Exploiting scale-free information from expression data for cancer classification

Alexey V. Antonov; Igor V. Tetko; Denis Kosykh; Dmitrij Surmeli; Hans Werner Mewes

Exploiting scale-free information from expression data for cancer classification

Alexey V. Antonov
, Igor V. Tetko
, Denis Kosykh
, Dmitrij Surmeli
, Hans Werner Mewes

Life Sciences

Helmholtz Zentrum München German Research Center for Environmental Health

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In most studies concerning expression data analyses information on the variability of gene intensity across samples is usually exploited. This information is sensitive to initial data processing which affects the final conclusions. However expression data contains scale free information which is directly comparable between different samples. We propose to use the pairwise ratio of gene expression values rather than their absolute intensities for classification of expression data. This information is stable to data processing and thus more attractive for classification analyses. In proposed schema of data analyses only information on relative gene expression levels in each sample is exploited. Testing on publicly available datasets leads to superior classification results.

Original language	English
Title of host publication	Proceedings of the German Conference on Bioinformatics, GCB 2005
Pages	93-102
Number of pages	10
State	Published - 2005
Event	German Conference on Bioinformatics, GCB 2005 - Hamburg, Germany Duration: 5 Oct 2005 → 7 Oct 2005

Publication series

Name	Proceedings of the German Conference on Bioinformatics, GCB 2005

Conference

Conference	German Conference on Bioinformatics, GCB 2005
Country/Territory	Germany
City	Hamburg
Period	5/10/05 → 7/10/05

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Cite this

@inproceedings{fb1ae3b0b8c44f66868db92ce0381781,

title = "Exploiting scale-free information from expression data for cancer classification",

abstract = "In most studies concerning expression data analyses information on the variability of gene intensity across samples is usually exploited. This information is sensitive to initial data processing which affects the final conclusions. However expression data contains scale free information which is directly comparable between different samples. We propose to use the pairwise ratio of gene expression values rather than their absolute intensities for classification of expression data. This information is stable to data processing and thus more attractive for classification analyses. In proposed schema of data analyses only information on relative gene expression levels in each sample is exploited. Testing on publicly available datasets leads to superior classification results.",

author = "Antonov, \{Alexey V.\} and Tetko, \{Igor V.\} and Denis Kosykh and Dmitrij Surmeli and Mewes, \{Hans Werner\}",

note = "Funding Information: This work was supported by 031U212C BFAM (BMBF) to HWM and TE 380/1-1 (DFG) to IVT/HWM. We thank Louise Riley for her help with English.; German Conference on Bioinformatics, GCB 2005 ; Conference date: 05-10-2005 Through 07-10-2005",

year = "2005",

language = "English",

isbn = "3885794004",

series = "Proceedings of the German Conference on Bioinformatics, GCB 2005",

pages = "93--102",

booktitle = "Proceedings of the German Conference on Bioinformatics, GCB 2005",

}

Exploiting scale-free information from expression data for cancer classification. / Antonov, Alexey V.; Tetko, Igor V.; Kosykh, Denis et al.
Proceedings of the German Conference on Bioinformatics, GCB 2005. 2005. p. 93-102 (Proceedings of the German Conference on Bioinformatics, GCB 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Exploiting scale-free information from expression data for cancer classification

AU - Antonov, Alexey V.

AU - Tetko, Igor V.

AU - Kosykh, Denis

AU - Surmeli, Dmitrij

AU - Mewes, Hans Werner

N1 - Funding Information: This work was supported by 031U212C BFAM (BMBF) to HWM and TE 380/1-1 (DFG) to IVT/HWM. We thank Louise Riley for her help with English.

PY - 2005

Y1 - 2005

N2 - In most studies concerning expression data analyses information on the variability of gene intensity across samples is usually exploited. This information is sensitive to initial data processing which affects the final conclusions. However expression data contains scale free information which is directly comparable between different samples. We propose to use the pairwise ratio of gene expression values rather than their absolute intensities for classification of expression data. This information is stable to data processing and thus more attractive for classification analyses. In proposed schema of data analyses only information on relative gene expression levels in each sample is exploited. Testing on publicly available datasets leads to superior classification results.

AB - In most studies concerning expression data analyses information on the variability of gene intensity across samples is usually exploited. This information is sensitive to initial data processing which affects the final conclusions. However expression data contains scale free information which is directly comparable between different samples. We propose to use the pairwise ratio of gene expression values rather than their absolute intensities for classification of expression data. This information is stable to data processing and thus more attractive for classification analyses. In proposed schema of data analyses only information on relative gene expression levels in each sample is exploited. Testing on publicly available datasets leads to superior classification results.

UR - https://www.scopus.com/pages/publications/84871242397

M3 - Conference contribution

AN - SCOPUS:84871242397

SN - 3885794004

SN - 9783885794004

T3 - Proceedings of the German Conference on Bioinformatics, GCB 2005

SP - 93

EP - 102

BT - Proceedings of the German Conference on Bioinformatics, GCB 2005

T2 - German Conference on Bioinformatics, GCB 2005

Y2 - 5 October 2005 through 7 October 2005

ER -

Exploiting scale-free information from expression data for cancer classification

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this