Binary tree-structured vector quantization approach to clustering and visualizing microarray data

Abstract

Starting with a systematic comparison of the underlying theories behind clustering approaches, we have devised a technique that combines tree-structured vector quantization and partitive k-means clustering (BTSVQ). This hybrid technique has revealed clinically relevant clusters in three large publicly available data sets. In contrast to existing systems, our approach is less sensitive to data preprocessing and data normalization. In addition, the clustering results produced by the technique have strong similarities to those of self-organizing maps (SOMs). We discuss the advantages and the mathematical reasoning behind our approach.

Molecular classification of oral cancer by cDNA microarrays identifies overexpressed genes correlated with nodal metastasis

“…We used BTSVQ 26 for microarray data analysis, to identify gene expression profiles correlating with clinicopathologic parameters. BTSVQ analysis successfully clustered genes across samples, generating useful and visible data organization.…”

“…Expression data for all 19,200 gene sequences in each tumor sample were analyzed using the BTSVQ method, 26 implemented in Matlab R12 (MathWorks, Natick, MA). Detailed information about this method of data analysis and software download is available for academic use (http://www.uhnres.utoronto.ca/ta3/ BTSVQ/).…”

An anatomic gene expression atlas of the adult mouse brain

“…To construct the hierarchical clustering, voxels are spatially organized as a binary tree 5 where each node represents a collection of voxels and has zero or two branches (children). To initialize, all 51,533 voxels were assigned to the root node of the tree.…”

Multiple dysregulated pathways in nasopharyngeal carcinoma revealed by gene expression profiling

“…[14][15][16] Raw expression data were loaded into the program, log-transformed, range-normalized and visualized using SOM component planes and binary-tree structured clusters.…”