Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps

Sampsa Hautaniemi, Olli Yli-Harja, Jaakko Astola, Päivikki Kauraniemi, Anne Kallioniemi, Maija Wolf, Jimmy Ruiz, Spyro Mousses, Olli Kallioniemi

Research output: Contribution to journalArticleScientificpeer-review

38 Citations (Scopus)

Abstract

cDNA microarrays permit massively parallel gene expression analysis and have spawned a new paradigm in the study of molecular biology. One of the significant challenges in this genomic revolution is to develop sophisticated approaches to facilitate the visualization, analysis, and interpretation of the vast amounts of multi-dimensional gene expression data. We have applied self-organizing map (SOM) in order to meet these challenges. In essence, we utilize U-matrix and component planes in microarray data visualization and introduce general procedure for assessing significance for a cluster detected from U-matrix. Our case studies consist of two data sets. First, we have analyzed a data set containing 13,824 genes in 14 breast cancer cell lines. In the second case we show an example of the SOM in drug treatment of prostate cancer cells. Our results indicate that (1) SOM is capable of helping finding certain biologically meaningful clusters, (2) clustering algorithms could be used for finding a set of potential predictor genes for classification purposes, and (3) comparison and visualization of the effects of different drugs is straightforward with the SOM. In summary, the SOM provides an excellent format for visualization and analysis of gene microarray data, and is likely to facilitate extraction of biologically and medically useful information.
Original languageEnglish
Pages (from-to)45-66
Number of pages22
JournalMachine Learning
Volume52
Issue number1-2
DOIs
Publication statusPublished - 2003
MoE publication typeA1 Journal article-refereed

Fingerprint

Self organizing maps
Microarrays
Gene expression
Visualization
Genes
Cells
Drug therapy
Molecular biology
Data visualization
Clustering algorithms

Keywords

  • bioinformatics
  • gene expression
  • in human cancer
  • self-organizing map

Cite this

Hautaniemi, S., Yli-Harja, O., Astola, J., Kauraniemi, P., Kallioniemi, A., Wolf, M., ... Kallioniemi, O. (2003). Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps. Machine Learning, 52(1-2), 45-66. https://doi.org/10.1023/A:1023941307670
Hautaniemi, Sampsa ; Yli-Harja, Olli ; Astola, Jaakko ; Kauraniemi, Päivikki ; Kallioniemi, Anne ; Wolf, Maija ; Ruiz, Jimmy ; Mousses, Spyro ; Kallioniemi, Olli. / Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps. In: Machine Learning. 2003 ; Vol. 52, No. 1-2. pp. 45-66.
@article{da72ad57410d482d929964dfb8514917,
title = "Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps",
abstract = "cDNA microarrays permit massively parallel gene expression analysis and have spawned a new paradigm in the study of molecular biology. One of the significant challenges in this genomic revolution is to develop sophisticated approaches to facilitate the visualization, analysis, and interpretation of the vast amounts of multi-dimensional gene expression data. We have applied self-organizing map (SOM) in order to meet these challenges. In essence, we utilize U-matrix and component planes in microarray data visualization and introduce general procedure for assessing significance for a cluster detected from U-matrix. Our case studies consist of two data sets. First, we have analyzed a data set containing 13,824 genes in 14 breast cancer cell lines. In the second case we show an example of the SOM in drug treatment of prostate cancer cells. Our results indicate that (1) SOM is capable of helping finding certain biologically meaningful clusters, (2) clustering algorithms could be used for finding a set of potential predictor genes for classification purposes, and (3) comparison and visualization of the effects of different drugs is straightforward with the SOM. In summary, the SOM provides an excellent format for visualization and analysis of gene microarray data, and is likely to facilitate extraction of biologically and medically useful information.",
keywords = "bioinformatics, gene expression, in human cancer, self-organizing map",
author = "Sampsa Hautaniemi and Olli Yli-Harja and Jaakko Astola and P{\"a}ivikki Kauraniemi and Anne Kallioniemi and Maija Wolf and Jimmy Ruiz and Spyro Mousses and Olli Kallioniemi",
year = "2003",
doi = "10.1023/A:1023941307670",
language = "English",
volume = "52",
pages = "45--66",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer",
number = "1-2",

