Publication Details

Gene Ontology Driven Feature Filtering from Microarray Data

ŠILHAVÁ Jana and SMRŽ Pavel. Gene Ontology Driven Feature Filtering from Microarray Data. In: Znalosti 2010. 9th Annual Conference, Jindřichův Hradec. Jindřichův Hradec, 2010, pp. 263-266. ISBN 978-80-245-1636-3.
English title
Gene Ontology Driven Feature Filtering from Microarray Data
Type
conference paper
Language
czech
Authors
Keywords

feature selection, gene ontology, microarray data, class prediction

Abstract

Microarray data is high-dimensional and noisy. Dimension reduction, i.e. selecting a small number of genes, is an effective way to improve mining efficiency. We propose a novel approach that integrates gene ontology knowledge at the level of feature selection into microarray data to improve binary class prediction. The advantage of this filtering approach lies in considering gene-to-gene relations and selecting more meaningful features comparing to the methods evaluating genes in isolation. In addition, gene ontology knowledge can overcome the limitations of noisy microarray data. Our approach is evaluated on a real benchmark dataset.

Published
2010
Pages
263-266
Proceedings
Znalosti 2010
Series
9th Annual Conference, Jindřichův Hradec
Conference
Znalosti 2010, Jindřichův Hradec, CZ
ISBN
978-80-245-1636-3
Place
Jindřichův Hradec, CZ
BibTeX
@INPROCEEDINGS{FITPUB9126,
   author = "Jana \v{S}ilhav\'{a} and Pavel Smr\v{z}",
   title = "Gene Ontology Driven Feature Filtering from Microarray Data",
   pages = "263--266",
   booktitle = "Znalosti 2010",
   series = "9th Annual Conference, Jind\v{r}ich\r{u}v Hradec",
   year = 2010,
   location = "Jind\v{r}ich\r{u}v Hradec, CZ",
   ISBN = "978-80-245-1636-3",
   language = "czech",
   url = "https://www.fit.vut.cz/research/publication/9126"
}
Back to top