomedical Engineering
CountryAustria
CityInnsbruck
Period2/15/062/17/06

Keywords

  • Gene expression microarrays
  • Gene ontology
  • Relational data mining

Fingerprint Dive into the research topics of 'Summarizing gene-expression-based classifiers by meta-mining comprehensible relational patterns'. Together they form a unique fingerprint.

Cite this