Advanced

Fast iterative gene clustering based on information theoretic criteria for selecting the cluster structure.

Giurcăneanu, Ciprian Doru; Tăbuş, Ioan; Astola, Jaakko; Ollila, Juha and Vihinen, Mauno LU (2004) In Journal of Computational Biology 11(4). p.660-682
Abstract
Grouping of genes into clusters according to their expression levels is important for deriving biological information, e.g., on gene functions based on microarray and other related analyses. The paper introduces the selection of the number of clusters based on the minimum description length (MDL) principle for the selection of the number of clusters in gene expression data. The main feature of the new method is the ability to evaluate in a fast way the number of clusters according to the sound MDL principle, without exhaustive evaluations over all possible partitions of the gene set. The estimation method can be used in conjunction with various clustering algorithms. A recent clustering algorithm using principal component analysis, the... (More)
Grouping of genes into clusters according to their expression levels is important for deriving biological information, e.g., on gene functions based on microarray and other related analyses. The paper introduces the selection of the number of clusters based on the minimum description length (MDL) principle for the selection of the number of clusters in gene expression data. The main feature of the new method is the ability to evaluate in a fast way the number of clusters according to the sound MDL principle, without exhaustive evaluations over all possible partitions of the gene set. The estimation method can be used in conjunction with various clustering algorithms. A recent clustering algorithm using principal component analysis, the "gene shaving" (GS) procedure, can be modified to make use of the new MDL estimation method, replacing the Gap statistics originally used in GS algorithm. The resulting clustering algorithm is shown to perform better than GS-Gap and CEM (classification expectation maximization), in the simulations using artificial data. The proposed method is applied to B-cell differentiation data, and the resulting clusters are compared with those found by self-organizing maps (SOM). (Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Contribution to journal
publication status
published
subject
keywords
B-Lymphocytes: cytology, B-Lymphocytes: physiology, Gene Expression Profiling: statistics & numerical data
in
Journal of Computational Biology
volume
11
issue
4
pages
660 - 682
publisher
Mary Ann Liebert, Inc.
external identifiers
  • pmid:15579237
  • scopus:4544279049
ISSN
1557-8666
DOI
10.1089/1066527041887285
language
English
LU publication?
no
id
c698a663-fd56-4e12-a0d6-4ad4751752bc (old id 3635446)
alternative location
http://www.ncbi.nlm.nih.gov/pubmed/15579237?dopt=Abstract
date added to LUP
2013-06-12 16:16:58
date last changed
2017-01-22 04:16:39
@article{c698a663-fd56-4e12-a0d6-4ad4751752bc,
  abstract     = {Grouping of genes into clusters according to their expression levels is important for deriving biological information, e.g., on gene functions based on microarray and other related analyses. The paper introduces the selection of the number of clusters based on the minimum description length (MDL) principle for the selection of the number of clusters in gene expression data. The main feature of the new method is the ability to evaluate in a fast way the number of clusters according to the sound MDL principle, without exhaustive evaluations over all possible partitions of the gene set. The estimation method can be used in conjunction with various clustering algorithms. A recent clustering algorithm using principal component analysis, the "gene shaving" (GS) procedure, can be modified to make use of the new MDL estimation method, replacing the Gap statistics originally used in GS algorithm. The resulting clustering algorithm is shown to perform better than GS-Gap and CEM (classification expectation maximization), in the simulations using artificial data. The proposed method is applied to B-cell differentiation data, and the resulting clusters are compared with those found by self-organizing maps (SOM).},
  author       = {Giurcăneanu, Ciprian Doru and Tăbuş, Ioan and Astola, Jaakko and Ollila, Juha and Vihinen, Mauno},
  issn         = {1557-8666},
  keyword      = {B-Lymphocytes: cytology,B-Lymphocytes: physiology,Gene Expression Profiling: statistics & numerical data},
  language     = {eng},
  number       = {4},
  pages        = {660--682},
  publisher    = {Mary Ann Liebert, Inc.},
  series       = {Journal of Computational Biology},
  title        = {Fast iterative gene clustering based on information theoretic criteria for selecting the cluster structure.},
  url          = {http://dx.doi.org/10.1089/1066527041887285},
  volume       = {11},
  year         = {2004},
}