Paper Info
Title
COMPACT: a comparative package for clustering assessment
Abstract
There exist numerous algorithms that cluster data-points from large-scale genomic experiments such as sequencing, gene-expression and proteomics. Such algorithms may employ distinct principles, and lead to different performance and results. The appropriate choice of a clustering method is a significant and often overlooked aspect in extracting information from large-scale datasets. Evidently, such choice may significantly influence the biological interpretation of the data. We present an easy-to-use and intuitive tool that compares some clustering methods within the same framework. The interface is named COMPACT for Comparative-Package-for-Clustering-Assessment. COMPACT first reduces the dataset’s dimensionality using the Singular Value Decomposition (SVD) method, and only then employs various clustering techniques. Besides its simplicity, and its ability to perform well on high-dimensional data, it provides visualization tools for evaluating the results. COMPACT was tested on a variety of datasets, from classical benchmarks to large-scale gene-expression experiments. COMPACT is configurable and expendable to newly added algorithms.
Year
DOI
Venue
2005
10.1007/11576259_18
ISPA Workshops
Keywords
Field
DocType
large-scale gene-expression experiment,clustering assessment,singular value decomposition,high-dimensional data,biological interpretation,clustering method,comparative package,appropriate choice,classical benchmarks,large-scale genomic experiment,various clustering technique,large-scale datasets,gene expression,high dimensional data
Singular value decomposition,Data mining,Computer science,Visualization,Parallel algorithm,Curse of dimensionality,Online analytical processing,Cluster analysis
Conference
Volume
ISSN
ISBN
3759
0302-9743
3-540-29770-7
Citations 
PageRank 
References 
7
1.00
10
Authors
3
Name
Order
Citations
PageRank
Roy Varshavsky1947.01
Michal Linial21502149.92
David Horn341451.58