Ghent University Academic Bibliography

Advanced

Gene expression trends and protein features effectively complement each other in gene function prediction

Krzysztof Wabnik UGent, Torgeir Hvidsten, Anna Kedzierska UGent, Jelle Van Leene UGent, Geert De Jaeger UGent, Gerrit Beemster UGent, Jan Komorowski and Martin Kuiper (2009) Bioinformatics. 25(3). p.322-330
abstract
Motivation: Genome-scale 'omics' data constitute a potentially rich source of information about biological systems and their function. There is a plethora of tools and methods available to mine omics data. However, the diversity and complexity of different omics data types is a stumbling block for multi-data integration, hence there is a dire need for additional methods to exploit potential synergy from integrated orthogonal data. Rough Sets provide an efficient means to use complex information in classification approaches. Here, we set out to explore the possibilities of Rough Sets to incorporate diverse information sources in a functional classification of unknown genes. Results: We explored the use of Rough Sets for a novel data integration strategy where gene expression data, protein features and Gene Ontology (GO) annotations were combined to describe general and biologically relevant patterns represented by If-Then rules. The descriptive rules were used to predict the function of unknown genes in Arabidopsis thaliana and Schizosaccharomyces pombe. The If-Then rule models showed success rates of up to 0.89 (discriminative and predictive power for both modeled organisms); whereas, models built solely of one data type (protein features or gene expression data) yielded success rates varying from 0.68 to 0.78. Our models were applied to generate classifications for many unknown genes, of which a sizeable number were confirmed either by PubMed literature reports or electronically interfered annotations. Finally, we studied cell cycle protein-protein interactions derived from both tandem affinity purification experiments and in silico experiments in the BioGRID interactome database and found strong experimental evidence for the predictions generated by our models. The results show that our approach can be used to build very robust models that create synergy from integrating gene expression data and protein features.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
NETWORK, IDENTIFICATION, MICROARRAY, YEAST, ONTOLOGY, BIOLOGICAL PROCESS, CELL-CYCLE, ARABIDOPSIS, PATTERNS, SYSTEM
journal title
Bioinformatics
Bioinformatics
volume
25
issue
3
pages
322 - 330
Web of Science type
Article
Web of Science id
000262959500006
JCR category
MATHEMATICAL & COMPUTATIONAL BIOLOGY
JCR impact factor
4.926 (2009)
JCR rank
2/29 (2009)
JCR quartile
1 (2009)
ISSN
1367-4803
DOI
10.1093/bioinformatics/btn625
language
English
UGent publication?
yes
classification
A1
copyright statement
I don't know the status of the copyright for this publication
id
528653
handle
http://hdl.handle.net/1854/LU-528653
date created
2009-03-23 17:22:02
date last changed
2009-04-02 09:50:18
@article{528653,
  abstract     = {Motivation: Genome-scale 'omics' data constitute a potentially rich source of information about biological systems and their function. There is a plethora of tools and methods available to mine omics data. However, the diversity and complexity of different omics data types is a stumbling block for multi-data integration, hence there is a dire need for additional methods to exploit potential synergy from integrated orthogonal data. Rough Sets provide an efficient means to use complex information in classification approaches. Here, we set out to explore the possibilities of Rough Sets to incorporate diverse information sources in a functional classification of unknown genes.

Results: We explored the use of Rough Sets for a novel data integration strategy where gene expression data, protein features and Gene Ontology (GO) annotations were combined to describe general and biologically relevant patterns represented by If-Then rules. The descriptive rules were used to predict the function of unknown genes in Arabidopsis thaliana and Schizosaccharomyces pombe. The If-Then rule models showed success rates of up to 0.89 (discriminative and predictive power for both modeled organisms); whereas, models built solely of one data type (protein features or gene expression data) yielded success rates varying from 0.68 to 0.78. Our models were applied to generate classifications for many unknown genes, of which a sizeable number were confirmed either by PubMed literature reports or electronically interfered annotations. Finally, we studied cell cycle protein-protein interactions derived from both tandem affinity purification experiments and in silico experiments in the BioGRID interactome database and found strong experimental evidence for the predictions generated by our models. The results show that our approach can be used to build very robust models that create synergy from integrating gene expression data and protein features.},
  author       = {Wabnik, Krzysztof and Hvidsten, Torgeir and Kedzierska, Anna and Van Leene, Jelle and De Jaeger, Geert and Beemster, Gerrit and Komorowski, Jan and Kuiper, Martin},
  issn         = {1367-4803},
  journal      = {Bioinformatics},
  keyword      = {NETWORK,IDENTIFICATION,MICROARRAY,YEAST,ONTOLOGY,BIOLOGICAL PROCESS,CELL-CYCLE,ARABIDOPSIS,PATTERNS,SYSTEM},
  language     = {eng},
  number       = {3},
  pages        = {322--330},
  title        = {Gene expression trends and protein features effectively complement each other in gene function prediction},
  url          = {http://dx.doi.org/10.1093/bioinformatics/btn625},
  volume       = {25},
  year         = {2009},
}

Chicago
Wabnik, Krzysztof, Torgeir Hvidsten, Anna Kedzierska, Jelle Van Leene, Geert De Jaeger, Gerrit Beemster, Jan Komorowski, and Martin Kuiper. 2009. “Gene Expression Trends and Protein Features Effectively Complement Each Other in Gene Function Prediction.” Bioinformatics 25 (3): 322–330.
APA
Wabnik, K., Hvidsten, T., Kedzierska, A., Van Leene, J., De Jaeger, G., Beemster, G., Komorowski, J., et al. (2009). Gene expression trends and protein features effectively complement each other in gene function prediction. Bioinformatics, 25(3), 322–330.
Vancouver
1.
Wabnik K, Hvidsten T, Kedzierska A, Van Leene J, De Jaeger G, Beemster G, et al. Gene expression trends and protein features effectively complement each other in gene function prediction. Bioinformatics. 2009;25(3):322–30.
MLA
Wabnik, Krzysztof, Torgeir Hvidsten, Anna Kedzierska, et al. “Gene Expression Trends and Protein Features Effectively Complement Each Other in Gene Function Prediction.” Bioinformatics 25.3 (2009): 322–330. Print.