}

Hautaniemi, S, Yli-Harja, O, Astola, J, Kauraniemi, P, Kallioniemi, A, Wolf, M, Ruiz, J, Mousses, S & Kallioniemi, O 2003, 'Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps', Machine Learning, vol. 52, no. 1-2, pp. 45-66. https://doi.org/10.1023/A:1023941307670

Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps. / Hautaniemi, Sampsa; Yli-Harja, Olli; Astola, Jaakko; Kauraniemi, Päivikki; Kallioniemi, Anne; Wolf, Maija; Ruiz, Jimmy; Mousses, Spyro; Kallioniemi, Olli.

In: Machine Learning, Vol. 52, No. 1-2, 2003, p. 45-66.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Analysis and visualization of gene expression microarray data in human cancer using self-organizing maps

AU - Hautaniemi, Sampsa

AU - Yli-Harja, Olli

AU - Astola, Jaakko

AU - Kauraniemi, Päivikki

AU - Kallioniemi, Anne

AU - Wolf, Maija

AU - Ruiz, Jimmy

AU - Mousses, Spyro

AU - Kallioniemi, Olli

PY - 2003

Y1 - 2003

N2 - cDNA microarrays permit massively parallel gene expression analysis and have spawned a new paradigm in the study of molecular biology. One of the significant challenges in this genomic revolution is to develop sophisticated approaches to facilitate the visualization, analysis, and interpretation of the vast amounts of multi-dimensional gene expression data. We have applied self-organizing map (SOM) in order to meet these challenges. In essence, we utilize U-matrix and component planes in microarray data visualization and introduce general procedure for assessing significance for a cluster detected from U-matrix. Our case studies consist of two data sets. First, we have analyzed a data set containing 13,824 genes in 14 breast cancer cell lines. In the second case we show an example of the SOM in drug treatment of prostate cancer cells. Our results indicate that (1) SOM is capable of helping finding certain biologically meaningful clusters, (2) clustering algorithms could be used for finding a set of potential predictor genes for classification purposes, and (3) comparison and visualization of the effects of different drugs is straightforward with the SOM. In summary, the SOM provides an excellent format for visualization and analysis of gene microarray data, and is likely to facilitate extraction of biologically and medically useful information.

AB - cDNA microarrays permit massively parallel gene expression analysis and have spawned a new paradigm in the study of molecular biology. One of the significant challenges in this genomic revolution is to develop sophisticated approaches to facilitate the visualization, analysis, and interpretation of the vast amounts of multi-dimensional gene expression data. We have applied self-organizing map (SOM) in order to meet these challenges. In essence, we utilize U-matrix and component planes in microarray data visualization and introduce general procedure for assessing significance for a cluster detected from U-matrix. Our case studies consist of two data sets. First, we have analyzed a data set containing 13,824 genes in 14 breast cancer cell lines. In the second case we show an example of the SOM in drug treatment of prostate cancer cells. Our results indicate that (1) SOM is capable of helping finding certain biologically meaningful clusters, (2) clustering algorithms could be used for finding a set of potential predictor genes for classification purposes, and (3) comparison and visualization of the effects of different drugs is straightforward with the SOM. In summary, the SOM provides an excellent format for visualization and analysis of gene microarray data, and is likely to facilitate extraction of biologically and medically useful information.

KW - bioinformatics

KW - gene expression

KW - in human cancer

KW - self-organizing map

U2 - 10.1023/A:1023941307670

DO - 10.1023/A:1023941307670

M3 - Article

VL - 52

SP - 45

EP - 66

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 1-2

ER -