Incorporating biological domain knowledge into cluster validity assessment

Authors:
Nadia Bolshakova;Francisco Azuaje;Pádraig Cunningham
Affiliations:
Department of Computer Science, Trinity College Dublin, Ireland;School of Computing and Mathematics, University of Ulster, Jordanstown, UK;Department of Computer Science, Trinity College Dublin, Ireland
Venue:
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
Year:
2006

Citing 9
Cited 1

Cluster validation techniques for genome expression data

Signal Processing - Special issue: Genomic signal processing
Verbs semantics and lexical selection

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Incorporating Ontology-Driven Similarity Knowledge into Functional Genomics: An Exploratory Study

BIBE '04 Proceedings of the 4th IEEE Symposium on Bioinformatics and Bioengineering
A global test for groups of genes: testing association with a clinical outcome

Bioinformatics
A graph-theoretic modeling on GO space for biological interpretation of gene clusters

Bioinformatics
New methods for joint analysis of biological networks and expression data

Bioinformatics
A knowledge-driven approach to cluster validity assessment

Bioinformatics
Ontological analysis of gene expression data: current tools, limitations, and open problems

Bioinformatics
Using information content to evaluate semantic similarity in a taxonomy

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1

Ontology - supported machine learning and decision support in biomedicine

DILS'07 Proceedings of the 4th international conference on Data integration in the life sciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an approach for assessing cluster validity based on similarity knowledge extracted from the Gene Ontology (GO) and databases annotated to the GO. A knowledge-driven cluster validity assessment system for microarray data was implemented. Different methods were applied to measure similarity between yeast genes products based on the GO. This research proposes two methods for calculating cluster validity indices using GO-driven similarity. The first approach processes overall similarity values, which are calculated by taking into account the combined annotations originating from the three GO hierarchies. The second approach is based on the calculation of GO hierarchy-independent similarity values, which originate from each of these hierarchies. A traditional node-counting method and an information content technique have been implemented to measure knowledge-based similarity between genes products (biological distances). The results contribute to the evaluation of clustering outcomes and the identification of optimal cluster partitions, which may represent an effective tool to support biomedical knowledge discovery in gene expression data analysis.